Browse Items (16481 total)
Sort by:
-
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. -
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. -
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. -
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. -
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. -
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. -
Microbial fuel cells for electricity generation and environmental bioremediation
The environmental impact on the use of fossil fuels and their unsustainable nature has led to the development of techniques using renewable energy and fuel cells. The recent decade has captured the attention of scientists towards the importance of microbial fuel cells (MFCs) with the role of microbial ability in converting organic wastes directly to electricity through microbially catalyzed anodic reactions along with microbial/enzymatic cathodic electrochemical reactions. MFC represents an environmental friendly approach for the use of generating electricity using wastewater, thus ensuring a bioremedial approach for effluent treatment with the achievement of chemical oxygen demand (COD) of about 50% chemical oxygen demand and power densities. This MFC utilises microbial metabolism for electricity generation. The overall performance of electricigens or MFC is based on the reactor design, operating conditions, electrode material used, types of substrates, and microorganisms involved. The optimization parameters studies for commercial production and their applications for MFC need to be intensified. Microbes have applications as biopolymer electrolytes that can be variously used in the applications of batteries, fuel cells and dye-sensitized solar cells. The use of MFCs has many advantages as they are eco-friendly, they have high performance abilities and they are costeffective and therefore can be used for modern applications. 2022 by Nova Science Publishers, Inc. -
-
Noise removal feature enhancement and speech recognition techniques for artificial larynx transducer speech
Speech impediments are the state of difficulty for a person to speak comfortably. These impediments make the spoken speech distorted and they are generally categorized as disordered speech. The quality of disordered speech is poor as clarity, intelligibility and naturalness is missing. In most type of disordered speech the voice is natural and produced by the vocal system of the human being. The vocal system includes the organ called as Larynx placed in the upper part of the neck. This organ has the vocal folds that contribute for pitch variation and volume of the speech. This organ will be malfunctioning some time or will be removed because of cancer. In both the case in order to restore speech, an external device called Artificial Larynx Transducer (ALT) is used to produce the sound. It is a small handheld battery operated device and is used for decades to obtain the audible speech for people who lost their speech because of removal of larynx. The quality of speech and its intelligibility of AL speakers have not improved for decades. The reason for poor quality is constant vibration of ALT, direct sound from ALT and pressure offered to produce the vibration. newlineSo in this research the nature of the speech produced from ALT is analyzed, a possible enhancement of the parameter is done and a recognition technique of the spoken word with the help of trained data is done. Here the approach followed to tackle the problem of poor quality in AL speech involves both speech enhancement and recognizer technique development. When it is looked as enhancement problem noise region localization, noise estimation and noise suppression methods were adopted. In the process of parameter enhancement, pitch frequency estimation and improvement is implemented. When it is looked as recognition problem the parameters pitch frequency, formant frequency, glottal excitation, spectral tilt, coefficients are extracted. As formant frequency is a sensitive parameter, its estimation was done using Recurrent Neural network. -
Formant frequency estimation of artificial larynx transducer speech using recurrent neural network
Human Beings communicate with each other by speaking. The speech as a signal has 2 components voiced and unvoiced speech. Voiced speech is produced by the excitation produced at glottis and unvoiced is produced by noise created at the mouth. The voiced components that is produced at glottis passes through the vocal tract and then reach the mouth. The nature of the speech is determined mostly at the vocal tract. But for some reason for some people the speech produced is not proper because of the organ problems or motor disorder issue. In these cases, the speech produced is called disordered speech and termed with the names like stammering, apraxia, dysar-theria and so on. In some case, the larynx is removed from human body because of cancer or other issues. For them, Artificial Larynx Transducer (ALT) is given to produce substitution voice. This paper aims at formant frequency estimation of the speech produced with the help of ALT using Recurrent Neural Network (RNN) method. The speech produced with the help of ALT will lack in naturalness and intelligibility. The direct noise coming from ALT device is called DREL noise. This also creates irritability to the listener. So in this paper, a method is proposed for the DREL noise removal and formant frequency estimation of the ALT speech. 2019, Institute of Advanced Scientific Research, Inc.. All rights reserved. -
Enhancement of substitution voices using F1 formant deviation analysis and DTW based template matching
Speech is the best way to express the thoughts and feelings among the human beings. But for many reasons the sound produced by human beings becomes disordered voice and termed with many names based on the cause as stammering, dys-theria, apraxia and so on. In the above mentioned few examples, the voice becomes disordered because of the underperformance of body's organ. The larynx is removed in some human beings because of cancer. For them an artificial larynx transducer (ALT) is used to produce the sounds. The above all sounds are categorized as disordered voice and the sound produced by ALT is also called as Substitution voice. In this paper, a method is used to improve the quality of substitution voice produced by ALT. Algorithm is developed to estimate undesired audio components from the device output and remove the same using Non Linear Spectral Subtraction (NLSS) technique. Further, Fundamental (F0) contour and novel parameter F1 formant deviation of healthy speech (HE) and ALT speech are determined. The above two parameters are estimated and stored during the training phase of the system. In the test phase, the above mentioned parameters are estimated and they are used to scale down the database to reduce overall enhancement time. Next step is template matching done by mapping test data with training data using Dynamic Time Warping (DTW) Technique. The data base with least distance estimation is recognized as the utterance and the same is played back. 2017 IEEE. -
Investigation of speech synthesis, speech processing techniques and challenges for enhancements
The sound produced by any human being or instrument can be used for various applications using the concept of extraction or selection. Using this concept, virtual sounds are produced which is prime requirement for various speech synthesis applications. In this paper we review the different speech processing methodologies, parameters involved and the various applications based on the speech quality produced. Though an overview is given on the processing and involved parameter, priority is given to the speech enhancement application. This survey helps to identify the challenges involved in various processing technique involved in speech enhancement of healthy and disordered speech. These findings with different speech production and speech synthesis techniques will help to improve the quality in various application of speech to text (STT), text to speech (TTS), Automatic speech production (ASP) and Automatic speech recognition (ASR). Copyright 2019 American Scientific Publishers All rights reserved. -
ALT speech recognition system using F0 improvement and spectral tilt method
Human Beings use voice as the medium for communication. Human Speech is a very complex signal with multiple frequencies, amplitudes and intensities that mix up to convey specific information. In international terminology, voice disorders are described as dysphonia. Various dysphonias are clearly organic origin due to nervous, muscular, neuro or cellular degenerative disease affecting the body or it is from local laryngeal changes. Other dysphonias having no visible laryngeal causes are grouped as non organic involving habitual dysphonias that arise from faulty speaking habits or the psycho genic dysphonias that stem from emotional causes. This paper looks at a speech recognition system for disordered speech generated by Physically Disabled people using Artificial Larynx Transducer (ALT) device from the perspective of Speech Signal Processing. From the ALT speech features like formant, pitch and spectral tilt is estimated. For formant frequency estimation RNN technique is used. Before training the system pitch frequency improvement is accomplished. Now the features and homomorphic based coefficients are used for training the system. The same operation is performed during the test phase and compared with the training set. Comparison and decision making is accomplished using distance estimator. BEIESP. -
Comprehensive study on using hydrogen-gasoline-ethanol blends as flexible fuels in an existing variable speed SI engine
The rising human population is causing the utilization of enormous amounts of fossil fuels to fulfill energy needs. Various renewable sources are used as fossil fuels however those resources are not powerful in supplanting customary non-renewable energy sources like gasoline in vehicles. The depletion of conventional fossil fuel utilized in a vehicle contributes to an increased portion of air contamination and is a danger to human well-being. Also, to maintain the supply demand, many active types of research have been carried out in mixing a higher percentage of ethanol over gasoline and further moving towards flex-fuel vehicles. But there arises a problem of knocking and higher CO, and HC emissions from the engine. To overcome the above problem, ethanol could be mixed in a higher percentage over gasoline with the help of hydrogen assistance and can completely avoid the problem of knocking and reducing CO and HC emissions. In this research, the combustion, emission, and performance characteristics of a variable-speed gasoline engine fuelled with ethanol-blended gasoline along with hydrogen assistance are taken for investigation at variable speeds like 1800, 1600, 1400, and 1200 rpm. Hydrogen is added to blended fuel (E30) which has better combustion, emission, and performance than other blended fuels. Hydrogen addition is done at 2, 3, and 4 ms respectively. The outcomes showed that the E30 + H2 at 3 ms has better combustion, emission, and performance, still, the emission of NOx is higher in comparison with all the other blends due to complete combustion. Thus, a two-stage analysis has been done, one is making a comparison among various blends of ethanol, and the second one is the comparison among the various energy shares of hydrogen. 2023 Hydrogen Energy Publications LLC -
Classification of a New-Born Infant's Jaundice Symptoms Using a Binary Spring Search Algorithm with Machine Learning
A yellowing of the skin and eyes, called jaundice, is the consequence of an abnormally high bilirubin concentration in the blood. All across the world, both newborns and adults are afflicted by this illness. Jaundice is common in new-borns because their undeveloped livers have an imbalanced metabolic rate. Kernicterus is caused by a delay in detecting jaundice in a newborn, which can lead to other complications. The degree to which a newborn is affected by jaundice depends in large part on the mitotic count. Nonetheless, a promising tool is early diagnosis using AI-based applications. It is straightforward to implement, does not require any special skills, and comes at a minimal cost. The demand for AI in healthcare has led to the realisation that it may have practical applications in the medical industry. Using a deep learning algorithm, we created a method to categorise jaundice cases. In this study, we suggest using the binary spring search procedure (BSSA) to identify features and the XGBoost classifier to grade histopathology images automatically for mitotic activity. This investigation employs real-time and benchmark datasets, in addition to targeted methods, for identifying jaundice in infants. Evidence suggests that feature quality can have a negative effect on classification accuracy. Furthermore, a bottleneck in classification performance may emerge from compressing the classification approach for unique key attributes. Therefore, it is necessary to discover relevant features to use in classifier training. This can be achieved by integrating a feature selection strategy with a classification classical. Important findings from this study included the use of image processing methods in predicting neonatal hyperbilirubinemia. Image processing involves converting photos from analogue to digital form in order to edit them. Medical image processing aims to acquire data that can be used in the detection, diagnosis, monitoring, and treatment of disease. Newburn jaundice detection accuracy can be verified using image datasets. As opposed to more traditional methods, it produces more precise, timely, and cost-effective outcomes. Common performance metrics such as accuracy, sensitivity, and specificity were also predictive. 2023 Lavoisier. All rights reserved. -
Driving purchase intentions through visual storytelling: a study of social media platform reels sponsored advertising
This study explores how social media platforms (for example, Instagram) and Reels-sponsored ads influence what makes consumers stop, watch and decide to buy. Using Consumer Engagement Theory (CET) as a lens, it looks at how people emotionally, cognitively and behaviourally respond to short-form video content. Four key factors were examined: engaging content, scenario-based experiences, user participation and perceived usefulness. Data from 393 active social media platform users in Indias National Capital Region revealed that all four elements positively shaped consumer attitudes, significantly influencing purchase intentions. Notably, relatable and emotionally engaging content had the most substantial impact. Attitude played a central role, bridging how consumers feel about a Reel and what they choose to do next. For marketers, the takeaway is clear: Reels that are visually appealing, useful and invite interaction are more likely to turn engagement into action. The study offers timely insights into how brands can connect meaningfully through short-form video. 2026 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. -
DFT study of structural and electronic properties of [Fe(CO)4(PbX)] complexes (X = O, S, Se and Te): Influence of terminal lead chalcogenide ligands on bonding and stability
Density Functional Theory (DFT) calculations at the B3LYP level were performed to investigate the structural and electronic properties of axial and equatorial isomers of [Fe(CO)4(PbX)] complexes, where X = O, S, Se, and Te. Total energy evaluations indicate that equatorial isomers are generally more stable than their axial counterparts. Detailed bonding analysis was carried out using Natural Population Analysis (NPA) and Energy Decomposition Analysis (EDA), providing insight into the nature of the FePbX interactions. The FePbX bond strengths were further assessed through Wiberg Bond Index (WBI) calculations. Frontier Molecular Orbital (FMO) analysis revealed HOMOLUMO gaps ranging from 3.04 to 3.97 eV, all of which are narrower than the corresponding gap in Fe(CO)5, suggesting enhanced electronic reactivity due to PbX substitution. Natural Bond Orbital (NBO) analysis indicated a greater electron density contribution from the Pb atom to the FePb bond, whereas for FeC bonds, carbon atoms contributed more significantly than Pb. These results collectively highlight the influence of terminal lead chalcogenide ligands on both the geometric and electronic structure of iron carbonyl complexes. 2025 Elsevier Inc. -
Framework for automatic examination paper generation system /
International Journal Of Computer Science And Technology, Vol.6, Issue 1, pp.128-130, ISSN No: 0976-8491 (Online) 2229-4333 (Pint). -
Enabling context-awareness: A service oriented architecture implementation for a hospital use case
The medical field is continuously flooded with newer technologies and tools for automating all kinds of medical care processes. There are a variety of software solutions and platforms for enabling smart healthcare and for assisting care providers such as doctors, nurses, surgeons and specialists with all kinds of timely insights to diagnose and decide the correct course of actions. There are patient monitoring and expert systems to simplify and streamline healthcare service design, development, and delivery. However there are concerns and challenges with the multiplicity and heterogeneity of technologies and solutions. The dense heterogeneous medical devices available in the intensive therapy units pose a challenge of medical device integration. Needless to say, lot of research work has gone in devising techniques in integrating these systems for exchange of data. However mere device integration does not exploit the modern technologies until meaningful and critical information is presented to doctors and patient care personals adapting to the changes in the patient condition. The goal of this research is to apply context aware computing using service oriented architecture in acquiring, analysing and assisting doctors and nurses with necessary information for easy and critical time saving decision making. This paper presents an implementation of the identified web services which can be consumed during a treatment at the Intensive Therapy Unit (ITU). 2015 IEEE. -
Establishing a service composition frame work for smart healthcare system
As the idea of location awareness has already matured and numerous applications are flooded in today???s word, the logical next step reasons out, to context-awareness. Though the idea of context-awareness has been in the research field for close to two decades, the recent advancement in Internet of Things has brought a more compelling thrust in its research. Sensor networks integrating billions of sensors and actuators will be prevalent in the near future producing big data. Filtering and analysing this data with the contextual information will yield more significant results. But deducing the context information itself poses many challenges and unresolved research problems. Context-awareness systems involve acquiring, analysing, reasoning the data and composing the services for suitable action. Service composition either by orchestrating or choreographing technique has been deployed in certain applications, however, each domain requires unique methodology. Healthcare has always been the top priority when it comes to applying novel technologies. Applying context-awareness computing in the healthcare service sector is of paramount importance. The problem context for this research lies in a cardiology speciality hospital???s Intensive Therapy Unit or the post-surgery recovery ward which has lot of scenarios emanating that involves course of actions to be delivered by the healthcare professionals depending on the context. Depending on mere human service may not be adequate. With the available advancements in technologies, it would be possible to leverage optimum service in that time critical situations, provided technology can sense the changes in context and act accordingly. The course of actions to be taken involves an amalgamation of understanding the location, presence availability, relevance of and coordination among various departments, machines and personnel. This can be summarized as ???Response??? with ???Context-Awareness???. The primarily task is to sense the context and then determine and locate the relevant services, which are distributed in the World Wide Web, to achieve a goal situation as a solution to the problem. In order to deliver such a solution we need to develop an exclusive context-aware framework. The existing frameworks will not be adequate to meet such a demanding situation and hence, the research problem is to evolve a comprehensive service composition framework for smart healthcare systems. In order to solve this problem, a use-case approach was followed. After identifying an appropriate use-case, the solution was first modelled using Automata. The concept of service automata and timed automata were fused to deliver a timed-service automaton which is appropriate to model and test the framework and algorithm for service composition. As a solution to the research problem, a composition based framework of a context-aware smart healthcare system has been presented. It will guide software developers to deploy services for critical healthcare, under the umbrella of Service Oriented Architecture. The matured concept of Automata has been tweaked to present novel timed-service automata which will enable service composition precisely for meeting the time constrained demands of modern healthcare service requirements. It has been tested with UPPAAL verification tool for validity and concurrency. A prototype has been implemented to study the validity of the established framework. Apache JMeter tool was used to test the strength of the services and engine developed based on the proposed algorithm for effective service composition.