International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Enhancing Management Strategies: Machine Learning and Creative Performance Insights in Employee Attrition Analysis and Prediction
Get PDFEmployee attrition and excessive turnover are major difficulties in today\u27s competitive employment market, affecting many industries. To overcome these difficulties, firms are increasingly relying on artificial intelligence (AI) to forecast staff loss and devise effective retention strategies. This study investigates famous machine learning (ML) models to forecast employee turnover and deliver data-driven solutions. The first section of the study compares various ML models on an imbalanced dataset. The second section introduces the Synthetic Minority Oversampling Technique (SMOTE) for data oversampling and applies ML models to the enlarged dataset. ML can predict employee turnover by examining historical data, employee behavior, and external factors. This early detection enables organizations to respond proactively with targeted retention strategies. The study concludes that the Random Forest model is the best model when combined with SMOTE, achieving performance scores of 0.96 out of 1
Effects of Filters in Retinal Disease Detection on Optical Coherence Tomography (OCT) Images Using Machine Learning Classifiers
Get PDFOptical Coherence Tomography (OCT) is an essential, non-invasive imaging technique for producing high-resolution images of the retina, crucial in diagnosing and monitoring retinal conditions such as DME, CNV, and DRUSEN. Despite its importance, there is a pressing need to enhance the early detection and treatment of these common eye diseases. While deep learning methods have shown higher accuracy in classifying OCT images, the potential for machine learning approaches, particularly in terms of data size and computational efficiency, remains underexplored. This study generates models for detecting retinal disease on a publicly available dataset of retinal OCT images using machine learning classifiers with the help of image feature extractions. It classifies the given retinal OCT images as DME, CNV, DRUSEN, and NORMAL. Firstly, it extracts image features using appropriate methods and then it is trained, after training it passes through machine learning classifiers to classify the given input images, and then it is tested to get a better accuracy performance. The above steps are iterated by varying over the pre-processing techniques in which we first resize the image into 100 x 100 after resizing, we remove the noise by using Gaussian Blur and then normalize the image. We systematically benchmark its performance against established built-in methods, such as HOG, LBP, and FOSF. This comparative analysis serves to assess the efficacy of finding the best approach in relation to these widely recognized methods. The proposed experiments based on these approaches reveal that the use of HOG on this dataset outperforms with SVM classifier with a maximum accuracy of 78.8%
AlzheimerNet-V3: Automated Deep Learning Approach for Detecting Alzheimer\u27s Disease
Get PDFIntroduction/Importance of Study:
Alzheimer’s Disease (AD) stands as the highly prevalent form of dementia, culminating in a progressive neurological brain disorder characterized by deteriorating memory function and impaired daily activities due to brain cell damage. This singular ailment is both unique and fatal, underscoring the critical importance of early detection worldwide. Timely identification holds promise in preemptively addressing the future challenges faced by numerous individuals.
Novelty statement:
By scrutinizing the disease\u27s ramifications via MRI imagery, Artificial Intelligence (AI) technology emerges as a valuable ally in categorizing AD patients, thus aiding in prognosticating the onset of this debilitating illness. In recent years, AI from Machine Learning (ML) tactics have proven instrumental in the diagnostic landscape of AD. This study employs a transfer learning methodology to accurately identify Alzheimer\u27s patients using MRI examination. Specifically, we introduce an adapted deep learning model dubbed AlzheimerNet-V3, leveraging a tailored version of the Inception v3 architecture.
Material and Method:
Our investigation encompasses comprehensive experimentation and assesses the efficiency of AlzheimerNet-V3 in collaboration with further pre-trained specimens. Notably, AlzheimerNet-V3 achieves the conclusion of accuracy, the outcome of precision, recall, and development of F1-score was computed as 94.06% for all traits. Furthermore, comparative analysis against contemporary techniques underscores the efficacy of AlzheimerNet-V3 for Alzheimer\u27s detection, highlighting its reliability for real-time implementation
Deep Learning-Based Automated Classroom Slide Extraction
Get PDFAutomated extraction of valuable content from real-time classroom lectures holds significant potential for enhancing educational accessibility and efficiency. However, capturing the spontaneous insights of live lectures often proves challenging due to rapid visual transitions, instructor movement, and diverse learning styles. This paper presents a novel approach that combines the strengths of YOLO and Scale-Invariant Feature Transform (SIFT) techniques to automatically extract slides from live classroom lectures. YOLO, a real-time object detection algorithm, is employed to identify board area, teacher, and other objects within the video stream. While SIFT, a robust feature-based method, was used to accurately merge key points from multiple pictures of the same region. The proposed method involves a multi-stage process: first, YOLO detects the potential place of the teacher, which occluded the board within the video frames. Subsequently, the teacher was removed from the image. The board was divided into multiple segments, to remove and merge redundant content Scale-invariant feature Transform (SIFT) was employed. Experimental results on a diverse dataset of classroom lecture videos demonstrated the effectiveness of the proposed method in extracting slides across different environments, lecture styles, and recording conditions. The potential benefits include improved note-taking, reduced manual effort in content curation, and enhanced accessibility to lecture materials. The presented approach contributes to the broader goal of leveraging computer vision and machine learning techniques to transform traditional classroom settings into modern, interactive, and adaptive learning environments
Meta-Space: Pioneering Education in the Metaverse
Get PDFIn the evolving landscape of learning methodologies, technology has emerged as a catalyst, transforming the educational experience. This study delves into the realm of Virtual Reality (VR) and Augmented Reality (AR), collectively referred to as the "Metaverse," as a pivotal tool in education. By conducting systematic literature reviews, we investigate the potential, effectiveness, and associated pros and cons of employing the Metaverse for learning. Our findings affirm that the Metaverse proves to be a highly effective learning platform, enhancing engagement through lifelike avatars and bridging the gap between the real and virtual worlds. While this innovative approach facilitates visualizing materials and fosters interactive and interesting learning environments, challenges such as the cost of requisite devices remain. Despite limitations, the advantages of integrating the Metaverse into education are evident, necessitating ongoing development to amplify benefits and address existing constraints. This research contributes valuable insights to the ongoing discourse on leveraging Metaverse technologies for enriching educational practices
Comparison of IoT Messaging Protocols: A novel Crop-Specific Protocol for Wheat, Banana, and Chili
Get PDFIoT systems mostly depend on messaging protocols to facilitate the exchange of IoT data, with various protocols or frameworks available to support different types of messaging patterns. Choosing a suitable IoT messaging protocol for a specific application is a significant task. It is crucial to select a protocol that meets criteria such as reliability, lightweight, scalability, extensibility, interoperability, and security. It is crucial to opt for a protocol that meets criteria such as being reliable, lightweight, scalable, extensible, interoperable, and secure. With the increasing prevalence of machine-to-machine communication, numerous standardized communication protocols have emerged for IoT applications. However, performance characteristics of IoT protocols can vary expressively, even when operating under the same conditions. This research paper presents a quantitative comparison of three well-known IoT messaging protocols: MQTT (Message Queuing Telemetry Transport), AMQP (Advance Message Queuing Protocol), and HTTP (Hypertext Transfer Protocol). This research focuses on comparison of existing protocols to latency and throughput. A novel crop-specific protocol is also designed for wheat, Banana, and chili crops
Lightweight Cryptography Algorithms for Internet of Things enabled Networks: A Comparative Study
Get PDFThe rapid advancement of technology has facilitated the interconnection of numerous devices, enabling the collection of vast amounts of data. Consequently, ensuring security within Internet of Things networks has become a top priority. Cryptography is crucial in safeguarding network authentication, confidentiality, data integrity, and access control. In Internet of Things settings, conventional cryptographic protocols frequently prove impractical owing to the limitations confronting Internet of Things devices. Consequently, scholars have suggested multiple lightweight cryptographic algorithms and protocols customized for safeguarding data in Internet of Things networks, aiming to overcome this hurdle. This review article delves into the most recent lightweight cryptographic protocols designed for Internet of Things networks and furnishes a comparative evaluation of prevalent modern block ciphers. The comparative study discusses the most recent lightweight cryptographic algorithms in different evaluation parameters in terms of their performance metrics, cryptographic features and offering in-depth analysis of their efficiency. In the concluding section, the paper discusses necessary adaptations and suggests future research directions
Enhancing Three-Phase Induction Motor Performance with Soft Ramp Control
Get PDFThree-phase induction motors experience high inrush currents during start-up, exceeding their rated capacity and potentially damaging stator windings. This paper explores the implementation of soft ramp control to address this challenge. Soft starters progressively increase the voltage applied to the motor, mitigating the current surge and associated electromagnetic torque. This reduces stress on the motor shaft, and connected equipment even though preventing disruptions in the power supply network. The proposed technique aims to start the motor at a lower speed and gradually climb to its maximum rated speed. This paper employed a gentle ramp control strategy using TRIAC-based voltage regulation. This technique prevents abrupt surges that could harm the motor and related equipment. The study illustrates the soft start process for a three-phase induction motor using a prototype setup and a simulation model. The soft start technique dramatically lowers starting current, mechanical stress, and electromagnetic disturbances, improving motor health and performance, according to experimental data. This method is a cost-effective alternative for industrial applications since it not only increases motor longevity but also lowers the related power losses
Physio-Mechanical and Petrographic Characteristics of Granitic Rocks from the Demote Valley, Gilgit, Pakistan: Implications for Strength and Bearing Capacity
Get PDFThe granitic rocks of the Damote Valley (Juglote Group, Kohistan Batholith) were evaluated for their physio-mechanical and petrographic properties to assess their suitability for construction, particularly as dimension stones. Detailed petrography and tests such as Uniaxial Compressive Strength (UCS), Brazilian Tensile Strength (BTS), Ultrasonic Pulse Velocity (UPV), Schmidt Hammer, Specific Gravity, Porosity, Water Absorption, and Slake Durability were conducted. The granitic rocks, medium to coarse-grained with no preferred orientation, consist mainly of plagioclase (19–35%), quartz (30–43%), and alkali feldspar (40–44%), along with biotite, muscovite, sericite, and minor opaque minerals. Based on geographic location, the granites are divided into three zones: Fulkin granite (Zone 1), Bargin (Zone 2), and Shing (Zone 3). The average Uniaxial Compressive Strength (UCS) values of the granite from the Demote area are 63 MPa for Fulkin granite, 66 MPa for Bargain granite, and 53 MPa for Shing granite, reflecting the granite’s suitability for engineering applications. BTS values range from 7.55 to 12.04 MPa. Schmidt hammer rebound values range from 43 to 47, while specific gravity averages from 2.5 to 2.98. Water absorption is low (0.34–0.60%), and porosity ranges from 1.19% to 1.28%. All results fall within ASTM specifications. The medium-grained granite is stronger and more durable than coarse-grained varieties due to its tighter grain packing and fewer microcracks. Based on these findings, Damote granites are suitable for construction in roads, bridges, constructions, and the dimension stone in the area
Harnessing Language Intelligence: Innovative Approaches to Sustainable Mental Health Interventions in the Digital Age
Get PDFThis study explores the advanced abilities of Natural Language Processing (NLP) methods to revolutionize mental health treatment by understanding how such interventions improve therapeutic outcomes. In doing so, the work of this study is demonstrated as an innovative approach to translating conversational data into actionable insights that bridge a large gap in the detection of subtle emotional cues in mental health assessments. The research used DistilBERT, an optimized version of the BERT framework, which has been fine-tuned on specially selected datasets to accurately identify emotional states such as sadness, joy, anger, and fear. Emotional and linguistic patterns were analyzed to identify often unarticulated signals to identify disorders such as depression, anxiety, and Post-Traumatic Stress Disorder (PTSD) much earlier. In this regard, the model has been found to significantly enhance the understanding of patients\u27 emotional states more accurately and subtly than through traditional means. The findings of this study highlight the potential of offering individualized therapeutic interventions within digital health applications, which enables immediate emotional well-being assessments. The study showcases the flexibility of AI-based systems, making them applicable to almost any environment, including a workplace setting, to promote both wellness and productivity. This study sets the ground for developing scalable, customized, and proactive mental health care strategies that are beyond conventional therapeutic frameworks