No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A hybrid memetic algorithm (Genetic Algorithm and Tabu Local Search) with back-propagation classifier for fish recognition
Abstract
In this research our goal is to develop a hybrid approach for optimizing and enhancing back- propagation classifier (BPC) performance using a Memetic Algorithm (Genetic algorithm and Tabu Local Search), thus; Memetic Algorithm used to tune the parameters of the BPC. The proposed hybrid approach (HGATS-BPC) was tested based on fish images recognition. To recognize the pattern of interest (fish object) in the image based on extracted features from color signature. Histogram technique and Gray Level Co-occurrence Matrix (GLCM) used to extract 20 features from fish images based on color signature. The general BPC has several issues to be optimized by Memetic Algorithm such as speed, and easy for running into local minimum. In our study we used 800 fish images for 20 different fish families; each family has a different number of fish types. These images are divided into two datasets: 560 training images and 240 testing images. HGATS-BPC successfully optimized and enhanced the performance of the BPC in term of accuracy and outperformed the traditional BPC and previous methodologies by obtaining more accurate results but with a high cost of computational time compared to the BPC. The overall accuracy obtained by BPC was 85%, while the HGATS-BPC obtained 94% based on 800 fish images. Finally; the HGATS-BPC classifier is able to classify the given fish images into poisonous or non-poisonous fish and classify the poisonous and non-poisonous fish into its family.
... The great deluge algorithm is a local search procedure that was introduced by Dueck in 1993. The idea of the great deluge comes from the analogy that a person climbs a hill and tries to move in any direction of finding a way up to keep his feet dry as the water level rises during a great deluge [7]. Inserting a great deluge algorithm within a genetic algorithm is considered an effective way to produce a high-quality solution rather than using a genetic algorithm alone [7]. ...
... The idea of the great deluge comes from the analogy that a person climbs a hill and tries to move in any direction of finding a way up to keep his feet dry as the water level rises during a great deluge [7]. Inserting a great deluge algorithm within a genetic algorithm is considered an effective way to produce a high-quality solution rather than using a genetic algorithm alone [7]. The study [7] explains that like other local search methods, the extended great deluge iteratively repeats the replacement of a current solution by a new one, until some stopping condition has been satisfied. ...
... Inserting a great deluge algorithm within a genetic algorithm is considered an effective way to produce a high-quality solution rather than using a genetic algorithm alone [7]. The study [7] explains that like other local search methods, the extended great deluge iteratively repeats the replacement of a current solution by a new one, until some stopping condition has been satisfied. They also say a new solution is selected from a neighborhood. ...
... Another problem is the selection of the optimal parameters which contribute to the modeling process. One solution for this problem is the use of the Artificial Neural Network (ANN) and Metaheuristic Algorithm (Badawi and Alsmadi, 2014). ANN was recognized and applied to many applications like the stock returns (Gibson, 1963), shift failures (Ljung and Söderström, 1983), estimating prices (Ljung, 1987), and sales prediction (Kothyari et al., 1993). ...
... To improve the quality of the matting pool if a better solution is reached, the algorithm keeps updating the population (Goldberg, 1989). For further explanations about GA please refer to (Alsmadi et al., 2011, andBadawi andAlsmadi, 2014). Tabu Search is one of the most common meta-heuristic algorithms. ...
... To improve the quality of the matting pool if a better solution is reached, the algorithm keeps updating the population (Goldberg, 1989). For further explanations about GA please refer to (Alsmadi et al., 2011, andBadawi andAlsmadi, 2014). Tabu Search is one of the most common meta-heuristic algorithms. ...
Water resource management is a very complex and important challenge in this century; most of the political analysts consider that the world is going to face a problem of water management and reservation in the future. water management and estimation in the short and long term is an essential tool in planning, maintaining, managing and controlling the unexpected events. In this work, a Metaheuristic Algorithm which hybridizes Tabu search and Genetic algorithms with Back-propagation Algorithm (MABP) were proposed for managing, controlling and predicting water flow. The proposed algorithm used the statistical data set of the Ontonagon River near Rockland in USA as a case study. Back-propagation algorithm was used to train the Artificial Neural Network (ANN) using 550 daily data sets and was tested for other different 550 daily data sets. Metaheuristic algorithm (MA) was used to enhance and improve the obtained weights (solutions quality) from Back-propagation Algorithm (BP) by increasing and enhancing the fitness cost number. The estimated time series, ANN convergence, training and tested graphs were also explored.
... According to the state-of-the-art literature [1,4,5,7,8,16,[27][28][29][30][31][32][33], there is no such review study has done before about the preprocessing methods, features extraction methods, classification algorithms and the datasets that were used for FC. While this study presents a survey of diverse preprocessing methods, feature extraction methods, classifiers algorithms, and the datasets that were used for FC. ...
... The FC techniques with their classification algorithms are shown in Table 1; it involves the algorithms which are utilized for the 3 steps which are preprocessing, feature extraction, and classification. Table 1 In most of the experiments, the database that was used is in [6,8,16,28,29,31] followed by the database used in [50,71]. The databases in [7,8,28,29] ...
Fish classification (FC) is an expansively studied problem in the domains of image segmentation, pattern recognition, and information retrieval. It has been applied in a countless number of domains including target marketing. Meanwhile, governments are obliged to maintain the fish supply and balance between the ecosystem, commercial, agriculture field, marine scientists, and industrial arena of fish including the nutrition and canning factories. The various FC techniques performance is compared relying on the availability of preprocessing and feature extraction methods, the number of extracted features and classification accuracy, the number of fish families /species recognized. This survey also reviewed the use of Databases such as Fish4-Knowledge (F4K), knowledge database, and Global Information System (GIS) on Fishes and other FC databases. The study on preprocessing methods features extraction techniques and classifiers are gathered from recent works to enhance the understanding of the characteristics of preprocessing methods, features extraction techniques, and classifiers to guide future research directions and compensate for current research gaps.
... Genetic algorithm (GA) is among the common meta-heuristic algorithms, it is a search algorithm that simulates the heredity in the biological systems (Goldberg, 1989), the basic mechanism of GA is finding the best solution among the search space (Badawi and Alsmadi, 2013). ...
... Crossover is the key operator within the algorithm. As explained by Badawi and Alsmadi (2013), employing single cut point, crossover produces a new generation (chromosomes) from two parents. This operation determines single crossover point on both parent chromosomes selected. ...
Content based image retrieval (CBIR) systems retrieve images linked to the query image (QI) from enormous databases. The feature sets extracted by the present CBIR systems are limited. This limits the systems’ effectiveness. This study extracts expansively robust and important features from the images database. These features are then kept inside the feature repository. This feature set is comprised of color signature containing features of shape and color. Here, from the given QI, features are extracted in the same manner. Accordingly, new evaluation of similarity employing a meta-heuristic algorithm (genetic algorithm with Iterated local search) is conducted between the query image features and the database images features. This study proposes CBIR system that is evaluated by investigating the number of images (from the test dataset). Meanwhile, the system’s efficiency of is assessed by performing computation on the value of precision-recall for the results. The obtained results were better in comparison other advanced CBIR systems in terms of precision.
... Genetic algorithm (GA) is a search algorithm which stimulates the heredity in the living things [15]. GA is very effective in finding the optimum solution from the search space [16]. ...
... Crossover is the main operator in the genetic algorithm. Crossover generates a new generation (chromosomes) from two parents using single cut point [16]. Where, this operation works by determining single crossover point on both selected parent chromosomes, a random number between 1 and 1c-1 is selected, 1c is the chromosome length. ...
Content based image retrieval (CBIR) systems work by retrieving images which are related to the query image (QI) from huge databases. The available CBIR systems extract limited feature sets which confine the retrieval efficacy. In this work, extensive robust and important features were extracted from the images database and then stored in the feature repository. This feature set is composed of color signature with the shape and color texture features. Where, features are extracted from the given QI in the similar fashion. Consequently, a novel similarity evaluation using a meta-heuristic algorithm called a memetic algorithm (genetic algorithm with great deluge) is achieved between the features of the QI and the features of the database images. Our proposed CBIR system is assessed by inquiring number of images (from the test dataset) and the efficiency of the system is evaluated by calculating precision-recall value for the results. The results were superior to other state-of-the-art CBIR systems in regard to precision.
... With the advent of computers, they gained their place in this research area, which was obvious to think of using them in such important process. Many approaches were used for image processing and pattern recognition [1][2][3][4][5][6][7]. In this research work, a prototype for image recognition using anchor points, texture and statistical measurements is introduced. ...
... A number of studies have been conducted in the field of image recognition. Nevertheless, it is still an active area of research due to many problems such as distortion, errors in the segmentation results, overlap and obstruction of objects in digital images [3,4,[6][7][8]. Based on recent studies, the developed fish recognition systems still have many limitations such as the low ability in detection and classification of fish. Moreover, a high number of deaths occur every day due to inability to differentiate dangerous from non-dangerous fishes [4,8]. ...
Pattern recognition is a system that recognizes isolated patterns of interest that could be an image. Many models such as noise, distortion, overlap, and errors in the segmentation results and obstruction of image’s objects could occur during the process of image recognition. The aim of this study is to develop a system to recognize isolated fish object in the image based on a combination of significant extracted features using anchor points, texture and statistical measurements. A generic fish classification method could be performed using a hybrid meta-heuristic algorithms (genetic algorithm with Great Deluge (GD) algorithm) with back-propagation algorithm (GAGD-BPC). Thus, it is used to classify the images of fish into dangerous and non-dangerous families, to recognize the dangerous fish families into Predatory and Poison fish family, and to recognize the non-dangerous fish families into garden and food fish family. A prototype to deal with the problem of fish images classification is presented in this research work. The proposed prototype has been tested based on 24 fish families, each family contains different number of species. Therefore, it has performed the classification process successfully. The experimental tests have been performed based on 320 distinct fish images that were divided into 220 images for training phase and 100 images for testing phase. An overall accuracy recognition rate was 83.2%, which was obtained using the proposed GAGD-BPC.
... 1. Consider H and W are the height and width of face image as shown in Figure 6. 2. Divide the height by four (H/4). 3. Skip the first upper quarter, because it doesn't contain any significant part. ...
... A multilayer feed forward NN with used in this study [2,3]. BP algorithm training and testing the extracted features from the right eye, left eye and mouth using radial curves and Cubic Bézier curves. ...
Researchers in different fields such as image processing, neural sciences, computer programs and psychophysics have investigated number of problems related to facial recognition by machines and humans since 1975. Automatic recognition of the human emotions using facial expression is an important, but difficult problem. This study introduces a novel and automatic approach to analyze and recognize human facial expressions and emotions using a Metaheuristic Algorithm (MA), which hybridizes iterated local search and Genetic Algorithms with Back-Propagation algorithm (ILSGA-BP). Back- propagation algorithm (BP) was used to train and test the extracted features from the extracted right eye, left eye and mouth using radial curves and Cubic Bezier curves, MA was used to enhance and optimize the initial weights of the traditional BP. FEEDTUM facial expression database was used in this study for training and testing processes with seven different emotions namely; surprise, happiness, disgust, neutral, fear, sadness and anger. A comparison of the results obtained using the extracted features from the radial curves, Cubic Bezier curves and the combination of them were conducted. The comparison shows the superiority of the combination of the radial curves and the Cubic Bezier curves with percentage ranges between 87% and 97% over the radial curves alone with a percentage ranges between 80% and 97% and over the Cubic Bezier curves with a percentage ranges between 83% and 97%. Moreover, based on the extracted features using the radial curves, Cubic Bezier curves and the combination of them, the experimental results show that the proposed ILSGA-BP algorithm outperformed the BP algorithm with overall accuracy 88%, 89% and 93.4% respectively, compared to 83%, 82% and 85% respectively using BP algorithm.
... Al Smadi [51] explored GIS-based fish classification, achieving accuracies of 81% to 83.2% using the BP (backpropagation) algorithm and GAGD-BPC (genetic algorithmbased group decision-making and backpropagation classifier) on a dataset of 320 images. Badawi and Alsmadi [52] extended this approach, achieving accuracies of 82% to 85% by combining the BP algorithm with GAILS-BPC (genetic algorithm-based improved learning system). Al Smadi et al. [53] achieved a slightly higher accuracy of 86% on a smaller dataset of 350 images by emphasizing shape and texture features. ...
Automated fish species classification is essential for marine biodiversity monitoring, fisheries management, and ecological research. However, challenges such as environmental variability, class imbalance, and computational demands hinder the development of robust classification models. This study investigates the effectiveness of convolutional neural network (CNN)-based models and hybrid approaches to address these challenges. Eight CNN architectures, including DenseNet121, MobileNetV2, and Xception, were compared alongside traditional classifiers like support vector machines (SVMs) and random forest. DenseNet121 achieved the highest accuracy (90.2%), leveraging its superior feature extraction and generalization capabilities, while MobileNetV2 balanced accuracy (83.57%) with computational efficiency, processing images in 0.07 s, making it ideal for real-time deployment. Advanced preprocessing techniques, such as data augmentation, turbidity simulation, and transfer learning, were employed to enhance dataset robustness and address class imbalance. Hybrid models combining CNNs with traditional classifiers achieved intermediate accuracy with improved interpretability. Optimization techniques, including pruning and quantization, reduced model size by 73.7%, enabling real-time deployment on resource-constrained devices. Grad-CAM visualizations further enhanced interpretability by identifying key image regions influencing predictions. This study highlights the potential of CNN-based models for scalable, interpretable fish species classification, offering actionable insights for sustainable fisheries management and biodiversity conservation.
... But each such algorithm suffers from a fundamental problem i.e. finding a proper trade-off for exploration and exploitation. The next generation of researchers have made efforts to solve this problem by hybridizing various algorithms together (Anter, Azar, & Fouad, 2019;Badawi, Khalil, & Alsmadi, 2013;Trivedi, Srivastava, Mishra, Shukla, & Tiwari, 2018). Although some algorithms have performed better than the others to find a proper balance between exploitation and exploration, the problem still remained. ...
'Hybrid meta-heuristics' is one of the most interesting recent trends in the field of optimization and feature selection (FS). In this paper, we have proposed a binary variant of Atom Search Optimization (ASO) and its hybrid with Simulated Annealing called ASO-SA techniques for FS. In order to map the real values used by ASO to the binary domain of FS, we have used two different transfer functions: S-shaped and V-shaped. We have hybridized this technique with a local search technique called, SA We have applied the proposed feature selection methods on 25 datasets from 4 different categories: UCI, Handwritten digit recognition, Text, non-text separation, and Facial emotion recognition. We have used 3 different classifiers (K-Nearest Neighbor, Multi-Layer Perceptron and Random Forest) for evaluating the strength of the selected featured by the binary ASO, ASO-SA and compared the results with some recent wrapper-based algorithms. The experimental results confirm the superiority of the proposed method both in terms of classification accuracy and number of selected features.
... Hybridization of two or more algorithms together has been attempted by countless scholars for the purpose of improving the performance of the search algorithms [47,48]. Such attempt is underpinned by the notion that hybridization allows the merging of the best features from one algorithm with those of others [49,50]. ...
Image recognition process could be plagued by many problems including noise, overlap, distortion, errors in the outcomes of segmentation, and impediment of objects within the image. Based on feature selection and combination theory between major extracted features, this study attempts to establish a system that could recognize fish object within the image utilizing texture, anchor points, and statistical measurements. Then, a generic fish classification is executed with the application of an innovative classification evaluation through a meta-heuristic algorithm known as Memetic Algorithm (Genetic Algorithm with Simulated Annealing) with back-propagation algorithm (MA-B Classifier). Here, images of dangerous and non-dangerous fish are recognized. Images of dangerous fish are further recognized as Predatory or Poison fish family, whereas families of non-dangerous fish are classified into garden and food family. A total of 24 fish families were used in testing the proposed prototype, whereby each family encompasses different number of species. The process of classification was successfully undertaken by the proposed prototype, whereby 400 distinct fish images were used in the experimental tests. Of these fish images, 250 were used for training phase while 150 were used for testing phase. The back-propagation algorithm and the proposed MA-B Classifier produced a general accuracy recognition rate of 82.25 and 90% respectively.
... The technological revolution influenced everything , even the methods that aim to improve the shopping and banking systems. Today, the use of Artificial Intelligence (AI) algorithms is expansive, particularly in providing solutions to challenging problems including patterns recognition and retrieval of information [26,39,43,[47][48][49][50][51][52][53][54][55][56][57][58][59][60][61], image segmentation [11,12,22,42,[62][63][64][65][66], analysis of medical images [67][68][69][70][71], Learning Management System , nurse rostering problem [41], Healthcare Monitoring system [25,98], as well as prediction of river flow [40,99,100]. Accordingly, many systems have used the Artificial Intelligence as an effective tool for biometric authentication and using it in the transactions and banking systems [101][102][103]. ...
The steady growth in electronic transactions has promoted the Automated Teller Machine (ATM) thereby making it the main transaction channel for carrying out financial transactions. Conventional method of identification based on possession of ID cards or exclusive knowledge like a social security number or a password are not all together reliable. However, this has also increased the amount of fraudulent activities carried out on Automated Teller Machines (ATMs) thereby calling for efficient security mechanisms and increasing the demand for fast and accurate user identification and authentication in ATMs. In this paper, an embedded fingerprint biometric authentication scheme for Point of Sale (POS) network as additional security option to the ATM card is proposed. A fingerprint biometric technique was fused with personal identification numbers (PIN's) for authentication to upgrade the security level. The proposed idea will solve the problems that may face the customers such as theft, counterfeiting, oblivion or loss the card. Therefore, the customer will be identified once putting his finger on the reader (based on finger scanning) and the system recognizes the customer without requiring keys or cards of support. We have distributed a questioner to 586 responders, the obtained results show the importance of fingerprint biometric authentication for POS network as additional security option to the ATM card.
... The Active Ageing, which is the process of improving opportunities for elderly's health, security and participation which aims to improve quality of life as individuals age, is portion of the process of handling these chronic diseases, to make effort to keep the elderly healthy and participating in the social live [4]. Recently; artificial intelligence algorithms were widely used for solving very complicated problems, such as patterns recognition and information retrieval [24][25][26][27][28][29][30][31][32][33], image segmentations [34][35][36][37][38][39][40] and river flow forecasting [41], Many researchers employed communication technologies and information [6,42], and artificial intelligence algorithms [43][44][45][46] for covering real health needs of patients. ...
Elderly chronic diseases are the main cause of death in the world, accounting 60% of all death. Because elderly with chronic diseases at the early stages has no observed symptoms, and then symptoms starts to appear, it is critical to observe the symptoms as early as possible to avoid any complication. This paper presents an expert system for an Elderly Health Care (EHC) at elderly home tailored for the specific needs of Elderly. The proposed EHC aims to develop an integrated and multidisciplinary method to employ communication technologies and information for covering real health needs of elderly people, mainly of people at high risk due to social and geographic isolation in addition to specific chronic diseases. The proposed EHC provides personalized intervention plans covering chronic diseases such as (body temperature (BT), blood pressure (BP), and Heart beat rate (HR)). The processes and architecture of the proposed EHC are based on the server side and three main clients, one for the elderly and another two for the nurse and the physicians whom take care of them. The proposed EHC model is discussed for proving the usefulness and effectiveness of the expert system.
... The technological revolution influenced everything , even the methods that aim to improve the community culture and knowledge by allowing the exchange of skills within the community through a free electronic platform. Today, the use of Artificial Intelligence (AI) algorithms is expansive, particularly in providing solutions to challenging problems including patterns recognition and retrieval of information [20,[26][27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42], image segmentation [5,6,16,[43][44][45][46][47][48], analysis of medical images [49][50][51][52][53] ...
The emergence of computer networking, e-mail and computer conferencing for exchange of scientific information encouraged the adoption of a collaborative learning approach to meet the needs of both learners. The platform aims to improve community culture and knowledge by allowing the exchange of skills within the community through a free electronic platform. It aims to shorten the distance between individuals and enrich the content of the platform with new courses including computer science, engineering, programming, artificial intelligence and space sciences. The platform aims to establish partnerships and cooperation agreements with regional and international leading institutions to exchange and develop skills and expertise. Also to improve and facilitate the process of communication between the parties to the maximum extent which ensures the success of the exchange process. The proposed system was developed using the Unified Modeling Language (UML) and Microsoft Visual Studio2010 programming language.
... They could be external hardware, human users or other Live Love RecycleApplication, the application helps individuals get rid of some recyclable waste in exchange for certain points and allows them to specify the days and hours they want to get rid technological revolution influenced everything , even the methods of complaint management applications for the real world complaint management issues. Today, the use of Artificial Intelligence (AI) algorithms is expansive, particularly in providing challenging problems including patterns recognition and retrieval of information [27,33 image segmentation [12,13,23,[50][51][52][53][54][55], analysis of medical image [56 86], nurse rostering problem [87], Healthcare Monitoring system [26,88], as well as prediction of river flow [89][90][91]. Accordingly, many researchers have used the Artificial Intelligence as an effective tool for environment protection, sustainability and Smart process of system analysis aims to study an existing system to entirely design a new system. ...
: Our society suffers a lot from the things that are thrown uselessly; these things may be beneficial to our society. On the other hand, communities suffer a lot of waste especially plastic waste; this has led to environmental pollution and depletion of natural resources. Therefore, this research aims to achieve sustainable development and achieve part of the Saudi Arabia vision 2030. Hence we have distributed a questionnaire to 88 responders, and based on the results of this study, which shows the importance of recycling and its impact on the environment and the extent of community interest in this subject and their supporters, The Let's Recycle site, based on the results of the questionnaire, will improve waste and plastics disposal in an environmentally positive manner. The proposed system was developed using the Unified Modeling Language (UML) and Microsoft Visual Studio2010 programming language.
... In the field of FS, GDA is used to improve local search of various state-of-the-art algorithms. This can be seen in [31] where Badawi et al. used a hybridised version of GA and GDA, Memetic Algorithm (MA), to perform fish classification. ...
Feature selection methods are used to identify and remove irrelevant and redundant attributes from the original feature
vector that do not have much contribution to enhance the performance of a predictive model. Meta-heuristic feature selection
algorithms, used as a solution to this problem, need to have a good trade-off between exploitation and exploration of
the search space. Genetic Algorithm (GA), a popular meta-heuristic algorithm, lacks exploitation capability, which in turn
affects the local search ability of the algorithm. Basically, GA uses mutation operation to take care of exploitation which
has certain limitations. As a result, GA gets stuck in local optima. To encounter this problem, in the present work, we have
intelligently blended the Great Deluge Algorithm (GDA), a local search algorithm, with GA. Here GDA is used in place
of mutation operation of the GA. Application of GDA yields a high degree of exploitation through the use of perturbation
of candidate solutions. The proposed method is named as Deluge based Genetic Algorithm (DGA). We have applied the
DGA on 15 publicly available standard datasets taken from the UCI dataset repository. To show the classifier independent
nature of the proposed feature selection method, we have used 3 different classifiers namely K-Nearest Neighbour (KNN),
Multi-layer Perceptron (MLP) and Support Vector Machine (SVM). Comparison of DGA has been performed with other
contemporary algorithms like the basic version of GA, Particle Swarm Optimisation (PSO), Simulated Annealing (SA) and
Histogram based Multi-Objective GA (HMOGA). From the comparison results, it has been observed that DGA performs
much better than others in most of the cases. Thus, our main contributions in this paper are introduction of a new variant of
GA for FS which uses GDA to strengthen its exploitational ability and application of the proposed method on 15 well-known
UCI datasets using KNN, MLP and SVM classifiers.
... The technological revolution influenced everything , even the methods of marketing, pattern recognition, business and educational applications for the real world business issues [24]. Today, the use of Artificial Intelligence (AI) algorithms is expansive, particularly in providing solution to challenging problems including image segmentation [39][40][41][42][43][44][45][46][47][48], analysis of medical image [49][50][51][52][53], nurse rostering problem [54], healthcare monitoring system [55,56], patterns recognition and retrieval of information [57][58][59][60][61][62][63][64][65][66][67][68][69][70][71][72], learning management system [73], as well as prediction of river flow [74][75][76]. Accordingly, utilizing the AI algorithms, countless scholars have created as well as implemented an algorithm for commanding using speech recognition in ARABIC language [77][78][79]. ...
This research adapted and implemented an algorithm for commanding using speech recognition in ARABIC language in addition to English, and the ability to train the system using other languages. The recognition based on discrete coefficient of the wavelet transform. Intelligent recognizer is built for two models, the first is Neural Networks, and the second is Fuzzy Logic Recognizer. The proposed speech recognition system consists of three phases; preprocessing phase (two processes are performed on the sound, DC level removal and resizing of sample for 2000 samples for each sound), feature extraction phase (features that distinguish each sound from another, it is wavelet transform coefficients), and recognition phase (many classifiers could be used for speaker recognition, in this research supervised neural networks, MLP and Fuzzy Logic classifiers are used. This research is also concerned with studying the recognition ability of MLP neural Network and Suggeno type Fuzzy Logic systems, for the recognition of Arabic and English Languages. The neural networks trained with features extracted from discrete wavelet transform. The use of Wavelet Transformation enables to extract an exact features form the speech. The research illustrates the effect of using two different intelligent approaches using MATLAB, and by applying the voice commands directly to an automated wheeled vehicle.
... The technological revolution influenced everything , even the methods of marketing, pattern recognition, business and educational applications for the real world business issues [24]. Today, the use of Artificial Intelligence (AI) algorithms is expansive, particularly in providing solution to challenging problems including image segmentation [39][40][41][42][43][44][45][46][47][48], analysis of medical image [49][50][51][52][53], nurse rostering problem [54], healthcare monitoring system [55,56], patterns recognition and retrieval of information [57][58][59][60][61][62][63][64][65][66][67][68][69][70][71][72], learning management system [73], as well as prediction of river flow [74][75][76]. Accordingly, utilizing the AI algorithms, countless scholars have created as well as implemented an algorithm for commanding using speech recognition in ARABIC language [77][78][79]. ...
This research adapted and implemented an algorithm for commanding using speech recognition in ARABIC language in addition to English, and the ability to train the system using other languages. The recognition based on discrete coefficient of the wavelet transform. Intelligent recognizer is built for two models, the first is Neural Networks, and the second is Fuzzy Logic Recognizer. The proposed speech recognition system consists of three phases; preprocessing phase (two processes are performed on the sound, DC level removal and resizing of sample for 2000 samples for each sound), feature extraction phase (features that distinguish each sound from another, it is wavelet transform coefficients), and recognition phase (many classifiers could be used for speaker recognition, in this research supervised neural networks, MLP and Fuzzy Logic classifiers are used. This research is also concerned with studying the recognition ability of MLP neural Network and Suggeno type Fuzzy Logic systems, for the recognition of Arabic and English Languages. The neural networks trained with features extracted from discrete wavelet transform. The use of Wavelet Transformation enables to extract an exact features form the speech. The research illustrates the effect of using two different intelligent approaches using MATLAB, and by applying the voice commands directly to an automated wheeled vehicle.
... Nowadays, Artificial Intelligence (AI) algorithms have been used widely for solving several difficult problems, such as image segmentation [9][10][11][12][13][14][15][16][17], medical image analysis [18][19][20][21][22], nurse rostering problem [23], Healthcare Monitoring [24,25], patterns recognition and information retrieval [26][27][28][29][30][31][32][33][34][35][36][37], Learning Management System [38] and river flow forecasting [39][40][41], Many researchers designed and implemented booking and scheduling web system using AI algorithms and web technology for covering real booking and reservations problems [42][43][44][45]. ...
To solve the imbalanced use of the university facilities such as Halls, Theaters, and Swimming pools and Sports Venues and as a part of the role of the university in the community services, the online facilities reservation system for Imam Abdulrahman Bin Faisal University (IAU) is designed and implemented through incorporating the existing online reservation systems experience. Based on the general requirement analysis, the basic function of the of the proposed IAU online reservation system are user's registration and login, halls, stadiums, theaters, swimming pools reservation and database construction. The proposed work was designed and implemented using the Unified Modeling Language (UML), MySQL and visual basic (VB) programming language. The proposed IAU online reservation system will solve the current lack of IAU facilities management system and give the ability to the people to reserve the university facilities as a part of the role of the university in the community services.
... The technological revolution influenced everything [13-22], even the methods of scheduling and booking for the real world reservations and booking issues. Nowadays, Artificial Intelligence (AI) algorithms is widely used, mainly in solving challenging problems including retrieval of information and patterns recognition [23][24][25][26][27][28][29][30][31][32][33][34], nurse rostering problem [35], analysis of medical image [36][37][38][39][40], Learning Management System (LMS) [41], prediction of river flow [42][43][44], image segmentation [45][46][47][48][49][50][51][52][53], as well as Healthcare Monitoring [54,55]. Consequently, utilizing the web technology and AI algorithms, there are numerous scholars have created and implemented scheduling and booking web systems to solve the real world reservations and booking issues [56][57][58][59]. ...
In most nations, the old transport system has been replaced with the evolutionary development of the new one to satisfy the socio economic necessity of the people. As Saudi Arabia's capital city, Riyadh is witnessing rapidly shifting microcosm of global trends in transportation, making this city an exceptional case study. This study examines the need and the development of computerized system of passenger reservation for Riyadh metro, with the aim of designing and implementing an online Metro Reservation System called Riyadh Metro Reservation System (RMRS). RMRS enables and assists passengers in managing reservation and modifying cancellation/refunds while overcoming excessing human interference in ticket's issuance process and efficiently managing their ticketing transaction, without having to face delay by the usual procedure of manual ticket issuing or obstacles from metro counter staff. The proposed system was designed and implemented utilizing the Unified Modeling Language (UML), Microsoft Access 2010 and ASP.NET programming languages.
... There exist already a variety of approaches for problem of classifying fish (Alsmadi et al., 2010;Badawi and Alsmadi, 2013;Lee et al., 2004;Matai et al., 2012;Rova et al., 2007;Spampinato et al., 2010) All of them have in common that the fish are classified according to engineered features, which are extracted from either the color/grayscale-image or the binary shape. This requires an exact delimitation of the fish from the background and the identification of certain key-points in an automated fashion. ...
This report presents a case study for automatic fish species classification in underwater video monitoring of fish passes. Although the presented approach is based on the FishCam monitoring system, it can be used with any video-based monitoring system. The presented classification scheme in this study, is based on Convolutional Neural Networks that do not require the calculation of any hand-engineered image features. Instead, these networks use the raw video image as input. Additionally, this study investigates, if the classification accuracy can be increased by adding additional meta-information (date of migration and fish length) to the network. The approach is tested on a subset of 10 fish species (8099~individuals) occurring in Austrian river. On an independent test set, the presented approach achieves a classification accuracy of 93 %.
... The future research should consider using algorithms of artificial intelligent (AI) in LMS for scheduling and matching users with courses and materials (Nabiyev et al., 2013;Cavus, 2010;Wakelam et al., 2015;Sivakumar et al., 2015;Gomede et al., 2018). The AI nowadays used extensively in solving many difficult problems, such as river flow forecasting (Alsmadi, 2017a;Adeyemo et al., 2018), medical image analysis (Alsmadi, 2014;2015;2016a;Park and Han, 2018;Kermany et al., 2018), image segmentation (Farag et al., 2017;Thalji and Alsmadi, 2013;Alsmadi, 2016b;Badawi and Alsmadi, 2013;Sharma et al., 2018;Gao et al., 2018), Healthcare Monitoring (Almarashdeh et al., 2018;Rasmi et al., 2018), patterns recognition and information retrieval (Al Smadi et al., 2015;Alsmadi, 2016;Alsmadi and Omar, 2012;Alsmadi, 2017b;2017c;Alsmadi et al., 2017;Badawi and Alsmadi, 2014;Yousuf et al., 2018) and nurse rostering problem (Jaradat et al., 2018). ...
In the last few years, the use of educational technology, particularly the concept of Learning Management System (LMS), has increased rapidly. With this fast development, the question arises as how to manage the LMS to obtain success and efficiency in online courses. One of the important factors that have received many citations in literature studies (and has a special position in information system research) is the user satisfaction. It is a crucial factor that can predict the success or failure of any LMS. In relation, this research examined the success factors that affect the user satisfaction and outcomes of LMS. This paper discusses the conceptual User Satisfaction Evaluation Model (USEM) employed to measures LMS success. In particular, it seeks to examine "the relationship between: Service quality, system quality, ease of use, perceived usefulness, information quality and students satisfaction, as well as to measure the outcomes of the LMS." Results from the data analysis indicate that all proposed factors have a positive effect on student satisfaction. The result also concludes that a higher rate of user satisfaction will lead to greater benefits for the students.
... There exist already a variety of approaches for problem of classifying fish (Alsmadi et al., 2010;Badawi and Alsmadi, 2013;Lee et al., 2004;Matai et al., 2012;Rova et al., 2007;Spampinato et al., 2010) All of them have in common that the fish are classified according to engineered features, which are extracted from either the color/grayscale-image or the binary shape. This requires an exact delimitation of the fish from the background and the identification of certain key-points in an automated fashion. ...
This report presents a case study for automatic fish species classification in underwater video monitoring of fish passes. Although the presented approach is based on the FishCam monitoring system, it can be used with any video-based monitoring system. The presented classification scheme in this study, is based on Convolutional Neural Networks that do not require the calculation of any hand-engineered image features. Instead, these networks use the raw video image as input. Additionally, this study investigates, if the classification accuracy can be increased by adding additional meta-information (date of migration and fish length) to the network. The approach is tested on a subset of 10 fish species (8099 individuals) occurring in Austrian river. On an independent test set, the presented approach achieves a classification accuracy of 93 %.
... The Active Ageing, which is the process of improving opportunities for elderly's health, security and participation which aims to improve quality of life as individuals age, is portion of the process of handling these chronic diseases, to make effort to keep the elderly healthy and participating in the social live [4]. Recently; artificial intelligence algorithms were widely used for solving very complicated problems, such as patterns recognition and information retrieval [24][25][26][27][28][29][30][31][32][33], image segmentations [34][35][36][37][38][39][40] and river flow forecasting [41], Many researchers employed communication technologies and information [6,42], and artificial intelligence algorithms [43][44][45][46] for covering real health needs of patients. ...
lderly chronic diseases are the main cause of death in the world, accounting 60% of all death. Because elderly with chronic diseases at the early stages has no observed symptoms, and then symptoms starts to appear, it is critical to observe the symptoms as early as possible to avoid any
complication. This paper presents an expert system for an Elderly Health Care (EHC) at elderly home tailored for the specific needs of Elderly. The proposed EHC aims to develop an integrated and multidisciplinary method to employ communication technologies and information for covering
real health needs of elderly people, mainly of people at high risk due to social and geographic isolation in addition to specific chronic diseases. The proposed EHC provides personalized intervention plans covering chronic diseases such as (body temperature (BT), blood pressure (BP), and Heart beat rate (HR)). The processes and architecture of the proposed EHC are based on the server side and three main clients, one for the elderly and another two for the nurse and the physician’s whom take care of them. The proposed EHC model is discussed for proving the usefulness and
effectiveness of the expert system
.
Real time bidding (RTB) is one of the most striking advances in online advertising, where the websites can sell each ad impression through a public auction, and the advertisers can participate in bidding the impression based on its estimated value. In RTB, the bidding strategy is an essential component for advertisers to maximize their revenues (e.g., clicks and conversions). However, most existing bidding strategies may not work well when the RTB environment changes dramatically between the historical and the new ad delivery periods since they regard the bidding decision as a static optimization problem and derive the bidding function only based on historical data. Thus, the latest research suggests using the reinforcement learning (RL) framework to learn the optimal bidding strategy suitable for the highly dynamic RTB environment. In this paper, we focus on using model free reinforcement learning to optimize the bidding strategy. Specifically, we divide an ad delivery period into several time slots. The bidding agent decides each impression’s bidding price depending on its estimated value and the bidding factor of its arriving time slot. Therefore, the bidding strategy is simplified to solve each time slot’s optimal bidding factor, which can adapt dynamically to the RTB environment. We exploit the Twin Delayed Deep Deterministic policy gradient (TD3) algorithm to learn each time slot’s optimal bidding factor. Finally, the empirical study on a public dataset demonstrates the superior performance and high efficiency of the proposed bidding strategy compared with other state of the art baselines.
This study aims to design a mathematical cost model for Blockchain Technology-enabled Supply Chain System (BT-enabled SCS), which may assist some companies that tend to evaluate the costs of BT as the main database in their SC system. We, therefore, identified the cost components of BT-enabled SCS based on the related literature review. The second purpose is to minimize the costs of the designed BT-enabled SCS model through Evolutionary Computation algorithms (CS/ACO/GA) as optimization techniques. To generate raw data for the model, the authors revised the Operations Research model and Inventory Management model as a mathematical formulation in Pharmaceutical Supply Chain. This mathematical formulation helps studies with a limitation of finding real data sets generate raw data in healthcare fields. Comparing CS/ACO/GA algorithms, the best solutions for the BT-enabled SCS cost model are CS and ACO with the higher Total Ranking Score (TRS) (scored by MSE, RMSE, and ROC), followed by GA standing in the second step. The more noteworthy finding is that all three algorithms have been able to find the global minimum for the BT-enabled SCS cost model with acceptable accuracy obtained from ROC.
The field of wild fish classification faces many challenges such as the amount of training data, pose variation and uncontrolled environmental settings. This research work introduces a hybrid genetic algorithm (GA) that integrates the simulated annealing (SA) algorithm with a back-propagation algorithm (GSB classifier) to make the classification process. The algorithm is based on determining the suitable set of extracted features using color signature and color texture features as well as shape features. Four main classes of fish images have been classified, namely, food, garden, poison, and predatory. The proposed GSB classifier has been tested using 24 fish families with different species in each. Compared to the back-propagation (BP) algorithm, the proposed classifier has achieved a rate of 87.7% while the elder rate is 82.9%.
Nowadays there are so many people who are surviving on only one meal per day. Especially in developing countries, it is one of the major problems. On the other hand, there is so much wastage of food every day. Some poor people need clothes and vessels, and children need some books and study kits. Solution to this is that we only need to donate the leftover food to needy people, charities, and our old stuff. For that to happen, we need some sort of platform. This could be any online platform like a website/web application. In Saudi Arabia, there are so many people who are capable of making donations and also there are so many Nongovernmental Organizations (NGOs) which are helping poor and needy people of Saudi Arabia. But to connection gap is not as blur as it should be. There has to be some simple, fast, intuitive and secure way of doing such online donations so that users can donate easily with just a click. The aim of this work is to design and develop a Web Based Online charitable Donation System. Where, the charitable website will collect the charitable donations (such as clothes, toys, school tools) and delivers it to the children who need it. The proposed system will provide voluntary opportunities for those wishing to be volunteer in delivering the donations to the homes of the poor for free. The proposed work was designed and developed using the Unified Modeling Language (UML), SQL Server for implemented the database, and ASP.net and Visual basic programming languages.
Modern institutions, corporations, schools and universities in developed countries believe that e-Learning is a way for educating larger number of students in less time and lesser amount of resources. This research aims to design and develop a web-based e-learning system to make the environment of e-learning more adaptive and intelligent for the learners. The main values of the proposed research are accessibility and interoperability that make learning applications and components share data more easily and communicate more effectively. The proposed work was developed and designed using ASP.Net, SQL, XML and the Unified Modeling Language (UML) programming languages.
Technology and Science have made Human life addictive to luxury but still there exists poor people who are trying to find innovative ways which make the communication process easier. Regarding to the World Health Organization, about 1 million people are dumb and 300 million are deaf in the world. Whereas; the communication is one of the most important issues for deaf and dumb people. This work aims to propose a smart application named "Jusoor" to improve the communication process and bridge the gap between the deaf, dumb People, and society. The proposed application provides the user with a dictionary that contains many vocabularies with videos explaining the way that the word is indicated, the most important sentences used in public places (markets, parks, restaurants, etc.), Emergency calls that enable recognizing the type assistance needed with the feature of locating the person which makes it easier to reach and provide the assistance, and service of communication with sign language experts. The proposed work was analyzed using the Unified Modeling Language (UML), Firebase, XML and Java programming languages.
Currently, the industry of tourism is meeting many challenges; one of the key challenges is the deficiency of having smart tourism systems which take advantage of the recent progresses in communication and information technology. Another problem is the design of a smart tourism systems while adopting diversified sustainable values of experience of the tourists (emotional values, social values, functional values, and epistemic values). The Kingdom of Saudi Arabia is characterized by the presence of many places of tourism, whether religious tourism or eco-tourism. The aim of this work is designing and implementing a web application named "travel key" that will help the tourists to get accurate and relevant information about the tourism places such as location, restaurants and events. The proposed application was designed and implemented by the Unified Modeling Language (UML), Microsoft Access 2010, and ASP.net, HTML, CSS, Visual basic programming languages. The proposed tourism system will be able to provide the tourists with recommendations for places to visit based on their preferences.
Information on pharmaceuticals is beneficial for patients, most patients like to read patient information leaflets for their pharmaceuticals. Nevertheless, the quality of the information written on pharmaceuticals gives space for improvement. To improve the inadequacies of patient information leaflets, an alternate approach for the provision of information on pharmaceuticals will be illustrated. This work aims to design and develop a web application that will provide pharmaceutical product leaflets information as well as the proposed web application will provide supplementary services. The proposed work was designed and developed using the Unified Modeling Language (UML), SQL, XML, and ASP.Net programming languages.
The increasing chronic disease’s epidemic is due to alcohol, smoking, lack of physical activity, obesity and unhealthy diet causing common diseases such as hypertension, osteoporosis, stroke, myocardial infarction renal insufficiency and diabetes. Preventive action against such diseases could be to improve health awareness through the use of health awareness platforms supporting behavior change and self-observation. Policy-makers play a vital role in decreasing the burden and risk of chronic diseases through implementing programs and policies that improve access to healthcare and provide a healthy environment. An official planning framework and national policy are crucial to give chronic diseases proper priority and to arrange resources properly. This work aims to design and develop a platform for chronic disease awareness. The proposed system was developed using the Unified Modeling Language (UML), ASP.NET, HTML and CSS.
Web-Based educational platform is now broadly adopted. These platforms are a real opportunities for education of a better quality for a lot of people. Though, people with disabilities are still meeting many barriers to use these systems. In fact, the main barrier is that most accessible Web-Based educational platforms is not available to people with disabilities and doesn’t consider their special needs. In this paper, we present an accessible web-based educational platform for children with special needs from the design step to the implementation. The motive for choosing this idea was the lack of comprehensive educational platforms for children in particular, which bring together children, parents and schools. The proposed platform will support the educational process in schools as the platform contains simplified explanations of what is taught in some school curricula such as numbers, letters and mathematical operations, and also forms a link between the child and his school where it contains worksheets and extracurricular activities that the teaching staff can benefit from. There is also a section for parents that include educational home games and simple books that enhance children's skills and train them on what has been learned. The proposed system was developed using the Unified Modeling Language (UML), ASP.NET , HTML and CSS.
Approximately 50% of all individuals with Autism have difficulties in developing functional language owing to communication deterioration. An online learning platform that provides educational games help these individuals feel more comfortable and relaxed doing such activities. Although numerous platforms are available for individuals with Autism, they are difficult to use; particularly in terms of user-interface design. In this paper, we present the design and develop online learning platforms, designed as a tool to encourage social interaction in autistic children. The proposed system was analyzed, design and developed using the Unified Modeling Language (UML) and ASP.NET.
According to the fast-changing business environment nowadays, we have to be more effective and faster in responding to customers' needs to make them able to access products instantly. This can be done by designing an E-commerce web website for unused goods, which sells various fashions and goods to the customers. To implement an online shopping website, a virtual store on the Internet is needed which allows customers to seek products and select them from a catalog. The customer needs to fill some fields to order a specific product. The purpose of this paper is designing and implementation of the website of unused goods, which sells various fashions and goods to the customers, the good that will be for sale on the website are new unused goods which the customer couldn’t return to the store they buy from to any reason. The proposed system was developed using the Unified Modeling Language (UML), ASP.NET and Access.
This work aims to design and develop a website that combines sports clubs in the Kingdom of Saudi Arabia, which provides all the information related to the clubs in the region in addition to the offers and discounts, with the ability to book and move from one club to another without the need to personally go to the club to register, in order to motivate them to participate in the appropriate clubs for them with ease way and show the best equipment and machines in addition to innovative programs, cardio and strength halls, freestyle and varied classes of exercise, internationally certified trainers and many features for members. The proposed system was developed using the Unified Modeling Language (UML) and PHP.
This paper presented a Smart Nursery application for busy parents so that they can ensure the safety and proper care for their babies. This system can show the baby’s motion, position and sound through live web-cam camera which is provided by the proposed smart application so that the parents or another responsible person can monitor the baby while away from him or her. This proposed smart application can provide a convenient and easy way for busy parents to take care of their babies. The proposed system was analyzed, design and developed using the Unified Modeling Language (UML), ASP.NET and HTML.
span>A smart city is a community that uses communication and information technology to improve sustainability, livability, and feasibility. As any community, there are always unexpected emergencies, which must be treated to preserve the regular order. However, a smart system is needed to be able to respond effectively to these emergent situations. The contribution made in this survey is twofold. Firstly, it provides a comprehensive exhaustive and categorized overview of the existing surveys for smart cities. The categorization is based on several criteria such as structures, benefits, advantages, applications, challenges, issues, and future directions. Secondly, it aims to analyze several studies with respect to emergent situations and management to smart cities. The analysis is based on several factors such as the challenges and issues discussed, the solutions proposed, and opportunities for future research. The challenges include security, privacy, reliability, performance, scalability, heterogeneity, scheduling, resource management, and latency. Few studies have investigated the emergent situations of smart cities and despite the importance of latency factor for smart city applications, it is rarely discussed.</span
Information-intensive Web services such as shipping comparison sites have recently been gaining popularity. However, most users including novice shoppers have difficulty in browsing such sites because of the massive amount of information gathered and the uncertainty surrounding Web environments. The aim of this research is to design a system which is called Shohnati to perform all procedures related to the order of shipment, and to store and process all information relating to customers or shipping companies in a database. Through this research, the customers will be able to order the shipment more easily by providing a complete comparison between the shipping companies, request the shipment from the preferred company's site, follow the shipment, and follow the latest offers of companies on our site. The proposed system was developed using the Unified Modeling Language (UML) and Visual Studio-ASP.NET programming language.
Image compression comprises a method for decreasing image size. In the image compression process, the redundancy in a matrix code is removed. Compression allows data to be efficiently transmitted or stored. This paper demonstrates the integration of the spatial domain and frequency domain in resizing image dimensions according to the pixel location. For image coding, the Discrete Cosine Transform (DCT) was employed in the frequency domain. Then, for coding and compressing the image, Huffman coding was used. During the first level, quantization was employed. Before using the Huffman decoding, Dequantization was used for image decoding. This prepares the matrix for the use of the Inverse Discrete Cosine Transform (IDCT), in the frequency domain for image decoding. The new algorithm is efficient, producing a high rate in image compression.
The diversity and quality of high-quality and diverse-solution external memory of the hybrid Elitist-Ant System is examined in this study. The Elitist-Ant System incorporates an external memory for preserving search diversity while exploiting the solution space. Using this procedure, the effectiveness and efficiency of the search may be guaranteed which could consequently improve the performance of the algorithm and it could be well generalized across diverse problems of combinatorial optimization. The generality of this algorithm through its consistency and efficiency is tested using a Nurse-Rostering Problem. The outcomes demonstrate the competitiveness of the hybrid Elitist-Ant System's performance within numerous datasets as opposed to those by other systems. The effectiveness of the external memory usage in search diversification is evidenced in this work. Subsequently, such usage improves the performance of the hybrid Elitist-Ant System over diverse datasets and problems.
Problem statement: One challenging research area nowadays is pattern recognition. Many applications lay under the field of pattern recognition such as face and iris recognition, speech recognition, texture discrimination and optical character recognition. A system that recognizes isolated pattern of interest is called pattern recognition. The pattern under consideration could be an image. During the process of image recognition, many problems could occur such as noise, distortion, overlap, errors in the segmentation results and obstruction of objects in the image. Several approaches to handle and solve pattern recognition problems have been developed. Examples of such approaches are neural networks (NN), Contour matching, texture and color signature. Approach: The aim of this study is to develop a system to recognize isolated fish object in the image based on a combination between significant extracted features using anchor points, texture and statistical measurements. A generic fish classification could then be performed using a hybrid meta-heuristic algorithms (genetic algorithm with iterated local search) with backpropagation algorithm (GAILS-BPC), to classify the images of fish into dangerous and non-dangerous families, and to recognize the dangerous fish families into Predatory and Poison fish family, and recognize the non-dangerous fish families into garden and food fish family. Conclusion and Results: A prototype to deal with the problem of fish images classification is presented in this research work. The proposed prototype has been tested based on 24 fish families, each family contains different number of species. The proposed prototype has performed the classification process successfully. The experimental tests have been performed based on 320 distinct fish images. The 320 distinct fish images were divided into 220 images for training phase and 100 images for testing phase. An overall accuracy recognition rate is 80.5% that was obtained using the proposed GAILS-BPC.
A variety of matching and classification techniques have been employed in applications requiring pattern recognition. In this
chapter we introduce a simple and accurate real-time contour matching technique specifically for applications involving fish
species recognition and migration monitoring. We describe FishID, a prototype vision system that employs a software implementation
of our newly developed contour matching algorithms. We discuss the challenges involved in the design of this system, both
hardware and software, and we present results from a field test of the system at Prosser Dam in Prosser, Washington. In tests
with up to four distinct species, the algorithm correctly determines the species with greater than 90 percent accuracy.
n this paper, a tabu-search algorithm enhanced by scatter search is presented. The algorithm solves the DNA sequencing problem with negative and positive errors, yielding outcomes of high quality. We compare the new method with two other metaheuristic approaches: a previous tabu-search method and a hybrid genetic algorithm, and also with an old branch-and-bound approach.
BPC method and previous methodologies by obtaining better quality results but with a high cost of computational time compared to the BPC method. Where the overall accuracy obtained using the traditional BPC was 86%, while the overall accuracy obtained by the HGAGD-BPC was 96% on the test dataset used. We developed a classifier for fish images classification. Eventually, the classifier is able to classify the given fish into poison and non-poison fish and classify the poison and non-poison fish into its family.
In this work we present an effective framework for color-texture classification where statistical features are computed from a generalized isotropic co-occurrence matrix extracted from color bands and combined with image entropies. The proposed approach has been effectively tested in RGB, HSL and La*b* color spaces. The tests were conducted in a variety of industrial samples. The obtained results are promising and show the possibility of efficiently classifying complex industrial products based on color and texture features.
There are several characteristics that make scheduling and timetabling problems particularly difficult to solve: they have
huge search spaces, they are often highly constrained, they require sophisticated solution representation schemes, and they
usually require very time-consuming fitness evaluation routines. There is a considerable number of memetic algorithms that
have been proposed in the literature to solve scheduling and timetabling problems. In this chapter, we concentrate on identifying
and discussing those strategies that appear to be particularly useful when designing memetic algorithms for this type of problems.
For example, the many different ways in which knowledge of the problem domain can be incorporated into memetic algorithms
is very helpful to design effective strategies to deal with infeasibility of solutions. Memetic algorithms employ local search,
which serves as an effective intensification mechanism that is very useful when using sophisticated representation schemes
and time-consumingfitness evaluation functions. These algorithms also incorporate a population, which gives them an effective
explorative ability to sample huge search spaces. Another important aspect that has been investigated when designing memetic
algorithms for scheduling and timetabling problems, is how to establish the right balance between the work performed by the
genetic search and the work performed by the local search. Recently, researchers have put considerable attention in the design
of self-adaptive memetic algorithms. That is, to incorporate memes that adapt themselves according to the problem domain being solved and also to the particular conditions of the search process.
This chapter also discusses some recent ideas proposed by researchers that might be useful when designing self-adaptive memetic
algorithms. Finally, we give a summary of the issues discussed throughout the chapter and propose some future research directions
in the design of memetic algorithms for scheduling and timetabling problems.
This paper proposes a novel approach to color–texture segmentation based on graph cut techniques, which finds an optimal color–texture segmentation of a color textured image by regarding it as a minimum cut problem in a weighted graph. A new texture descriptor based on the texton theory is introduced to efficiently represent texture attributes of the given image. Then, the segmentation is formulated in terms of energy minimization with graph cuts, where color and texton features are modelled with a multivariate finite mixture model with an unknown number of components. Contrary to previous supervised graph cut approaches, our method finds minimum cuts using split moves in an unsupervised way. The segmentation result, including the number of segments, is determined during the split moves without user interaction. Thus, our method is called unsupervised graph cuts. Experimental results of color–texture segmentation using various images including the MIT VisTex datasets and the Berkeley datasets are presented and analyzed in terms of precision and recall to verify its effectiveness.
This paper presents an interactive graphical user interface (GUI) based multiobjective evolutionary algorithm (MOEA) toolbox for effective computer-aided multiobjective (MO) optimization. Without the need of aggregating multiple criteria into a compromise function, it incorporates the concept of Pareto's optimality to evolve a family of nondominated solutions distributing along the tradeoffs uniformly. The toolbox is also designed with many useful features such as the goal and priority settings to provide better support for decision-making in MO optimization, dynamic population size that is computed adaptively according to the online discovered Pareto-front, soft/hard goal settings for constraint handlings, multiple goals specification for logical "AND"/"OR" operation, adaptive niching scheme for uniform population distribution, and a useful convergence representation for MO optimization. The MOEA toolbox is freely available for download at http://vlab.ee.nus.edu.sg/-kctan/moea.htm which is ready for immediate use with minimal knowledge needed in evolutionary computing. To use the toolbox, the user merely needs to provide a simple "model" file that specifies the objective function corresponding to his/her particular optimization problem. Other aspects like decision variable settings, optimization process monitoring and graphical results analysis can be performed easily through the embedded GUIs in the toolbox. The effectiveness and applications of the toolbox are illustrated via the design optimization problem of a practical ill-conditioned distillation system. Performance of the algorithm in MOEA toolbox is also compared with other well-known evolutionary MO optimization methods upon a benchmark problem.
Texture and color are two very important attributes in image analysis. While the color information describes the first order image properties, the texture generally describes second order property of surfaces and scenes, measured over image intensities. The need to include color aspect in texture analysis is being felt increasingly. The important aspect is, the way in which the chromatic information is involved in the formation and description of a texture. This paper describes an algorithm for classifying color textures using wavelet transform. Wavelet transform is useful for extracting texture features of images. A set of features are derived and color texture classification is done for different combination of the features and for different color models. The results obtained are found to be satisfactory.
This paper describes an approach to perceptual segmentation of
color image textures. A multiscale representation of the texture image,
generated by a multiband smoothing algorithm based on human
psychophysical measurements of color appearance is used as the input.
Initial segmentation is achieved by applying a clustering algorithm to
the image at the coarsest level of smoothing. The segmented clusters are
then restructured in order to isolate core clusters, i.e., patches in
which the pixels are definitely associated with the same region. The
image pixels representing the core clusters are used to form 3D color
histograms which are then used for probabilistic assignment of all other
pixels to the core clusters to form larger clusters and categorise the
rest of the image. The process of setting up color histograms and
probabilistic reassignment of the pixels to the clusters is then
propagated through finer levels of smoothing until a full segmentation
is achieved at the highest level of resolution