International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Enhancing Skin Cancer Detection: A Study on Feature Selection Methods for Image Classification
Full text linkVisually comparable images can be easily recognized by the human eye, but specialist knowledge is needed to correctly describe medical images, such as those showing skin afflicted by cancer. As skin cancer is becoming more commonplace worldwide, there is a growing need for qualified specialists to help with its diagnosis. Several intricate genetic abnormalities lead to cancer, one of the most serious illnesses. Skin cancer is the most frequently diagnosed type of cancer. The present research examines two main methods: segmentation and feature extraction, since early identification is essential to enhancing treatment results. Our research focuses on identifying malignant melanoma, which is caused by an overabundance of melanocytes in the dermis layer of the skin. We used the well-known dermatological approach known as asymmetry, border, color, and differential (ABCD) dermoscopy to aid in early identification. Asymmetry (differences in shape and structure), border irregularity (uneven or jagged borders), color variation (differing pigmentation inside the lesion), and differential structure (development in size and appearance over time) are the criteria used in this technique to analyze skin lesions. CNN-based deep learning models are used for image pre-processing, segmentation, feature extraction, and classification in the organized process of the suggested framework. Additionally, sophisticated digital image processing methods like size estimates, color identification, border analysis, and symmetry detection are included. By using CNNs to collect texture-based information, feature extraction is improved and skin lesions can be precisely categorized. We suggest using a Backpropagation Neural Network (BPNN) to increase classification accuracy and make efficient decisions when distinguishing between benign and malignant skin diseases. To overcome this difficulty, machine learning classifiers have surfaced as a viable way to automate the classification of images for skin cancer. In this paper, deep convolutional neural networks (CNNs) are used to construct a predictive model for skin cancer diagnosis. Using the HAM10000 dataset, the suggested method produced a 92% accuracy rate
Securing Cloud Data: An Approach for Cloud Computing Data Categorization Based on Machine Learning
Full text linkIntroduction/Importance of Study: A novel innovative technique known methodical approach is referring as cloud computing (CC), which allows users to store data on remote servers that are accessible through the internet. This method makes it simple to move and retrieve vital and personal data storage. As a result, the demand for it is rising daily. This can be used to store a variety of data, including multimedia content, paperwork-based files, and financial transactions. Furthermore, by lowering operating and maintenance expenses, CC lessens the reliance of the services on local storage.
Novelty statement: Current systems apply only one key size with which all data is encrypted without concerning the level of privacy of the data. This results in higher processing costs and longer processing times. Furthermore, none of these methods improves secrecy and only achieves a low accuracy rate in data classification.
Material and Method: This study presents a cloud computing strategy for data sensitivity that is based on automated data classification. The model suggested in this study utilizes Random Forest (RF), Naïve Bayes (NB), k-nearest neighbor (KNN), and support vector machine (SVM) classifiers to achieve automated feature extraction. This methodology is designed to operate effectively across three sensitivity levels: basic, confidential, and highly confidential.
Results and Discussion: The experiments were performed on the Reuters-21578 dataset, which consists of 21,578 documents. The simulation results demonstrated that the three proposed models achieved accuracy rates of 97%, 96%, and 95%, respectively. These findings indicate that SVM, RF, and KNN outperform NB in classification performance.
Concluding Remarks: Additionally, the suggested study offers helpful recommendations for researchers and cloud service providers (like Dropbox and Google Drive)
Silver Nanoparticles Synthesis by Serratia Marcescens W2 Strain, Its Biocontrol Efficacy Against Fungal Phytopathogens, And Its Effect on Wheat Seeds
Full text linkDue to its cost-effectiveness and eco-friendliness, the production of silver nanoparticles (AgNPs) utilizing biological agents has attracted a lot of attention. In this study, we investigate the potential of the Serratia marcescens W2 strain as a bio-factory for the production of silver nanoparticles and evaluate the biocontrol capability of this strain against fungal phytopathogens as well as its impact on wheat seeds. Using the extracellular enzymes and metabolites produced by Serratia marcescens W2, AgNPs were biosynthesised. The size, form, and composition of the AgNPs were determined using a variety of analytical techniques, such as X-ray diffraction (XRD), and scanning electron microscopy (SEM). AgNPs\u27 impressive ability to inhibit fungal growth in vitro experiments demonstrates their robust biocontrol capabilities. Microscopic and biochemical investigations helped to better clarify the AgNPs\u27 mode of action against these phytopathogens. Additionally, investigations on seed germination and seedling growth were used to evaluate the effect of the AgNPs on wheat seeds. As a result of the application of AgNPs, seed germination rates, and seedling vigor dramatically increased, according to the findings. Additionally, compared to the control group, the seedlings treated with AgNPs showed enhanced resistance to fungal infection. Overall, the results of this study demonstrate the potential of Serratia marcescens W2 strain in the green synthesis of AgNPs with improved antifungal activities. Furthermore, the use of these AgNPs promotes the germination and growth of wheat seedlings, indicating their potential use as a biocontrol agent and seed treatment to safeguard crops against fungus phytopathogens in sustainable agriculture. To completely understand the underlying mechanisms and determine the long-term impacts of AgNPs on the ecosystem and human health, more research is necessary
Comparative Study of Food Image Classification Performance Using the Xception Architecture
Full text linkFood allergies remain a critical issue that needs more research. To identify and manage food allergies, the integration of complex computational approaches is becoming more and more important, opening the door to more individualized and efficient food safety solutions. Which aims to end hunger, achieve food security, improve nutrition, and promote sustainable agriculture. This research investigates the application of image classification techniques for allergen detection in food images. Specifically, we compare two models Model 1 serves as the baseline, trained on 11 classes. Two variations were explored: Model 2 focuses on Pakistani dishes, to investigate the impact of learning rate on the balance between adaptation speed and model precision. The objective is to determine the most effective model for classifying food images therefore Model 2 achieves the highest accuracy of 94%. These findings suggest that Model 2 is a promising candidate for real-world allergen detection applications. Future research will focus on creating a comprehensive new dataset of food images encompassing a wider variety of food items, as well as exploring the integration of a model similar to model 2 into mobile applications for consumer use
Comparative Performance of Deep Learning Approaches for Sentiment Analysis on Pakistani Dramas and Movies Reviews
Full text linkSentiment analysis plays an important role in natural language processing, helping to understand public opinions shared through text. This study focuses on the challenge of analyzing sentiments in reviews of Pakistani dramas and movies, where mixed languages, informal expressions, and noisy data make accurate classification difficult. To solve this problem, several deep learning models were used and tested, including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional LSTM (Bi-LSTM), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN). A detailed dataset of 12,000 user reviews was collected from platforms like IMDb and YouTube. The data was cleaned and prepared through steps such as tokenization, removing unnecessary columns, normalizing, and using sentiment scoring and word embedding for feature extraction. These models were trained and tested, with their performance evaluated using accuracy, precision, recall, and F1-score. Among all, the CNN model performed the best, achieving 98.71% accuracy and a 98.49% F1-score. The Bi-LSTM model was close behind, with 98.59% accuracy and a 98.47% F1-score. In the future, the research will explore the use of advanced transformer-based models like BERT and GPT for multilingual sentiment analysis. It will also aim to build real-time sentiment classification systems. Moreover, creating sentiment lexicons for regional languages and using hybrid deep learning methods are suggested to further improve accuracy and generalization
AI Vision for Health Care: Virtual Keyboard and Mouse Empowering Partially Disabled Patients
Full text linkThis paper introduces a machine-learning-based virtual keyboard and mouse system designed to assist individuals with physical disabilities. The system recognizes hand gestures using computer vision techniques and translates them into keyboard inputs and mouse controls. By utilizing Convolutional Neural Networks (CNNs) and the YOLOv8 model, the system achieves real-time performance with an average accuracy of 92%, enabling touchless interaction with computers. The solution uses widely available hardware like standard webcams, making it accessible, affordable, and easy to deploy. This system improves the usability of computing devices for people with motor impairments, offering an innovative, touchless alternative to traditional input methods. It also supports essential tasks such as scrolling, clicking, and zooming through simple gestures. The framework is adaptable to various environments, ensuring it is easy to use in different settings. Our system offers a complete virtual keyboard and mouse solution using a common webcam and real-time gesture recognition, making computer use easier and more affordable for users with motor impairment
Optimal Coordination of Directional Overcurrent Relays in Interconnected Networks Using an Improved Multi-Strategy Coati Optimization Algorithm
Full text linkThe proper coordination of directional overcurrent relays (DOCRs) in interconnected power systems is essential for selective and time-efficient protection. This study introduces a Tuned Non-inertial T-distribution based Weighted Coati Optimization Algorithm (TNTWCOA) to solve the challenging, highly constrained DOCR coordination problem. The proposed method optimizes time dial settings (TDS) and plug settings (PS) to minimize relay operating times while maintaining selectivity. Coordination is critical for both primary and backup protection devices to prevent fault currents from rising to dangerously high levels too quickly. TNTWCOA uses a chaotic sequence mechanism for better population initialization, a nonlinear inertia weight to balance exploration and exploitation, an adaptive T-distribution strategy to increase diversity and avoid local optima, and an alert update mechanism to improve search adaptability. The algorithm was tested on IEEE 3-bus and 15-bus networks, considering both mid and near-end faults with a normal inverse relay characteristic. A comparative analysis with other advanced metaheuristics shows that TNTWCOA outperforms classical and recent optimization methods by reducing total relay operation time. The results confirm that TNTWCOA helps prevent premature convergence and boosts search efficiency, making it a highly effective solution for DOCR coordination in modern power systems
AmpliStride: From Signal to Stride a Breakthrough for Leg Paralysis Rehabilitation
Full text linkFoot drop is a condition in which a patient fails to lift a foot due to neuro-muscular disorder of the lower body. Many assistive devices are available, but they have some limitations. For this purpose, we offer a solution: Muscle Signal Amplification and Transmission System (MSATS). The system picks muscle signal from the healthy leg and after necessary processing and amplification transmits it to the muscle stimulator worn on the affected leg. The system stimulates the muscle with proper timing according to the gait cycle. This project aims to improve the quality of life of those afflicted with foot-drop by assisting their mobility and independence. 
University Auto-Gate Management through AI-Driven License Plate Recognition
Full text linkThe rapid growth in the number of vehicles and transportation systems has made Automatic Number Plate Recognition (ANPR) an essential tool for modern traffic management and security. With the rising vehicle count, manual monitoring and control of traffic have become increasingly difficult. ANPR, a complex field within computer vision, faces challenges due to variations in license plate styles, sizes, orientations, and lighting conditions. License plate recognition, leveraging advanced image processing techniques, represents a promising research domain, especially in the context of IoT and smart city development. With the exponential rise in the number of vehicles, automated systems are essential for retaining vehicle information for various purposes. Researchers are increasingly focused on developing reliable ANPR systems, spurred by advancements in portable electronics and machine learning techniques. Although numerous ANPR approaches have been documented for surveillance systems and intelligent transportation applications, creating a robust system remains a challenging research problem. This research aims to investigate the utilization of ANPR for managing vehicle access at the entrance gates or parking areas of private or government universities and colleges. The system aims to maintain a record of vehicles entering and exiting the premises, as the performance of existing techniques depends on various factors and local conditions. The study introduces an AI-powered ANPR system that restricts access to authorized vehicles by capturing and identifying license plates. This technology can be used to track vehicle entry and exit at university campus gates, improving traffic regulation and security during peak hours
Fingerprint Based Smart Digital Life Certificate Using Mobile Technology
Full text linkA pension plan is a savings solution for pensioners that plays a vital role in pensioner’s life after retirement. Different pension disbursing systems have been implemented which aim to support individual pensioners after retirement. This study highlights several critical issues of pensioners. Most of the pensioners are of old age, and it is difficult for them to move physically towards the concerned authority for life authentication in a periodic manner. This study proposes a model for pension disbursing based on the fingerprint scanner enabled smartphone. The proposed model is designed for pensioner’s bi-annual authentication and issuance of Digital Life Certificate (DLC) ubiquitously. The proposed model eliminates the physical presence and travelling expenses. The Hammer and Champy methodology are utilized to construct the model while the Delphi method is used for evaluating the proposed model. This study involves quantitative research to investigate the behavioural intention to accept fingerprint scanner enabled smartphone for the pension receiving process. The data was analysed by applying the goodness-of-fit Chi-square test to inspect the efficiency and impact of the adoption of mobile-based biometric fingerprint system (MBFPS) for the pension disbursing system