Browse Items (2150 total)
Sort by:
-
Handwritten Telugu Character Recognition Using Machine Learning
The Telugu language is the most prominent representative within the Dravidian language family, predominantly spoken in the southeastern regions of India. Handwritten character recognition in Telugu has significant applications across diverse fields such as healthcare, administration, education, and paleography. Despite its importance, the Telugu script differs significantly from English, presenting distinct challenges in recognizing characters due to its complexity and diverse character shapes. This study explores the application of machine learning, particularly delving into deep learning techniques, to improve the accuracy of Telugu character recognition. This paper proposes a model to recognize handwritten Telugu characters using Convolutional Neural Network (CNN). The proposed study demonstrates the accuracy in identifying diverse handwritten Telugu characters. We assess the system's performance against conventional and machine learning methodologies and preprocess an extensive dataset to guarantee strong model training. The proposed model excels in accurately predicting visually similar but distinct characters, achieving an impressive accuracy rate of 96.96%. 2024 IEEE. -
Harnessing Machine Learning for Mental Health: A Study on Classifying Depression-Related Social Media Posts
This study is of particular relevance in the way it identifies depression-related content on social media using a machine learning model to classify posts and comments. This dataset, encompassing around 6500 entries from various platforms including Facebook, was rigorously annotated by four proficient English-speaking undergraduate students together with the final label which is established via majority voting. Data Preprocessing, initial cleaning, normalization and TF-IDF feature creation through vectorization for the output of POS tags. The different machine learning models that were trained and tested are Logistic Regression, Random Forest, SVM (Support Vector Machine), Naive Bayes Gradient Boosting Algorithm K-NN (K nearest Neighbors) AdaBoost Decision Tree. Authors evaluated the models and measured their accuracy, precision score, recall rate (also known as sensitivity) in addition to F1-score. Gradient Boost, Random Forest, and SVM were top performers among which Gradient boosting was found to be an overall best one with almost 98.5%. They show that machine learning model can successfully predict the label of social media posts, as a way for accurately identifying depression from text data. This detailed model performance evaluation is useful in understanding what each approach does well and poorly, shedding light into whether they are / would be actually suitable for real-world applications. This study not only developed discriminative classifiers, but also included detailed analysis of their performance which should hopefully guide future work and help in practical implementations for real-time mental health monitoring. Through this work, this study aim to facilitate timely identification of depression-related posts, ultimately supporting mental health awareness and intervention efforts on social media platforms. 2024 IEEE. -
Harnessing Medical Databases and Data Mining in the Big Data Era: Advancements and Applications in Healthcare
In the contemporary period of Big Data, the healthcare industry is witnessing a transformative paradigm shift, propelled by the convergence of medical databases and data mining technology. This research paper delves into the multifaceted application of this synergy, offering a comprehensive overview of its implications and opportunities. With the exponential growth of healthcare data, the utilisation of medical databases serves as the bedrock for data mining techniques, fostering critical advancements in diagnosis, treatment, and patient care. Through this research, we explore the integration of electronic health records, genomic data, and clinical databases, unveiling new dimensions of predictive analytics, patient profiling, and disease monitoring. Moreover, we assess the ethical and privacy concerns entailed in this data-rich landscape, emphasising the need for robust governance and security measures. Our paper encapsulates the evolving landscape of health care, demonstrating the immense potential and the ethical responsibilities accompanying this groundbreaking merger of technology and medicine in the period of Big Data. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Harnessing nanotechnology applications and solutions for environmental and climate protection-an overview
Nanotechnology is an emerging technology that has drawn considerable interest from environmentalists. Numerous nano techniques identify Nanotechnology applications as having the potential for imperative advantages and innovation. This work offers a wide-overview of the main beliefs that strengthen s nanotechnology. We focus on the potential applications of nanotechnology for environmental protection and management by thoroughly reviewing past literature. To our understanding, this is an academic, peer-reviewed work to deliver a systematic review of nano-activities in the areas of environmental and climate protection. Our study has been systematically arranged into two different groups (1) Potential applications of nanotechnology in r environmental protection and (2) The best part of Nanotechnology that combats Climate Change. For each of these cases, our contribution is twofold: First, in identifying the technical ways by which nanotechnology can solve environmental risks, and secondly, in briefly presenting its potential advantages. The paper ends with deliberation of challenges and operational barriers that technology needs to overcome to prove its commercial viability and for being adopted for commercial use. 2021 Author(s). -
Harnessing technology for mitigating water woes in the city of Bengaluru
Industrialization has caused most of the world's environmental problems like climate change, water security issues, biodiversity issues among others. Water-related issues like water scarcity, lack of water quality, water sanitation issues, lack of proper water resources management are some of them. Urbanization, population increase, pollution has led to an increase in water demand. Water being the elixir of life, is essential for the day-to-day living of an individual. The Fourth Industrial Revolution technologies like AI, IoT, Blockchain, Machine Learning have the capability of bringing solutions to these issues. The current study focuses on the water woes of Bengaluru, a fast-growing urban city, due to its migrating population. The woes are also due to the irresponsible behaviour of builders converting lakes into real estate infrastructure leading to clogged drains, excess sewage creation and flooding. A huge mismatch between demand and supply of water is created due to these issues. Before the city hits the Day Zero - no water day, it is significant to set up water infrastructure along with technology implementation which will help resolve this burning issue at the earliest. Published under licence by IOP Publishing Ltd. -
Harnessing the Power of Simulation Games for Effective Teaching in Business Schools
This research delves into the effectiveness of simulation games, in business education specifically focusing on how they improve decision making skills, critical thinking, real world business applications, student engagement and problem-solving abilities. While simulation games are widely recognized as cutting edge tools that provide learning experiences beyond traditional methods there remains a gap in empirical research assessing their overall impact on educational outcomes. Using a combination of analysis and qualitative case studies this study seeks to address this gap by examining how simulation games influence factors in business education. The methodology involves using a one-way ANOVA to compare learning outcomes across business disciplines and conducting detailed case studies for context. The results reveal effects of integrating simulation games into curricula on the mentioned learning outcomes. These findings highlight the importance of incorporating simulation games into business education to enhance students learning experiences effectively. By offering insights on optimizing and tailoring the use of simulation games in education settings this study contributes to improving teaching practices in business schools and encourages research into the interaction, between educational technology and learning efficacy. 2024 IEEE. -
Heart Disease Prediction Using Ensemble Voting Methods in Machine Learning
Heart disease is the leading cause of mortality globally according to the World Health Organization. Every year, it results in millions of mortalities and thus billions of dollars in economic damage throughout the world. Many lives can be saved if the disease is detected early and accurately. The typical methods to predict or diagnosis heart diseases require medical expertise. Such facilities and experts are relatively expensive and not very commonly available in under developed and developing countries. Recent times, much research is done on leveraging technology for the prediction as well as diagnosis of heart diseases. Machine Learning techniques have been extensively deployed as quick, inexpensive, and noninvasive ways for heart disease identification. In this work, we present a machine learning approach in detecting heart disease using a dataset that contains vital body parameters. We used seven different models and combined them with Soft-Voting and Hard-Voting ensemble approaches to improve accuracy in 7-model and various 5-model combinations. The ensemble combinations of 5 models achieved the highest test accuracy score of 94.2%. 2022 IEEE. -
Heart Disease PredictionA Computational Machine Learning Model Perspective
Relying on medical instruments to predict heart disease is either expensive or inefficient. It is important to detect cardiac diseases early to avoid complications and reduce the death rate. This research aims to compare various machine learning models using supervised learning techniques to find a better model that gives the highest accuracy for heart disease prediction. This research compares standalone and ensemble models for prediction analysis. Six standalone models are logistic regression, Naive Bayes, support vector machine, K-nearest neighbors, artificial neural network, and decision tree. The three ensemble models include random forest, AdaBoost, and XGBoost. Feature engineering is done with principal component analysis (PCA). The experimental process resulted in random forest giving better prediction analysis with 92% accuracy. Random forest can handle both regression and classification tasks. The predictions it generates are accurate and simple to comprehend. It is capable of effectively handling big datasets. Utilizing numerous trees avoids and inhibits overfitting. Instead of searching for the most prominent feature when splitting a node, it seeks out an optimal feature among a randomly selected feature set in order to minimize the variance. Due to all these reasons, it has performed better. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Hidden Markov Model: Application towards genomic analysis
Hidden Markov Model (HMM) has become one of the interesting methods for the researchers, especially in bioinformatics where different analysis are carried out. These are widely used in science, engineering and many other areas such as bioinformatics, genomic mapping, computer vision, finance and economics, and in social science. HMMs require much smaller training sets, and that the examination of the inner structure of the model provides often a deeper understanding of the phenomenon. In this survey, we first describe the important algorithms for the HMMs, and provide useful comparisons, aiming at their advantages and shortcomings. We then consider the major g applications, such as annotations, gene alignment and profiling of sequences, DNA structure prediction, and pattern recognition. We also list some analysis on how to use HMM for DNA genomes. Finally, we conclude use and perspectives of HMMs in bioinformatics and provide a critical appraisal for the same. 2016 IEEE. -
High Gain Miniature Antenna Arrays for 2.4 GHz Applications
In this paper, miniature corporate feed Four Element Array (FEA), Eight Element Array (EEA) and Sixteen Element Array (SEA) are presented. The proposed antenna arrays are created on Rogers Duroid 5880 substrate with permittivity 2.2 and thickness of 0.782 mm. Initially, a single element antenna was created, then it was used in a corporate feed network designed for the 4-element array. As an extension, the 4-element array was used as a template and created an 8-element array and 16-element array to achieve high gain and directivity at 2.4 GHz. The proposed FEA, EEA, and SEA exhibit reflection coefficients of -25.55 dB, -37.14 dB, and -30.61 dB respectively. The peak gains obtained are 11.5 dB, 13.67 dB, and 16.76 dB respectively for FEA, EEA, and SEA. Also, the directivity has improved corresponding to the increase in the number of elements. Therefore, it can be a suitable candidate for applicationswhere extended range and coverage with better signal quality and higher data transfer rates is a priority. 2024 IEEE. -
High-Speed Parity Number Detection Algorithm inRNS Based onAkushsky Core Function
The Residue Number System is widely used in cryptography, digital signal processing, image processing systems and other areas where high-performance computation is required. One of the computationally expensive operations in the Residue Number System is the parity detection of a number. This paper presents a high-speed algorithm for parity detection of numbers in Residue Number System based on Akushsky core function. The proposed approach for parity detection reduces the average time by 20.39% compared to the algorithm based on the Chinese Remainder Theorem. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Hotel Recommendation System Based on Customer's Reviews Content Based Filtering Approach
Recommendation systems are fantastic tools for remembering people's ideas in order to gain knowledge more efficiently and selectively. Recently, booking and searching for hotels online has become more common. As it takes more time, online hotel research is growing more quickly. In addition, the amount of knowledge accessible online is continuously expanding. User preferences have a big impact on hotel recommendations. The most effective recommendations may be made by recommendation systems by utilising historical user preference data. To solve this problem, recommender systems have suggested content-based filtering methods. Product recommendations, recommendations for websites, news articles, restaurants, and TV series are all examples of applications for content-based recommender systems. The dataset for this project includes client evaluations of the offered Kaggle profile. Word embedding, word2vec, and TF-IDF natural language processing methods were used for feature extraction. The algorithm shows the user the top 10 suggested hotels based on the user's past knowledge of the hotel's location. 2022 IEEE. -
How AI and other Emerging Technologies are Disrupting Traditional HR Practices
With technology running and changing this whole generation and the way it works, this dynamic leads to changes in the conventional ways of Human resource management (HRM). The environment of HRM has shifted from traditional to modern with the use of various automation tools with the help of digital transformations that include Artificial intelligence (AI) in employee management, multiple software to track the applications, payroll, performance management systems. These have caused a drastic change in the basic traditional operations in human resource management. This paper is a study about how AI and various other emerging technologies have a significant effect on the workplace, the employees, and their mindset on the dynamic digital environmental transformation. 2024 IEEE. -
How much can we trust high-resolution spectroscopic stellar chemical abundances?
To study stellar populations, it is common to combine chemical abundances from different spectroscopic surveys/studies where different setups were used. These inhomogeneities can lead us to inaccurate scientific conclusions. In this work, we studied one aspect of the problem: When deriving chemical abundances from high-resolution stellar spectra, what differences originate from the use of different radiative transfer codes? 2016 Proceedings of the 12th Scientific Meeting of the Spanish Astronomical Society - Highlights of Spanish Astrophysics IX, SEA 2016. All rights reserved. -
HULA: Dynamic and Scalable Load Balancing Mechanism for Data Plane of SDN
Multi-rooted topologies are used in large-scale networks to provide greater bisectional bandwidth. These topologies efficiently use a higher degree of multipathing, probing, and link utilization. An end-to-end load balancing strategy is required to use the bisection bandwidth effectively. HULA (Hop-by-hop Utilization-aware Load balancing Architecture) monitors congestion to determine the best path to the destination but, needs to be evaluated in terms of scalability. The authors of this paper through artifact research methodologies, stretch the scalability up to 1000 nodes and further evaluate the performance of HULA on software defined network platform over ONOS controller. A detailed investigation on HULA algorithm is analysed and compared with four proficient large-scale load balancing mechanisms including: connection hash, weighted round-robin, Data Plane Devlopment Kit (DPDK) technique, and a Stateless Application-Aware Load-Balancer (SHELL). 2023 IEEE. -
Human activity recognition using wearable sensors
The advancement of the internet coined a new era for inventions. Internet of Things (IoT) is one such example. IoT is being applied in all sectors such as healthcare, automobile, retail industry etc. Out of these, Human Activity Recognition (HAR) has taken much attention in IoT applications. The prediction of human activity efficiently adds multiple advantages in many fields. This research paper proposes a HAR system using the wearable sensor. The performance of this system is analyzed using four publicly available datasets that are collected in a real-time environment. Five machine learning algorithms namely Decision tree (DT), Random Forest (RF), Logistics Regression (LR), K-Nearest Neighbor (kNN), and Support Vector Machine (SVM) are compared in terms of recognition of human activities. Out of this SVM responded well on all four datasets with the accuracy of 77%, 99%, 98%, and 99% respectively. With the support of four datasets, the obtained results proved that the performance of the proposed method is better for human activity recognition. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021. -
Human Body Pose Estimation and Applications
Human Pose Estimation is one of the challenging yet broadly researched areas. Pose estimation is required in applications that include human activity detection, fall detection, motion capture in AR/VR, etc. Nevertheless, images and videos are required for every application that captures images using a standard RGB camera, without any external devices. This paper presents a real-time approach for sign language detection and recognition in videos using the Holistic pose estimation method of MediaPipe. This Holistic framework detects the movements of multiple modalities-facial expression, hand gesture and body pose, which is the best for the sign language recognition model. The experiment conducted includes five different signers, signing ten distinct words in a natural background. Two signs, 'blank' and 'sad, ' were best recognized by the model. 2021 IEEE. -
Human heart disease prediction system using data mining techniques
Nowadays, health disease are increasing day by day due to life style, hereditary. Especially, heart disease has become more common these days, i.e. life of people is at risk. Each individual has different values for Blood pressure, cholesterol and pulse rate. But according to medically proven results the normal values of Blood pressure is 120/90, cholesterol is and pulse rate is 72. This paper gives the survey about different classification techniques used for predicting the risk level of each person based on age, gender, Blood pressure, cholesterol, pulse rate. The patient risk level is classified using datamining classification techniques such as Nae Bayes, KNN, Decision Tree Algorithm, Neural Network. etc., Accuracy of the risk level is high when using more number of attributes. 2016 IEEE. -
Human Resource Management in the Power Industry Using Fuzzy Data Mining Algorithm
Currently, database and information technology's frontier study area is data mining. It is acknowledged as one of the essential technologies with the greatest potential. Numerous technologies with a comparatively high level of technical substance are used in data mining, including artificial intelligence, neural networks, fuzzy theory, and mathematical statistics. The realization is challenging as well. Job satisfaction is one of several factors that cause employees to leave or switch jobs, and it is also closely tied to the organization's human resource management (HRM) procedures. It is continuously difficult and at times beyond the HR office's control to keep their profoundly qualified and talented specialists, yet data mining can assume a part in recognizing those labourers who are probably going to leave an association, permitting the HR division to plan a mediation methodology or search for options. We have analysed the major thoughts, techniques, and calculations of affiliation rule mining innovation in this article. They effectively finished affiliation broadcasting, acknowledged perception, and eventually revealed valuable data when they were coordinated into the human resource management arrangement of schools and colleges. 2023 IEEE. -
Human-Computer Interaction: Innovations and Challenges in Virtual Reality
In an effort to shed light on the advances and difficulties that are shaping the area of Virtual Reality (VR), this research paper digs into the ever-evolving world of Human-Computer Interaction (HCI) within the context of VR. We have found important insights with theoretical and practical applications via a careful research technique comprising mathematical modelling, data collecting, and empirical analysis. Through our investigation of new technologies, we have shown the revolutionary potential of haptic feedback systems in VR settings. Our results, backed by a solid mathematical model, provide light on the measurable effect of haptic feedback and suggest it has the potential to radically alter user experiences in fields as diverse as gaming, instruction, and treatment. At the same time, we have overcome a number of obstacles inherent to virtual reality human-computer interaction, including motion sickness. Our mathematical model of motion sickness and its treatment lays the groundwork for creating VR experiences that are both enjoyable and safe for a wider range of users. This study highlights the ethical implications of VR HCI, highlighting the importance of responsible development and deployment in addition to advances and problems. To make sure that the advantages of this gamechanging technology are used in a responsible manner, we discuss issues like privacy, informed consent, and the possibility for addiction in VR. Our results, as we reach the end of our trip, are both a celebration of potential and a guide for where VR HCI is headed. They motivate more research into inclusive and human-centered design, personalized motion sickness prevention, and cutting-edge haptic feedback technologies. To further lead the development of VR HCI, we advocate for continuous multidisciplinary cooperation and the adoption of thorough ethical rules and regulations. 2024 IEEE.