Browse Items (11810 total)
Sort by:
-
Rating of Online Courses: A Machine Learning Based Prediction Model
Online courses market has provided an economical and easy access to knowledge. When it comes to make a decision related to purchase of online course, little is known about what attributes can be depended upon to guess the quality of an online course. Ratings for online courses act as a reliable signal for assessing the quality of a course. The study discusses the prediction of ratings for online courses using Artificial Neural Network based on Particle Swarm Optimization (ANN-PSO). The experimental results suggests that ANN-PSO model has the capacity to predict the ratings for online courses on the basis of its attributes with accuracy. 2021 IEEE. -
Unveiling the Potential of Bacillus paramycoides, a Halotolerant Endophytic Bacterium with Heavy Metal Tolerance and Plant Growth Promotion Properties
The use of heavy metal resistant plant growth promoting endophytes is an effective method for improving crop yield and cleaning up contaminated sites. In our study, we have isolated thirteen bacterial endophytes from the shoots of Alternanthera philoxeroides, an aquatic plant from Bellandur lake, Bangalore, India. Among the isolates, Bacillus paramycoides showed significant plant growth promotion properties including an extortionate amount of indole acetic acid (IAA) production (144.69 1.01 g/mL) along with other plant growth promoting attributes like ammonia production, nitrogen fixation, phosphate, potassium solubilization, 1-aminocyclopropane-1-carboxylic acid (ACC) deaminase and siderophore production. The isolate also demonstrated the ability to resist pathogen attacks by producing extracellular enzymes, which could have potential industrial uses. Furthermore, it displayed resistance to multiple heavy metals like chromium (Cr), copper (Cu), lead (Pb), zinc (Zn) and cadmium (Cd) as well as the ability to tolerate high salt concentrations (up to 7% NaCl). These characteristics make it an ideal candidate for promoting plant growth in stressful environments and as an effective bioremediation agent. 2024 World Researchers Associations. All rights reserved. -
Deep Learning-Based Prediction of Physical Activity Intensity for Athletes
Maximizing training plans for athletes and lowering the risk of injury depends on a precise assessment of the degree of physical activity. Existing system in-use systems often employ simplistic models, which leads to inaccurate projections. The paper presents a deep learning-based system that uses convolutional neural networks (CNNs) to create real-time predictions using wearable sensor data. Because it automatically extracts relevant features from raw sensor data, the technique does not need human feature engineering. Utilizing thorough model training and evaluation, it exceeded the most recent methods in terms of accuracy (0.92), precision (0.90), recall (0.92), F1-score (0.91), and ROC AUC (0.94). Results of cross-validation over many data subsets confirm the resilience of the method. Comparisons of confusion matrices also demonstrate how effectively the algorithm forecasts various activity intensities. Overall, the proposed system represents a breakthrough in accurately estimating how much physical activity athletes do, enhancing the efficacy of their training, and reducing the possibility of damage in sporting settings. 2024 IEEE. -
Green Synthesis of ?-Fe2O3 Nanoparticles Mediated Musa Acuminata: A Study of Their Applications as Photocatalytic Degradation and Antibacterial Agent
The present study was aimed to green synthesize of ?-Fe2O3 nanoparticles (NPs) using flower extract of Musa acuminata and examination of their antibacterial and photocatalytic activities. The synthesized NPs were investigated using UV-visible spectroscopy, which exhibited a colour change pattern, and the maximum absorption peak at 265 nm confirmed the formation of ?-Fe2O3 NPs. The FTIR analysis showed the presence of various functional groups coated over the synthesized ?-Fe2O3 NPs. The XRD pattern showed that the formation of rhombohedral structure with an average crystallite size was 21.86 nm. FESEM micrographs revealed that ?-Fe2O3 NPs were roughly spherical in shape. EDX spectrum confirmed the presence of Fe and O elements. By TEM analysis, the average particle size was calculated to be 32 nm. Using the well diffusion method, the antibacterial activity of ?-Fe2O3 NPs was tested against both gram positive and negative bacterial strains of Staphylococcus aureus (S. aureus) and Escherichia coli (E. coli). The NPs exhibited good antibacterial activity against the tested bacteria. Finally, the synthesized ?-Fe2O3 NPs demonstrated the photocatalytic degradation of Crystal Violet (CV) dye under sunlight. The efficiency of degradation within 150 min was determined to be 90.27% for CV. This effective removal method under sunlight may support a cost-effective method for degradation of CV dyes from wastewater. Copyright T Indhumathi, N Krishnamoorthy, R. Valarmathy, K Saraswathi, S Dilwyn and S. Prabhu. -
Secured personal health records using pattern-based verification and two-way polynomial protocol in cloud infrastructure
This present research proposes the digitalised healthcare system that enables patients to generate, aggregate and store in the form of personal health records (PHRs). This requires more attention on cost effectiveness and less response time on public cloud platform. The existing cloud platforms have failed to implement the systemic approach for immediate verification and correction models on increasing PHR datasets. The storage and computation are two prime factors. Moreover, cloud systems need more attention on security and privacy breaches. In this proposed model the publisher-observer pattern-based healthcare systems allow the patients to verify and correct the PHRs before any type of computations. The cloud system acts as a backend framework that offers openness and easy accessibility. The experimental segment ensures the computational cost and response time for multiple polynomial PHR variations. The details evaluation also ensures the security and privacy preservation on sensitive healthcare datasets. Copyright 2022 Inderscience Enterprises Ltd. -
Advancing Collaborative AI Learning Through the Convergence of Blockchain Technology and Federated Learning
Artificial intelligence (AI) has revolutionized multiple sectors through its growth and diversification, notably with the concept of collaborative learning. Among these advancements, federated learning (FL) emerges as a significant decentralized learning approach; however, it is not without its issues. To address the challenges of trust and security in FL, this paper introduces a novel blockchain-based decentralized collaborative learning system and a decentralized asynchronous collaborative learning algorithm for the AI-based industrial Internet environment. We developed a chaincode middleware to bridge blockchain network and AI training for secure, trustworthy and efficient federated learning and presented a refined directed acyclic graph (DAG) consensus mechanism to reduce stale models impact, ensuring efficient learning. Our solutions effectiveness was demonstrated through application on an energy conversion prediction dataset from hydroelectric power generation, validating the practical applicability of our proposed system. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Digital twin technologies for automated vehicles in smart healthcare systems
The idea of being comfortable seems appealing to a vast majority of people, from the start humans were always dependent on something. First the tools were invented and with the help of the tools, amazing things were built. From the invention of the wheel to the steam-powered machines and now the introduction of electronic automation, digitization and making intelligent production processes is the need for todays industry. Industry 4.0 is now the standard by which businesses must measure their progress. It enables businesses to reinvent themselves. Manufacturing systems go beyond simple connections here, communicating, analyzing, and using data to drive more intelligent activities. It combines Internet of Things (IoT), analytics, additive manufacturing, robots, artificial intelligence, sophisticated materials, and augmented reality. The autonomous vehicle (AV) is one of the applications of Industry 4.0. AVs can make passenger transfers more efficient. Furthermore, smart sensors, when combined with cognitive computing and IoT, portray an AV as a cyber-physical system where data from all relevant viewpoints is closely monitored and synced between physical devices and the cyber computational realm. By utilizing sophisticated information analytics, AVs will be able to work more effectively, collaboratively, and resiliently. As a result, AVs might be able to work with Industry 4.0 systems. 2023 Elsevier Inc. All rights reserved. -
FloodWatch: Suggesting an IoT-Driven Flood Monitoring and Early Warning System for the Flood-Prone Cuddalore District in the Indian State of Tamilnadu
Floods continue to pose significant threats to communities worldwide, causing loss of life, property damage, and disruption of vital services. Timely and accurate flood monitoring and early warning systems play a critical role in mitigating these impacts. This chapter presents FloodWatch, an innovative IoT-based flood monitoring and early warning system designed to enhance community resilience and response capabilities for the Cuddalore district, classified as one of the multi-hazard-prone districts of Tamilnadu. The Cuddalore district has a coastal line of 68 km, hence it is vulnerable to cyclones, and heavy rainfall, in turn causing floods. FloodWatch leverages the power of the Internet of Things (IoT) technology and provides real-time data collection, analysis, and dissemination for flood-related parameters. FloodWatch integrates a network of smart sensors strategically deployed in flood-prone areas, including rivers, streams, and urban drainage systems. These sensors continuously measure key variables, such as water level, rainfall intensity, weather conditions, and soil moisture content. The collected data is transmitted to a centralized cloud-based platform, where advanced data analytics and machine learning algorithms are employed to process and analyze the information. FloodWatch utilizes historical data and predictive modeling to assess the risk of flooding and generate accurate early warnings. Through intuitive interfaces and mobile applications, relevant stakeholders, including local authorities, emergency responders, and residents, receive real-time alerts and notifications, enabling timely decision-making and appropriate response actions. Key features of FloodWatch include its scalability, adaptability, and user-friendliness. The system can be easily customized to cater to different geographical and environmental conditions, ensuring its applicability in diverse regions. Additionally, FloodWatchs intuitive interfaces provide actionable insights in a visually comprehensible manner, facilitating effective communication and community engagement. The implementation of FloodWatch offers several notable benefits, including improved flood preparedness, reduced response time, and enhanced disaster management. By equipping communities with the tools to monitor, predict, and respond to floods, FloodWatch contributes to minimizing the impact of flood-related disasters, ultimately fostering greater resilience and safeguarding lives and property. FloodWatch represents a significant advancement in flood monitoring and early warning systems, harnessing IoT technology to provide accurate and timely information to communities at risk. This chapter highlights the architecture, functionality, and advantages of FloodWatch, underscoring its potential to enhance resilience and contribute to more effective flood management strategies on a global scale. 2025 selection and editorial matter, A. Daniel, Srinivasan Sriramulu, N. Partheeban, and Santhosh Jayagopalan; individual chapters, the contributors. -
Simulations of electric vehicle model for insights into pre-planned trajectory profiles
Electric vehicles are slowly gaining its significance in the automobile sector due to stringent emission norms. This research article highlights the fundamental modeling steps required for an electric vehicle designing following a simulation approach using MATLAB/Simulink software. It gives a clear and concise way to interpret vehicle model from a simple to complex modelling approach. Unlike other research works, this paper helps to thoroughly perceive the fundamentals involved in modeling an electric vehicle with different trajectory profiles. The vehicles behavior when subjected to different external forces, steering characteristics under different path profiles are analyzed in a systematic way. This research work highlights the significance of identifying and solving issues faced in the safety sub-system of an EV. 2020 SERSC. -
A Study on Machine Learning Techniques for Internet of Things in Societal Applications
Until recent years, monitoring and analysing system inputs, responses were merely based on Sensor Systems. Gradually, Embedded Systems and other Data Resources including Remote Monitoring Units started gaining momentum. But, with advent of Internet of Things (IoT), the outlook and expectations are broadened. IoT introduced incredible volumes of structured and unstructured data of different formats. There is a need to investigate, the underlying concepts of Machine Learning, Internet of Things (IoT) and Embedded Systems. These domains grow and expand its frontiers at a very fast pace. This paper attempts to throw light on possibilities of combining different technological domains, for design and development of Smarter and Context Aware Intelligent Electronics Systems for Societal Utility. Effective implementation and realization of such systems by suitable fusion of essential inter-disciplinary concepts is expected to have considerable potential for societal impact in the years to come. 2019 IEEE. -
Design and performance analysis of braking system in an electric vehicle using adaptive neural networks
Research article emphasizes on the impact of braking concepts considering regenerative braking system and energy consumption aspects in electric vehicles through a new perspective. The electric vehicle system is modeled and simulated using the MATLAB/Simulink software. A dataset is developed using the virtual simulation environment created by co-simulation using the MATLAB/Simulink and the IPG Carmaker software. This dataset is also used in a neural network model based on adaptive neuro fuzzy logic and the system performance is analyzed. Parameters considered for training the neural network are the brake pedal displacement, braking change rate and the need for brake application. The highlight of this study is the focus on a front wheel driven electric vehicle, which uses a standard drive cycle input to validate the model. The significant parameters evaluated in this study include the braking effects, kinetic energy, regenerative braking torque, battery state of the charge and the motor torque. The torque generation and its intended braking force requirements based on the acceleration, deceleration and braking conditions are the notable observations. The regenerative capability of this proposed system design is also illustrated along with the surface plots based on the training dataset. Investigation and analysis reveal that, the battery state of charge could be revived throughout the drive with a steady and stable increase. Transitions of motor torques between tractive and regenerative phases are also illustrated and explained for clarity and brevity. 2023 Elsevier Ltd -
Simulations of electric vehicle model for insights into pre-planned trajectory profiles
Electric vehicles are slowly gaining its significance in the automobile sector due to stringent emission norms. This research article highlights the fundamental modeling steps required for an electric vehicle designing following a simulation approach using MATLAB/Simulink software. It gives a clear and concise way to interpret vehicle model from a simple to complex modelling approach. Unlike other research works, this paper helps to thoroughly perceive the fundamentals involved in modeling an electric vehicle with different trajectory profiles. The vehicles behavior when subjected to different external forces, steering characteristics under different path profiles are analyzed in a systematic way. This research work highlights the significance of identifying and solving issues faced in the safety sub-system of an EV. 2020 SERSC. -
A Fundamental Study on Electric Vehicle Model for Longitudinal Control
Stricter emission norms need to drift toward being environment friendly have shifted the concentration in the automobile sector toward electric vehicles. This research article highlights the fundamental modeling steps required for an electric vehicle control system design following a simulation approach using MATLAB/Simulink software. From an electric vehicle design perspective, this approach offers an excellent solution to give insights into EV research involving multidisciplinary engineering aspects. The study presents longitudinal control technique, relevant observations and results to bring out the differences in open-loop and closed-loop case studies. It also intends to provide better understanding toward the need for a feedback, realization of an expected path profile for students and researchers in this field of interest. The steps involved in transforming the mathematical model into a simulation model and analysis of the simulation results are detailed in this article. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Electric Vehicle Control and Driving Safety Systems: A Review
The relevance of Electric Vehicles (EVs) and the overall market demands of the respective control units is in a never before leap all around the globe as seen from the news, business studies, research trends and technological innovations today. Compared to earlier years, the relevance of driving safety in EVs also gains special attention due to the unforeseen surge in promoting EVs by National, State and City administrations for better environment and societal changes in future. For EV, the scenario broadens to a wider landscape beyond the earlier passive safety design features, to a highly comfortable and safer possible road travel. Safety enhancements can be experimented and implemented on EVs in a reliable way with higher end control of the dynamics, stability and optimised utilisation of individual vehicle characteristics and driver behaviours. In this paper, an attempt is made to scrutinise different control design approaches and possible solution paths experimented upon in the past and currently for EV as seen in the published literature. The quest is also to explore optimisation strategies in an organised way to ensure best possible driving safety along with passenger safety in EVs. 2023 IETE. -
AI for Optimization of Farming Resources and their Management
The chapter explores the incorporation of artificial intelligence (AI) into framework strategies aimed at addressing the dynamic challenges confronting the agricultural industry. It focuses on issues like resource depletion, escalating labor costs, and the impacts of climate change, emphasizing the necessity for inventive solutions. The proposed framework adopts a comprehensive approach that integrates farm-to-fork strategies, smart agricultural practices, and advanced crop planning. Its primary objectives are to enhance crop yields, establish transparent supply chains, and optimize resource allocation. The chapter underscores the potential synergies associated with contextual understanding, efficient communication, and personalized user experiences, anticipating a transformative impact on agriculture. The integration of AI is anticipated to yield unprecedented benefits, paving the way for a more technologically advanced, sustainable, and productive future. Despite these promising prospects, challenges emerge during the integration process, manifesting as regulatory hurdles, infrastructure deficiencies, and inherent complexities. The chapter acknowledges these obstacles and asserts that overcoming them is crucial for realizing the full transformative potential of AI in agriculture. Looking ahead, the convergence of AI and framing strategies is poised to revolutionize the agricultural landscape, ushering in increased efficiency and sustainability. This innovative partnership holds the promise of building a resilient foundation for agriculture, ensuring its adaptability to changing needs and contributing to a greener and more productive future. 2025 selection and editorial matter, Sirisha Potluri, Suneeta Satpathy, Santi Swarup Basa, and Antonio Zuorro; individual chapters, the contributors. All rights reserved. -
Design, Analysis and Validation of Electric Vehicle Control and Safety for Different Path Profiles and Braking Conditions
Energy conservation and Environmental pollution are two major challenges today for our society. Currently, utilization of the latest technology, to reduce energy consumption and harmful emissions from vehicles, is gaining significance in the contexts related to automobile, energy and power industries. Considerations of these contexts enable us to form a more realistic newlineperspective and a need for developing fuel efficient, comfortable and affordable electric vehicles. The importance of design and development of electric vehicle (EV) is better perceived when, there is a major impact on our future society due to (i) the energy saving aspect from newlineboth the customer side on individual expenditure as well as from the national economy viewpoint and (ii) the huge benefit due to reduction of emissions from internal combustion engines using fossil fuels. EV offers the best solution which not only avoids emissions but overcome the dependency on petroleum resources as well. Due to fewer moving parts, monitoring and controlling of EV are also smooth and relatively much easier. The embedded control techniques used in EV also contribute for a better controllable, observable, predictable newlineand efficient vehicle drive. This current research work focuses mainly on Electric Vehicle Mobility and Control aspects for a deeper study. This research work addresses topics related to mathematical modelling and simulation studies for design and analysis of EV control and safety. Validations of the several case studies done during this research are supported by software tools namely MATLAB/Simulink and IPG Carmaker Virtual Driving Simulation Platform. Starting from modelling, throughout the various stages of this work, realistic vehicle parameters and specifications are considered. The newlinedifferent levels of testing, validation and trial runs of the model-based designs are also validated by software in loop and hardware in loop approaches. Automotive Safety Integrity Level B/C hardware was used for the implementation purpose. -
Bridging Digital Divide in India: Positive Outlook Amid COVID-19
The digital divide is described as the gap in access to, knowledge of, use of, or ability to comprehend information and communication technology (ICT) between different societal groups. The digital divide can often give way to an upsurge in social inequalities. This study intended to comprehend the extent of the rural-urban digital divide in India regarding access to the internet and to analyze the increase or decrease in the same due to the global coronavirus pandemic. The analysis of the paper was primarily based on secondary data collected from the report on The Indian Telecom Services Performance Indicators issued by the Telecom Regulatory Authority of India for June 2019 and June 2020. Percentage analysis was employed to comprehend the trend of the digital divide in terms of access for the years 2019 and 2020. The results disclosed that there was an increase in internet access in the rural population during the time frame of COVID-19, and this increase has led to a decrease in the digital divide in terms of access to the internet. Moreover, the study revealed that COVID-19, to some extent, has resulted in bridging the rural-urban digital divide in India in terms of access. The study further highlighted the importance of digital literacy and access to ICT, and suggested ways to improve digital literacy in India. 2022, Associated Management Consultants Pvt. Ltd.. All rights reserved. -
Phytoextract-mediated synthesis of Cu doped NiO nanoparticle using cullon tomentosum plant extract with efficient antibacterial and anticancer property
In the present study, nickel oxide (NiO) and copper-doped nickel oxide (NiCuO) nanoparticles (NPs) were successfully synthesized using Cullen tomentosum plant extract with the co-precipitation method. This work focuses on the Phyto-mediated synthesis and characterization of NPs for their biological applications. Phytochemicals that exist in the plant extract acts as reducing and capping agent. The successful formation of the NPs was validated by various analysis as XRD, FESEM, EDAX, FT-IR, UVVis, and Photoluminescence. According to XRD studies, the average crystallite size of NiO and NiCuO NPs is 36 nm and 31 nm, respectively. The river stone and nanoflower like morphology for NiO and NiCuO NPs are confirmed by FESEM image. Furthermore, the synthesized NPs were tested against Gram-positive (Bacillus subtilis, Streptococcus pneumoniae) and Gram-negative (Klebsiella pneumoniae, Escherichia coli) bacteria, which showed enhanced antibacterial activity of NiCuO NPs. The cytotoxicity of NPs was investigated against human breast cancer cells (MDA-MB-231) and fibroblast L929 cell lines. Also, the IC50 value for human breast cancer cells is 11.8 ?g/mL. According to these findings, NiCuO NPs are potential nanomaterials with advanced healthcare uses. 2023 -
Synthesis and characterization of 4-nitro benzaldehyde with ZnO-based nanoparticles for biomedical applications
Globally, cancer is the leading cause of death and morbidity, and skin cancer is the most common cancer diagnosis. Skin problems can be treated with nanoparticles (NPs), particularly with zinc oxide (ZnO) NPs, which have antioxidant, antibacterial, anti-inflammatory, and anticancer properties. An antibacterial activity of zinc oxide nanoparticles prepared in the presence of 4-nitrobenzaldehyde (4NB) was also tested in the present study. In addition, the influence of synthesized NPs on cell apoptosis, cell viability, mitochondrial membrane potential (MMP), endogenous reactive oxygen species (ROS) production, apoptosis, and cell adhesion was also examined. The synthesized 4-nitro benzaldehyde with ZnO (4NBZnO) NPs were confirmed via characterization techniques. 4NBZnO NPs showed superior antibacterial properties against the pathogens tested in antibacterial investigations. As a result of dose-based treatment with 4NBZnO NPs, cell viability, and MMP activity of melanoma cells (SK-MEL-3) cells were suppressed. A dose-dependent accumulation of ROS was observed in cells exposed to 4NBZnO NPs. As a result of exposure to 4NBZnO NPs in a dose-dependent manner, viable cells declined and apoptotic cells increased. This indicates that apoptotic cell death was higher. The cell adhesion test revealed that 4NBZnO NPs reduced cell adhesion and may promote apoptosis of cancer cells because of enhanced ROS levels. 2023 Wiley-VCH GmbH. -
Calcination process of porous metalorganic frameworks derived from nickel sulfide composites for supercapacitor and computer vision for investigating the porosity-electrochemical correlation
The utilization of metalorganic framework nanostructured electrode materials in supercapacitors and sensor applications is achieved by various chemical methods. In this study, we create NiS and NiS@MOF-BDC by employing nickel precursors and benzene dicarboxylic acid (BDC) as chelating organic linkers through a thermal reduction procedure at a temperature of 400 C to produce the composite. The composite heterostructure enhanced the conductivity, porous characteristics, and diverse potential morphological qualities. The production of composite electrodes demonstrates a specific capacity of 260F/g (104C/g) when subjected to a current density of 1A/g. Additionally, these electrodes exhibit exceptional cyclic stability, enduring 5000 cycles, when used with a 2 M KOH electrolyte. Moreover, the synthesized composite HR-TEM images were analyzed using computer vision and AI techniques for estimating the porosity and investigating the enhanced electrochemical correlation. 2024 Elsevier B.V.