International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Deep Learning-based Weapon Detection using Yolov8
Full text linkDeep learning (DL), a subset of machine learning (ML), has demonstrated remarkable success in image recognition and object detection tasks. This study presents a deep learning-based approach for offline weapon detection using the YOLOv8m architecture. A custom YOLO-formatted dataset was developed, comprising over 10,000 annotated images spanning two weapon categories: guns (all types of firearms) and knives (all types). The model achieved a Mean Average Precision ([email protected]) of 0.852. and [email protected]:0.95 of 0.622, with precision and recall scores of 0.89 and 0.80, respectively. The class-wise evaluation revealed strong detection across both weapons, with [email protected] of 0.871 for knives and 0.831 for guns. Despite occasional false positives and class confusion, the system shows promise for offline weapon detection tasks
Developing a Quranic QA System: Bridging Linguistic Gaps in Urdu Translation Using NLP and Transformer Model
Full text linkThe limited access to Quranic knowledge for Urdu speakers is due to inadequate Natural Language Processing (NLP) tools, which hinder precise Quranic understanding and retrieval. This research introduces a Transformer-based Urdu Quranic Question-Answering (QA) system, a novel approach that enhances semantic accuracy and retrieval precision, unlike existing Arabic- and English-based models. This study primarily leverages Transformer-based technology to develop a context-aware Urdu Quranic chatbot, unlike conventional systems, which primarily support Arabic and English Quranic texts. The system addresses the missing linguistic gaps in Quranic QA by enhancing both precision and semantic interpretation for Urdu users. The system was trained using Fateh Muhammad Jalandhari’s Urdu Quranic translation and fine-tuned with Roberta for enhanced semantic text analysis. It integrates TF-IDF with SBERT for improved question-answering performance. The NLP system went through multiple evaluation metrics were used to assess its precision and overall capability. The chatbot achieved high retrieval accuracy with a Mean Average Precision of 0.85, an Exact Match of 0.82, and an F1 Score of 0.88. User satisfaction reached 92%, indicating its effectiveness in providing precise Quranic answers. Future updates will introduce that include voice detection features, expanded language support, and integration with Tafsir and Hadith databases for improved contextual understanding. This study enhances Urdu Quranic information retrieval by providing an improved NLP-based solution for automated Islamic knowledge dissemination
An IoT Distributive SM Controller for Mitigation of Circulating Currents Among Sources in a Standalone DC Microgrid
Full text linkSources of similar or different power ratings are connected in parallel within the DC microgrid. During operation, these sources generate circulating currents along with their normal currents, which disrupt proper current sharing among power electronic converters based on their capacity. Consequently, voltage regulation across the system weakens. Additionally, the resistance of the connecting lines contributes to this imbalance in current distribution. To address circulating currents, droop controllers are commonly used. This method allows converters to share power according to their capacity without requiring internal communication. However, a major drawback of conventional droop control is that as output voltage decreases, the converter\u27s output current increases linearly, leading to significant voltage fluctuations. As a result, droop control inherently involves a trade-off between voltage regulation and current sharing, making it impossible to optimize both simultaneously. To overcome this issue, this paper proposes a sliding mode (SM) controller implemented through an IoT-based distributed architecture. A system model is developed to evaluate its performance, and conditions for stability and existence are analyzed. MATLAB simulations provide detailed experimental results, demonstrating the effectiveness of the proposed technique
Design Of a Photocatalytic Reaction System for Pollutant Degradation: A Computational Study
Full text linkIn this study, Computational Fluid Dynamics (CFD) was used to model and simulate the photocatalytic degradation of methyl orange (MeO) in a stirred photoreactor, particularly in the presence of a bismuth oxide catalyst. This approach not only provides an effective method for treating wastewater by breaking down harmful dye pollutants but also highlights the potential of cost-effective and eco-friendly catalytic materials for environmental cleanup.
In the first phase, the catalyst was evenly distributed in an aqueous MeO solution, where photocatalysis was employed to degrade the pollutant. The structural properties of the catalyst were analyzed using scanning electron microscopy (SEM). Experiments were conducted to examine how different factors, such as pH and pollutant concentration, influenced MeO removal.
In the next step, CFD was used to numerically analyze MeO degradation through photocatalysis. The results showed that the photoreactor effectively broke down MeO. CFD modeling further explained the degradation mechanism, revealing that hydroxyl radicals (OH•) played a key role in the heterogeneous photocatalytic process. Photocatalysis significantly contributed to pollutant breakdown in both experimental and simulated phases.
The CFD models closely matched experimental data, confirming the findings related to fluid dynamics and species concentration. By offering deeper insights into mass transfer and reaction kinetics at a fraction of the cost and time, CFD proved to be more efficient than experimental methods in analyzing MeO degradation
Current-Injected Mode Control for Coupled-Inductor (Ci) Based Boost Converter
Full text linkWith the increasing demand for electrical energy, there is a need to replace conventional energy resources with renewable energy resources. To properly implement renewable resources at a larger scale, DC/DC converters play a major role. Owing to the variable and unreliable nature of renewable energy resources like PV systems there is a requirement for converters that can regulate the voltage at the output side. High-gain DC/DC converters are preferred for the integration of the solar system in smart grids or microgrids. In this context, a high-gain boost converter utilizing a coupled inductor is a preferable choice. High gain is achieved by the proper selection of the turn’s ratio of coupled inductors in such converters. Whereas to obtain voltage regulation there is a need to employ an effective control scheme. In this paper current-injected control topology has been utilized for coupled inductor-based boost converter. The proposed converter with an appropriate control scheme aims to achieve high voltage gain, reduced switching losses, minimization of current ripple, and less conduction losses while increasing the efficiency of the overall system. A small signal model based on the state space averaging technique is used to derive control to output transfer function for the proposed converter. A hardware prototype has been implemented for the validation of theoretical work. The overall efficiency of the converter is calculated to be around 96% at specific load conditions
Thermal Macro-Modeling and Safe Operating Area Analysis of MOSFETs
Full text linkThermal dissipation in electronic circuits is always an important design constraint. Excessive heat can degrade component performance, reduce lifespan, and in severe cases, cause permanent failure. This paper uses the thermal modeling approach at the circuit level and focuses on the Safe Operating Area (SOA) of MOSFETs (Metal-Oxide-Semiconductor Field-Effect Transistors). The SOA defines the operational limits of MOSFETs by considering the power dissipation to prevent thermal runaway and device failure. In the area of power electronics, it is important to ensure the reliability and efficiency of circuits under different thermal conditions. In this paper, the thermal behavior of MOSFETs is modeled considering factors such as ambient temperature, gate capacitance, PCB (printed circuit board) thermal dissipation, and heatsink addition. This research highlights the importance of thermal design principles in predicting the junction and case temperatures of MOSFETs under various operating conditions. This systematic approach to thermal macro-modeling is crucial for optimizing the performance and reliability of electronic circuits, particularly in high-power applications where thermal management is a critical concern
AI-Driven Parking Management: ANPR-Based Entry & Biometric Gate Control
Full text linkThere is now a greater need for effective and safe parking solutions due to the growth in urbanization. To provide an anodyne parking experience, this article introduces an AI-driven parking management system that combines biometric authentication for gate control with Automatic Number Plate Recognition (ANPR) for vehicle classification. This paper will present an IoT-based automatic number plate recognition (ANPR) and biometric gate control system designed to optimize parking management through automated vehicle access. We suggested a biometric-integrated Internet of Things-based parking access management system with fingerprint recognition for user authentication. The system uses a Raspberry Pi 4 as its central controller and uses automatic number plate recognition (ANPR) to classify vehicles. Our suggested framework will utilize the camera to capture images of vehicles, then extract the license plate number and compare it to a database of permitted vehicles using ANPR software for vehicle classification and allocation. The system uses AI and IoT-based technologies to enhance security, automate vehicle entrances, and track real-time parking occupancy. Only registered users or authorized personnel are permitted to enter the restricted parking area. The proposed system is designed to operate in real-time, minimizing unauthorized access, reducing congestion, and enhancing overall parking efficiency. As a result of integrating with IoT systems, the solution will improve security and operational efficiency by enabling real-time monitoring, dynamic updates of parking availability, and logging of entry and exit events
Assessing Drought Conditions using SPEI in Bahawalpur Division, Punjab, Pakistan
Full text linkThis research study analyzes drought conditions using the Standardized Precipitation Evapotranspiration Index (SPEI) in Bahawalpur Division, South Punjab, Pakistan. Drought is one of the most complex natural disasters and is difficult to predict due to several involved factors. Among all natural hazards, drought causes significant damage to human lives and other living communities. Nearly 85% of all disasters are related to weather events, and drought is one of the most damaging among them. In Pakistan, drought causes damage in many areas, and Bahawalpur Division is one of those facing severe drought conditions. Temporal data on temperature and rainfall were collected from the Pakistan Meteorological Department for the period 1992 to 2020. The data were analyzed spatially using GIS technology. Precipitation and temperature data were analyzed using SPEI to monitor drought in three selected districts in Bahawalpur Division: Bahawalnagar, Bahawalpur, and Rahim Yar Khan. The study revealed that less rainfall was recorded in all three districts, leading to drought conditions. Moreover, this reduced rainfall severely affected the concerned districts
The Role of Industries in Accelerating Climate Change: A Case Study of Karachi (SITE Industrial Area)
Full text linkKarachi, Pakistan, is a densely populated city with a strong industrial presence, and it is increasingly threatened by climate change. This includes rising temperatures and changes in rainfall patterns. This paper examines how these climatic changes affect key industries in Karachi. It looks at how higher temperatures and limited water resources, intensified by the city\u27s extensive concrete and industrial development, create operational and economic challenges for various sectors. This study utilized a combination of satellite datasets (Landsat 8 and 9), climatic data (CHIRPS), and ancillary data (KDA maps) to analyze environmental changes in Karachi\u27s SITE area from 2015 to 2025. The analysis included rainfall analysis, LULC change detection, NDVI and LST trend analysis, and random point sampling for site-specific correlation. The presented results are accompanied by a narrative interpretation of environmental changes and their implications on the SITE industrial zone. This study examines the impact of climate change and urban-industrial growth on Karachi\u27s SITE area from 2015 to 2025. The findings reveal environmental stress due to declining vegetation cover and rising land surface temperatures, likely driven by unregulated industrial expansion and rainfall variability. However, signs of ecological recovery in 2025 suggest potential benefits from natural regeneration or better land management. To enhance climate resilience, the study recommends promoting urban greening, controlling industrial sprawl, improving water management, adopting climate-friendly practices, and regular monitoring using satellite data and GIS tools. By adopting climate-resilient practices and transitioning to low-carbon technologies, Karachi\u27s industries can reduce their environmental footprint and contribute to a more sustainable future
A Lightweight Blockchain-Enabled Trust Management Model for Secure Vehicular Communication
Full text linkVehicular Ad Hoc Networks (VANETs) are emerging as a pivotal component in intelligent transportation systems, offering safety-critical and comfort-related information to drivers and passengers. The effectiveness of VANETs relies on the timely exchange of messages between vehicles and roadside units (RSUs), where trustworthiness of shared data is paramount. Traditional centralized trust models, though efficient in information validation, suffer from single points of failure, limited scalability, and vulnerability to insider threats. This has driven a paradigm shift toward decentralized architectures, with blockchain technology standing out due to its immutable, transparent, and distributed nature. This study presents a comprehensive review of existing centralized and decentralized trust management models in VANETs, analyzing their methodologies, strengths, and limitations. By examining trust metrics, validation schemes, and message verification strategies across the literature, it identifies critical gaps in scalability, response time, and resistance to malicious behavior. Addressing these limitations, we propose a novel blockchain-based trust model named CB-RTM (Consortium Blockchain for RSU-Assisted Trust Management), an intelligent framework designed to ensure secure, verifiable, and real-time dissemination of safety messages in VANETs. The CB-RTM model integrates consortium blockchain with RSU-based validation and a Proof-of-Authority (PoA) consensus mechanism to filter and authenticate event messages using location certificates and trust scores. Unlike existing approaches, the model localizes trust updates and block propagation to geographically bounded regions, enhancing scalability and latency performance. Experimental evaluation demonstrates that the proposed CB-RTM outperforms state-of-the-art models across key metrics. The model achieves a trust accuracy of 96.2%, latency of 0.42 seconds, and throughput of 245 messages per second, while maintaining a manageable communication overhead of 11.2%. These results confirm that CB-RTM is a robust, scalable, and efficient solution for trust management in real-time VANET environment