Browse Items (11809 total)
Sort by:
-
Exploration and Analysis of Seizure Spikes Through Spectral Domain Transformation
Seizure detection is the most crucial area of investigation when it comes to understanding brain disorders. This proposed research study embarked on an automated model for epileptic seizure diagnosis by means of different kinds of Spectral transformation using EEG inputs from seizure sufferers and healthy subjects. This automated model accommodates non-invasive brain electrical activity monitoring. This method aims to facilitate the analysis and identification of epileptic seizure states since, monitoring and diagnosing such brain electrical activity is a complex task due to its numerous divisions and underlying features. The primary objective of this research study is to distinguish between EEG-based seizures and healthy individuals. To achieve this goal, a combination of spectral transformation and EEG analysis techniques is utilized. These techniques include examining the frequency spectrum, magnitude spectrum, correlation, and T-Distributed Stochastic Neighboring Embedding (T-SNE) analysis. This analysis yields valuable insights from EEG data, refining the input data and making it more suitable for prediction and identification. The models performance is evaluated using two distinct datasets: real-time EEG data from individuals experiencing epileptic seizures and EEG data from healthy subjects. These datasets are sourced from the Bangalore EEG Epilepsy Dataset (BEED), India and the BONN epilepsy dataset from the UCI repository. In a comparative study of spectral transformation methods, including Complex Fast Fourier Transform (CFFT) and Real-Valued Fast Fourier Transform (RFFT), it is discovered that reducing the data dimension by using feature extraction is not the optimal approach. This simplification leads to the loss of valuable information. Therefore, preserving the full spectrum of EEG characteristics is crucial for gaining valuable insights into brain neuronal functions, ultimately enabling more accurate seizure prediction. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Quality and Security Assurance Workload Scheduling in Heterogeneous Cloud Environment
The adoption of cloud computing has transformed how businesses manage their workloads, offering flexibility and efficiency. This study introduces a novel model that leverages trust mechanisms to ensure secure workload execution within heterogeneous cloud environments. The primary objective of this research was to enhance efficiency by reducing both time and energy consumption associated with executing workloads. The proposed model's efficacy was assessed through the examination of Montage and Inspiral workloads. The evaluation encompassed two smaller tasks from both Montage and Inspiral workloads, in addition to one larger task. To gauge performance, a comparative analysis was conducted between the proposed model and established models such as Energy Minimized Scheduling (EMS), Efficient Replanning (ERP), and Evolutionary Computing Workload Scheduling (EC-WSC). The findings reveal that the proposed model outperforms the existing models in terms of mitigating both time and energy expenditure for the considered workloads. 2023 IEEE. -
Consolidation of Cloud Computing in Smart and Sustainable Environment
Cloud computing has revolutionized IoT device data collection, administration, and analysis by offering a scalable and sustainable solution for managing vast amounts of data. The paper highlights cloud computing's benefits in data processing, device management, cost efficiency and scalability. However, challenges related to security, data ownership, and vendor lock-in require attention. A novel sustainable cloud-IoT model is presented by integrating smart computing with cloud infrastructure. It is observed that the model records promising performance. The mean response delay is 1.9 seconds and the 89.5% is the generated mean computational storage accuracy rate. In conclusion, the cloud computing empowered sustainable model can be used in organizations to gain insights from IoT data and make informed decisions, shaping future research in this rapidly evolving field. 2023 IEEE. -
Three-component p-TSA catalyzed synthesis of hydrazinyl thiazole derivatives
A direct single-pot three-component procedure for synthesizing bio-active hydrazinyl thiazole derivatives has been demonstrated. The reaction involves substituted 2-Bromoacetophenones, carboxaldehydes, and thiosemicarbazide to form the hydrazinyl thiazole scaffolds via a simple condensation reaction followed by intramolecular cyclization with p-TSA as a catalyst at room temperature. The ease of product separation, lack of column chromatographic purification, and use of readily available starting materials result in an efficient approach for organic synthesis. 2023 Elsevier Ltd. All rights reserved. -
Sustainable driven Predictive Approaches to Address Climatic Crisis: Issues and Challenges
The issue of climate crisis is currently one of the critical challenges humanity faces in the present era and it holds significant implications, for the future of our planet. To gain an understanding and mitigate the impacts of climate change several methods have been developed to model and forecast future climate trends. This paper critically analyzes sustainable techniques utilized in studying the climate crisis, such as statistical models, machine learning algorithms and climate simulations. The strengths and limitations of each method is analyzed while also considering the factors that can affect their accuracy and reliability. By consolidating existing research on this subject our aim is to provide insights into the effective sustainable approaches for predicting our climates future trajectory while offering suggestions for further research, in this crucial field. 2023 IEEE. -
Manta Ray Foraging Optimizer with Deep Learning based Malicious Activity Detection for Privacy Protection in Social Networks
Malicious activity detection is a vital component of ensuring privacy protection in social media networks. As users engage in online interactions, protecting their sensitive information becomes paramount. Social networks can proactively identify and mitigate malicious behaviors, such as cyberbullying, data breaches, and phishing attacks by applying advanced AI and machine learning (ML) technologies. This detection system analyzes user behavior patterns, content, and network traffic to flag suspicious activities, thus safeguarding user privacy and fostering a safer online environment. The incorporation of robust malicious activity detection mechanisms helps maintain trust in social networks and reinforces the commitment to preserving user privacy in an increasingly interconnected digital landscape. This article introduces a novel Manta Ray Foraging Optimizer with Deep Learning based Malicious Activity Detection (MRFODLMAD) technique for privacy protection in social networks. The drive of the MRFODL-MAD technique is to detect and classify malicious activities in the social network. To accomplish this, the MRFODL-MAD technique preprocesses the input data. For malicious activity detection, the MRFODL-MAD technique employs long short term memory (LSTM) system. The MRFO algorithm has been executed to hyperparameter tuning process to improve the performance of the LSTM network. The experimental outcomes of the MRFODL-MAD algorithm can be tested on social networking database and the results inferred the improved performance of the MRFODL-MAD algorithm under various different measures. 2023 IEEE. -
Experimental scrutinization on production of biogas from vegetable and animal waste
Anaerobic fermentation is a highly promising technology for converting biomass waste into methane, which may directly be used as an energy source. The objective of this research was to investigate production rate of biogas from camel dung, chicken dropping and vegetable waste. Attempts have been made in this study to optimize various parameters in order to determine the most favorable conditions for maximum biogas production from three different types of wastes such as camel dung (CAD), chicken droppings (CHD) and vegetable waste (VW). The amount of biogas produced from the wastes is compared as: VW >CHD>CAD. The results showed that biogas produced from VW is 720 ml in 32 days as compared to CHD and CAD which are 600 ml in 36 days and 80 ml in 40 days respectively. The effect of the pH and temperature on the amount of biogas produced was also studied. The experiments were conducted in temperatures ranging from 36 C to 44 C. 2023 Author(s). -
Algorithm trading and its application in stock broking services
Purpose: Algorithmic trading provides a more systematic approach to active trading than methods based on trader intuition or instinct. The aim of the study is to examine the level of awareness among the brokers when integrated with technology for the purpose of executing the trades. Design/Methodology: A self-administered and structured 350 questionnaires were designed and circulated to collect the preliminary information from the stock brokers operating in NSE and BSE within the geographical limits of Bangalore district using the Systematic Sampling method to obtain a sample size of 235. Awareness, Automated trading, Elimination of human error, portfolio management, tracking order, order placement were the critical variables observed to validate the hypothesis using Simple Percentage Analysis & Chi-Square Analysis using Statistical Analysis Software (SAS). Findings: It was found that there is robust association between the level of awareness of the mentioned technology in its application by the stock brokers of NSE and BSE operating in Bangalore. Portfolio management and automated trading are the highly associated application of Algorithmic trading among the stock brokerage services. Originality: Algorithmic trading makes use of complex formulas, combined with mathematical models and human oversight, to make decisions to buy or sell financial securities on an exchange. It can be used in a wide variety of situations including order execution, arbitrage, and trend trading strategies. Algorithmic traders often make use of high-frequency trading technology, which can enable a firm to make tens of thousands of trades per second. The Authors, published by EDP Sciences. -
Studies on design and simulation of di-methyl ether plant of 160 TPD capacity
Energy is needed to run almost everything we see around us, from cars to the electricity power generation plants and everything else. Fossil fuels produce harmful products on combustion. One such eco-friendly alternative is Di-Methyl Ether also known as DME. In this study, a DME plant of capacity 160 tons per day was designed. Methanol dehydration process has been adapted as the process of production. The purity of DME from this plant is 99.5% by weight. Distillation column T-202 and heat exchanger E-208 were designed in detail. The detail design results showed that T-202 needed 6 stages for separation and a column diameter of 1.28m, while the simulation results showed 7 stages and column diameter as 1.285m for the same separation process. Furthermore, E-208 is of type 1-2 shell & tube heat exchanger with 307 tubes and tube length of 5.5m, however the Aspen EDR simulation results were also in close agreement with 304 tubes and 5m length for the same heat exchanger. This paper presents the results of simulation results of the simulation of these equipment's and full plant done using Aspen plus V8.8 software and Aspen EDR. 2023 Author(s). -
Talent acquisition-artificial intelligence to manage recruitment
The research aims to examine the awareness of Artificial Intelligence among the HR managers and Talent Acquisition managers in the process of Talent Acquisition, Investigating the factors influencing the adoption and usage of Assisted Intelligence, and evaluating the impact of Artificial Intelligence on Talent Management. Multi-Stage sampling method was adopted to collect the responses from the 384 customers across the HR and TA managers working across the IT companies situated in Bangalore, Mysore, Pune, and Chennai & Hyderabad. SAS was applied to perform the Simple Percentage Analysis, Correlation Analysis, Multiple Linear Regression Analysis to validate the hypothesis. The demographic & construct variables considered were Adoption, Actual usage, Perceived usefulness, Perceived Ease of Use, & Talent Management. Awareness of the Artificial Intelligence technology and its adoption in managing Talent Acquisition has the positive and high correlation and followed by its actual usage. Candidate experience is the most influencing variable from the first factor, Competency and Easy to use is the most influencing variable from the second factor, Effectiveness in the adoption and actual usage of Artificial Intelligence in Talent Acquisition. Talent Management is the highest predictor of using the technology and its adoption is the most influencing predictor in the effective implementation of the technology among the Information Technology Companies. The Authors, published by EDP Sciences. -
Pedestrian crossing behaviour between transport terminals
Pedestrians possess special requirements for protecting their privacy while interacting with other users of a transport network. There exists a need in order to obtain a deeper knowledge of pedestrian traffic behaviour in between transport terminals. When different transportation terminals come closer, there will be an increased pedestrian flow caused due to change in modes used. The main aim was to analyses the general pedestrian behaviour while crossing a road and to find out different human factors which affect this behaviour. The crossing patterns were observed and also the chances of conflict with vehicles. The paper brought out the fact that the pedestrians always preferred different types of crossings. These varied with the gender and age of the pedestrians and also with luggage carrying or not. There seemed to be a greater flow of pedestrians during the peak hours and then they faced difficulty in crossing due to heavy traffic. Crosswalks are locations in which pedestrians are exposed to fewer rights of accident prevention even though they may approach the roadway and be alert of approaching traffic. Pedestrian unlawful crossing attitude is a crucial factor inside area issue of safety on the road. Thus, there is a requirement to take more steps towards bringing safety. 2023 Author(s). -
Intelligent approach to automate a system for simulation of nanomaterials
Nanomaterial composites are generally found to have great thermal properties and hence have witnessed an increasing demand in the recent years for manufacturing of efficient miniature electronic devices. The process of finding the right composites that exhibit the desired properties is a rather tedious task involving a lot of trial and error in the current scenario. This paper proposes a methodology to digitize and automate this entire process by administering certain efficient practices of assessing the properties of nanomaterial like Coarse Grained Molecular Dynamics thus resulting in faster simulations. 2023 Author(s). -
Mobile Freeze-Net with Attention-based Loss Function for Covid-19 Detection from an Imbalanced CXR Dataset
In this paper, we present a novel framework, that is, Mobile Freeze-Net along with Attention-based Loss Function, for Covid-19 detection from a Chest X-Ray (CXR) dataset. First, we have observed that by freezing 50% of a Mobile Net-V2 model (means fine-tuning 50% layers from ImageNet dataset) has automatically removed the class imbalance problem from the CXR dataset considerably. We call this 50% frozen Mobile Net-V2 model as Mobile Freeze-Net. Secondly, we have proposed an Attention-based Loss function, which provides more attention to the class, having higher inter-class similarity. We have computed attention weights for each class from the statistical inference of the dataset itself, by employing a Monte-Carlo method and thereafter, we have incorporated those weights into WCCE loss function of Mobile Freeze-Net model. By utilizing Mobile freeze-Net, we have achieved testing accuracy, F1 score, precision and recall of 93%, 94%, 93% and 94% respectively. This is approximately 3-4% improvement compared to 100% fine tuning of Mobile-Net V2. Furthermore, we have achieved approximate 1-2% improvement of Mobile Freeze-Net, after incorporating Attention-based Loss function. For the validity of the proposed framework, we have conducted experiments with 10-fold cross validation. All these experimental results suggest that our proposed framework has outperformed other existing models considerably. 2023 Owner/Author(s). -
Reliability analysis of cement manufacturing technique in computerized clinker processing method
Cement production will face severe resource constraints in the future, as they rely on natural resources. Therefore, the industry focuses on raising natural resource requirements at both the development and operational levels. One of the situations left unattended in cement production is modelling reliability on a clinker production device with a defect in its three main components. Bridging this gap, this paper provides a reliability model on the manufacturing method of clinkers. The manufacturing of clinkers is the first step in the cement production process. The clinker manufacturing process comprises three main components: crusher, roller mill, and rotary kiln. Three reliability models are developed in this paper, with failures in its three important components considering three situations. All three components are operative, the first two components are operative, and only the first component is operative. In this paper, the transition probabilities and mean sojourn times and also MTSF are measured. 2023 Author(s). -
An IoT-Based System for Fault Detection and Diagnosis in Solar PV Panels
This abstract describes an IoT-based system for fault detection and diagnosis in solar PV panels. The proposed Fuzzy logic-based fault detection algorithms aims to improve the performance and reliability of solar PV panels, which can be affected by various faults such as shading, soiling, degradation, and electrical faults. The system includes wireless sensor nodes that are deployed on the panels to collect data on their electrical parameters and environmental conditions, such as temperature, irradiance, and humidity. The collected data is then transmitted to a central server for processing and analysis using machine learning algorithms. The system can detect and diagnose faults in real-time, and provide alerts and recommendations to maintenance personnel to take appropriate actions to prevent further damage or downtime. The system has several advantages over traditional manual inspection and maintenance methods, including reduced downtime, lower maintenance costs, and improved energy efficiency. The proposed system has been validated through experimental tests, and the results show that it can accurately detect and diagnose faults in solar PV panels with high reliability and efficiency. 2023 EDP Sciences. All rights reserved. -
Efficiency of Indian Banks with Non-Performing Assets as Undesirable Outputs
The performance evaluation of any banks is of utmost importance for bank management, investors, and policymakers. Due to globalization, all the banks are working in a competitive environment. Several risk factors affect the operational efficiency of banking system. This study aims to evaluate the efficiency of Indian banks with NPAs as uncontrolled variables. Due to the nature of NPAs, these are assumed as undesirable outputs in the DEA modelling. The results reveal that public sector banks experienced more input losses due to NPAs compared to private banks. The private banks experienced more loss in inputs due to the scale of operation. The Wilcoxon Signed-Rank test shown that the impact of NPAs and scale of operation are statistically significant at 0.05 level. 2023 American Institute of Physics Inc.. All rights reserved. -
Character recognition for Malayalam palm leaf manuscripts: An overview of techniques and challenges
Kerala is a small, ocean-facing state in South India and has been home to several ancient civilizations in the past. The yesteryears have rewarded the state with great cultural heritage, monuments, historic artifacts and the like. Palm leaf manuscript is one such antiquity. Before paper became common, palm leaf was the medium for writing in Kerala. Such manuscripts capture the glory of our past and deals with different domains such as arts, astrology, medicine, science, religion and spirituality. Palm leaf manuscripts have value both as a cultural asset and as a knowledge repository. Palm leaf manuscripts are organic and degrades with age. The environmental conditions can also accelerate its degradation. A viable solution in preserving the knowledge contained in these manuscripts is Handwritten Character Recognition (HCR). Digitized manuscripts have infinite life. Character recognition in Indian languages, including Malayalam, is considered a complex process mainly due to the size of character set, the similarity of characters and the presence of compound characters. This paper surveys existing works in the field of HCR relevant to Malayalam palm leaf manuscripts. 2023 Author(s). -
Exploring Explainable Artificial Intelligence for Transparent Decision Making
Artificial intelligence (AI) has become a potent tool in many fields, allowing complicated tasks to be completed with astounding effectiveness. However, as AI systems get more complex, worries about their interpretability and transparency have become increasingly prominent. It is now more important than ever to use Explainable Artificial Intelligence (XAI) methodologies in decision-making processes, where the capacity to comprehend and trust AI-based judgments is crucial. This abstract explores the idea of XAI and how important it is for promoting transparent decision-making. Finally, the development of Explainable Artificial Intelligence (XAI) has shown to be crucial for promoting clear decision-making in AI systems. XAI approaches close the cognitive gap between complicated algorithms and human comprehension by empowering users to comprehend and analyze the inner workings of AI models. XAI equips stakeholders to evaluate and trust AI systems, assuring fairness, accountability, and ethical standards in fields like healthcare and finance where AI-based choices have substantial ramifications. The development of XAI is essential for attaining AI's full potential while retaining transparency and human-centric decision making, despite ongoing hurdles. 2023 EDP Sciences. All rights reserved. -
Artificial intelligence: A new model for online proctoring in education
As a result of technological advancements, society is becoming increasingly computerized. Massive open online courses and other forms of remote instruction continue to grow in popularity and reach. COVID-19's global impact has boosted the demand for similar courses by a factor of ten. The ability to successfully assign distant online examinations is a crucial limiting factor in this next stage of education's adaptability. Human proctoring is now the most frequent method of evaluation, which involves either forcing test takers to visit an examination centre or watching them visually and audibly throughout tests via a webcam. However, such approaches are time-consuming and expensive. In this paper, we provide a multimedia solution for semi-automated proctoring that does not require any extra gear other than the student's computer's webcam and microphone. The system continuously monitors and analyses the user based on gaze detection, lip movement, the number of individuals in the room, and mobile phone detection, and captures audio in real time through the microphone and transforms it to text for assessment using speech recognition. Access the words gathered by speech recognition and match them for keywords with the questions being asked for higher accuracy using Natural Language Processing. If any inconsistencies are discovered, they are reported to the proctor, who can investigate and take appropriate action. Extensive experimental findings illustrate the correctness, resilience, and efficiency of our online exam proctoring system, as well as how it allows a single proctor to simultaneously monitor several test takers. 2023 Author(s). -
Regression Test List Sharding in a Distributed Test Environment
One of the major issues during the regression test of the new version of Real Time Operating System (RTOS) is the time involved in test case execution. The main reason being a single embedded system device under test (DUT) is used to execute the test list containing several test cases. This traditional method of regression test also leads to wasted productivity of the other devices at hand that could be otherwise used during this regression test. Hence, in this paper, we propose a technique that aims at reducing the overall regression test cycle time of a newer version of a Real Time Operating System (RTOS) by employing a method known as "test-list sharding"in a distributed test environment. In the proposed work, multiple DUTs are connected to the test server via a communication network. The test server executes the test list containing several test cases and performs the test-list sharding, that is, distributing test cases to different DUTs and executing them in parallel. After the test is executed on the DUT, the test results are sent back to the test server which will summarize all the results. In the proposed work, the sharding is done by distributing the test cases without overloading or under loading any of the DUTs. Test list is sharded in such a way that the same tests are not sent to multiple DUTs. The main advantage of the proposed method is that the test sharding can be easily scalable to accommodate any number of devices that can be connected to the test server. Also, the test list sharding is done in a dynamic way so that the tests are distributed to an idle DUT that has completed a test execution and ready for another test to execute. The comparison study of executing a sample test list sequentially on a single DUT and distributed test system with multiple DUTs is performed. Results obtained showed the performance gain in terms of test cycle time reduction, scalability, equal load distribution and effective resource utilization. 2023 EDP Sciences. All rights reserved.