International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Architectural Framework for Scalable On-Demand Service Aid Platform
Get PDFThis innovative web-based platform designed to connect skilled workers with service seekers, addressing challenges such as accessibility, affordability, and trustworthiness in the skilled labor market. The platform provides a seamless experience for users, enabling them to post job requirements, browse available professionals, and hire based on specific needs, all within an intuitive interface. Built with modern technologies, the platform\u27s front end is developed using HTML, CSS, JavaScript, and Bootstrap, ensuring responsiveness and ease of use. The back end, powered by Java with Spring Boot and integrated with a robust MySQL database, ensures efficient data management and secure user interactions. The platform’s architecture facilitates smooth navigation and quick access to essential features. Service seekers can easily sign up and explore a pool of skilled workers categorized by their expertise, location, and ratings. The system includes a user feedback mechanism that enhances trust by allowing users to rate and review workers based on their experiences. Workers, in turn, benefit from consistent job opportunities and the ability to showcase their skills to a wider audience. This project also addresses the unique challenges of underserved regions, such as Hyderabad, where digital platforms for hiring local services are scarce. By providing a comprehensive solution that caters to diverse household needs, from plumbing to carpentry, the platform bridges the gap between demand and supply in the skilled labor market. The research stands out as a transformative tool, creating economic opportunities for skilled workers while offering service seekers a reliable and efficient solution for their everyday needs. It fosters a sense of empowerment and convenience, making it a vital contribution to the digital transformation of the Labor market
Generative AI Ethical Challenges: By Creative and Professional Communities
Get PDFThis Paper investigates the ethical transformations and creative dilemmas emerging from the widespread adoption of generative artificial intelligence (GenAI) in content creation. The study examines attitudes regarding authorship, ethical issues, and regulatory rules by conducting interviews with 120 GenAI users from academic, creative, and professional fields. Results show that most participants prefer to give credit to co-authors or themselves when using GenAI and only a small percentage want the AI to have sole authorship. Concerns over ethics are moderate and almost always present, reaching their highest-level concerning liability (3.12), then labeling (3.00), and then bias (2.98) on a 5-point scale. Although individuals frequently used GenAI tools, there was no clear link between the amount of GenAI they used and their sensitivity to ethics. People working in creative fields were more likely than technologists to back stronger government oversight. Users notice GenAI’s ability to generate fresh ideas, though they also have doubts about its accountability, the roles it plays in knowledge, and its ability to replace human creativity. It ends by urging the development of strategies and education focused on ethical principles, ensuring that technology serves society
Advancing Diagnosis Capabilities with Smart AI Techniques for Early Symptoms Prediction of Brain Stroke
Get PDFThe brain, a vital organ in the human body, can suffer severe damage during a Brain Stroke (BS) due to blocked blood vessels. The interruption in blood flow and nutrient supply leads to significant symptoms and is considered a medical emergency. BS often results in long-term neurological impairments, complications, or even death, underscoring its critical nature. The World Health Organization (WHO) estimates that BS is the most prevalent cause of disability and death globally. Failure to detect a stroke early may result in delayed treatment, leading to severe complications such as lifelong neurological impairment or death. Early identification with Machine Learning (ML) and Deep Learning (DL) approaches can improve the treatment of patients and reduce the long-term impacts of stroke. The purpose of this research is to predict the signs of a stroke taking place at an early stage employing ML and DL models. To evaluate the efficiency of the approach, a comprehensive training set for BS recognition was collected from a well-known source, Kaggle. The training dataset contains eleven attributes, including age, gender, hypertension, etc., with 5110 records. Multiple classification models, like Support Vector Machine (SVM), Gradient Boosting (XG Boost), Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), K Nearest Neighbors (KNNs), and Artificial Neural Network (ANN), were efficiently employed in this study for the identification of initial signs of BS. The suggested ANN has a recognition accuracy of 94.35%, whereas RF has an identification rate of 94.15%. Both have about identical forecast accuracy for BS. The findings of the study revealed that ML and DL approaches have the potential to improve the identification of a variety of illnesses, such as BS, hence reducing the load and subjectivity issues in the medical field that existed owing to earlier traditional methods
Addressing Class Imbalance in Credit Card Fraud Detection: A Hybrid Deep Learning Approach
Get PDFThe rise of credit card fraud is a global concern, demanding reliable detection methods that can overcome challenges with imbalanced datasets and limited exploration of hybrid modeling approaches. This study introduces a hybrid deep learning architecture combining Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) layers alongside SMOTE-TOMEK preprocessing to address imbalanced data issues in credit card fraud detection. The research analyzes a substantial dataset containing both legitimate and fraudulent transactions, evaluating the performance of GRU, LSTM, and the novel Hybrid model through comprehensive data exploration, preprocessing, and feature selection. Performance evaluation uses metrics including accuracy, precision, recall, F1 Score, AUROC, and AUPRC. The experimental results demonstrate the effectiveness of deep learning architectures, with AUROC values of 0.974551 for LSTM, 0.958174 for GRU, and 0.976205 for the Hybrid model. The Hybrid model showed particularly promising results with a precision of 0.9121 and AUPRC of 0.886068, outperforming the individual models. These findings indicate that combining complementary deep learning architectures enhances fraud detection by leveraging their respective strengths in capturing both long-term dependencies and transaction patterns. These insights offer valuable guidance to financial institutions in implementing effective fraud detection systems while emphasizing the importance of continuous improvement of deep learning algorithms to address evolving cyber threats
Impact of Different Feature Engineering Techniques for Better Classification of Diverse Crops with Sentinel-2 Imagery
Get PDFObserving a large area of Earth\u27s surface using remote sensing has made our work very easy in order to monitor changes. This revolutionary tech can help us make big decisions on time. For this purpose, Sentinel-2 imagery is considered to be perfect since the imagery provided by this satellite is easily available https://scihub.copernicus.eu/ website. The European Space Agency (ESA) and the European Union (EU) have created the Copernicus Program, which includes the Sentinel-2 satellites that use onboard multispectral scanners to effectively monitor the Earth’s surface. This program has contributed significantly to the production of Sentinel-2 multispectral products, which provide high-resolution satellite data for monitoring land cover and use. The Sentinel-2 constellation is the second set of satellites in the ESA Sentinel missions, with the primary goal of land cover/use monitoring. Besides the availability of imagery, Sentinel-2 temporal resolution is 5 days, which helps in quick observation. In this manuscript, we have used different feature engineering techniques on our dataset in order to observe their performance and importance for better classification of diverse crops. We have achieved an overall accuracy of 99% after extracting important information from the dataset and applying a random forest and a gradient boosting classifier. The data set used for this research work was collected by surveying diverse crops in the region of Harichand, which is located North-South of Charsada District in Khyber-Pakhtunkhwa, Pakistan. The detailed Explanation of our Work and proposed methods is discussed in this article
Modeling and Implementation of a Density-Based Traffic Management System via Programmable Logic Controller
Get PDFTraditional traffic signal systems face challenges in efficiently managing traffic when a large number of vehicles move to different lanes. To address this issue, a programmable logic controller (PLC) has been applied Density-Based Smart Traffic Control system using PLC (Programmable logic controller). This work develops a smart traffic control system to keep an eye on the vehicle density at a 4-way junction. Using specific functions, calculations, and logical operations, the system program calculates the traffic density in each lane and transmits data to make automatic decisions regarding traffic signal priorities. The proposed system ensures that the traffic control system adjusts to real-time traffic conditions on the road. By utilizing a PLC (programmable logic controller), all sensors continuously check the position of each lane and perform logical operations. These operations control lanes that require immediate attention and service. Next, the system program is executed to generate output signals to control the traffic lights on the poles, facilitating the switching of red, yellow, or green lights. The duration of the green light, which indicates the ON time for each lane of the intersection, is dynamically adjusted based on the priorities calculated by the system. In summary, the execution of the density-based smart traffic control system with a programmable logic controller enables a more responsive and adaptive approach to traffic management, proficiently allocating priority based on real-time traffic situations at the intersection. This study addresses the challenges of traffic flow with improved safety and reduced congestion at busy junctions
Predictive Modeling of Hospital Waste Generation Using Machine Learning Based on Patient Inflow
Get PDFEffective hospital waste management is a key to the security of the environment and provision of healthcare hygiene. This paper develops a predictive analytics model to forecast the amount of daily hospital waste generated based on patient inflow using a linear regression model. Real-time data from 60 days were gathered in a tertiary healthcare institution, which informed the number of patients and the resultant waste in kilograms. The model obtained the R value of 0.88 in the training and 0.81 in the validation datasets and a Root Mean Square Error (RMSE) of 130.52 kg. The predictor of patient volume was established as significant through statistical validation via ANOVA, and the model was found to be within the key regression assumptions through the residual analysis. The findings emphasize that predictive modeling within a hospital waste planning system is viable, and a cost-efficient and explainable option can be used in operational forecasting. The offered method contributes to enhanced resource distribution, risk aversion, and adherence to the sustainable healthcare objectives
Deep Learning Based Sentiment Analysis on Instagram Insights of Consumer Behavior for Improving Business Decision Making
Get PDFThe increasing use of social media platforms such as Instagram has made them a significant source of consumer insights for businesses, highlighting the importance of automated sentiment analysis. This study aims to address the challenge of accurately classifying consumer sentiments in Instagram posts, where informal language, slang, and sarcasm often reduce the effectiveness of traditional models. To overcome this gap, two deep learning approaches were employed: a Bidirectional Long Short-Term Memory (BiLSTM) network as a classical recurrent baseline and transformer-based architectures (BERT and DistilBERT) as state-of-the-art models. A dataset of 184,010 Instagram posts was preprocessed, tokenized, and mapped into positive and negative sentiments, and the models were trained and evaluated using accuracy, precision, recall, F1-score, ROC-AUC, and confusion matrices. The results demonstrated that BERT achieved the highest performance with an accuracy of 0.91 and an F1-score of 0.91, outperforming BiLSTM (accuracy 0.87, F1-score 0.86), while DistilBERT provided a competitive balance between accuracy (0.89) and efficiency. These findings confirm that transformer-based models, particularly BERT, are better suited for capturing nuanced sentiments in social media text. The study concludes that models can provide actionable insights into consumer behavior, enabling businesses to enhance brand monitoring and customer engagement
Python and GLO-DEM Pixel-Based Hypsometry in Upper Indus Basin
Get PDFNorthern Pakistan’s Hunza and Shyok headwaters, where the Karakoram, Himalaya, and Hindukush ranges converge, host some of the largest mid-latitude valley glaciers outside the polar regions and play a decisive role in runoff and hazards of the Upper Indus Basin. Hypsometry provides a rapid, terrain-based approach to assess basin condition in such high mountain settings. In this study, a 30 m digital elevation model was used to delineate 31 sub-catchments, and for each unit, the hypsometric curve and hypsometric integral (HI) were derived. Methods were kept consistent across scales, with HI also recalculated on 1-4 km grid tiles, and spatial organisation tested through Global Moran’s I and the Getis-Ord Gi* statistic. Results reveal coherent belts of high HI aligned with the Main Karakoram Thrust, the Main Mantle Thrust, and the Karakoram Fault, indicating actively rising terrain and focused incision. Lower HI corridors occur in wider valley floors and recent fills, reflecting more mature landscapes and enhanced storage. HI distributions remain stable across tile sizes with mean values below one-half, while significant clustering confirms that these belts are intrinsic terrain signals. Harder crystalline and intrusive lithologies show higher HI on average, though wide variance suggests the combined influence of structure, rock strength, and relief. These geomorphic patterns carry direct hydrological meaning: high-HI belts imply fast translation of snow and ice melt with sharper seasonal peaks, whereas low-HI corridors favour storage and delay. Hypsometry, therefore, offers a cost-effective and reproducible tool for identifying active belts and providing priors for hydrological modelling and hazard planning in the Upper Indus Basin
Remote Sensing and Machine Learning-Driven Flood Inundation Mapping of September 2025 Ravi Watershed Using Sentinel-1 SAR
Get PDFFloods is among the most devastating natural hazards in South Asia. The September 2025 flood in the Ravi Basin was triggered by heavy monsoon rainfall and the release of water from cross-border dams. This study utilized Sentinel-1 SAR data, including both ascending and descending passes in VH polarization, to map flood inundation across the basin using a Random Forest classifier. Pre-flood and post-flood composites were prepared for April-May and 27 August to 5 September, respectively. The predictors feature includes VH_pre, VH_post, VH_diff, and VH_ratio. Terrain correction using the NASA DEM and landcover filtering with ESA WorldCover at 10m improved classification accuracy. Results showed that 1,885 km² of land was inundated, representing 5% of the total basin area. Approximately 260 settlements were impacted, including Dera Baba Nanak, Kartarpur, and the low-lying regions of Lahore. Croplands were the most affected class, with 1,610 km² flooded, followed by grasslands (90 km²) and sparse vegetation (62 km²). Built-up areas accounted for 0.7 km² of inundation, though the socio-economic impact was disproportionately high. Precipitation analysis from NOAA CPC confirmed rainfall clustering in the Sialkot and Narowal corridor. The peaks exceeding 800 mm/day cause this region as the epicenter of the flood. News reports corroborated satellite findings, noting that over 2.5 million displaced and more than 100 lives were lost. The study highlights how tributary floods involving the Ravi, Sutlej, and Chenab are emerging as severe hazards for Punjab. Findings underline the need for improved monitoring, resilient agricultural strategies, and disaster preparedness to mitigate future economic and food security risks