International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
A Machine Learning Prediction of Mechanical Properties in Reinforcement Bars: A Data-Driven Approach
No full textIntroduction/Importance of Study: This study addresses the pressing need for precise prediction of mechanical properties in steel reinforcement bars (rebars) through a data-driven approach utilizing machine learning techniques.
Novelty statement: Our research provides a solution to the challenge of predicting mechanical properties in rebars using advanced machine learning algorithms, filling a critical gap in existing methodologies.
Material and Method: Our study utilized a meticulously curated dataset comprising over 10,300 samples of diverse rebar types manufactured through industrial methods. We leveraged the latest PyCaret model to integrate machine learning algorithms, with a focus on training and rigorously testing linear regression models. Data preprocessing involved thorough cleaning using Python libraries such as Pandas and NumPy, supplemented by cross-validation techniques to ensure robust model generalization.
Result and Discussion: The core findings of our study revolve around the linear regression model algorithm trained within the machine learning framework, enabling precise determination of key mechanical properties including Yield Strength (YS) and ultimate Tensile Strength (UTS). Additionally, we explored the Ratio of UTS to YS (UTS/YS) as a critical mechanical property, incorporating essential input features such as weight percent of carbon (C), manganese (Mn), silicon (Si), carbon equivalent (Ceq), quenching parameters (Q), and diameter (d).
Concluding Remarks: Our research offers valuable insights into the application of machine learning for the precise prediction of mechanical properties in reinforcement bars, contributing to enhanced quality control and optimization in the steel manufacturing industry
Digital Twins and Engineering Education: Current Status
Get PDFThis paper presents a comprehensive review of the use of Digital twins in engineering education among various disciplines. A total of 83 research papers were analyzed, spanning the last decade from 2012 to 2022. Almost all publications were reported after the year 2018, indicating a recent surge in interest and development in this area. The review reveals that digital twin technology offers students an interactive experience with virtual models of real-world products and systems, significantly enhancing the effectiveness of engineering education. It also improves industrial competitiveness through predictive maintenance and fault diagnosis. Digital twins can be used in various engineering disciplines and for personalized learning. However, challenges such as model accuracy and data transfer must be considered when implementing them. Overall, this technology can improve student learning outcomes, increase education accessibility and cost-effectiveness, and improve production systems\u27 safety, visibility, and accessibility. Future requirements of the field are also discussed in this paper
Exploring Agile Testing Methodologies: A Perspective from the Software Industry
Get PDFAgile testing is a fast-paced testing method that adheres to the principles outlined in the Agile Manifesto. This research paper explores the adoption of Agile testing methodologies in the context of software houses in Pakistan. The study focuses on identifying the prevalent Agile testing techniques preferred by Software Quality Assurance (SQA) teams and the factors influencing their selection. A survey was conducted to gather insights from professionals in the industry, including SQA experts, developers, and project managers. The findings provided valuable information on the most widely used Agile testing methodologies and the reasons behind their popularity. The core objective of this research is to provide the knowledge related to implemented methodologies, reasons behind the selection of these methodologies, factors that influence the selection of testing tools and techniques, satisfaction level of their selected tools, and how effective their selected tools or techniques are in terms of reducing the number of bugs. The study\u27s contribution lies in offering guidance to software houses in Pakistan by facilitating the adoption of effective Agile testing techniques. The research concludes with recommendations for improving testing practices and enhancing the overall quality of software products in the industry.
Assessing Eight Years of Monsoon Rainfall Patterns in Karachi, Pakistan: Study of the Intense Rainfall Events
Get PDFRainfall plays a pivotal role in regulating water levels in reservoirs, which can lead to overflow or drought, depending on the unpredictability of rainfall patterns. In 2020 and 2022, Sindh experienced seven episodes of normal to heavy rains, causing flooding and disrupting major highways such as Gwadar-Karachi. This study evaluates daily and cumulative rainfall data in Karachi for the months of June, July, and August from 2016 to 2023. The rainfall data is divided, focusing on the monsoon rains over the eight-year period. Among these years, the highest recorded rainfall of 93.099mm occurred on August 11, 2019, while the lowest rainfall of 0.001mm was noted on July 26, 2016, and June 18, 2017. The yearly (2016-2023) cumulative rainfall for the study period was 114.6mm, 187.0mm, 34.9mm, 310.5mm, 347.9mm, 285.3mm, 761.4mm, and 167.6mm respectively. Notably, the cumulative rainfall and the frequency of rain events were highest in August 2020 and 2022. The monthly data revealed that Karachi experienced exceptionally heavy rainfall in August 2020 and 2022, resulting in significant disruption and chaos in the city. Moreover, when considering the data across the years, it becomes evident that Karachi faced unprecedented rainfall in 2020 compared to the preceding years. This research represents the first comprehensive analysis of the intense rainfall events in August 2020 and 2022 in Karachi. It identifies trends in rainfall patterns that led to flood-like conditions in the city. This study provides a detailed and quantitative understanding of rainfall occurrences during the monsoon season. Such insights are invaluable for assessing flood risks in Karachi, Pakistan
A Deep Learning Based Mobile Application for Wheat Disease Diagnosis
Get PDFWheat is one of the major staple crops in Pakistan, playing a crucial role in ensuring food security and contributing to the country\u27s economy. The productivity and quality of wheat crops, however, are vulnerable to several illnesses. The ability to diagnose these diseases quickly and accurately is crucial for taking the appropriate preventative actions, limiting losses, and maintaining food security. In this research paper, we build and test a wheat disease detection system adapted to the conditions in Pakistan. The suggested method uses machine learning-based techniques along with image processing algorithms to automatically detect and categorize various wheat diseases based on their symptoms. High-resolution photos of healthy wheat plants and sick plants displaying different diseases were collected from different regions of Pakistan in order to construct an accurate and robust disease detection model. The dataset has been annotated by plant pathologists who provided true labels for use in evaluation and training. To achieve the best results in wheat disease diagnosis, many cutting-edge deep-learning architectures were investigated and optimized. These included Convolutional Neural Networks (CNNs) and Transfer Learning models. Multiple models’ effectiveness was evaluated using accuracy, precision, and recall, in a series of extensive trials
Smart Fire Safety: Real-Time Segmentation and Alerts Using Deep Learning
Get PDFFires are the major causes of property damage, injuries, and death worldwide. The ability to avoid or reduce the effects of fires depends on their early identification. The accuracy and responsiveness of conventional fire detection systems, such as smoke detectors and heat sensors, are constrained. Computer vision-based fire and smoke detection systems have been suggested as a replacement for conventional systems in recent years. To tackle the challenges a robust real-time framework has been proposed, whereby, images are taken from cameras and using a custom train YOLOv8 object segmentation model smoke and fires are localized in the image which are then fed to an expert system for alert generation. The expert system makes decisions on the fire status based on its size and growth across multiple frames. Furthermore, A new dataset was meticulously curated and annotated for the segmentation task, to assess the efficacy of the proposed system, comprehensive benchmarking was conducted on the proposed dataset using a suite of benchmarks. The proposed system achieved an mAP score of 74.9% on the benchmark dataset. Furthermore, it was observed that employing segmentation for localization as opposed to detection, resulted in system accuracy improvement. The system can immediately identify fires and smoke and send accurate alerts to emergency services
NEUROSCAN: Revolutionizing Brain Tumor Detection Using Vision-Transformer
Get PDF Brain tumor detection is a pivotal component of neuroimaging, with significant implications for clinical diagnosis and patient care. In this study, we introduce an innovative deep-learning approach that leverages the cutting-edge Vision Transformer model, renowned for its ability to capture complex patterns and dependencies in images. Our dataset, consisting of 3000 images evenly split between tumor and non-tumor classes, serves as the foundation for our methodology. Employing Vision Transformer architecture, we processed high-resolution brain scans through patching and self-attention mechanisms. The model is trained through supervised learning to perform binary classification tasks. Our employed model achieved a high of 98.37% in tumor detection. While interpretability analysis was not explicitly performed, the inherent use of attention mechanisms in the Vision Transformer model suggests a focus on important brain regions and enhances its potential for prioritizing crucial information in brain tumor detection
Potential Challenges and Solutions for Implementing NOMA in Smart Grid
Get PDFEfficient two-way communication is crucial for Smart Grid (SG) networks, enabling real-time monitoring, data collection, and control. This study introduces the novel integration of Non-Orthogonal Multiple Access (NOMA) into SG systems to enhance spectral efficiency and support numerous smart devices, addressing the limitations of traditional communication methods. A comprehensive survey of existing wired and wireless communication technologies was conducted, followed by the implementation of a NOMA scheme tailored for SG environments. Results demonstrate that NOMA significantly improves spectral efficiency, enables access to a large number of smart meters, and enhances the system\u27s resilience to electromagnetic interference. Additionally, the study addresses challenges such as impulse noise, optimizing spectral and energy efficiency tradeoffs, and power consumption in interference cancellation. These findings underscore the potential of NOMA to revolutionize SG communication infrastructure. Conclusively, integrating NOMA in SG networks offers a robust solution for future smart grid communication needs
AI-Driven Weed Classification for Improved Cotton Farming in Sindh, Pakistan
Get PDFThis research study proclaims the combination of artificial intelligence and also IoT in precision agriculture, highlighting weed discovery plus cotton plant monitoring in Sindh, Pakistan. The uniqueness lies in creating a deep learning-based computer system vision application to develop a durable real-time weed category system, dealing with a problem not formerly solved. The study entailed gathering datasets utilizing mobile cams under varied ecological problems. A CNN version was educated utilizing the open-source Cotton Weeds dataset, annotated with clinical problems such as Broadleaf and Horse Purslane. Examinations used a Wireless Visual Sensor Network (WVSN) with Raspberry Pi for real-time photo catching as well as category. The CNN version, readjusted to identify in between cotton along with Horse Purslane weed accomplished a precision of 86% and also an ROC AUC rating of 0.93. Efficiency metrics consisting of precision-recall, as well as F1 rating, suggest the model\u27s viability for various other weed category jobs. Nonetheless, obstacles such as photo top-quality variants and also equipment constraints were kept in mind. The research ends that using artificial intelligence as well as IoT in farming can dramatically improve plant return plus assist lasting methods for future generations
Deep Learning Based Identification and Categorization of Various Phases of Diabetic Retinopathy
Get PDFDiabetic Retinopathy is a growing disease that affects the human retina of diabetic patients and if it is left untreated it leads to loss of vision. Early diagnosis and accurate classification of DR stages are important for immediate intervention and efficient control. Therefore, this study focuses on the classification of different stages of diabetic retinopathy in retinal images by using a DL (deep learning) model named Densenet121. The dataset used in this research contains various collections of color fundus images obtained from diabetic patients, labelled with corresponding disease stages. The dataset used was taken from Kaggle named APTOS 2019. Standard metrics such as accuracy, recall, F1-score, and precision are used to measure the effectiveness of the proposed model. The proposed DL based classification model shows encouraging results and has achieved a high level of accuracy across various severity levels. This model offers an automated method for detection and classification of the disease facilitating early diagnosis. Overall, this study advances automated diagnosis to lessen the burden of diabetic retinopathy