b) 2024 - 140 Documents

Permanent URI for this communityhttps://dspace.psgrkcw.com/handle/123456789/4916

Browse

Now showing 1 - 20 of 143

A COMPREHENSIVE REVIEW OF LEARNING RULES AND ARCHITECTURE OF PERCEPTRON IN ARTIFICIAL NEURAL NETWORKS (ANNS) (Book Chapter)
(CRC Press, 2024-1) Shanthini S; Devi, M. Sindhana; Grace, R. Suriya
The complicated neural networks of the human mind have acted as a significant model for creating artificial neural networks (ANNs) of computational intelligence. ANNs can recognize patterns in data, make decisions, and perform other functions. The study provides a comprehensive review that explores ANNs by analysing the crucial elements of learning rules and perceptron architectures. This chapter clarifies the foundational learning rules underlying ANNs’ ability to adapt and generalize from data. The investigation comprehensively inspects the vital elements of learning rules and perceptron architectures in Artificial Neural Networks (ANNs) inspired by the detailed neuronal networks of the human brain. This chapter subsequently explores the dynamic realm of perceptron architectures within ANNs. Single-layer perceptrons are examined for their inability to handle intricate relationships. In contrast, multilayer perceptrons (MLPs) emerge as formidable solutions. The complex composition of MLPs, characterized by input, hidden, and output layers, is deconstructed, highlighting their potential to capture intricate non-linear patterns through the strategic deployment of activation functions. This analysis showcases a merging of academic notions and actionable effects. The combined effect between learning rules and perceptron architectures forms the foundation of ANNs’ expertise in pattern recognition, prediction, and decision-making tasks. By comprehensively understanding these underpinnings, researchers and practitioners can connect the potential of ANNs across diverse domains.
ADSORPTION BEHAVIOR OF VX NERVE AGENT ON X12Y12 NANOCAGES: A DENSITY FUNCTIONAL THEORY STUDY
(Springer, 2024-08) Prince Makarios Paul, S; Parimala devi, D; Praveena, G; Jeba Beula, R
Herein our study, analysis on the adsorption of VX nerve agent on to X12Y12(Al12N12, Al12P12, C12Si12 and Mg12O12) nanocages is done using density functional theory (DFT). All the calculations were performed using DFT/B3LYP-D3/6-31G (d) basis set, to delve into the capability of these nanocages for sensing and adsorption of VX. Various parameters such as adsorption energy (Eads), energies of highest occupied molecular orbital (HOMO), lowest unoccupied molecular orbital (LUMO), Fermi energy (EF), work function alteration (%∆Φ), energy gap (Eg), global electron density transfers (GEDT) along with molecular electrostatic potential (MEP) and density of states (DOS) profiles of the isolates and complex were calculated, compared and examined. The findings exhibited O atom of VX to interact with Al, Si and Mg atoms of the respective nanocages, and the nature of interaction was from nearly covalent to van der Waals. Furthermore, the potential for the nanocage to sense the target gas was analyzed by means of Fermi energy (EF), alteration in work function (%∆Φ) and its recovery time (τ). Among the considered nanostructures, Mg12O12 was recorded with the highest adsorption energy of−97.39 kcal/mol, suggesting it to be a promising adsorbent for VX.
AIR QUALITY INDEX PREDICTION MODEL USING TEMPORAL FUSION TRANSFORMER
(International Journal of Intelligent Systems and Applications in Engineering, 2024-02-02) Santhana Lakshmi, V; Vijaya, M S
Air pollution’ emerges as a substantial universal concern with far-reaching consequences for people health, affecting numerous persons worldwide. Its adverse effects encompass various respiratory and cardiovascular issues. The Air Quality Index (AQI) serves as a numeric gauge for evaluating air quality, furnishing details about pollutant levels like particulate matter, ammonia, carbon monoxide, NO2, ozone and SO2. The anticipation of AQI proves instrumental in empowering individuals and communities to undertake precautionary measures against the detrimental impacts of air pollution. Leveraging deep learning for AQI prediction becomes imperative. Positioned within machine learning, deep learning employs artificial neural networks as a potent tool to address complex challenges. This study employs an attention-based Arcane Neural Web, specifically the TFT, for constructing the estimating model. The model's efficacy is then juxtaposed with other deep learning models, including Long Short-Term Memory, Bidirectional Long Short-Term Memory, and Fenced Repeated Unit
ALMOND GUM-CHITOSAN NANOCOMPOSITE AS EDIBLE FORMULATION FOR ADVANCING POSTHARVEST LONGEVITY OF FRUITS AND VEGETABLES
(John Wiley and Sons Ltd, 2024-06) Siva Nandhini, Suresh; Praveetha, SenthilKumar; Charumathi, Pushparaj; Prakash Kumar, Sarangi; Viduthalai Rasheedkhan, Regina; Ramesh, Subramani
Postharvest produces including fruits and vegetables are perishable and require preservation for prolonged shelf life. Edible coatings are emerging as a safe and value-added alternative for traditional preservation methods such as refrigeration and chemical treatments. In this article, we have developed almond gum/chitosan (AC)-based edible coating/formulation and investigated the effectiveness of coating on improving the shelf life of tomatoes and blueberries. The coated tomatoes and blueberries, after a shelf life of 25 and 20 days, respectively exhibited a significant improvement in weight loss (5%–20%), reduced acidity (1–3 folds), and kept the ascorbic acid content lower when compared to the uncoated tomatoes and blueberries. Both the coated tomatoes and blueberries did not exhibit spoilage indicating antimicrobial activity of the coating. Direct testing of the coating formulations exhibited significant anti-microbial activity against Staphyococcus aureus and Pseudomonas aeroginosa. The polymer films, prepared using the coating formulation, exhibited low moisture content (34.8 ± 2.02% and 41.5 ± 1.34%), low solubility (42.56 ± 2.3% and 31.31 ± 3.1%), low tensile strength (0.34 ± 0.05 N m−2 and 0.75 ± 0.07 N m−2) and high elongation (63.2 ± 4.12% and 71.5 ± 3.8%). These measured film properties confirm that the polymer film has good flexibility and is suitable for edible packaging. Overall, the newly developed AC edible coating exhibits significant potential for a wide range of applications within the food processing industry, offering a viable substitute for conventional wax and lipid-based coatings.
AMINOGUANIDINIUM HYDROGEN 1,1-CYCLOBUTANE DICARBOXYLATE: SYNTHESIS, STRUCTURAL CHARACTERIZATION AND MOLECULAR DOCKING STUDIES
(Elsevier B.V, 2024) Sheikdawood, Parveen; Shanmugapriya, A; Saravanakumar, B; Hung-Huy, Nguyen; Kanchana, P; Regina Delcy, V
On neutralization of Aminoguanidine bicarbonate (H2Agun) with 1,1 -cyclobutane dicarboxylic acid (H2CBD) resulted aminoguanidinium salt, [(HAgun)+ (HCBD)-]. Using FT-IR, 1H NMR, 13C NMR, and analytical spectroscopy, the compound was identified and characterized. Furthermore, single X-ray diffraction experiment confirms the molecular structure of the salt. The molecular docking approach has been employed to investigate the inhibitory properties of aminoguanidinium hydrogen 1,1-cyclobutane dicarboxylate on three key cancer protein receptors: 3WZE (VEGFR kinase), 5ZMA (crystal structure of an allosteric Eya2 phosphates inhibitor lung cancer protein), and 1JNX (BRCT repeat region from the breast cancer associated protein). Observation of lower binding energy of −4.67 kcal/mol for 3WZE, −4.57 kcal/mol for 5ZMA and 1.7 kcal/mol for 1JNX, respectively, indicating high stability with the protein molecule.
ANTIBACTERIAL AND ANTICANCER ACTIVITY (PANC-1) OF GREEN SYNTHESIZED COPPER OXIDE NANOPARTICLES FROM CATHARANTHUS ROSEUS
(Taylor and Francis Ltd, 2024) Karthika, S; Kanchana, P; Prabha Devi, B; Shanmuga Sundari, S
Copper oxide nanoparticle was biosynthesized using the petals of Catharanthus roseus, and it was found to exhibit anticancer activity in a human pancreatic cell line (PANC-1). The obtained nanoparticles were characterized using XRD, FTIR, FESEM, and TEM techniques. XRD confirms the coexistence of CuO and Cu2O nanoparticles with an average grain size of 15 nm. FTIR spectra possess bands that indicate the formation of copper oxide nanoparticles. FESEM and TEM show spherical shape morphology with an average particle size of 19.6 nm to 32.6 nm. The synthesized copper oxide nanoparticles were tested for antibacterial activity, and the gram-negative bacteria Escherichia coli and Pseudomonas aeruginosa showed a better zone of inhibition than standard streptomycin. The copper oxide nanoparticle was tested for anticancer activity in the PANC-1 line, and the results confirm that cells undergo cell shrinkage in the cytoplasm, which suggested the cytotoxic behavior. The viability of cells was evaluated by an inverted phase contrast microscope followed by the MTT assay method.
APPLICATION OF QUERCETIN AS A GREEN INHIBITOR TO PREVENT MILD STEEL CORROSION IN THE PETROLEUM INDUSTRY: EXPERIMENTAL AND MODELLING TECHNIQUES
(Elsevier, 2024-03) Saranya, J; Vagdevi, K; Jyothirmai, B; Anusuya, N; Benhiba, F; Warad, I; Zarrouk, A
Quercetin (QT) is found to be a green source of anti-corrosion additive for M-S protection in 0.5 M sulfuric solution. Weight loss, surface studies, atomic absorption spectroscopy, potentiodynamic polarization (PP), impedance spectroscopy (EIS), - more especially, scanning electron microscopy combined with energy dispersive spectroscopy SEM/EDS—and simulation studies were among the methods used to evaluate the efficacy of corrosion inhibition. With 1000 ppm of the inhibitor at 303 K, the weight loss trials had the highest inhibition effectiveness of 96.8 % which obeyed Langmuir adsorption isotherm. The inhibitor QT is represented as mixed-type as per polarization studies. Scanning electron microscopy test results showed the lesser degradation of the lower M-S surface in 0.5 M H2SO4 solution at 1000 ppm QT. Moreover, modelling studies employing density functional theory (DFT) and molecular dynamics (MD) showed that the green inhibitor QT adsorbed on the M-S surface and formed a barrier on the metal surface.
ASSESSING THE ECOLOGICAL IMPACT OF PESTICIDES/HERBICIDES ON ALGAL COMMUNITIES: A COMPREHENSIVE REVIEW
(Elsevier, 2024-03) Mathiyazhagan, Narayanan; Kesavan, Devarayan; Monu, Verma; Manickam, Selvaraj; Hamed A, Ghramh; Sabariswaran, Kandasamy
The escalating use of pesticides in agriculture for enhanced crop productivity threatens aquatic ecosystems, jeopardizing environmental integrity and human well-being. Pesticides infiltrate water bodies through runoff, chemical spills, and leachate, adversely affecting algae, vital primary producers in marine ecosystems. The repercussions cascade through higher trophic levels, underscoring the need for a comprehensive understanding of the interplay between pesticides, algae, and the broader ecosystem. Algae, susceptible to pesticides via spillage, runoff, and drift, experience disruptions in community structure and function, with certain species metabolizing and bioaccumulating these contaminants. The toxicological mechanisms vary based on the specific pesticide and algal species involved, particularly evident in herbicides' interference with photosynthetic activity in algae. Despite advancements, gaps persist in comprehending the precise toxic effects and mechanisms affecting algae and non-target species. This review consolidates information on the exposure and toxicity of diverse pesticides and herbicides to aquatic algae, elucidating underlying mechanisms. An emphasis is placed on the complex interactions between pesticides/herbicides, nutrient content, and their toxic effects on algae and microbial species. The variability in the harmful impact of a single pesticide across different algae species underscores the necessity for further research. A holistic approach considering these interactions is imperative to enhance predictions of pesticide effects in marine ecosystems. Continued research in this realm is crucial for a nuanced understanding of the repercussions of pesticides and herbicides on aquatic ecosystems, mainly algae.
AN ASSESSMENT OF METAL ABSORPTION COMPETENCE OF INDIGENOUS METAL TOLERANT BACTERIAL SPECIES- AN IN-VITRO STUDY
(Elsevier, 2024) Anusha, P; Natarajan, D; Sumathy, Rengarajan; Saleh, Alfarraj; Sabariswaran, Kandasamy
Heavy metals pose a serious global threat to the environment. Hence, removing hazardous metals from soil samples has become complicated over the past few years. The current work looked into the remediation of heavy metals from aqueous solutions using a bacterial community and a unique bacterium obtained from metal-contaminated soil. In this investigation, the isolates of Bacillus anthracis A1-7, Bacillus. thuringiensis A1-3, Bacillus. cereus A1-5, and Pseudomonas aeruginosa A-33 actively demonstrated metal tolerances to various tested metals. Furthermore, an in-vitro biosorption study was performed under ideal concentration. The bacterial consortia achieved the highest biosorption effectiveness for Cu & Zn, 92.7% and 90.3%, respectively. When compared with a single bacterium, the group exhibited inferior Pb biosorption (86%). Since then, P. aeruginosa A33 has had the highest Pb biosorption. Finally, a bacterial consortium has devised an intriguing strategy for eliminating Cu and Pb from the polluted medium. P. aeruginosa A33 was found to be a mighty microbe that extracts Zn from polluted water. This metal-tolerant bacterium also exhibited specific proportions of selective commercially available antibiotics, which were analyzed using the Multiple Antibiotic Resistance (MAR) Index. In conclusion, these findings indicated that bacterial consortia composed of four bacterial isolates can remove metals from a metal-polluted medium.
BINARY SOFT SIMPLY* ALPHA OPEN SETS AND CONTINUOUS FUNCTION
(Forum-Editrice Universitaria Udinese SRL, 2024) Parvathy, C R; Sofia, A
A topological rough approximation space is defined over two different universes using binary soft relations. A new class of binary soft set and its corresponding soft topology is obtained. Continuity functions for the newly defined set are introduced. The characteristics of continuity functions between two binary soft topological spaces and that between binary soft topological space and topological rough approximation space are examined. The proposed definitions and properties are demonstrated with suitable examples.
BOOTSTRAPPING OF FINE-TUNED SEGMENTATION AND CLASSIFICATION NETWORK FOR EPIDERMIS DISORDER CATEGORIZATION
(Springer Link, 2024) Kalaivani, A; Karpagavalli, S
As all people have been affected by various skin related illnesses, categorization of skin disorders has become prominent in recent healthcare system. To identify and categorize skin related syndromes, many transfer learning frameworks were used. Amongst, a Fine-tuned Segmentation and Classification Network (F-SegClassNet) achieved better efficacy by using the novel unified loss function. Nonetheless, it was not apt for the datasets that lack in training images. Hence in this article, Bootstrapping of F-SegClassNet (BF-SegClassNet) model is proposed which solves the imbalanced images in the training set via generating the group of pseudo balanced training batches relying on the properties of the considered skin image dataset. This model fits the distinct abilities of Deep Convolutional Neural Network (DCNN) classifier so that it is highly useful for classifying the skin disorder image dataset with a highly imbalanced image data distribution. According to the Bootstrpping, better tradeoff between simple and complex image samples is realized to make a network model that is suitable for automatic skin disorders classification. In this model, statistics across the complete training set is calculated and a new subset is produced that retains the most essential image samples. So, the skin images are segmented and categorized by this new model to identify the varieties of epidermis infections. At last, the testing outcomes exhibits BF-SegClassNet-model accomplishes the mean accuracy with 96.14% for HAM dataset which is compared to state-of-the-art models.
BOX-BEHNKEN DESIGN FOR PHOTOCATALYTIC DEGRADATION OF SUDAN BLACK B BY CATALYST-EMBEDDED MULTIWALLED CARBON NANOTUBES
(Institute for Environmental Nanotechnology, 2024) Angulakshmi, V S; Mageswari, S; Kalaiselvan, S; Padmavathi, R; Parvathi, K
This research employs a Box Behnken design-based technique for photocatalytic use of Multiwalled Carbon Nanotubes (MWCNTs) derived from spray pyrolysis. This procedure was used for photocatalytic degradation applications on Sudan black dye using Citrus limonum oil as a carbon precursor and Fe/Co/Mo supported on silica as a catalyst. The influence of initial dye concentration was compared to the effects of H2O2, catalyst concentration and solar light intensity. The Response Surface Methodology was used to optimize growth parameters for higher yield and graphitization. The as-grown CNTs were exemplified using scanning and transmission electron microscopy and Raman spectroscopy. This work resulted in the identification of the optimal set of spray pyrolysis turning parameters for achieving high CNT yield and effective decolorization of Sudan black B dye by employing MWCNTs as catalyst. The degree of decolorization of Sudan black B dye increases upto a certain level with an increase in initial H2O2 concentration and subsequently declines as excess H2O2 hydroxyl radicals formed serve as scavengers, resulting in less dye decolonization.
CAMELLIA SINENSIS ASSISTED GREEN SYNTHESIS OF METAL OXIDE NANOPARTICLES: INVESTIGATION OF STRUCTURAL, VIBRATIONAL, MORPHOLOGICAL AND THERMAL ANALYSIS
(2024-06) Sathyapriya, R; Nilofur Fathima, S J; Arun Paul, C; Prakash, T; Ranjith Kumar, E; Arunadevi, Natarajan
Metal oxide nanoparticles were created via a green combustion approach, with natural tea extract and metal nitrates as the key starting components. The X-ray diffraction (XRD) spectra were used to determine the phase of CuO, NiO, and Co3O4 nanoparticles. The findings validate the monoclinic and cubic structures of CuO, NiO, and Co3O4 nanoparticles. The X-ray diffraction (XRD) profiles of CuO, NiO, and Co3O4 nanoparticles show crystallite sizes of 25.2, 31.2, and 32.5 nm, respectively. Metal oxide nanoparticles exhibit approximately equal average crystallite diameters, demonstrating the consistency of the synthesis procedure. The FTIR spectra were utilized to investigate the functional groups and other chemical components present in CuO, NiO, and Co3O4 nanoparticles. FESEM investigation revealed a leaf-like surface morphology in CuO nanoparticles. The EDX spectra confirm the presence of metals and oxygen in the produced metal oxide nanoparticles. The study focused on the thermal stability and weight loss % of metal oxide nanoparticles. Metal oxide nanoparticles synthesized from natural tea have been shown to have good thermal stability.
CHITOSAN – AN ALTERNATIVE DRUG DELIVERY APPROACH FOR NEURODEGENERATIVE DISEASES
(Elsevier Ltd, 2024) Mahalaxmi, Iyer; Ajay, Elangovan; Ramya, Sennimalai; Harysh Winster, Suresh Babu; Saranya, Thiruvenkataswamy; Jayalakshmi, Krishnan; Mukesh Kumar, Yadav; Abilash Valsala, Gopalakrishnan; Balachandar, Vellingiri
Neurological disorders have become severe and dreadful issues around the globe that are rarely directly mediated because of the blood-brain barrier (BBB). Despite the various therapeutic strategies, including the utilization of cholinesterase inhibitors, metal chelators, molecular chaperones, and anti-body treatment that have been put forth, drug delivery to the brain has remained a problem in the treatment of neurodegenerative disorders (NDD). Chitosan, one of nature's multifunctional polymers, is acknowledged as a useful chemical in the medical and pharmaceutical industries due to its distinctive and flexible biological characteristics. By using Chitosan and its derivatives as drug delivery methods, it is possible to give medications in a sustained and regulated way, increase their stability, and lessen the likelihood of adverse drug reactions. In the current review, we have concentrated on the significance of Chitosan and its derivatives to become a hotspot in drug delivery, particularly for NDDs. This review also explains their properties as drug delivery vectors and their ability to cross the BBB, which is a significant obstacle to medication administration in NDDs. In conclusion, this review suggests that expanding the scope of such research would make it possible to develop NDD drug delivery systems that are more efficient.
CHITOSAN-BASED INSECTICIDE FORMULATIONS FOR INSECT PEST CONTROL MANAGEMENT: A REVIEW OF CURRENT TRENDS AND CHALLENGES (Review)
(Elsevier B.V., 2024-11) Mohan, Kannan; Kandasamy, Sabariswaran; Rajarajeswaran, Jayakumar; Sundaram, Thanigaivel; Bjeljac, Marko; Surendran, Ramya Preethi; Ganesan, Abirami Ramu
Future agricultural practices necessitate green alternatives to replace hazardous insecticides while distinguishing between pests and beneficial insects. Chitosan, as a biological macromolecule derived from chitin, is biodegradable and exhibits low toxicity to non-target organisms, making it a sustainable alternative to synthetic pesticides. This review identifies chitosan-derivatives for insecticidal activity and highlights its efficacy including genotoxicity, defense mechanism, and disruption of insect's exoskeleton at different concentrations against several insect pests. Similarly, synergistic effects of chitosan in combination with natural extracts, essential oils, and plant-derived compounds, enhances insecticidal action against various pests was evaluated. The chitosan-based insecticide formulations (CHIF) in the form of emulsions, microcapsules, and nanoparticles showed efficient insecticide action on the targeted pests with less environmental impact. The current challenges associated with the field-trial application were also recognized, by optimizing potent CHIF-formulation parameters, scaling-up process, and regulatory hurdles addressed alongside potential solutions. These findings will provide insight into achieving the EU mission of reducing chemical pesticides by 50 %.
CLASSIFICATION OF CYBER ATTACKS IN INTERNET OF MEDICAL THINGS USING PARTICLE SWARM OPTIMIZATION WITH SUPPORT VECTOR MACHINE
(Springer Science and Business Media Deutschland GmbH, 2024-09-06) Viji Gripsy, J; Sasikala, M; Maneendhar, R
The Internet of Medical Things (IoMT) is a tangible application of the IoT inside the healthcare sector, presenting an opportunity to enhance the existing healthcare system and enhance patient well-being and quality of life. The presence of vulnerabilities in the ongoing transmission of IoMT data is a potential risk, since it enables unauthorised individuals to criminally get access to sensitive health information. This compromised data might then be used for malicious purposes. A multitude of security approaches have been suggested and developed in order to effectively mitigate the security problems associated with the IoMT. This paper aims to frame cyber-attack prediction as a classification issue, with a focus on the field of networking. The objective is to predict the specific kind of network attacks using machine learning algorithms. The classification of different forms of Denial of Service (DOS) assaults includes the following: BENIGN, MSSQL, DNS, LDAP, TFTP, SSDP, SYN Flood, PORTMAP, SNMP, NetBIOS, UDP, UDP-Lag, and WebDDoS. The findings indicate that the suggested PSO with SVM algorithm has a 97% accuracy rate, outperforming than existing algorithms.
THE COMPREHENSIVE REVIEW ON 3D PRINTING- PHARMACEUTICAL DRUG DELIVERY AND PERSONALIZED FOOD AND NUTRITION
(Elsevier Ltd, 2024) Meenakshi, Murugan; Selva Kumar, Ramasamy; Geetha, Venkatesan; Jintae, Lee; Selvaraj, Barathi; Sabariswaran, Kandasamy; Prakash Kumar, Sarangi
Three-dimensional printing is one of the emerging technologies that is gaining interest from the pharmaceutical industry as it provides an opportunity to customize drugs according to each patient's needs. Combining different active pharmaceutical ingredients, using different geometries, and providing sustained release enhances the effectiveness of medicine. One of the most innovative uses of 3D printing is producing fabrics, medical devices, medical implants, orthoses, and prostheses. This review summarizes the various 3D printing techniques such as stereolithography, inkjet printing, thermal inkjet printing, fused deposition modelling, extrusion printing, semi-solid extrusion printing, selective laser sintering, and hot-melt extrusion. Also, discusses the drug relies profile and its mechanisms, characteristics, and applications of the most common types of 3D printed API formulations and its recent development. Here, Authors also, summarizes the central flow of 3D food printing process and knowledge extension toward personalized nutrition.
COMPUTATIONAL STUDY ON ALKALI AND ALKALINE EARTH METAL DECORATED B20 CLUSTER FOR HYDROGEN STORAGE APPLICATION
(Springer Link, 2024) Parimala devi, Duraisamy; Prince Makarios Paul, S; Praveena, Gopalan; Abiram, Angamuthu
The potential of B20 cluster decorated with alkali metals (AM = Li, Na, and K) and alkaline earth metals (AEM = Ca, Mg, and Be) to adsorb hydrogen molecules is investigated using density functional theory (DFT). The Bader’s topological parameters suggest the presence of non-bonded interaction between the bare structures and H2 molecules. Global reactivity descriptor values confirm that the structures remain stable even after the adsorption of H2 molecules. The results indicate that Na adorned B20 (B20Na2) can store up to 12H2 molecules, with a hydrogen storage capacity of 8.33 wt% and an average adsorption energy is 0.127 eV/H2. The findings suggest that B20 cluster decorated with AM and AEM have the ability to be a promising hydrogen storage material. Additionally, to gain insights into the adsorption and desorption behaviors of H2 molecules, ADMP molecular dynamics simulations methods were performed at room temperatures.
CONSTRUCTING AN AI-ASSISTED PRONUNCIATION CORRECTION TOOL USING SPEECH RECOGNITION AND PHONETIC ANALYSIS FOR ELL
(Institute of Electrical and Electronics Engineers Inc., 2024-04-14) Lara, Mathusha Sam; Subhashini, R; Shiny, Crispine; Lawrance, Joy Christy; Prema, S; Muthuperumal, S
This research proposes the development of an innovative AI-assisted Pronunciation Correction Tool designed to enhance the English language learning experience for nonnative speakers. The tool combines advanced speech recognition technology with detailed phonetic analysis to provide personalized feedback on pronunciation errors. The system employs state-of-the-art automatic speech recognition (ASR) algorithms to accurately transcribe spoken language input. This transcription is then compared with the target pronunciation using sophisticated phonetic analysis techniques. The tool leverages a comprehensive phonetic database to identify specific phonemes, intonation patterns, and stress points that contribute to pronunciation challenges for English Language Learners (ELL). To ensure adaptability and effectiveness, the tool incorporates machine learning models that continuously evolve based on user interactions. The AI model learns from user-specific pronunciation patterns, adapting feedback to address individual strengths and weaknesses. Users receive instant visual and auditory cues highlighting areas of improvement, along with detailed suggestions for correction. The tool also offers interactive exercises and practice modules to reinforce learning and encourage consistent improvement. The proposed AI-assisted Pronunciation Correction Tool has the potential to revolutionize language learning. The robust 88% accuracy in evaluating intonation and stress patterns is crucial for achieving the research goal of providing comprehensive feedback on speech dynamics.
CONTROLLABILITY OF IMPULSIVE FRACTIONAL DAMPED INTEGRODIFFERENTIAL SYSTEMS WITH DISTRIBUTED DELAYS
(Springer Science and Business Media Deutschland GmbH, 2024) Arthi, G; Sivasangari, R
This paper focuses on controllability results for impulsive fractional distributed delay systems with damping behavior, involving the Caputo fractional derivative (CFD) for both linear and integro-differential systems. For linear systems, controllability results are established through the controllability Grammian matrix and employing a control function. Sufficient conditions for the controllability of nonlinear systems are derived using the Schauder fixed point theorem. An example is provided to illustrate the theory.