International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Machine Learning in Livestock Management: A Systematic Exploration of Techniques and Outcomes
Get PDFThis Systematic Literature Review (SLR) examines the growing field of leveraging Machine Learning (ML) to improve livestock productivity. Through a meticulous analysis of peer-reviewed articles, the study categorizes research into key domains such as disease detection, feed optimization, and reproductive management. Various ML algorithms, including supervised, unsupervised, and reinforcement learning, are evaluated for their efficacy in enhancing herd health and management. The review also addresses the role of diverse data sources, such as sensor technologies and electronic health records and discusses the socio-economic and ethical implications of ML adoption in livestock farming. Insights into scalability, economic viability, and future research directions contribute to a comprehensive understanding of the current background and pave the way for sustainable and technologically advanced livestock management practices. This review serves as a valuable resource for researchers, practitioners, and policymakers in shaping the future of precision agriculture in improving livestock productivity
Review of Peer Feedback in Collaborative Tutoring Systems
Get PDFIntroduction/Importance of Study:
Collaborative tutoring systems (CTSs) allow students to communicate from different geographical areas to learn, share, and explain ideas related to a particular problem.
Novelty statement:
Many CTSs employ peer tutor evaluation to offer feedback to students as they solve scenarios. When they receive similar questions, the students utilize the feedback to enhance their thinking. The accuracy of peer feedback is important because it helps students to enhance their learning skills. If the student serving as a peer tutor is unfamiliar with the topic, he or she may suggest incorrect feedback. Considering peer feedback’s importance in learning systems, this study\u27s primary goal is to critically examine various collaborative tutoring systems and evaluate the strategies they have created to enhance group learning. Numerous reviews have been published in the past, but none of them have taken into account the methods by which these systems deliver or assess peer feedback.
Material and Method:
This article critically reviews different CTSs based on the proposed evaluation scheme to investigate their design and methods that support peer collaboration.
Result and Discussion:
Through this study, it was found that there are few attempts in which the feedback sent from one student to another student is evaluated by CTS. The peer feedback accuracy is important, because a student who gets inaccurate feedback may reach the wrong conclusions, which would affect the learner\u27s knowledge.
Concluding Remarks:
It is concluded that all of the CTSs provide chances to boost student\u27s learning gains. Fortunately, the entire degree to which these advantages can be realized is subject to further investigation
Algorithmic Implementation and Evaluation for Image Segmentation Techniques
Get PDFThis research conducts a comprehensive comparative analysis of five prominent image segmentation algorithms, including Thresholding, K-Means Clustering, Mean Shift, Graph-Based Segmentation (Watershed), and U-Net (Deep Learning). The study employs a diverse set of five images and associated masks to rigorously evaluate algorithmic performance using key metrics such as Jaccard Index, Dice Coefficient, Pixel Accuracy, Hausdorff Distance, and Mean Intersection over Union. The findings reveal that the Threshold Algorithm consistently outperformed its counterparts, achieving perfect scores in Jaccard Index, Dice Coefficient, Pixel Accuracy, and Mean Intersection over Union, while minimizing Hausdorff Distance to 0. This emphasized its exceptional accuracy, precision, and agreement with ground truth segmentation, positioning it as an optimal choice for applications demanding precise segmentation, such as medical imaging or object detection. The research underscores the need to carefully consider specific application requirements and tradeoffs when selecting an algorithm, offering valuable guidance to researchers and practitioners in the field of image segmentation. The standardized approach outlined in the material and methods section ensures fair comparisons, making this study a valuable resource for informed decision-making in diverse imaging applications
Enhancing Face Mask Detection in Public Places with Improved Yolov4 Model for Covid-19 Transmission Reduction
Get PDFOver the past decade, computer vision has emerged as a pivotal field, focusing on automating systems through the interpretation of images and video frames. In response to the global impact of the COVID-19 pandemic, there has been a notable shift towards utilizing computer vision for face mask detection. Face masks, endorsed by international health authorities, play a crucial role in preventing viral transmission, prompting the development of automated monitoring systems in various public settings. However, existing artificial intelligence (AI) technologies\u27 effectiveness diminishes in congested environments. To address this challenge, the study employs a meticulously fine-tuned YOLOv4 model for identifying instances of mask non-compliance in accordance with COVID-19 Standard Operating Procedures (SOPs). A distinctive feature of the training dataset is its inclusion of images featuring Muslim women with both half and full-face veils, considered compliant with face mask guidelines. The dataset, comprising 5800 images, including veil images from various sources, facilitated the training process, achieving a comparatively good 97.07% validation accuracy using transfer learning. The adaptations, coupled with a custom dataset featuring crowded images and advanced pre-processing techniques, enhance the model\u27s generalization across diverse scenarios. This research significantly contributes to advancing computer vision applications, particularly in enforcing COVID-19 safety measures within public spaces. The tailored approach, involving model adjustments, underscores the adaptability of computer vision in addressing specific challenges, highlighting its potential for broader societal applications beyond the current global health crisis
Enhancing Cardiovascular Disease Risk Prediction Using Resampling and Machine Learning
Get PDFCardiovascular Disease (CVD) remains a critical health concern around the globe, requiring precise risk prediction approaches for timely intervention. The primary motive of this study is to enhance CVD risk prediction through innovative techniques, just like resampling the imbalanced datasets using random oversampling and employing advanced Machine Learning (ML). In this study, different robust ML algorithms such as Random Forest Classifier, Decision Tree Classifier, XGBoost Classifier and Logistic Regression were trained on a diverse dataset encompassing demographic, clinical and lifestyle factors related to CVD. By addressing class imbalance through oversampling, the models showed significant performance improvements, showcasing the effectiveness of our ML algorithms in accurately forecasting CVD risks. Specifically, the Random Forest model with an accuracy score of 96% and AUC-ROC score of 99%. This study emphasizes the potential of modern approaches to improve CVD risk assessment by leveraging cutting-edge technologies for enhanced healthcare outcomes. Enfolding these approaches and tools, it becomes easy to pave the way for more personalized risk assessment and early intervention strategies, eventually aiming to alleviate the global burden of CVD
Skin Scan: Cutting-edge AI-Powered Skin Cancer Classification App for Early Diagnosis and Prevention
Get PDFMobile health applications (mHealth) use machine learning (AI)-based algorithms to classify skin lesions; nevertheless, the influence on healthcare systems is unknown. In 2019, a large Dutch health insurance provider provided 2.2 million people with free mHealth software for skin cancer screening. To evaluate the effects on dermatological care consumption, the research conducted a practical transitional and population-based study. To evaluate dermatological needs between the two groups throughout the first year of free access, the research compared 18,960 mHealth users who completed at least one successful evaluation with the app to 56,880 controls who did not use the app. The odds ratios (OR) were then computed. A cost-effectiveness analysis was conducted in the near term to find out the expense for each extra-diagnosed premalignancy. Here, results indicate that mHealth users had a three-fold greater incidence of requests for benign tumors on the skin and the nevi (5.9% vs 1.7%, OR 3.7 (95% CI 3.4–4.1)), and they had greater numbers of claims for (pre)malignant skin cancers as groups (6.0% vs 4.6%, OR 1.3 (95% CI 1.2– 1.4)). Compared to the existing standard of care, the expenses associated with using the app to detect one additional (pre) malignant skin lesion were €2567. These results suggest that AI in m Health may help identify more dermatological (pre)malignancies, but this could be weighed against the current greater rise in the need for care for benign tumors of the skin and nevi
Use of Artificial Intelligence in Ethereum Forecasting: The Deep Learning Models RNN and CNN with Ensemble Averaging Technique
Get PDFIn the fast-evolving cryptocurrency market, accurately predicting Ethereum prices is crucial for investors, traders, and financial analysts. Traditional machine learning (ML) models often struggle to capture the market\u27s complex dynamics due to their inability to consider all influencing factors. This study introduces an advanced ensemble machine learning approach to enhance Ethereum price prediction accuracy. By combining the strengths of Bi-directional Long Short-Term Memory (Bi-LSTM) and Convolutional Neural Network (CNN) models, our ensemble averaging method compensates for individual model weaknesses, improving forecast reliability and precision. Results show that our ensemble model offers significant advantages, particularly in terms of generalizability and resistance to overfitting with LSTM and CNN models and this technique is offering a more effective tool for navigating cryptocurrency market complexities. This research highlights the importance of ensemble learning in financial forecasting and provides a practical framework for developing superior predictive models. “Moreover, This study explores an advanced ensemble machine learning approach to enhance Ethereum price predictions, combining the strengths of Bi-directional Long Short-Term Memory (Bi-LSTM) and Convolutional Neural Network (CNN) models. While Bi-LSTM individually exhibits slightly higher performance in our tests, the ensemble method demonstrates enhanced stability and reliability, making it a valuable tool for navigating the unpredictable dynamics of the cryptocurrency market. We found that Bi-LSTM is good on its own, but the balanced approach of the ensemble model is far better, especially when it comes to generalizability and overfitting resistance. Insights into creating flexible and trustworthy prediction models are provided by this study, which highlights the possibilities of ensemble learning in financial forecasting
Heterotrophic Denitrification Of Wastewater By Using Melanoidin As Sole Carbon Source
Get PDFRemoving nitrate effects through heterotrophic denitrification is an effective approach to treating water or wastewater containing these contaminants. The effective management of wastewater is of paramount importance to mitigate its adverse impacts on both human health and the environment. This study delves into the biodegradation and removal of nitrate and nitrite by introducing melanoidin as a carbon source, the research explores the influence of batch test strategy using a heterotrophic denitrification process for removal of toxicity by using inoculum from MCR (master culture reactor) for 48 hours in which four controls (C1, C2, C3, C4) and five test sample of different dilutions of melanoidin i.e. 100 ppm, 250 ppm, 500ppm, 700 ppm and 1000 ppm were used. The results demonstrate that remarkable removal of nitrate, nitrite, and TOC was found in 100 ppm, 250 ppm and 500 ppm dilutions, with a marked reduction of Total organic carbon (TOC), indicating successful toxicity removal, 750 ppm and 1000 ppm dilutions were not affected by denitrification in TOC removal. Subsequent denitrification of the T1, T2, and T3 samples showcases the potent synergy between treatment processes. Through the use of a C:N ratio of 2:1 and 3:1, 98.14% of nitrate was successfully removed within 48 hours. High-Performance Ion Chromatography (HPIC) was employed to analyze the samples treated with denitrification, revealing the complete elimination of toxicity. These results highlight the crucial role of melanoidin as a carbon source in denitrification, enabling thorough nitrate degradation and detoxification. This study underscores the importance of adopting innovative treatment methods to address the growing challenges associated with wastewater management
The Exploring Political Emotions Sentiment Analysis of Urdu Tweets
No full textThis research is a multi-text categorization based on a collection of Pakistani political texts. The major goal of this research is to use Natural Language Processing (NLP) and Machine Learning classification models to categorize multi-text for Urdu. Political tweets from 13 different Pakistani famous leaders were collected for this research. These politicians make use of the platform to promote themselves and engage with their supporters. To analyze the model accuracy the desired dataset is divided into six categories which have been composed of their official Twitter account. We also collect top trends from Pakistan and around the world to examine current trends regularly. In the proposed research, the major political corpus data comprises 1300+ tweets in the Urdu language, encompassing political policies, campaigns, opinions, and so on. Sentiment analysis is an essential component of every deep learning approach. For that, we have used the deep learning approach i.e. sentiment analysis of the politician since it provides insight into their moods and views on a certain topic. Furthermore, text corpus pre-processing is conducted utilizing NLP techniques, such as data cleaning, data balancing, and stop word removal. TF-IDF is used as word filtering for feature extraction count vectors. Machine Learning classification algorithms such as SVM, Decision Tree, XGboost, and Random Forest, and for implementation of neural network we have used Word2vector
Efficiency Assessment for Crop Classification Using Multi-Sensor Data in Google Earth Engine
Get PDFAccurate mapping of agricultural lands and crop distribution is crucial for food security, sustainable development, and informed policymaking. This research classified agricultural crops in the Rahim Yar Khan district of Pakistan using multi-sensor images from Sentinel-1 and Sentinel-2 satellites. The study employed the cloud computing platform Google Earth Engine (GEE) and compared the performance of the Random Forest (RF) algorithm using Sentinel-1 (VV, HV, and HV+VV), Sentinel-2, and integrated datasets. Ground truth information obtained from field surveys and high-resolution images served as reference samples for training and validation. The fusion of Sentinel-1 and Sentinel-2 data enhanced feature extraction, leading to improved crop type classification. Post-processing procedures ensured that the maps were visually clear and free of noise, allowing for accurate crop mapping and land cover categorization. The classification results indicated high accuracy for crops such as sugarcane, cotton, rice, and water bodies. The RF classifier using fused data achieved the highest accuracy (overall accuracy of 93% and Kappa coefficient of 90%), followed by Sentinel-2 (89%), Sentinel-1 VV+VH (72%), Sentinel-1 VH (66%), and Sentinel-1 VV (62%). The study underscores the value of data integration in improving the classification accuracy of major crops (sugarcane, cotton, and rice) in the region. While some classes showed exceptional accuracy, others, such as Orchard, require further refinement in categorization methods. Overall, the study provides valuable insights into using multi-sensor remote sensing data for agricultural monitoring and decision-making