No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A Capsule Attention Network for Plant Disease Classification
Abstract
The identification of plant diseases is one of the most essential and difficult concerns in agriculture, necessitating solutions with a brighter light. With the onset of artificial intelligence (AI), machine learning (ML) and deep learning (DL) algorithms have aided farmers in identifying and classifying plant features with a high degree of intellectual precision. However, accurate disease classification in plants is essential for empowering farmers to cultivate more and produce more. This study therefore presents a unique assembly of attention, capsule, and feedforward classification layers for reaching the maximum classification accuracy for plant diseases. The proposed system uses user-defined customized Convolutional Transfer Learning networks (CTLN) to extract features and the attention networks exclude unnecessary features and highlight only critical features for classification. Finally, the selected characteristics are sent to the Feedforward Capsule networks to improve performance. This paper proposes a paradigm that overcomes the constraints of existing deep learning networks and drastically decreases the computing burden. The suggested network is thoroughly evaluated utilizing Plant Village databases containing over 50,000 photos of healthy and diseased plants. The performance metrics of the proposed method are evaluated and compared to those of other learning networks. Compared to previous models, experimental results indicate that the proposed model has a 99.8 percent accuracy rate, lending support to the new categorization method that benefits farmer well-being.
... Nonetheless, these methods introduce processing overhead and are vulnerable to unidentified hazard. The emergence of AI Models has enhanced the design of IDS, offering distinct advantages over conventional methodologies, effectively mitigating the challenge of detecting unknown attacks [10][11][12][13]. While machine and deep learning algorithm-driven Intrusion Detection Systems (IDS) present numerous advantages over traditional approaches, they encounter challenges with overfitting as the volume of attacks grows [14]. ...
... Else if (Tc < Tt21) 10 Anticipate a second assault. 11 ...
... In addition to real-time data collection, this research incorporates three distinct benchmarks to assess the proposed model. (10) In this context, TP and TN denote the values signifying correct identifications and accurate exclusions, while DR and TNI stand for the count of identified outcomes and the total number of trials, respectively. ...
The burgeoning importance of Internet of Things (IoT) and its diverse applications have sparked significant interest in study circles. The inherent diversity within IoT networks renders them suitable for a myriad of real-time applications, firmly embedding them into the fabric of daily life. While IoT devices streamline various activities, their susceptibility to security threats is a glaring concern. Current inadequacies in security measures render IoT networks vulnerable, presenting an enticing target for attackers. This study suggests a novel dealing to address this challenge through the execution of Intrusion Detection Systems (IDS) leveraging superior deep learning models. Inspired by the benefits of Long Short Term Memory (LSTM), we introduce the Genetic Bee LSTM(GBLSTM) networks for the development of intelligent IDS capable of detecting a wide range of cyber-attacks targeting IoT area. The methodology comprises four key execution: (i) collection of unit for profiling normal IoT device behavior, (ii) Identification of malicious devices during an attack, (iii) Prediction of attack types implemented in the network. Intensive experimentations of the suggested IDS are conducted using various validation methods and prominent metrics across different IoT threat scenarios. Moreover, comprehensive experiments are conducted to evaluate the suggested models alongside existing learning models. The results demonstrate that the GBLSTM-models outperform other intellectual models in terms of accuracy, precision, and recall, underscoring their efficacy in securing IoT networks.
... From Table 12, it is apparent that the encrypted bits demonstrate an increased randomness, making it significantly more challenging for an attacker to alter the medical data while transmitting. [37] 50.45 [38] 34.45 [39] 45.89 [40] 34.89 [41] 33.90 Proposed Encryption Schemes 18.89 ...
... To calculate the communication cost of the recommended model, encryption time is evaluated for the recommended model and contrasted with the existing models including Homographic Encryption model and other hybrid encryption models [37][38][39][40][41][42]. Table 13 presents the encryption time analysis between the different schemes. ...
... The methodology for the proposed paper is to focus on low-cost, strong encryption. In comparison, Habib et al. and Kalpna P et al. [38]. focus on functionality and physical control, while emphasizing strong encryption and authentication aims to solve the computational overhead problem found in other research. ...
... An overview of the comparison between the suggested protocol and existing state-ofthe-art protocols is provided in Table 3, which draws from references [37][38][39][40]43]. ...
Healthcare 4.0 is considered the most promising technology for gathering data from humans and strongly couples with a communication system for precise clinical and diagnosis performance. Though sensor-driven devices have largely made our everyday lives easier, these technologies have been suffering from various security challenges. Because of data breaches and privacy issues, this heightens the demand for a comprehensive healthcare solution. Since most healthcare data are sensitive and valuable and transferred mostly via the Internet, the safety and confidentiality of patient data remain an important concern. To face the security challenges in Healthcare 4.0, Web 3.0 and blockchain technology have been increasingly deployed to resolve the security breaches due to their immutability and decentralized properties. In this research article, a Web 3.0 ensemble hybrid chaotic blockchain framework is proposed for effective and secure authentication in the Healthcare 4.0 industry. The proposed framework uses the Infura Web API, Web 3.0, hybrid chaotic keys, Ganache interfaces, and MongoDB. To allow for more secure authentication, an ensemble of scroll and Henon maps is deployed to formulate the high dynamic hashes during the formation of genesis blocks, and all of the data are backed in the proposed model. The complete framework was tested in Ethereum blockchain using Web 3.0, in which Python 3.19 is used as the major programming tool for developing the different interfaces. Formal analysis is carried out with Burrows–Abadi–Needham Logic (BAN) to assess the cybersecurity reliability of the suggested framework, and NIST standard tests are used for a thorough review. Furthermore, the robustness of the proposed blockchain is also measured and compared with the other secured blockchain frameworks. Experimental results demonstrate that the proposed model exhibited more defensive characteristics against multiple attacks and outperformed the other models in terms of complexity and robustness. Finally, the paper gives a panoramic view of integrating Web 3.0 with the blockchain and the inevitable directions of a secured authentication framework for Healthcare 4.0.
... However, it has yielded considerable success and has been integrated into various phases of plant growth realized in the domain of precision agriculture. These include plant growth stress and disease detection [18][19][20][21] , growth monitoring 22,23 , plant seedling classification 24,25 , yield prediction 26 among others. Among these applications of AI on big data in agriculture, strawberry growth stage classification for nutrition management has remained largely unexplored. ...
Agriculture is vital for human sustenance and economic stability, with increasing global food demand necessitating innovative practices. Traditional farming methods have caused significant environmental damage, highlighting the need for sustainable practices like nutrition management. This paper addresses the emerging integration of artificial intelligence (AI) in agriculture, focusing on the specific challenge of growth stage classification of strawberry plants for optimized nutrition management. While AI has been successfully applied in various agricultural domains, such as plant stress detection and growth monitoring, the precise classification of strawberry growth stages remains underexplored. Accurate growth stage identification is vital for timely nutrient application, directly impacting yield and fruit quality. Our research identifies common gaps in existing literature, including limited or inaccessible datasets, outdated methodologies, and insufficient benchmarking. To overcome these shortcomings, we introduce a robust greenhouse-based dataset covering seven distinct strawberry growth stages, captured under diverse conditions. We then benchmark multiple state-of-the-art models on this dataset, finding that EfficientNetB7 achieves a testing accuracy of 0.837-demonstrating the promise of AI-driven approaches for precise and sustainable nutrient management in horticulture.
... Designing an intelligent detection system is vital as it empowers investigators to ascertain unusual behavioral patterns that could indicate criminal activity. Traditionally, anomaly detection in DF has relied on statistical methods and rule-based systems [12]. These techniques may fail to detect subtle irregularities intended to deceive investigative frameworks. ...
... The training dataset includes 12 different DDOS attacks and represents the specific DoS attack methodology. The 12 types of attacks are detailed in [26]. ...
Denial of service (DoS) attacks occur more frequently with the progressive development of the Internet of things (IoT) and other Internet-based communication technologies. Since these technologies are deeply rooted in the individual’s comfort life, protecting the user’s privacy and security against the growing DoS attack has become a major challenge among researchers. In recent times, intrusion detection systems (IDS) have developed a vital part in ensuring security against these growing attacks. IDS is still unable to attain the optimum categorization performance due to a few bottlenecks. The speed and performance of the existing IDS are challenged by the intricacy of high-dimensional data and the efficacy of the conventional base classifiers. To tackle this aforementioned problem, this research article presents the hybrid IDS based on the combination of stacked feature selection methods such as Random Boruta Selector (RFS), Relief, Pearson coefficient (PCE) and Stacked learning classifiers (SLF). To reduce the dimension of the data features and to select the optimal feature sets, novel integration of RFS, Relief, PCE are deployed. As the final step, stacked classifiers are used for the classification of DoS attacks. All the trials in this framework were accompanied utilizing CICDDoS-2019 datasets and contrasted with the other similar models. The validation boundaries such as accuracy, precision, recall, specificity, and F1-score are used to evaluate the proposed framework. With an F1-score of 96%, accuracy of 96.5%, precision of 96.0%, and recall of 95.8%, the suggested model obtained a CICDDoS-2019 score of 96%. Compared with the other traditional classifiers, the suggested framework has produced the best classification performance in detecting the DoS attacks.
... In [23], MedRec is presented as an Ethereum-based platform for medical data sharing, enabling the secure and decentralized integration of medical information across various healthcare organizations. It consumes the high computing overload while deploying in the block chain network. ...
Internet of Things (IoT) is adopted in a wide spectrum of applications in which a vast amount of data are produced and distributed to centralized cloud platforms to deliver various services. It involves smart devices that collect thousands of terabytes of heterogeneous data and deployed this to make instant decision that aids for the better performance and most comfort life. Traditional IoT architecture is heavily centralized, where it stores the most sensitive information that creates the multiple threats and security breaches as the attackers target towards these centralized cloud systems. To improve the security chain in IoT environment, edge computing (EC) was introduced to distribute the applications of IoT at the edge of the communication networks. However, these edge-based IoT are also vulnerable to many threats due to their decentralized and in secured management. Block chain (BC) technology offers a most trusted solution to resolve the security issues in the IoT-Edge computing environment. This research study presents the block chain driven medical image encryption technique using modified honey badger optimization with the ensemble chaotic systems. The proposed block chain framework uses the divergent methods that integrates differential scroll, Hénon chaotic maps and modified honey badger optimization to generate the optimum keys and high secured image data. These high secured data are stored in the block chain, ensuring the image security to be stored in edge nodes. The complete framework was experimented using Ethereum using Ganache API and Python3.19 are utilized as the major programs for designing the varied interfaces of the recommended model. The comprehensive experimentation is undertaken to assess the security strength of the recommended encryption scheme. The evaluation metrics like as NACI, UACI, Entropy and standard verification methods such as NIST standard tests are deployed and analyzed. To prove it security strength, proposed secured BC framework is compared with the wide-variety of secured frameworks. The experimental findings reveal that the suggested framework establishes a more robust and secure environment for image exchange, surpassing the performance of other blockchain-based systems in terms of integrity, robustness and security. Finally, the paper spreads the bright light of advantages in deploying the proposed framework to formulate the most secured environment in the IoT-Edge environment for medical image transmission.
... These structures enable DL to extract more intricate features from the data. Existing DL methods such as U-NETS [11], SegNets [12], Fully Connected Convolutional Neural Networks [13] and Hybrid ResNets [14,15] are deployed for the segmentation. Furthermore, these methods suffer from the gradient problems [16][17][18][19][20] which stops to achieve the best performance. ...
... Motivated by the COVID-19 outbreak, the quick shift to online learning has exposed several challenges including technology acceptability, student participation, and effective evaluation techniques [20,21]. While various studies have proposed multi-criteria decision-making models for optimising distant learning, these models sometimes need extensive validation across several educational contexts and demographic groups [22]. Even it is studied well in different applications [26][27][28][29][30][31][32][33][34][35][36][37]. ...
Artificial intelligence (AI) into education is becoming a transformative agent offering new chances for enhancing administrative processes, teaching, and learning. Particularly machine learning (ML) and deep learning (DL), recent advances in artificial intelligence technologies have shown great potential in predicting academic achievement, improving teaching strategies, and so supporting decision-making inside educational institutions. Notwithstanding these advances, there are obvious problems and limits that have to be addressed if we are to fully exploit the potential of artificial intelligence in the field of education. Recent research reveals significant limits like poor contextual adaptability of artificial intelligence models, insufficient integration of emerging technologies like augmented reality (AR), and challenges in improving distance learning. Although the integration of AR into educational systems is still under investigated, current artificial intelligence models usually rely on generalised datasets lacking the diversity of educational environments. The shift to online learning has underscored even more the requirement of solid, contextually relevant models to manage assessment strategies, student interaction, and technology acceptance. By means of a comprehensive examination of the corpus of present literature, this paper evaluates the present position of artificial intelligence applications in education so highlighting research needs and constraints. Emphasising their capacity to solve the discovered challenges, the survey focusses on ML and DL application. By means of analysis of current studies and recommended future research routes, this study aims to offer pragmatic insights and recommendations for enhancing the efficiency of artificial intelligence in educational environments.
... Diseases affecting common crops like potatoes, tomatoes, and peppers can result in substantial financial losses for farmers each year. For instance, blight, a prevalent disease, has two forms: early blight, caused by a fungus, and late blight, caused by specific bacteria [2][3][4][5][6][7][8][9]. By detecting these diseases early, farmers can mitigate costs and prevent waste. ...
Plant disease detection is critical for ensuring agricultural productivity. Early and accurate identification of plant diseases can help in the timely application of remedies, reducing yield loss and improving crop quality. This paper presents a deep learning(DL) approach using Convolutional Neural Networks (CNN) for plant disease detection, combined with an advanced optimization technique named the Beluga Whale Optimization Mechanism (BWOM). The CNN is implemented to extract and features from plant images, providing a robust model capable of differentiating between healthy and diseased plants. The BWOM is utilized to optimize the CNN's hyper parameters and weights, enhancing model accuracy and efficiency by reducing overfitting and improving generalization. The BWOM mimics the social behaviour and echolocation techniques of beluga whales to navigate and optimize solution spaces effectively. By iterating through population-based exploration and exploitation phases, BWOM provides a balanced search mechanism to fine-tune CNN parameters. Further the results demonstrate the effectiveness of combining CNN with BWOM in achieving high accuracy rates for plant disease classification.
... To mitigate these challenges, various network security countermeasures such as firewalls and intrusion detection systems (IDS) have been implemented. Recently, Artificial Intelligence (AI) has been leveraged to address these security challenges without human intervention [10][11][12]. However, as the number of IoT devices increases, the volume and complexity of data also grow exponentially, resulting in significant computational overhead when deploying AI in IoT-based smart city infrastructures. ...
Recent advancements in the Internet of Things (IoT) have paved the way for intelligent and sustainable solutions in smart city environments. However, despite these advantages, IoT-connected devices present significant privacy and security risks, as network attacks increasingly exploit user-centric information. To protect the network against the rapidly growing number of cyber-attacks, it is essential to employ a cognitive intrusion detection system (CIDS) capable of handling complex and voluminous network data. This research presents a novel ensemble deep learning framework designed to enhance cybersecurity in IoT-based smart city ecosystems. The proposed architecture integrates Self-Attention Convolutional Neural Networks, Bidirectional Gated Recurrent Units, and Shark Smell Optimized Feed Forward Networks to create a robust, adaptive system for detecting and mitigating cyber threats. By leveraging fog computing, the model significantly reduces latency and computational overhead, making it highly suitable for large-scale IoT deployments. Extensive experimentation using the ToN-IoT dataset demonstrates the framework's exceptional performance, achieving a 99.78% detection rate across various attack types and an AUC of 0.989. The proposed model outperforms existing state-of-the-art approaches, achieving a mean fitness function value of 0.85640 and a standard deviation of 0.037630 in binary classification outcomes. In multi-class classification, the model maintains a mean fitness function value of 0.8230 and a variance of 2.28930 × 104, significantly outperforming other meta-heuristic algorithms such as Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). The model exhibits superior accuracy and efficiency compared to existing state-of-the-art approaches, particularly in identifying complex and emerging threats. This research makes significant contributions by introducing innovative feature extraction techniques, optimizing model performance for resource-constrained environments, and providing a scalable solution for securing smart city infrastructure. The findings highlight the potential of ensemble deep learning approaches to fortify IoT networks against cyberattacks, paving the way for more resilient and secure smart cities.
... Networks linking physical systems with their control software are especially susceptible to external threats, as attackers may target these systems to disrupt CPS functionality and trigger malfunctions in the physical components [9]. Machine learning is increasingly adopted in cyber-physical security because it can establish correlations between inputs and outputs using vast data sets without relying on physical laws [10]. ML-based approaches offer advanced detection capabilities, making them critical in safeguarding CPS. ...
Cyber-Physical Systems (CPS) have become a research hotspot due to their vulnerability to stealthy network attacks like ZDA and PDA, which can lead to unsafe states and system damage. Recent defense mechanisms for ZDA and PDA often rely on model-based observation techniques prone to false alarms. In this paper, we present an innovative approach to securing CPS against Advanced Persistent Threat (APT) injection attacks by integrating machine learning with blockchain technology. Our system leverages a robust ML model trained to detect APT injection attacks with high accuracy, achieving a detection rate of 99.89%. To address the limitations of current defense mechanisms and enhance the security and integrity of the detection process, we utilize blockchain technology to store and verify the predictions made by the ML model. We implemented a smart contract on the Ethereum blockchain using Solidity, which logs the input features and corresponding predictions. This immutable ledger ensures the integrity and traceability of the detection process, mitigating risks of data tampering and reducing false alarms, thereby enhancing trust in the system's outputs. The implementation includes a user-friendly interface for inputting features, a backend for data processing and model prediction, and a blockchain interaction module to store and verify predictions. The integration of blockchain with Machine learning enhances both the precision and resilience of APT detection while providing an additional layer of security by ensuring the transparency and immutability of the recorded data. This dual approach represents a substantial advancement in protecting CPS from sophisticated cyber threats.
... Despite these challenges, such approaches offer potential solutions for enhancing the robustness of FL against adversarial threats. By carefully selecting participants and ensuring secure communication, these methods aim to create a more resilient network capable of withstanding Byzantine attacks [13]. Ultimately, these techniques contribute to the overall security and integrity of FL models, making them more robust and reliable in real-world applications. ...
Federated learning, which enables decentralized training across multiple devices while maintaining data privacy, is susceptible to Byzantine poisoning attacks. This paradigm reduces the need for centralized data storage and transmission, thereby mitigating privacy risks associated with traditional data aggregation methods. However, FL introduces new challenges, notably susceptibility to Byzantine poisoning attacks, where rogue participants can tamper with model updates, threatening the consistency and security of the aggregated model. Our approach addresses this vulnerability by implementing robust aggregation methods, sophisticated pre-processing techniques, and a novel Byzantine grade-level detection mechanism. We introduce a federated aggregation operator designed to mitigate the impact of malicious clients. Our pre-processing includes data loading and transformation, data augmentation, and feature extraction using SIFT and wavelet transforms. Additionally, we employ differential privacy and model compression to improve the robustness and performance of the federated learning framework. Our approach is assessed using a tailored neural network model applied to the MNIST dataset, achieving 97% accuracy in detecting Byzantine attacks. Our results demonstrate that robust aggregation significantly improves the resilience and performance. This comprehensive approach ensures the integrity of the federated learning process, effectively filtering out adversarial influences and sustaining high accuracy even when faced with adversarial Byzantine clients.
... The testing is conducted using component architectures that have the same specifications as the suggested framework. Specifications of the residing frameworks included "one-dimensional LSTM [34], hybrid GRU [35], optimized LSTM [36], and attention-based BiGRU(A-BiGRU) [37]." For validating the algorithm, a comparative analysis has been conducted utilizing four distinct datasets. ...
The Internet of Things (IoT) has emanated as an innovative technology that grants users to establish connections to external servers located in the cloud and the uninterrupted Internet, allowing them to live more comfortably. As the number of users increases, security and privacy breaches also increase exponentially, as it invests the greatest threats to the IoT networked devices and cloud storage. Though machine and deep learning algorithms have paved the bright light toward the design of intelligent systems to mitigate the attacks, creating effective defenses against numerous assaults remains a significant design challenge for researchers, and accurately predicting these attacks continues to pose an ongoing hurdle. To solve this problem, this paper proposes a hybrid learning model that ensembles the skip connection-based gated recurrent units (Skip-GRU) and bi-layered self-attention networks to predict and mitigate the different attacks. First, Skip-GRU is constructed using residual connections that remove redundant information and capture only global features. Second, novel bi-layered privacy-preserving networks are combined to obtain the spatial and temporal attributes. Finally, softmax is utilized to obtain the prediction results of sample labels. Performance parameters including accuracy, precision, recall, and F1-score are assessed and evaluated during the comprehensive eradication exploration that is conducted utilizing the NSL-KDD and UNSW datasets. By comparing how it performs to other cutting-edge approaches to learning, the one recommended demonstrates its superiority. The technique has proven its efficacy in providing enough security versus various threats, as seen by the results, which show that it has obtained 0.97 accuracy, 0.96 precision, 0.96 recall, and 0.96 F1-score.
... The positive Lyapunov is a symptom of chaotic conditions. This crucial characteristic increases output unpredictability, encouraging many research efforts to employ chaotic systems in cryptographic encryptions [12]. Besides Lorentz maps, logistic maps are predominantly used for encryption to achieve lightweight and highly secured data transmission. ...
The telemedicine sector has entered a new phase marked by the integration of Internet of Things (IoT) devices to identify and then send patient health data to medical terminals for additional diagnostic and therapeutic procedures. Today, patients can receive prompt and expert medical care at home in comfortable settings. Due to the unique nature of these services, it is essential to verify patient healthcare data, as it contains a greater amount of personal information that is vulnerable to privacy violations and data breaches. Blockchain technology has attracted interest in addressing security concerns due to its decentralized, immutable, shared, and distributed characteristics. This study proposes lightweight dynamic blockchain-enabled encryption schemes to secure physiological data during authentication and exchange processes. The proposed scheme introduces the logistic Advanced Encryption Scheme (AES) that combines chaotic logistic maps to secure the data in the blockchain network and mitigate different attacks. The model was deployed on the Ethereum blockchain and performance metrics, such as computation and transaction time, were calculated and compared with other current blockchain-inspired encryption models. Furthermore, the NIST test was conducted to prove the strength of the proposed scheme. The proposed model exhibits high security and a shorter transaction time (0.964 s) than other existing schemes. Finally, the proposed model generates high-dynamic keys that are suitable for defending against unpredictable attacks on blockchain.
Chemotaxonomic profiling based on secondary metabolites offers a reliable approach for identifying and authenticating medicinal plants, addressing limitations associated with traditional morphological and genetic methods. Recent advances in microfluidics and nanoengineered technologies—including lab-on-a-chip systems as well as nano-enabled optical and electrochemical sensors—enable the rapid, accurate, and portable detection of key metabolites, such as alkaloids, flavonoids, terpenoids, and phenolics. Integrating artificial intelligence and machine learning techniques further enhances the analytical capabilities of these technologies, enabling automated, precise plant identification in field-based applications. Therefore, this review aims to highlight the potential applications of micro- and nanoengineered devices in herbal medicine markets, medicinal plant authentication, and biodiversity conservation. We discuss strategies to address current challenges, such as biocompatibility and material toxicity, technical limitations in device miniaturization, and regulatory and standardization requirements. Furthermore, we outline future trends and innovations necessary to fully realize the transformative potential of these technologies in real-world chemotaxonomic applications.
With the revolutionary change in emerging technologies, the usage of drones or unmanned aerial vehicles (UAV) has exponentially increased in different sectors like Industry, healthcare, military, agriculture, real estate, manufacturing, logistics, energy and many more utilities. This rapid growth creates a concern for the secure communication between the internal communication modules and the ground based computer system used for controlling the UAV. Intruder can hack into the device and attack the internal communication device with the injection of the malicious code which can lead to the malfunction of the aircraft. Security issues related to the communication between the internal modules of the drone and the ground based computer system is of major concern and is crucial. UAVs have to operate in constrained networks with limited bandwidth. In such a constrained environment MQTT protocol can be an excellent protocol. No cryptographic techniques are used to retain the simplicity and the light weight of the MQTT protocol. This contributes for the large scope for emerging with new solutions in the protection issues of MQTT communications. This paper mainly focuses on Armstrong number encryption standard algorithm for providing a computationally simple yet a secure and strong algorithm for UAVs encryption and decryption process on the communication links using MQTT protocol.
LTE (Long-Term Evolution) is one of the appropriate technologies to sever the requirement of the IoT (Internet of Things) together with mobile UE (User Equipment), because of priority services, high data rate, low latency, etc. LTE has received OFDM for the transmission because it meets the necessity of LTE-like range flexibility and empowers the cost gainful responses for the wide carriers. LTE offers big-data values, allows spectrum reframing, reduces cost, etc. We proposed a 4G/5G adopted OFDM based on the multi-equalizer and BPSK (Binary-Phase Shift Keying). The BER (Bit Error Rate) of the system is reduced through the optimal wavelet coefficient at the transmitter side. This optimal wavelet coefficient is obtained by applying a DWT (Discrete Wavelet Transform) to the input signal through a BFF (Binary Firefly) algorithm. The serial to parallel process is carried out through the BPSK modulation. At last, the multi-equalizer like MMSE (Minimized Mean Square Error) and MLE (Maximum Likelihood) is applied to the OFDM model to reduce the BER. The system is analyzed using the parameter like SER (Symbol Error Rate), spectral efficiency, MSE (Mean Square Error), and BER. The proposed methodology provides a better outcome than the other existing approaches.
The field of peptides and proteins has opened up new doors for plant-based medication development because of analytical breakthroughs. Enzymatic breakdown of plant-specific proteins yields bioactive peptides. These plant-based proteins and peptides, in addition to their in vitro and vivo outcomes for diabetes treatment, are discussed in this study. The secondary metabolites of vegetation can interfere with the extraction, separation, characterization, and commercialization of plant proteins through the pharmaceutical industry. Glucose-lowering diabetic peptides are a hot commodity. For a wide range of illnesses, bioactive peptides from flora can offer up new avenues for the development of cost-effective therapy options.
Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations. That is highly inefficient and for large datasets implies a massive redundancy of features detectors. Even though capsules networks are still in their infancy, they constitute a promising solution to extend current convolutional networks and endow artificial visual perception with a process to encode more efficiently all feature affine transformations. Indeed, a properly working capsule network should theoretically achieve higher results with a considerably lower number of parameters count due to intrinsic capability to generalize to novel viewpoints. Nevertheless, little attention has been given to this relevant aspect. In this paper, we investigate the efficiency of capsule networks and, pushing their capacity to the limits with an extreme architecture with barely 160 K parameters, we prove that the proposed architecture is still able to achieve state-of-the-art results on three different datasets with only 2% of the original CapsNet parameters. Moreover, we replace dynamic routing with a novel non-iterative, highly parallelizable routing algorithm that can easily cope with a reduced number of capsules. Extensive experimentation with other capsule implementations has proved the effectiveness of our methodology and the capability of capsule networks to efficiently embed visual representations more prone to generalization.
This study presents a new deep learning approach based on capsule networks and ensemble learning for the detection of plant diseases. The developed method is called as multi-channel capsule network ensemble. The main innovation behind the proposed method is the use of multi-channel capsule networks, individually trained on images applied different preprocessing techniques and then combined together. In this way, the final ensemble can better detect plant diseases by making use of different attributes of the data. Our experiments carried out using a well-known data set and various state-of-the-art classification methods demonstrate that our classification approach can provide competitive advantages in terms of classification accuracy.
Article Highlights
An ensemble of capsule networks has been developed for the automated detection of plant diseases with high accuracies.
Better accuracy has been achieved with ensemble learning compared to a single model
With the proposed method, better results have been obtained compared to state-of-the-art classification methods in the literature
Deep Learning (DL) is a high capable machine learning algorithm which composed the advanced image processing as feature learning and supervised learning with detailed models with many hidden layers and neurons. DL demonstrated its efficiency and robustness in many big data problems, computer vision, and more. Whereas it has an increasing popularity day by day, it has still some deficiencies to construe the relationship between learned feature maps and spatial information. Capsule network (CapsNET) is proposed to overcome the shortcoming by excluding the pooling layer from the architecture and transferring spatial information between layers by capsule. In this paper, CapsNET architecture was proposed to evaluate the performance of the model on classification of plant leaf diseases using simple reduced capsules on leaf images. Plant leaf diseases are common and prevalent diseases that disrupt harvesting and yielding for agriculture. CapsNET has capability of detailed analysis for even small stains that may lead seed dressing time and duration. The proposed CapsNET model aimed at assessing the applicability of various feature learning models and enhancing the learning capacity of the DL models for bell pepper plants. The healthy and diseased leaf images were fed into the CapsNET. The proposed CapsNET model reached high classification performance rates of 95.76%, 96.37%, and 97.49% for accuracy, sensitivity, and specificity, respectively.
National-level mapping of crop types is important to monitor food security, understand environmental conditions, inform optimal use of the landscape, and contribute to agricultural policy. Countries or economic regions currently and increasingly use satellite sensor data for classifying crops over large areas. However, most methods have been based on machine learning algorithms, with these often requiring large training datasets that are not always available and may be costly to produce or collect. Focusing on Wales (United Kingdom), the research demonstrates how the knowledge that the agricultural community has gathered together over past decades can be used to develop algorithms for mapping different crop types. Specifically, we aimed to develop an alternative method for consistent and accurate crop type mapping where cloud cover is quite persistent and without the need for extensive in situ/ground datasets. The classification approach is parcel-based and informed by concomitant analysis of knowledge-based crop growth stages and Sentinel-1 C-band SAR time series. For 2018, crop type classifications were generated nationally for Wales, with regional overall accuracies ranging between 85.8 % and 90.6 %. The method was particularly successful in distinguishing barley from wheat, which is a major source of error in other crop products available for Wales. This study demonstrates that crops can be accurately identified and mapped across a large area (i.e., Wales) using Sentinel-1 C-band data and by capitalizing on knowledge of crop growth stages. The developed algorithm is flexible and, compared to the other methods that allow crop mapping in Wales, the approach provided more consistent discrimination and lower variability in accuracies between classes and regions.
Tomato is affected by various diseases and pests during its growth process. If the control is not timely, it will lead to yield reduction or even crop failure. How to control the diseases and pests effectively and help the vegetable farmers to improve the yield of tomato is very important, and the most important thing is to accurately identify the diseases and insect pests. Compared with the traditional pattern recognition method, the diseases and pests recognition method based on deep learning can directly input the original image. Instead of the tedious steps such as image preprocessing, feature extraction and feature classification in the traditional method, the end-to-end structure is adopted to simplify the recognition process and solve the problem that the feature extractor designed manually is difficult to obtain the feature expression closest to the natural attribute of the object. Based on the application of deep learning object detection, not only can save time and effort, but also can achieve real-time judgment, greatly reduce the huge loss caused by diseases and pests, which has important research value and significance. Based on the latest research results of detection theory based on deep learning object detection and the characteristics of tomato diseases and pests images, this study will build the dataset of tomato diseases and pests under the real natural environment, optimize the feature layer of Yolo V3 model by using image pyramid to achieve multi-scale feature detection, improve the detection accuracy and speed of Yolo V3 model, and detect the location and category of diseases and pests of tomato accurately and quickly. Through the above research, the key technology of tomato pest image recognition in natural environment is broken through, which provides reference for intelligent recognition and engineering application of plant diseases and pests detection.
To improve the recognition model accuracy of crop disease leaves and locating diseased leaves, this paper proposes an improved Faster RCNN to detect healthy tomato leaves and four diseases: powdery mildew, blight, leaf mold fungus and ToMV. First, we use a depth residual network to replace VGG16 for image feature extraction so we can obtain deeper disease features. Second, the k-means clustering algorithm is used to cluster the bounding boxes. We improve the anchoring according to the clustering results. The improved anchor frame tends toward the real bounding box of the dataset. Finally, we carry out a k-means experiment with three kinds of different feature extraction networks. The experimental results show that the improved method for crop leaf disease detection had 2.71% higher recognition accuracy and a faster detection speed than the original Faster RCNN.
Accurate spatio-temporal classification of crops is of prime importance for in-season crop monitoring. Synthetic Aperture Radar (SAR) data provides diverse physical information about crop morphology. In the present work, we propose a day-wise and a time-series approach for crop classification using full-polarimetric SAR data. In this context, the 4 × 4 real Kennaugh matrix representation of a full-polarimetric SAR data is utilized, which can provide valuable information about various morphological and dielectric attributes of a scatterer. The elements of the Kennaugh matrix are used as the parameters for the classification of crop types using the random forest and the extreme gradient boosting classifiers. The time-series approach uses data patterns throughout the whole growth period, while the day-wise approach analyzes the PolSAR data from each acquisition into a single data stack for training and validation. The main advantage of this approach is the possibility of generating an intermediate crop map, whenever a SAR acquisition is available for any particular day. Besides, the day-wise approach has the least climatic influence as compared to the time series approach. However, as time-series data retains the crop growth signature in the entire growth cycle, the classification accuracy is usually higher than the day-wise data. Within the Joint Experiment for Crop Assessment and Monitoring (JECAM) initiative, in situ measurements collected over the Canadian and Indian test sites and C-band full-polarimetric RADARSAT-2 data are used for the training and validation of the classifiers. Besides, the sensitivity of the Kennaugh matrix elements to crop morphology is apparent in this study. The overall classification accuracies of 87.75% and 80.41% are achieved for the time-series data over the Indian and Canadian test sites, respectively. However, for the day-wise data, a ∼6% decrease in the overall accuracy is observed for both the classifiers.
This paper applies deep convolutional neural network (CNN) to identify tomato leaf disease by transfer learning. AlexNet, GoogLeNet, and ResNet were used as backbone of the CNN. The best combined model was utilized to change the structure, aiming at exploring the performance of full training and fine-tuning of CNN. The highest accuracy of 97.28% for identifying tomato leaf disease is achieved by the optimal model ResNet with stochastic gradient descent (SGD), the number of batch size of 16, the number of iterations of 4992, and the training layers from the 37 layer to the fully connected layer (denote as “fc”). The experimental results show that the proposed technique is effective in identifying tomato leaf disease and could be generalized to identify other plant diseases.
Automatic and accurate estimation of disease severity is essential for food security, disease management, and yield loss prediction. Deep learning, the latest breakthrough in computer vision, is promising for fine-grained disease severity classification, as the method avoids the labor-intensive feature engineering and threshold-based segmentation. Using the apple black rot images in the PlantVillage dataset, which are further annotated by botanists with four severity stages as ground truth, a series of deep convolutional neural networks are trained to diagnose the severity of the disease. The performances of shallow networks trained from scratch and deep models fine-tuned by transfer learning are evaluated systemically in this paper. The best model is the deep VGG16 model trained with transfer learning, which yields an overall accuracy of 90.4% on the hold-out test set. The proposed deep learning model may have great potential in disease control for modern agriculture.
The ability of learning networks to generalize can be greatly enhanced by providing constraints from the task domain. This paper demonstrates how such constraints can be integrated into a backpropagation network through the architecture of the network. This approach has been successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service. A single network learns the entire recognition operation, going from the normalized image of the character to the final classification.
When anyone is looking to enroll for a freely available online course so the first and famous name comes in front of the searcher is MOOC courses. So here in this article our focus is to collect the comments by enrolled users for the specified MOOC course and apply sentiment analysis over that data. The significance of our article is to introduce a proficient sentiment analysis algorithm with high perceptive execution in MOOC courses, by seeking after the standards of gathering various supervised learning methods where the performance of various supervised machine learning algorithms in performing sentiment analysis of MOOC data. Some research questions have been addressed on sentiment analysis of MOOC data. For the assessment task, we have investigated a large no of MOOC courses, with the different Supervised Learning methods and calculated accuracy of the data by using parameters such as Precision, Recall and F1 Score. From the results we can conclude that when the bigram model was applied to the logistic regression, the Multilayer Perceptron (MLP) overcomes the accuracy by other algorithms as SVM, Naive Bayes and achieved an accuracy of 92.44 percent. To determine the sentiment polarity of a sentence, the suggested method use term frequency (No of Positive, Negative terms in the text) to calculate the sentiment polarity of the text. We use a logistic regression Function to predict the sentiment classification accuracy of positive and negative comments from the data.
Plant diseases and pernicious insects are a considerable threat in the agriculture sector. Therefore, early detection and diagnosis of these diseases are essential. The ongoing development of profound deep learning methods has greatly helped in the detection of plant diseases, granting a vigorous tool with exceptionally precise outcomes but the accuracy of deep learning models depends on the volume and the quality of labeled data for training. In this paper, we have proposed a deep learning-based method for tomato disease detection that utilizes the Conditional Generative Adversarial Network (C-GAN) to generate synthetic images of tomato plant leaves. Thereafter, a DenseNet121 model is trained on synthetic and real images using transfer learning to classify the tomato leaves images into ten categories of diseases. The proposed model has been trained and tested extensively on publicly available PlantVillage dataset. The proposed method achieved an accuracy of 99.51%, 98.65%, and 97.11% for tomato leaf image classification into 5 classes, 7 classes, and 10 classes, respectively. The proposed approach shows its superiority over the existing methodologies.
Crop type mapping visualizes the spatial distribution patterns and proportions of the cultivated areas with different crop types, and is the basis for subsequent agricultural applications. Understanding the effectiveness of different temporal and spectral features in detailed crop classification can help users optimize temporal window selection and spectral feature space construction in crop type mapping applications. Therefore, in this study, we used time-series Sentinel-2 image data from Yi’an County, Heilongjiang province, China, to analyze the effectiveness of the temporal and spectral features used in three common machine learning classification methods: classification and regression tree (CART) decision tree, Support Vector Machine (SVM), and random forest (RF). For CART and SVM classifiers, the relative importance of the features was reflected by the order and frequency of attributes selected as the node and the square of the model weight. In RF, the change in prediction error as calculated by out of bag data is taken as the measure of feature importance. The standard deviation of the average value of all labeled pixels was used to evaluate the correctness of the unanimous conclusions drawn by these three methodologies. The quantitative evaluation results given by the confusion matrix show that random forest achieved the best overall accuracy, while support vector machine ranked second, and the decision tree algorithm yielded the least accurate classification results. From the perspective of feature importance, making full use of the discriminative information between different crops, and constructing a rational feature space, can help to improve classification accuracy significantly. In detail, the discriminative information between the different crop types is as follows: 1) images at the peak of the crop growth period are crucial in the classification of different crops; 2) the short-wave infrared bands are particularly suitable for fine crop classification; and 3) the red edge bands can effectively assist classification. Finally, our study achieved crop type mapping in the study area with an overall accuracy of 97.85% and a Kappa coefficient of 0.95.
The overarching goal of smart farming is to develop innovative solutions for future sustainability of humankind. Crop protection from biological/non-biological factors is a major hindrance for food security, plant diseases being one of the foremost challenges. Not only, plant diseases destroy the crops or diminish their overall quality, use of pesticides for their treatment renders the soil contaminated, which after a time becomes unsuitable for sowing and planting. Potato is a key crop and a major source of livelihood for a vast population. In this study, the authors have implemented capsule networks for classification of potato diseases, and compared the performance with few popular pretrained CNN models, namely ResNet18, VGG16 and GoogLeNet, implemented via transfer learning. Colored images of healthy as well as diseased leaf images were employed from the PlantVillage dataset and used for training the models. CapsNet proved to have achieved comparable performance to state-of-the-art CNN models, with 91.83% accuracy.
Cadastral information of rice fields is important for monitoring cropping practices in Taiwan due to official initiatives. Remote sensing based rice monitoring has been a challenge for years because the size of rice fields is small, and crop mapping requires information of crop phenology, relating to spatiotemporal resolution of satellite data. This study aims to develop an approach for mapping rice-growing areas at field level using multi-temporal Sentinel-2 data in Taiwan. The data were processed for 2018, following four main steps: (1) construct time-series Enhanced Vegetation Index (EVI) and Land Surface Water Index (LSWI), (2) noise filtering of the time-series data using wavelet transform, (3) rice crop classification using information of crop phenology, and (4) parcel-based accuracy assessment of the mapping results. The parcel-to-parcel comparisons between mapping results and ground reference data indicated satisfactory results. These findings were confirmed by close agreement between satellite-derived rice area and government’s statistics. Although some factors, including mixed-pixel issues and cloud-cover effects, lowered the mapping accuracies of townships along the coastline, this study has demonstrated the efficacy of using multitemporal Sentinel-2 data to create a reliable database of rice-growing areas over a large and heterogeneous region. Such a quantitative information was important for updating rice crop maps and monitoring cropping practices.
The development of computerized automated diagnostic systems ensures more effective health screening in plants. In this way, the damage caused by diseases can be reduced by early detection. Light reflections from plant leaves are known to carry information about plant health. In the study, healthy and fusarium diseased peppers (capsicum annuum) was detected from the reflections obtained from the pepper leaves with the aid of spectroradiometer. Reflections were taken from four groups of pepper leaves (healthy, fusarium-diseased, mycorrhizal fungus, fusarium-diseased and mycorrhizal fungus) grown in a closed environment at wavelengths between 350 nm and 2500 nm. Pepper disease detection takes place in two stages. In the first step, the feature vector is obtained. In the second step, the feature vectors of the input data are classified. The feature vector consist of the coefficients of wavelet decomposition and the statistical values of these coefficients. Artificial Neural Networks (ANN), Naive Bayes (NB) and K-nearest Neighbor (KNN) were used for classification. In detection the health case of pepper, the average success rates of different classification algorithms for the first two groups (diseased and healthy peppers) were calculated as 100% for KNN, 97.5% for ANN and 90% for NB. Likewise, these rates for the classification of all groups were calculated as 100% for KNN, 88.125% for ANN and 82% for NB. Overall, the results have shown that leaf reflections can be successfully used in disease detection.
Accurate diagnosis of wheat leaf rust is of high interest for precision farming. Spectral data have been increasingly employed to detect this disease at leaf or canopy scales; however, less attention has been paid to the variations of leaf area index (LAI). Therefore, in this study, identification of wheat leaf rust was investigated at canopy scale and under different LAI levels, namely high, medium and low. Four machine learning (ML) methods including ν-support vector regression (ν-SVR), boosted regression trees (BRT), random forests regression (RFR) and Gaussian process regression (GPR) were built to estimate disease severity (DS) levels at canopy scale, where the reflectance data were measured in field situ by using a spectroradiometer, in which records spectra from 350 to 2500 nm. Results showed that ν-SVR outperformed the other ML methods at all three LAI levels with the R 2 measures all being around 0.99. The results, particularly, showed that the performances of the ML methods were improved with increasing LAI value, where RFR reported the worst R 2 value of 0.79 (RMSE = 8.5%) at low LAI level. The variable importance obtained using BRT showed three distinct regions of wavelengths that were appropriate across different LAI levels. The results of this research confirmed that hy-perspectral signature can be reliably considered to identify wheat leaf rust disease at different LAI levels. Moreover, performances of several spectral vegetation indices (SVIs) were compared with those of the ML techniques. The results showed that the SVIs were consistently outperformed by the ML methods, particularly at low LAI level in which the SVIs were adversely affected. Nevertheless, all the SVIs, except for the RVSI, performed moderately well at high and medium LAI levels.
The citrus plants such as lemons, mandarins, oranges, tangerines, grapefruits, and limes are commonly grown fruits all over the world. The citrus producing companies create a large amount of waste every year whereby 50% of citrus peel is destroyed every year due to different plant diseases. This paper presents a survey on the different methods relevant to citrus plants leaves diseases detection and the classification. The article presents a detailed taxonomy of citrus leaf diseases. Initially, the challenges of each step are discussed in detail, which affects the detection and classification accuracy. In addition, a thorough literature review of automated disease detection and classification methods is presented. To this end, we study different image preprocessing, segmentation, feature extraction, features selection, and classification methods. In addition, also discuss the importance of features extraction and deep learning methods. The survey presents the detailed discussion on studies, outlines their strengths and limitations, and uncovers further research issues. The survey results reveal that the adoption of automated detection and classification methods for citrus plants diseases is still in its infancy. Hence new tools are needed to fully automate the detection and classification processes.
In the present study, multiple linear regression models were constructed to simulate the yield of winter wheat, rapeseed, maize and sunflower in Hungary for the 2000–2016 time period. We used meteorological data and soil water content from meteorological reanalysis as predictors of the models in monthly resolution. We included annual fertilizer amount in the analysis to remove trend from the census data. We also used remote sensing based vegetation index to extend the approach for early crop yield forecast purposes and to study the added value of proxy data on the predictive power of the statistical models. Using a stepwise linear regression-like method the most appropriate models were selected based on the statistical evaluation of the model fitting. We provided simple equations with well interpretable coefficients that can estimate crop yield with high accuracy. Crossvalidated explained variance were 67% for winter wheat, 76% for rapeseed, 81% for maize and 68.5% for sunflower. The modelling exercise showed that positive anomaly of minimum temperature in May has a substantial negative effect on the final crop yield for all four crops. For winter wheat increasing maximum temperature in May has a beneficial effect, while higher-than-usual vapour pressure deficit in May decreases yield. For maize soil water content in July and August is crucial in terms of the final yield. Incorporation of the vegetation index improved the predictive power of the models at country scale, with 10%, 2% and 4% for winter wheat, rapeseed and maize, respectively. At the county level, remote sensing data improved the overall predictive power of the models only for winter wheat. The results provide simple yet robust models for spatially explicit yield forecast as well as yield projection for the near future.
In general, in order to reduce the number of bands in hyper-spectral images, transformed features such as principal component analysis (PCA) cannot directly provide information indicating which raw spectral bands are essential, even though they provide reduced dimensionality for the consecutive analysis. This paper proposes minimum redundancy and maximum relevance (mRMR) feature selection techniques to directly choose essential raw bands from hyper-spectral images. In addition a deep neural network is suggested to classify the hyper-spectral data with reduced dimension, which consists of a convolutional neural network (CNN) followed by a fully connected network (FCN). The CNN extracts meaningful features like PCA, but in a nonlinear, supervised manner, and the FCN classifies the six apple leaf conditions including normal, young, malnutrition, early and late stages of apple Marssonina blotch (AMB), and background. Experimentally, we found five essential spectral bands using the mRMR techniques (777.24 nm, 547.77 nm, 474.32 nm, 859.45 nm, and 735.85 nm), which proved to have better accuracy than RGB image for the classification using the deep neural network. The proposed scheme is applicable for band reduction to obtain the efficient multispectral sensor system in the sense that only several essential spectral bands are chosen, and more accurate diagnosis of plant diseases is possible by reducing the complexity involved in hyper-spectral images.
A neural network model for a mechanism of visual pattern recognition is proposed in this paper. The network is self-organized by "learning without a teacher", and acquires an ability to recognize stimulus patterns based on the geometrical similarity (Gestalt) of their shapes without affected by their positions. This network is given a nickname "neocognitron". After completion of self-organization, the network has a structure similar to the hierarchy model of the visual nervous system proposed by Hubel and Wiesel. The network consists of an input layer (photoreceptor array) followed by a cascade connection of a number of modular structures, each of which is composed of two layers of cells connected in a cascade. The first layer of each module consists of "S-cells", which show characteristics similar to simple cells or lower order hypercomplex cells, and the second layer consists of "C-cells" similar to complex cells or higher order hypercomplex cells. The afferent synapses to each S-cell have plasticity and are modifiable. The network has an ability of unsupervised learning: We do not need any "teacher" during the process of self-organization, and it is only needed to present a set of stimulus patterns repeatedly to the input layer of the network. The network has been simulated on a digital computer. After repetitive presentation of a set of stimulus patterns, each stimulus pattern has become to elicit an output only from one of the C-cells of the last layer, and conversely, this C-cell has become selectively responsive only to that stimulus pattern. That is, none of the C-cells of the last layer responds to more than one stimulus pattern. The response of the C-cells of the last layer is not affected by the pattern's position at all. Neither is it affected by a small change in shape nor in size of the stimulus pattern.
Classification of plant leaf diseases based on capsule network-support vector machine model
- L W Waweru
- B T Kipyego
- D M Muchangi
Waweru, L.W., Kipyego, B.T., Muchangi, D.M. (2021).
Classification of plant leaf diseases based on capsule
network-support vector machine model. International
Journal of Electrical Engineering and Technology, 12(6):
188-199. https://doi.org/10.34218/IJEET.12.6.2021.018