Browse Items (2150 total)
Sort by:
-
CNN based Model for Severity Analysis of Diabetic Retinopathy to aid Medical Treatment with Ayurvedic Perspective
One among the major modern life-style diseases is Diabetes. Diabetic Retinopathy is a major cause for blindness even at an early age. Clinical assessments for eye disease are done using visual examinations and probing. Retinal vessel segmentation is an important technique which helps in detection of changes that happens in blood vessel as well as gives information regarding the location of vessels. The work presented in this paper tries to detect and analyze the changes occurred in the blood vessels of human retina caused by diabetic retinopathy. Using digital imaging techniques, the severity screening technique facilitates the diagnosis of diabetic retinopathy. The model works in such a way that it helps the Ayurvedic treatment methodology for Diabetic Retinopathy. Results are obtained to categorize the data elements according to the severity of the disease and different classifications. 2022 IEEE. -
Nine Level Quadra Boost Inverter with Modified Level Shifted Pulse Width Modulation Technique
This research initiatives to introduce a switched capacitor based nine level boost inverter (SC-9LBI) powered by modified level shifted pulse width modulation (PWM) technique. The SC-9LBI equipped with single DC source along with three capacitors and eight controlled switches to develop nine level inverter output voltage. The suggested inverter configuration has the ability of boosting the inverter input voltage into 1:4 ratio. Also, this research involves modified level shifted PWM technique to enhance the quality of inverter output voltage. The effectiveness of the NLMLI is assessed through parameters such as harmonic distortion, peak voltage, and output voltage root mean square value (rms). Simulation studies have been conducted using MATLAB/Simulink to evaluate the proposed inverter's performance. 2024 IEEE. -
Level Shifted Phase Disposition PWM Control for Quadra Boost Multi Level Inverter
This article introduces a novel boost switched capacitor Inverter (NBSCI) that significantly advances existing designs. Many recently developed multilevel voltage source inverters stand out for their ability to reduce the number of DC sources while markedly improving voltage levels with fewer switching devices. Building on these advancements, our work proposes an innovative inverter arrangement that, utilizing 1 DC source, eight switches and 3 capacitors, achieves 9-level output voltage waveforms. The increased range of voltage levels facilitates the generation of high-quality sine wave output signals with minimal Total Harmonic Distortion (THD). Also, this work employs Level shifted - Phase Disposition (LS-PD) pulse width modulation techniques to generate gating signals, ensuring the production of superior output waveforms. The article also presents various simulation results conducted using MATLAB-SIMULINK, providing a comprehensive assessment of the proposed configuration's precise effectiveness under diverse modulation index. 2024 IEEE. -
Significance of extra-framework monovalent and divalent cation motion upon CO2 and N2 sorption in zeolite X
Experimental observations and the GCMC (Grand Canonical Monte Carlo) simulations with fixed and mobile cations in their cavities have been used to study nitrogen and carbon dioxide sorption in divalent cation (Ca, Sr, and Ba) exchanged Zeolite X. Simulations of carbon dioxide and nitrogen adsorption isotherms and the heat of adsorption in divalent cation exchanged zeolite X produced results that were similar to those found in experimental results. Both experimental and simulated isotherms showed that carbon dioxide adsorption capacity is saturated at lower pressure with high adsorption capacity than the nitrogen isotherm in all zeolite samples. In the order of electronegativity of the extra-framework cations, the isosteric heat of sorption results show that carbon dioxide as well as nitrogen molecules interact more with divalent metal ion exchanged zeolites. Simulations of carbon dioxide and the nitrogen sorption in zeolite -X revealed that the mobile extra-framework cations in the cages of zeolite X had a significant advantage over zeolite molecular sieves in the separation process. The simulation with mobile cations can be a good tool for developing selective and purposeful zeolite-based adsorbents by knowing the cation position and its migration upon the adsorption of various gases. 2022 -
Molecular simulations to investigate the guest-induced flexibility of Pu-UiO-66 MOF
Actinide metal-organic frameworks are highly popular because of their significant coordination benefits. Due to production and characterisation challenges, An-MOFs are a relatively less explored coordination polymer. In this study, we considered the experimentally synthesised Pu-UiO-66 MOF, which was the first reported plutonium MOF. In most MOF studies, the framework has been maintained rigid, however, in this case, we investigate both rigid and flexible frameworks. To gain a better understanding of the framework's flexibility, flexible Grand Canonical Monte Carlo (GCMC) simulations were conducted and the calculated results were compared with that of rigid frameworks. Molecular Dynamics (MD) simulations were carried out to examine the effects of framework flexibility of Pu-UiO-66 MOF, a force field-built Grand Canonical Monte Carlo (GCMC) on adsorption of guest molecules, and to analyse the self-diffusion coefficients of acidic gases such as CO2, SO2, and NO2 in the framework. The adsorption isotherms and radial distribution functions for both rigid and flexible frameworks in the presence of gas molecules were compared and analysed using GCMC simulation. Similarly, molecular dynamics simulations including guest molecules were carried out. Following that, the GCMC and MD results were compared and analysed to determine the flexibility of the system. Diffusion studies were conducted at various temperatures and the coefficient of self-diffusion of each gas was examined. In addition, structural analyses, such as angle analysis, were carried out to explore the local changes, such as tilting, observed in the organic ligand derivative. It was also shown that the UFF force field is suitable for Pu-UiO-66. 2022 -
Prediction of Rainfall Using Seasonal Auto Regressive Integrated Moving Average and Transductive Long Short-Term Model
One of the most crucial parts of the practical application in recent years has been the analysis of time series data for forecasting. Because of the extreme climate variations, it is now harder than ever to estimate rainfall accurately. It is possible to forecast rainfall using a number of time series models that uncover hidden patterns in past meteorological data. Choosing the right Time Series Analysis Models for predicting is a challenging task. This study suggests using a Seasonal Auto Regressive Integrated Moving Average (SARIMA) to forecast values that are similar to historical values that exhibit seasonal patterns. Twelve years of historical weather data for the city of Lahore (from 2005 to 2017) and Blora Regency are taken into account for the prediction. The dataset underwent pre-processing operations like cleaning and normalisation before to the classification procedure. For classification, Transductive Long Short-Term Model (TLSTM) is employed which has learned the dependency values where the memory blocks are recurring and capable of learning long-term dependencies on this model. Further, TLSTM's goal is to increase accuracy close to the test point, where test points are selected as a validation group. The performance of the models has been assessed based on accuracy (99%), precision (98%), recall (96%) and fl-score (98%). Proposed SARIMA model showed optimistic results when compared to existing models. 2023 IEEE. -
An Efficient Approach for Obstacle Avoidance and Navigation in Robots
Reinforcement learning has emerged as a prominent technique for enhancing robot obstacle avoidance capabilities in recent years. This research provides a comprehensive overview of reinforcement learning methods, focusing on Bayesian, static, dynamic policy, Deep Q-Learning (DQN) and extended dynamic policy algorithms. In the context of robot obstacle avoidance, these algorithms enable an agent to interact with its physical environment, learns effective operating strategies, and optimize actions to maximize a reward signal. The environment typically consists of a physical space that the robot must navigate without encountering obstacles. The reward signal serves as an objective measure of the robot's performance towards accomplishing specific goals, such as reaching designated positions or completing tasks. Furthermore, successful obstacle avoidance strategies acquired in simulation environments can be seamlessly transferred to real-world scenarios. The promising results achieved thus far indicate the potential of reinforcement learning as a powerful tool for enhancing robot obstacle avoidance. This research concludes with insights into the future prospects of reward learning, high-lighting its ongoing importance in the development of intelligent robotics systems. The proposed algorithm DQN outperforms well among all the other algorithms with an accuracy of 81%, Through this research, we aim to provide valuable insights and directions for further advancements in the field of robot obstacle avoidance using reinforcement learning techniques. 2023 IEEE. -
Interval-Valued Fuzzy Trees and Cycles
Interval-valued fuzzy tree (IVFT) and interval-valued fuzzy cycle (IVFC) are defined in this chapter. We characterize interval-valued fuzzy trees. We also prove that if G is an IVFG whose underlying crisp graph is not a tree then G is an IVFT if and only if G contains only ? strong arcs and weak arcs. It is shown that an IVFG G whose underlying crisp graph is a cycle is an IVFC if and only if G has at least two ? strong arcs. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
On the Laplacian energy of interval valued fuzzy graphs
Interval valued fuzzy Laplacian matrix (IVFLM) associated with an interval valued fuzzy graph (IVFG) is studied in this paper. We define spectrum, energy, Laplacian spectrum and Laplacian energy and obtain some bounds for energy and Laplacian energy. 2020 Author(s). -
On interval valued fuzzy graphs associated with a finite group
We associate a particular type of interval-valued fuzzy graph(IVFG) called interval-valued fuzzy identity graph(IVFIG) with every finite group and study its various properties. We show that IVFIG associated with a finite group is not unique. We also show that every IVFIG associated with a finite group is a strong IVFG. It does not contain any feeble or weak arcs. Further, it is strongly connected. We prove that the IVFIG associated with a finite group in which every element is self inversed is an interval-valued fuzzy tree and the IVFIG of Zn (n is odd) under addition modulo n is the disjoint union of interval-valued fuzzy cycles. 2020 Author(s). -
Characterization of interval-valued fuzzy bridges and cutnodes
In this paper, we characterize interval - valued fuzzy bridges and interval-valued fuzzy cutnodes in terms of ? strong arcs. We discuss about the behaviour of arcs in a strongest path of an interval - valued fuzzy graph. An example is provided to prove that strongest paths are not in general related to strong paths in an interval - valued fuzzy graph. Finally we give a particular condition under which strong paths and strongest paths are equivalent. 2019 Author(s). -
Advancing the Evaluation of Oral Fluency in English for Specific Classrooms: Harnessing Natural Language Processing Tools for Enhanced Assessment
A crucial component of language learning and teaching is evaluating students' speaking abilities. Natural language processing (NLP) techniques have been employed recently in language assessment to automate the evaluation process and produce more impartial and reliable findings. In this study, we offer a speaking evaluation tool based on Natural Language Processing (NLP) that assesses a learner's speaking ability in real-time using cutting-edge algorithms. The instrument is altered to assess the fundamental facet of speaking skills - Fluency. As a result of the tool's immediate feedback, learners may pinpoint their areas of weakness and focus on honing their language abilities. The usefulness of the instrument was assessed through an intervention with a sample size of 30 students of the post-graduate students of a college in Pune, India. Python libraries, including random and re, were utilized to implement the algorithm. Data preprocessing involved accurate transcription of videos using an online tool and manual checking for corrections. Despite acknowledging limitations, such as potential biases in manually inserted hesitation markers, the study serves as a pivotal step toward automated fluency assessment, presenting exciting prospects for NLP and language education advancements. 2024 IEEE. -
Early detection of breast cancer using ER specific novel NIR fluorescent dye conjugate: A phantom study using FD-f-DOT system
Fluorescence diffuse optical tomography (f-DOT) is an imaging technique that can quantify the spatial distribution of fluorescent tracers in small animals and human soft tissues. Efficacy of f-DOT imaging can be improved by tagging a functional group to the dye. A novel estrogen receptor (ER) specific near-infrared (NIR) fluorescent dye conjugate was synthesized which can be effectively used for detecting breast cancer tissues at an early stage. Our novel dye, Near Infrared Dye Conjugate-2 (NIRDC-2), is a conjugate of 17?-estradiol with an analogue of Indocyanine Green dye, bis1,1-(4-sulfobutyl) indotricarbocyanine-5-carboxylic acid, sodium salt. Our present study focuses on imaging cylindrical silicone phantoms using Frequency Domain f-DOT system. Background absorption and scattering coefficients were 0.01mm-1 and 1mm-1 respectively. 10?M concentration of NIRDC-2 and Indocyanine Green (ICG) were administered separately into a cylindrical hole (target) of size 8mm diameter in the phantom. In-silico studies were performed to analyze the properties of dyes using experimental data. Absorption coefficient of 0.0002 mm-1 was recovered for the background. Fluorophore absorption coefficient at the target recovered were 0.000173 mm-1 and 0.000408 mm-1 for ICG and NIRDC-2 respectively. In comparison with ICG, our novel dye had a two fold higher target to background contrast. Recovered target position was accurate but size altered. In concurrence with the recovered fluorescent property and the cell lines studies carried out earlier, binding properties of NIRDC-2 makes it a potential probe for the early tumor detection using f-DOT system. COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only. -
Machine Learning-Based Imputation Techniques Analysis and Study
Missing values are a significant problem in data analysis and machine learning applications. This study looks at the efficacy of machine learning (ML) - based imputation strategies for dealing with missing data. K-nearest Neighbours (KNN), Random Forest, Support Vector Machines (SVM), and Median/Mean Imputation were among the techniques explored. To address the issue of missing data, the study employs k-nearest neighbors, Random Forests, and SVM algorithms. The dataset's imbalance is considered, and the mean F1 score is employed as an evaluation criterion, using cross-validation to ensure consistent results. The study aims to identify the most effective imputation strategy within ML models, offering crucial insights about their adaptability across various scenarios. The study aims to determine the best plan for data preprocessing in machine learning by comparing approaches. Finally, the findings help to improve our knowledge and application of imputation techniques in real-world data analysis and machine learning. 2024 IEEE. -
Node Overlapping Detection for Draggable Node-Based Applications
Node-based interfaces are user interfaces that are based on the concept of nodes, which represent individual units of functionality, and edges, which represent the connections between nodes. In a node-based interface, nodes are connected by edges to form a graph, which represents the data flow and relationships between different parts of the system. The Node overlapping detection technique is only for react flow version 11 and higher. Users having previous versions are not able to use that functionality. To detect the overlapping, based on the output of this library, several user-defined functions can be used to resolve to overlap. It will see the single-pixel overlap. Using this library, users can avoid Node and edge overlapping by creating custom edges. It is a simple JavaScript function currently used for reactjs. In the future, if any other script develops a draggable node-based flowsheet-creating feature, the user can use this library accordingly. 2023 IEEE. -
Research Initiative on Sustainable Education System: Model of Balancing Green Computing and ICT in Quality Education
Green Computing Practices (GCP) convey the revolutionary changes of the modern education system. The education system is transforming into a hybrid mode of operations in effective teaching and learning procedure. In the modern era, computer devices are playing a foremost role in performing ICT based teaching and learning (ICT-BTL). The GCP and ICT-BTL are the creative and innovative practices that can ensure the eco-friendly enactment and safeguard from various harmful environmental impacts. The motive of projecting the present research outcome is to address the impact of GCP on ICT-BTL activities. The creative and innovative practices of ICT-BTL support the implementation of GCP towards a sustainable education system. A sustainable education system interconnects the teachers, learners, institutions, and industrial experts through eco-friendly electronic and computer devices that ensure maximum efficiency in education with minimum environmental impacts. 2022 IEEE. -
Impact of blended education system on outcome-based learning and sector skills development
An effective education system transforms the teaching and learning process into innovative idea generation and independent working ability. A blended education system is the representation of effective education that connects the teachers, students, and educational institutions for content development, delivery of effective teaching methods, and choice-based learning. The motive for initiating the research work was to address the demand for outcome-based learning in society that can fulfill the sector-wise human resource requirements and sector skill development. A blended education system helps to design effective courses and degrees with the capacity of choosing subjects, lectures, and teachers either in online or offline mode of education. The system may also assist in preparing the learning pattern like classroom-based learning, internship-based learning, or learning through project works. The researchers identified the dependent and independent variables with the help of expert opinion. The questionnaire was designed with all relevant questions based on the variables and refined through a pilot study. The research outcomes are described by understanding the nature of quantitative data using statistical tools like frequency distribution, t-test, and ANOVA test with the connectivity of qualitative data and the reality of social issues. 2023 IEEE. -
Unsupervised Learning for Understanding Diversity: Applying Feature Engineering and Cluster Analysis to Deaf and Hard of Hearing Data
As e-Learning emerges as a promising tool for instruction delivery, personalizing the e-Learning platform for DHH learners will benefit them to improve their learning engagement and educational attainment. This study aims to collect and analyze the different features unique to DHH learners and analyze the significant features among them. This study highlights the importance of addressing the diversity among DHH learners, while creating a personalized learning environment for them. With this focus, we employ the K-Means clustering algorithm to group the learners based on similar needs and preferences and identified that distinguishing clusters can be formed within the DHH group. We also tried to understand the significant features contributing to forming well separated groups. These results provide valuable insights into the diverse preferences and requirements when they interact with the learning materials. These findings emphasize the significance of personalized approach for DHH learners in educational settings and serve as the stepping stone to develop a personalized learning environment for them. 2024 IEEE. -
A Comprehensive Study on E-learning Environments for Deaf or Hard of Hearing Learners
Quality education is the fundamental right of every individual regardless of the disabilities they have. For the Deaf or Hard of Hearing (d/DHH) people, e-learning is the most promising way to access the educational materials referred to as digital learning objects (LO) at any time and space which increase their autonomous learning skills. This form of instruction delivery was widely accepted during the outbreak of Covid-19. Hence a background study has been conducted to investigate the challenges in teaching the d/DHH learners during the pandemic. This research work aims at providing a personalized e-learning environment to the d/DHH student community belonging to St. Clare Oral Higher Secondary School for The Deaf, situated in Kerala. To build personalized systems, the primary step is to review the existing e-learning solutions available in the literature and the adaptation techniques implemented by them to offer personalization in line with the components of traditional adaptive e-learning systems. The study carried out in this paper illuminates the need of personalized e-learning platforms that adapt the basic needs, abilities and disabilities of deaf learners which will find the 'best learning solutions' in the form of learning objects. 2023 IEEE. -
Tomato Plant Disease Classification Using Transfer Learning
Detecting and categorizing diseases in tomato plants poses a significant hurdle for farmers, resulting in considerable agricultural losses and economic harm. The prompt underscores the significance of promptly identifying and classifying diseases to enact successful management strategies. Convolutional Neural Networks (CNNs) have demonstrated their effectiveness in tasks involving image classification, notably in categorizing diseases that impact tomato plants. However, CNN models can be computationally expensive to train and require large datasets of labeled images. Utilizing advanced CNN models can enhance the efficacy of classification models for tomato plant diseases, simultaneously decreasing computational expenses and the demand for extensive training data. Enhanced CNN models can be developed using a variety of techniques, such as transfer learning, data augmentation, and residual networks. This project aims to implement a tomato plant disease classification model using an enhanced convolution neural network. This work uses the lifelong learning method which is the model that allows one to learn new tasks without forgetting previous knowledge. Leveraging sophisticated CNN models can improve the effectiveness of classification models for tomato plant diseases, while also reducing computational costs and the need for extensive training data. It is beneficial for tasks where there is limited data available to train a model from scratch. 2024 IEEE.