Browse Items (11858 total)
Sort by:
-
Unobtrusive Engagement Detection through Semantic Pose Estimation and Lightweight ResNet for an Online Class Environment
Analysing student engagement in a class through unobtrusive methods enhances the learning and teaching experience. During these pandemic times, where the classes are conducted online, it is imperative to efficiently estimate the engagement levels of individual students. Helping teachers to annotate and understand the significant learning rate of the students is critical and vital. To facilitate the analysis of estimating the engagement levels among students, this paper proposes a dual channel model to precisely detect the attention level of individual students in a classroom. Considering the possible inaccuracy of emotion recognition, a dual channel is configured with a Lightweight ResNet model for macro-level attention estimation and a 3d pose estimation using Euler angles for Pitch, yaw and roll that is trained, validated and tested on the Daisee database. The Emotional detection extracts the context of Engaged, frustrated, confused and disgust as higher levels of classroom attention cognition while the facial pose coordinates provide the real-time movement of the faces in the video to provide a series of engaged and disengaged coordinates. The Lightweight ResNet Model achieves a 95.5% accuracy and the Pose estimation test is able to distinguish the test videos at 92% as Engaged and Bored on the Daisee Dataset. The Overall Accuracies using the Dual channel was curated to 87%. 2023 Scrivener Publishing LLC. -
Engagement Detection through Facial Emotional Recognition Using a Shallow Residual Convolutional Neural Networks
Online teaching and learning has recently turned out to be the order of the day, where majority of the learners undergo courses and trainings over the new environment. Learning through these platforms have created a requirement to understand if the learner is interested or not. Detecting engagement of the learners have sought increased attention to create learner centric models that can enhance the teaching and learning experience. The learner will over a period of time in the platform, tend to expose various emotions like engaged, bored, frustrated, confused, angry and other cues that can be classified as engaged or disengaged. This paper proposes in creating a Convolutional Neural Network (CNN) and enabling it with residual connections that can enhance the learning rate of the network and improve the classification on three Indian datasets that predominantly work on classroom engagement models. The proposed network performs well due to introduction of Residual learning that carries additional learning from the previous batch of layers into the next batch, Optimized Hyper Parametric (OHP) setting, increased dimensions of images for higher data abstraction and reduction of vanishing gradient problems resulting in managing overfitting issues. The Residual network introduced, consists of a shallow depth of 50 layers which has significantly produced an accuracy of 91.3% on ISED & iSAFE data while it achieves a 93.4% accuracy on the Daisee dataset. The average accuracy achieved by the classification network is 0.825 according to Cohens Kappa measure. 2020, Intelligent Engineering & System. All rights reserved. -
EMONET: A Cross Database Progressive Deep Network for Facial Expression Recognition
Recognizing facial features to detect emotions has always been an interesting topic for research in the field of Computer vision and cognitive emotional analysis. In this research a model to detect and classify emotions is explored, using Deep Convolutional Neural Networks (DCNN). This model intends to classify the primary emotions (Anger, Disgust, Fear, Happy, Sad, Surprise and Neutral) using progressive learning model for a Facial Expression Recognition (FER) System. The proposed model (EmoNet) is developed based on a linear growing-shrinking filter method that shows prominent extraction of robust features for learning and interprets emotional classification for an improved accuracy. EmoNet incorporates Progressive- Resizing (PR) of images to accommodate improved learning traits from emotional datasets by adding more image data for training and Validation which helped in improving the model's accuracy by 5%. Cross validations were carried out on the model, this enabled the model to be ready for testing on new data. EmoNet results signifies improved performance with respect to accuracy, precision and recall due to the incorporation of progressive learning Framework, Tuning Hyper parameters of the network, Image Augmentation and moderating generalization and Bias on the images. These parameters are compared with the existing models of Emotional analysis with the various datasets that are prominently available for research. The Methods, Image Data and the Fine-tuned model combinedly contributed in achieving 83.6%, 78.4%, 98.1% and 99.5% on FER2013, IMFDB, CK+ and JAFFE respectively. EmoNet has worked on four different datasets and achieved an overall accuracy of 90%. 2020. All Rights Reserved. -
Multimodal emotional analysis through hierarchical video summarization and face tracking
The era of video data has fascinated users into creating, processing, and manipulating videos for various applications. Voluminous video data requires higher computation power and processing time. In this work, a model is developed that can precisely acquire keyframes through hierarchical summarization and use the keyframes to detect faces and assess the emotional intent of the user. The key-frames are used to detect faces using recursive Viola-Jones algorithm and an emotional analysis for the faces extracted is conducted using an underlying architecture developed based on Deep Neural Networks (DNN). This work has significantly contributed in improving the accuracy of face detection and emotional analysis in non-redundant frames. The number of frames selected after summarization was less than 30% using the local minima extraction. The recursive routine introduced for face detection reduced false positives in all the video frames to lesser than 2%. The accuracy of emotional prediction on the faces acquired through the summarized frames, on Indian faces achieved a 90%. The computational requirement scaled down to 40% due to the hierarchical summarization that removed redundant frames and recursive face detection removed false localization of faces. The proposed model intends to emphasize the importance of keyframe detection and use them for facial emotional recognition. 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. -
Multitask EfficientNet affective computing for student engagement detection
In the realm of education, feedback emerges as a pivotal component, serving to foster engagement and interaction while also facilitating the refinement of teaching methods to capture and maintain student attention. Traditional classroom assessment methods often struggle to accurately gauge the degree of comprehension among students during lectures, relying on manual comment collection that inherently carries the risk of inaccuracies. In response to this challenge, a novel system has been proposed, harnessing the power of Facial Emotion Recognition (FER) technology to capture student feedback. Within this framework, students are given a unique avenue to convey their emotions and reactions, employing facial expressions and gestures as the means to communicate. This innovative approach enables the analysis of students emotional responses and thereby provides invaluable insights into their comprehension levels, as well as the overall quality and engagement experienced during lectures. The approach takes shape through the utilization of Computer Vision techniques, with a particular focus on an unobtrusive methodology for assessing students overall engagement. Overcoming limitations of traditional assessment, our approach integrates compound scaling, employing the proposed Multitask EfficientNetB0 model recognized for its proved accuracy in emotion recognition (95.7%) and behavior analysis (96.3%) across diverse datasets (DAiSEE, iSED, iSAFFE). The behavioral classification system categorizes students into Engaged and Disengaged classes within a multi-class framework, providing nuanced insights into comprehension and Student engagement. Assessment metrics, including ROC Curves, Precision, Recall, and F1-Score, ensure a thorough evaluation. Our systems adaptability is demonstrated across varied educational environments, showcasing real-world efficacy in classrooms, laboratories, and seminar halls. The inclusion of MTCNN enhances face detection capabilities, facilitating robust analysis in dynamic scenarios. Expanding its applicability, the model has been put to the test in a range of educational settings, including classrooms, laboratory environments, and seminar halls, offering dual-capability analysis of both emotions and behavior. This comprehensive approach yields nuanced insights into student engagement and interaction, and its performance has been validated through real-world deployment within classrooms and seminars The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024. -
Effect of Mentha arvensis enriched diet to promote the growth and immune response of Clarias batrachus against Aeromonas hydrophila challenge
The study was conducted to investigate the effects of fish fed diet Mentha arvensis extract on growth performance, non-specific immunity and expression of some immune-related genes and resistance to Aeromonas hydrophila in Clarias batrachus. Five diets were formulated with 0, 1, 2, 3, and 4% of M. arvensis leaf extract. The results indicated that, compared to the control groups, 2-4% dietary inclusion increased growth and feed consumption. In the dietary inclusion of 3-4% M. arvensis extract groups were increased relative on weight gain, specific growth rate, RBC, WBC, total hemocyte counts, total protein, globulin than control. Fed diet supplements with 3% mint-extract increased the total protein, WBC and globulin and phagocytic indexes and lysozyme activity increased at the 2, 3 and 4% of mint groups relative to the control. The PCR analysis showed that TNF, IL-1, MyD88, and TLRs were increased in the 2-4% fed diet M. arvensis extract groups than the control. These results suggest that 3% of M. arvensis extract significantly influences the immunomodulatory activity and immune-specific genes of C. batrachus. 2024 The Authors -
Identification of potential ZIKV NS2B-NS3 protease inhibitors from Andrographis paniculata: An insilico approach
Andrographis paniculata is a widely used medicinal plant for treating a variety of human infections. The plant's bioactives have been shown to have a variety of biological activities in various studies, including potential antiviral, anticancer, and anti-inflammatory effects in a variety of experimental models. The present investigation identifies a potent antiviral compound from the phytochemicals of Andrographis paniculata against Zika virus using computational docking simulation. The ZIKV NS2B-NS3 protease, which is involved in viral replication, has been considered as a promising target for Zika virus drug development. The bioactives from Andrographis paniculata, along with standard drugs as control were screened for their binding energy using AutoDock 4.2 against the viral protein. Based on the higher binding affinity the phytocompounds Bisandrographolide A (-11.7), Andrographolide (-10.2) and Andrographiside (-9.7) have convenient interactions at the binding site of target protein (ZIKV NS2B-NS3 protease) in comparison with the control drug. In addition, using insilico tools, the selected high-scoring molecules were analysed for pharmacological properties such as ADME (Absorption, Distribution, Metabolism, and Excretion profile) and toxicity. Andrographolide was reported to have strong pharmacodynamics properties and target accuracy based on the Lipinski rule and lower binding energy. The selected bioactives showed lower AMES toxicity and has potent antiviral activity against zika virus targets. Further, MD simulation studies validated Bisandrographolide A & Andrographolide as a potential hit compound by exhibiting good binding with the target protein. The compounds exhibited good hydrogen bonds with ZIKV NS2B-NS3 protease. As a result, bioactives from the medicinal plant Andrographis paniculata can be studied in vitro and in vivo to develop an antiviral phytopharmaceutical for the successful treatment of zika virus. Communicated by Ramaswamy H. Sarma. 2021 Informa UK Limited, trading as Taylor & Francis Group. -
Phytofabricated bimetallic synthesis of silver-copper nanoparticles using Aerva lanata extract to evaluate their potential cytotoxic and antimicrobial activities
In this study, we demonstrate the green synthesis of bimetallic silver-copper nanoparticles (AgCu NPs) using Aerva lanata plant extract. These NPs possess diverse biological properties, including in vitro antioxidant, antibiofilm, and cytotoxic activities. The synthesis involves the reduction of silver nitrate and copper oxide salts mediated by the plant extract, resulting in the formation of crystalline AgCu NPs with a face-centered cubic structure. Characterization techniques confirm the presence of functional groups from the plant extract, acting as stabilizing and reducing agents. The synthesized NPs exhibit uniform-sized spherical morphology ranging from 7 to 12nm. They demonstrate significant antibacterial activity against Staphylococcus aureus and Pseudomonas aeruginosa, inhibiting extracellular polysaccharide secretion in a dose-dependent manner. The AgCu NPs also exhibit potent cytotoxic activity against cancerous HeLa cell lines, with an inhibitory concentration (IC50) of 17.63gmL?1. Additionally, they demonstrate strong antioxidant potential, including reducing capability and H2O2 radical scavenging activity, particularly at high concentrations (240gmL?1). Overall, these results emphasize the potential of A. lanata plant metabolite-driven NPs as effective agents against infectious diseases and cancer. 2024, The Author(s). -
Enhancing Banana Cultivation: Disease Identification through CNN and SVM Analysis for Optimal Plant Health
Detection and effective remedies play a crucial role in revolutionizing banana crop health. The banana industry faces numerous challenges, including the prevalence of diseases and pests that can lead to significant yield losses. This paper explores the potential impact of detection techniques and remedies on improving banana crop management. Disease detection models based on machine learning, image processing and deep learning offer high accuracy in identifying diseases like Fusarium Wilt, Yellow Sigatoka, and Black Sigatoka. Implementing detection and targeted treatments can enhance crop productivity, reduce pesticide usage, and ensure sustainable banana production. 2024 IEEE. -
AI-Enhanced IoT Data Analytics for Risk Management in Banking Operations
Using IoT data analytics in conjunction with artificial intelligence (AI) has the potential to improve banking operations' risk management. Sophisticated analytical methods are necessary for the detection and management of possible risks due to the increasing complexity and amount of data generated by the banking industry. This research proposes a novel method for analysing real-time data from IoT devices by employing artificial intelligence algorithms. The risks associated with financial transactions and operations can be better and more accurately assessed using this method. Through the integration of AI's pattern recognition, anomaly detection, and predictive modelling capabilities with the massive amounts of data generated by Internet of Things devices, this project aims to substantially enhance the efficacy and efficiency of risk management approaches in the banking sector. Research like this could lead to innovative solutions that make financial institutions more resistant to rising risks by enhancing decision-making, reducing operational weaknesses, and so on. 2024 IEEE. -
IoT-Driven Credit Scoring Models: Improving Loan Decision Making in Banking
By the game-changing possibilities of credit scoring models driven by the Internet of Things, this hopes to shed light on how the banking sector may enhance its loan decision-making procedures. Financial organisations are putting more and more faith in Internet of Things technologies to improve their risk assessment and lending processes. These IoT-driven models provide a more accurate and thorough assessment of creditworthiness by including real-time and detailed data on borrowers' activities, spending habits, and asset utilisation. This research examines the practicality and accuracy of Internet of Things (IoT) credit scoring by comparing it to conventional methods, looking closely at case researches, and analysing empirical data. The findings shed light on potential ways to enhance the loan approval and risk prediction procedures while also addressing concerns and considerations related to data privacy, security, and regulatory compliance. It is possible that decision-making frameworks could be altered by IoT-driven credit scoring algorithms, which could lead to a more inclusive and informed lending atmosphere. The contributes to the growing area of banking credit evaluation by showing that these models have promise. 2024 IEEE. -
The Role of IoT in Revolutionizing Payment Systems and Digital Transactions in Finance
The revolutionary impact of the Internet of Things (IoT) on payment systems and digital transactions within the financial industry is investigated so as to better understand its implications. During this period of unparalleled digitalization in the financial environment, the Internet of Things has emerged as a crucial participant in the process of altering traditional payment paradigms. For the purpose of improving efficiency, security, and the overall user experience, this article analyzes the incorporation of Internet of Things (IoT) devices into financial transactions. These devices include smart cards, wearables, and linked appliances. The paper elucidates how Internet of Things-driven innovations are expediting payment processes, reducing transaction costs, and mitigating fraud risks. This is accomplished through a comprehensive investigation of case Researches, technology breakthroughs, and regulatory frameworks. In addition to this, the article investigates the implications of the Internet of Things (IoT) in terms of promoting financial inclusion by providing digital payment services to groups that were previously underserved. This research gives useful insights for policymakers, financial institutions, and technologists who are looking to navigate and harness the potential of the Internet of Things in transforming payment systems. These insights are gained through an examination of the obstacles and opportunities related with the adoption of IoT in the financial sector. 2024 IEEE. -
Studies on the characterisation of thiophene substituted 1,3,4-oxadiazole derivative for the highly selective and sensitive detection of picric acid
A novel thiophene substituted 1,3,4-oxadiazole based chemosensor namely 2-(4-(5-(5-hexylthiophen-2-yl) thiophen-2-yl)phenyl) -5-(5-(5-(5-hexylthiophen-2-yl) thiophen-2-yl)thiophen-2-yl)-1,3,4-oxadiazole [TKO] has been characterised for the efficient detection of picric acid (PA) based on fluorescence quenching mechanism. In this regard, the electronic absorption spectra, fluorescence spectra, and fluorescence lifetime of TKO are recorded in the presence of different nitroaromatic compounds (NACs) in ethanol at room temperature. The absorption studies exhibited a blue shift in the absorption maxima with the increase in the concentration of PA. In the fluorescence titration studies, TKO shows a remarkable fluorescence quenching with picric acid as compared to other nitroaromatic compounds. Using the Benesi-Hildebrand plot, the binding constant value of PA with TKO is determined and is of the order of 6.467 104 M?1. Job's plot analysis confirms the 1:1 binding stoichiometry ratio between TKO and PA and is supported by the 1H NMR studies. The detection limit is determined and is of the order of 10.08 M. The competitive studies revealed that TKO is highly selective for recognizing PA without the interference of other NACs. The theoretical studies were also carried out to understand the binding mechanisms of PA with TKO. The fluorescence quenching of TKO by PA may be attributed to photo induced electron transfer (PET). Overall, the experimental findings suggest that, the novel probe TKO may be used as a highly selective and sensitive chemosensor for the detection of explosives like picric acid. 2022 Elsevier B.V. -
Roadmap of effects of biowaste-synthesized carbon nanomaterials on carbon nano-reinforced composites
Sustainable growth can be achieved by recycling waste material into useful resources without affecting the natural ecosystem. Among all nanomaterials, carbon nanomaterials from biowaste are used for various applications. The pyrolysis process is one of the eco-friendly ways for synthesizing such carbon nanomaterials. Recently, polymer nanocomposites (PNCs) filled with bio-waste-based carbon nanomaterials attracted a lot of attention due to their enhanced mechanical properties. A variety of polymers, such as thermoplastics, thermosetting polymers, elastomers, and their blends, can be used in the formation of composite materials. This review summarizes the synthesis of carbon nanomaterials, polymer nanocomposites, and mechanical properties of PNCs. The review also focuses on various biowaste-based precursors, their nanoproperties, and turning them into proper composites. PNCs show improved mechanical properties by varying the loading per-centages of carbon nanomaterials, which are vital for many defence-and aerospace-related indus-tries. Different synthesis processes are used to achieve enhanced ultimate tensile strength and mod-ulus. The present review summarizes the last 5 years work in detail on these PNCs and their appli-cations. 2021 by the authors. Licensee MDPI, Basel, Switzerland. -
Analysis of zoochemical from Meretrix casta (Mollusca: Bivalvia) extracts, collected from Rameswaram, Tamil Nadu, India and their pharmaceutical activities
The marine ecosystem's diverse animal species offer a unique opportunity to discover marine-derived natural products. While numerous invertebrates have been studied, research on Indian marine invertebrates, especially Meretrix casta, remains limited. This study explores the zoochemical composition of ethyl acetate and methanolic extracts from Meretrix casta off Rameswaram, Tamil Nadu, India, and evaluates their bioactive potential, focusing on antioxidant properties, glucose uptake in yeast cells, and alpha-amylase activity. The results reveal the presence of alkaloids, flavonoids, polyphenols, sterols, terpenoids, and cardiac glycosides in both extracts, highlighting their bioactive potential. Although their antioxidant capacity is slightly lower than ascorbic acid, the extracts demonstrated significant alpha-amylase inhibition, suggesting their potential in blood sugar regulation and diabetes management. These findings underscore the therapeutic potential of M. casta in developing anti-diabetic compounds, warranting further pharmacological exploration. Authors. -
Hybrid scheme image compression using DWT and SVD
Image compression is process of reducing data size to represent an image by removing redundant data. Hybrid scheme image compression is combination of methods performed in order or as an amalgam to form a new technique. In this paper, we proposed a new approach to compress the image by collaborating Discrete Wavelet Transformation (DWT) and Singular Value Decomposition (SVD). Image is decomposed into wavelets using DWT and approximate wavelet is subsequently transformed into four bands. Different wavelet filters are implemented for transformation namely Haar, Daubechies, Biorthogonal and Coiflets. Apart from approximate image, SVD is applied on remaining wavelets (Horizontal, Vertical and Diagonal Details) at each decomposition level. On reconstruction, various singular values are selected depending on the level transformation. The performance of the proposed method is compared and evaluated with SVD, DCT-SVD and DWT-DCT-SVD. Evaluation is carried out based on Compression Ratio (CR), Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) index. From the experimental results, it is observed that proposed method yields better MSE, PSNR and SSIM compared to state-of-the-art methods. 2017, Institute of Advanced Scientific Research, Inc. All rights reserved. -
-
Design and Development of Dual Fuzzy Technique to Optimize Job Scheduling and Execution Time in Cloud Environment
Cloud computing is a type of computing that relies on sharing a pool of computing resources, rather than deploying local or personal hardware and software. It enables convenient, on-demand network access to a shared pool of configurable computing re- sources (e.g., applications, storage, networks, services, and servers) that can be swiftly provisioned and released with minimal management control or through the interaction of the cloud service provider. The increasing demand for computing resources in the cloud has made elasticity an important issue in the cloud. The availability of extending the resources pool for the user provides an effective alternative to deploying applications with high scalability and processing requirements. Providing a satisfactory Quality of Service (QoS) is an important objective in cloud data centers. The QoS is measured in terms of response time, job completion time and reliability. If the user jobs cannot be executed in high load and the job is crashed, it will enormously increase the response time and also push up the job completion time. Also due to load, the jobs may be still in the waiting queue and could not find a resource to execute. In such a situation, the user notices a big response delay and it will affect the QoS. Towards ensuring QoS, this research proposes the following solution - Dual Fuzzy Load Balancing for jobs. Dual Fuzzy Load Balancing balances the load in the data center with an overall goal of reduction of response and execution time for tasks. The proposed solutions were simulated in the Cloudsim simulator and performance metrics in terms of job response time, job completion time, resource utilization, a number of SLA violations, and along with the cost comparison to the existing algorithms of Load Balancing. The proposed solutions are also implemented in a real cloud environment and the effectiveness of the solution is evaluated. -
Multi-view video summarization
Video summarization is the most important video content service which gives us a short and condensed representation of the whole video content. It also ensures the browsing, mining, and storage of the original videos. The multi- view video summaries will produce only the most vital events with more detailed information than those of less salient ones. As such, it allows the interface user to get only the important information or the video from different perspectives of the multi-view videos without watching the whole video. In our research paper, we are focusing on a series of approaches to summarize the video content and to get a compact and succinct visual summary that encapsulates the key components of the video. Its main advantage is that the video summarization can turn numbers of hours long video into a short summary that an individual viewer can see in just few seconds. Springer India 2016. -
An integration of big data and cloud computing
In this era, Big data and Cloud computing are the most important topics for organizations across the globe amongst the plethora of softwares. Big data is the most rapidly expanding research tool in understanding and solving complex problems in different interdisciplinary fields such as engineering, management health care, e-commerce, social network marketing finance and others. Cloud computing is a virtual service which is used for computation, data storage, data mining by creating flexibility and at minimum cost. It is pay & use model which is the next generation platform to analyse the various data which comes along with different services and applications without physically acquiring them. In this paper, we try to understand and work on the integration model of both Cloud Computing and Big Data to achieve efficiency and faster outcome. It is a qualitative paper to determine the synergy. Springer Science+Business Media Singapore 2017.