Krishna Institute Of Engineering And Technology

This paper introduces a graphical user interface (GUI) built on the foundation of MultiSmart3D_Dynamics (or simply MultiSmart3D ) code. Through this GUI, we calculate the pavement design parameters associated with fatigue cracking and rutting deformation. Besides the time-harmonic loading case, the moving loading case is further analyzed based on a simple relation between the moving velocity and frequency. Several numerical examples pertaining to static and dynamic (time-harmonic and moving) responses are studied for two typical pavement structures in Taiwan. The efficiency and accuracy of MultiSmart3D GUI are validated by comparing the present results with those from experimental loading frequency and real-world frequency. Our results reveal that the thickness of the asphalt concrete and base layers have a significant impact on fatigue and rutting lives. In addition, we have found that incorporating dynamic load into the structure may offer potential benefits in terms of cost reduction for optimizing the lifespan of the pavement.

The underwater multichannel analysis of surface wave (UMASW) is becoming an essential tool for surveying subbottom shear wave velocity. Current practice is limited to interpretation based on the fundamental mode. This paper investigates the full dynamic response of the underwater-multilayered structure under two different types of sources (impact and explosion). Fundamental solutions in the transformed domain, after applying both Fourier transform and Fourier–Bessel transform, are derived utilizing the global stiffness matrix method, analogous to a 1-D finite element approach. Solutions in the physical domain are then obtained using the fast and accurate Fourier series and Fourier–Bessel series approach proposed in this paper. The most attractive feature of this novel approach is that the expansion coefficients (or Love numbers) can be pre-calculated, saved, and repeatedly used for other field points. Through numerical analyses, we quantitatively investigate the effect of the water depth and source/receiver types/locations on different wave features (i.e., Scholte, fast-guided, and acoustic modes) from different perspectives (i.e., dispersion curve, Green’s function, frequency-velocity spectrum (FVS), and waveform). We find that (1) unlike the impact source, stronger acoustic waves can be produced by the explosive source, which sometimes causes difficulty in identifying the Scholte waves. (2) The acoustic and interface-guided waves exhibit distinct behaviors depending on the source and receiver locations. Scholte waves and fast-guided waves are weakened when the source and receivers are elevated far from the water/soil interface. Moreover, (3) the response of the Scholte wave can be enhanced by muting the direct acoustic waves. However, (4) the fast-guided wave may also arise in underwater surveys when the Vs of the underlying half-space is much higher than those of the upper layers, exerting a significant influence on the shallow water scenarios and posing challenges for correct mode identification. With the ability to model the entire wavefield (or FVS) that takes into account all propagation modes and the actual survey configuration, inversion can be performed by fitting the entire FVS. This approach eliminates the need to pick dispersion curves and provides a more accurate and stronger model constraint.

Magneto-electro-elastic (MEE) materials are a specific class of advanced smart materials that simultaneously manifest the coupling behavior under electric, magnetic, and mechanical loads. This unique combination of properties allows MEE materials to respond to mechanical, electric, and magnetic stimuli, making them versatile for various applications. This paper investigates the static and time-harmonic field solutions induced by the surface load in a three-dimensional (3D) multilayered transversally isotropic (TI) linear MEE layered solid. Green’s functions corresponding to the applied uniform load (in both horizontal and vertical directions) are derived using the Fourier-Bessel series (FBS) system of vector functions. By virtue of this FBS method, two sets of first-order ordinary differential equations (i.e., N-type and LM-type) are obtained, with the expansion coefficients being Love numbers. It is noted that the LM-type system corresponds to the MEE-coupled P-, SV-, and Rayleigh waves, while the N-type corresponds to the purely elastic SH- and Love waves. By applying the continuity conditions across interfaces, the solutions for each layer of the structure (from the bottom to the top) are derived using the dual-variable and position (DVP) method. This method (i.e., DVP) is unconditionally stable when propagating solutions through different layers. Numerical examples illustrate the impact of load types, layering, and frequency on the response of the structure, as well as the accuracy and convergence of the proposed approach. The numerical results are useful in designing smart devices made of MEE solids, which are applicable to engineering fields like renewable energy.

Embracing hybrid energy systems (HES) to ensure access to clean, reliable, and cost-effective energy is necessary for nations that are striving for sustainable development. By leveraging precise meteorological data from forecasts, the HES can be rendered more accurate. Thus, firstly, the research presented here employed four machine learning approaches, such as Gaussian process regression (GPR), support vector regression, extreme gradient boosting, and decision trees, to carry out hourly forecasting of meteorological data over a year. The results obtained revealed that the GPR outperformed the other three forecasting models. For this reason, the forecasted meteorological data acquired from GPR is employed in the sizing of the HES. Tunicate swarm algorithm (TSA), a recently developed method, is applied to perform the size optimization of HES capable of meeting the energy necessities at remote sites in the Indian province of Uttar Pradesh. Following a comparative study of TSA, particle swarm optimization, and harmony search, TSA proved to yield a better outcome. Additionally, the simulation result showed a 0.33% cut in the per-unit cost of energy when forecasted data becomes the basis for the optimization of system size.

The poor quality of asphalt roads has a significant impact on driver safety, damages the mechanical structure of vehicles, increases fuel consumption, annoys passengers and is sometimes also responsible for accidents. Further, the poor quality of the road can be described as a rough surface and the presence of potholes. The potholes can be one of the main reasons for accident cause, increased fuel consumption and annoying passengers. Furthermore, the potholes can be of varied size, radiance effect, shadow and scales. Hence, the detection of potholes in asphalt roads can be considered a complex task and one of the serious issues regarding the maintenance of asphalt roads. This work focuses on the detection of the potholes in the asphalt roads. So in this work, a pothole detection model is proposed for accurate detection of potholes in the asphalt roads. The effectiveness of the proposed pothole detection model is tested over a set of real-world image datasets. In this study, the asphalt roads of the Delhi-NCR region are chosen and real-world images of these roads are collected through the smart camera. The final road image dataset consists of a total of 1150 images including 860 pothole images and the rest of are without pothole images. Further, the deep belief network is integrated into a proposed model for the detection of pothole images as a classification task and classified the images as pothole detected and not pothole. The experimental results of the proposed detection model are evaluated using accuracy, precision, recall, F1-Score and AUC parameters. These results are also compared with ANN, SVM, VGG16, VGG19 and InceptionV3 techniques. The simulation results showed that the proposed detection model achieves a 93.04% accuracy rate, 94.30% recall rate, 96.31% precision rate and 96.92% F1-Score rate than other techniques.

The MSME sector, which employs over 11.10 crore workers in non-agricultural activities and contributes to approximately 50% of India's exports, is the backbone of the economy. Unfortunately, the ongoing health emergency has created a distressing situation for these units, as the severely constrained demand has led to a significant decline in their revenue. This situation is further exacerbated by the pandemic, which has created a myriad of problems for the sensitive MSME sector, as their liquidity depends on the daily demand for their product, and they lack significant cash reserves. This is putting the sustainability of MSMEs at stake, which is concerning since they contribute approximately 30-35% to the GDP. The current scenario presents a very gloomy picture of the prospects of India's economic development. This chapter discusses the nonperforming assets (NPAs) and their impact on the sustainability of the MSME sector. This chapter also discusses the causes and effects NPAs on the sustainability of the MSME sector.

With the vast number of people present on online social network platforms like Twitter, Instagram, Facebook, etc., many business people looked into this number as a business opportunity. Thus, they started converting this number to business with the help of influencer marketing. An influencer is a person who can change the opinion or purchase behavior of people who are following them. Marketing that relies on individuals with strong social media presence to promote brands is called influence marketing. Due to their authority in a specific field or industry, influencers influence their fans’ buying habits and beliefs through their persuasive powers. Thus, determining influencers in the network is currently a popular research topic. The influence score of a person has been calculated in two ways: one based on the structure of the network and the user’s connectivity in the network, and another based on the user’s activity in the network. Research has been going on to find the influence of the user on social networks based on the user’s behavior and engagement ratio. This work focuses on finding the influencer who positively influences the given context. This paper proposes a method to find the context-based positive influence. We also need to consider the user’s sentiment before finding the list of influential users. The result shows that even if we find the influential user if the influence isn’t positive, the influence marketing may have a negative effect.

With the advent of technology, abundant electronic biomedical data is available and extracting relevant information from huge data is a fundamental need. In medical image retrieval, majority of the information is extracted either through content-based or context-based retrieval. The semantic information in images is not considered in previous research. In this work, the proposed hybrid query refinement framework for medical image retrieval shows promising results in improving the accuracy of search results compared to existing approaches. By incorporating both low-level features and high-level semantic terms based on the MeSH hierarchy, the framework addresses some existing limitations of content-based image retrieval (CBIR) approach based on relevance feedback and semantic knowledge. The framework uses the OpenI search engine to retrieve a pool of images based on user-generated queries related to a medical disease. Then, the images are processed using Scikit Image library to extract features like size, orientation, shape, and color. Edge feature extraction and region-based segmentation are performed to identify important features and analyze them more closely. The results show that the proposed approach achieves improved precision@10 and MAP for OpenI search engine compared to baseline CBIR. The number of retrieved images is also significantly reduced, indicating the relevance of the retrieved images. The proposed approach provides a more accurate and efficient medical image retrieval system that can help medical practitioners conclude diagnoses faster. Future research can focus on expanding the framework to incorporate more advanced machine learning algorithms for feature extraction and classification.

Big data analytics is essential for many industries that use computing applications, like real-time purchasing and e-commerce. Big data is used to promote products and improve the communication among retailers and shoppers. At present, individuals frequently utilize online promotions to identify the best shops for purchasing higher-quality goods. This shopping experience shared on social media platforms can be used to observe the opinions regarding the shoppers shop. New customers search the shop for knowing information about manufacturing date (MRD), manufacturing price (MRP), offers, quality, and suggestions. All these information are provided only through previous customer experience. On the product cover or label, the MRP and MRD are already available. Numerous methods have been employed to predict the details of product, but none of them provides accurate details. To overcome these issues, binarized spiking neural networks optimized with Nomadic People Optimization-based sentiment analysis is proposed for social product recommendations (BSNN-NPO). The product–product (P–P) similarity and collaborative filtering (CF) techniques are used for modeling the new recommendation system. The P–P similarity approach predicts the best products, while CF method predicts the best shops. The product data along customer reviews is gathered through Amazon product recommendation. From the results and comparison, it is found that the proposed BSNN-NPO method outperforms than other approaches. The performance of proposed technique offers higher mean absolute percentage error 38.56%, 23.67%, and 30.22% and lower mean squared error 34.67%, 45.7%, and 15.21% compared to the existing models, respectively.

In recent generations of the digital world medical data in Recommender Systems. Health Care Recommender System (HCRS) analyses the medical data and then predicts the user’s or patient’s illness. Nowadays, healthcare data is used by various users or patients in recommendation systems which are useful for everyone. Analysing and predicting medical data provides awareness to users and these data predictions may be enriched using various techniques of RS. Machine learning techniques are used to make sure that health data is reliable and of high quality. In every RS the issues are targeted such as scalability, sparsity and cold start problems. In many social networking applications, these issues are resolved using ML algorithms. However, there is a significant gap between IT systems and medical diagnosis. The fuzzy genetic method is used in HCRS in order to bridge the gap between IT and healthcare applications. Through the use of the mutation and crossover operators, a real-value genetic method is used in this to compute similarity. With the user’s extra personalized information, fuzzy rules are later generated for the database. The Hybrid fuzzy-genetic method, also known as this situation, combines both techniques to improve recommendation quality. Utilizing this method will improve the quality of the recommendation process by discovering the most precise similarity measures among different users. Six factors are subjected to fuzzification, including age, gender, employment, height, weight, and region. Genre-interesting measure weights are then used, including Very Light, Light, Average, Heavy, and Very Heavy. Finally, the evaluation metrics used MAE and RMSE to evaluate the recommendation accuracy which showed the best results in comparison with baseline approaches such as Convolutional Neural Networks and Restricted Boltzman Machine.

COVID-19 has spread like wildfire across the globe since the start of the SARS-CoV-2 outbreak, hampering quality of life at multiple levels and causing many deaths. Many aspects of the human experience have been affected, with a body of research being published on its effects on psychological and physical well being, loss of jobs, pay cuts, education, and unpaid caregiving. New findings on these aspects are still emerging as we learn more about the consequences of the pandemic. This book is intended as a simple summary of recent findings about COVID-19 for academicians and students from science, humanities and commerce backgrounds to understand the pandemic from a microscopic view and how it has touched our lives at different levels. A collection of topics is presented and explored through chapters dedicated to niche topics on COVID-19. Each chapter is authored by expert scientists, academicians and scholars from leading institutions in India. The key features of this book set are: - Interdisciplinary content, making it useful for readers from different academic streams - A blend of basic and applied research in biology, medicine and social science - A focus on findings from India - Updated References for advanced readers This collection of topics is invaluable for researchers and working professionals in industry and academia as well as general readers who want a broad, insightful perspective on COVID-19.

Disaster relief, police work, and environmental checks rely heavily on satellite imagery. Some users need human assistance manually identifying facilities and items in the photos. Due to the significant regions that need to be searched and the scarcity of available analysts, automation is crucial. Yet, standard object identification and classification techniques must improve accuracy to solve the problem. A set of machine learning techniques called “deep learning” has shown promise for automating these operations. It has had success using convolutional neural networks to comprehend images. Using high-resolution, multi-spectral satellite images, we apply them to the issue of object and facility identification in this work. We outline a deep-learning object classification system. We use the Satellite Image Classification Dataset-RSI- CB256 for this study. This dataset has four classifications combined using Google Maps snapshots and sensors. Suggested hybrid model in this paper gives an accuracy of 98.96%.