Evaluating Hybrid Model Performance in Predicting the Impact of Lockdown on Controlling Covid-19 Cases Progression in Middle Income Settings
A Method for the Identification of Denial of Service (DoS) Attack in Network Traffic using Machine Learning Techniques
Agriculture Management System
Unveiling Sentiment Analysis: A Comparative Study of LSTM and Logistic Regression Models with XAI Insights
Resume Screener System
Efficient Agent Based Priority Scheduling and LoadBalancing Using Fuzzy Logic in Grid Computing
A Survey of Various Task Scheduling Algorithms In Cloud Computing
Integrated Atlas Based Localisation Features in Lungs Images
A Computational Intelligence Technique for Effective Medical Diagnosis Using Decision Tree Algorithm
A Viable Solution to Prevent SQL Injection Attack Using SQL Injection
In computer vision, image dehazing remains a pivotal challenge, especially in accommodating diverse weather conditions that greatly impact visibility and image quality. The development of deep learning algorithms for image dehazing has been a prominent area of research in recent years. Two such methods are the Cross-Entropy Deep Learning Neural Network (CE-DLNN) and the Guided Multi-Model Adaptive Network (GMAN), which have shown promising results in removing haze from images. In this paper, the performance of these two methods is compared in terms of PSNR, SSIM, and MAE on dehazed images. It is found that GMAN outperforms CE-DLNN in these metrics, producing dehazed images with higher PSNR, SSIM, and lower MAE. Additionally, an investigation into the combination of GMAN and CE-DLNN demonstrates further improvements in the performance of both methods, resulting in higherquality dehazed images with enhanced details and textures. These findings substantiate the potential of utilizing deep learning-based approaches for image dehazing and highlight the benefits of synergistically integrating various methodologies to optimize performance.
Through the National Registration Bureau (NRB), the Malawi government introduced mandatory registration and the issuance of National Identity Cards (IDs) to its bona fide Malawian citizens aged 16 and above, in accordance with the Registration Act of 2010. This administration is currently carried out manually in a few designated National Registration Bureau (NRB) offices. As a result, citizens find it time-consuming and congested to renew their IDs in case of loss, damage, or expiration. Due to these drawbacks, there was a need for a new system that could help overcome these challenges, leading to the proposition of an "Online National Citizen's ID Renewal System. The system is aimed at simplifying the process of renewing national ID cards for Malawian citizens in a convenient and secure manner. Through the web portal provided by the system, citizens are able to complete the renewal process in one sitting without being required to physically visit the National Registration Bureau offices (NRB). The functionality of the system requires citizens to create an account, wherein their names and their previous ID numbers are used as usernames and passwords, respectively, or credentials to log in to the system. Once the information has been verified, citizens would be able to access renewal or registration forms (which are currently collected, filled, and submitted manually) and pay the relevant renewal fee, which is currently at MWK2500, through secure payment gateways. To ensure the security and privacy of the citizens' personal information, the system is implementing industry-standard encryption and authentication protocols and is complying with data protection laws and regulations mandated by the Malawi Government. The online national Citizens ID renewal system will provide a more efficient, accessible, and secure system for managing citizen ID renewals. It has also reduced waiting times, improved accuracy, and increased accessibility for all citizens, while also providing better security and efficiency for government staff managing the system. The Online National Citizen's ID Renewal System is expected to improve the current manual ID renewal system, which poses several challenges and limitations, such as long waiting times, errors, inaccuracies, and inefficiency.
Magnetic Resonance Imaging (MRI) plays a pivotal role in non-invasively diagnosing knee injuries. This research focuses on cost-effective, efficient solutions for enhancing automated knee injury detection in MRI scans. The study aims to boost diagnostic accuracy for abnormalities, Anterior Cruciate Ligament (ACL) tears, and meniscal tears using advanced deep learning techniques. Transfer learning is employed, combining pretrained neural networks with transfer models. AlexNet and SqueezeNet are explored as feature extraction architectures, assessing the attention mechanism and maxpooling for sequence reduction. This yields four models, MRNet, MRNet-Squeeze, MRNet-Attend, and MRNet- SqueezeAttend. The primary evaluation metric is the Area Under the ROC Curve (AUC), providing a comprehensive assessment by averaging AUC scores for abnormal, ACL tear, and meniscus tear labels. The initial MRNet achieves the highest AUC (0.940) for anomaly detection, while MRNet-Squeeze excels in diagnosing ACL damage. MRNet- SqueezeAttend achieves the highest AUC (0.885) for meniscus tears. The ensemble of all four models outperforms individual models with an outstanding average AUC of 0.931. Each model exhibits unique strengths. MRNet excels at spotting anomalies, MRNet-Squeeze accurately detects ACL tears, and MRNet-SqueezeAttend excels in identifying meniscal tears. Notably, the ensemble leverages these diverse strengths to deliver cutting-edge results for all injury types. Further investigation reveals varying correlations between model-specific predictions and different diagnosis or sequence combinations. Scrutinizing the MRI sequence frames capturing the models' attention identifies key contributors to the diagnosis.
In many different industrial, residential, and commercial situations, gas leakage poses a serious hazard. Its discovery is crucial since it might have severe effects like explosions and fires. For the protection of persons and property, as well as to avert catastrophic tragedies, accurate and prompt gas leak detection is essential. Convolutional Neural Networks (CNNs), in particular, have demonstrated encouraging results in the detection of gas leaks in recent years. Here, a CNNbased method is provided for detecting gas leaks from image data. The suggested method employs a Softmax classifier for gas classification after extracting features from the image dataset using a combination of convolution, pooling, and fully connected layers. The usefulness of the suggested approach in accurately detecting gas leakage is shown by the experimental findings and the proposed approach is tested on a real-world gas leakage dataset. It can be added to gas detection systems to improve their functionality, lowering the likelihood of gas-related mishaps. The findings support current work to create accurate and effective machine learning-based gas leak detection systems.
The Internet of Things (IoT) has emerged as a transformative technology, connecting a wide range of devices and sensors to the internet, enabling data-driven decision-making and automation across various domains. Deep learning, a subset of machine learning, has played a pivotal role in advancing IoT applications by providing the means to process and interpret the massive volumes of data generated by IoT devices. This comprehensive survey provides an extensive review of the integration of deep learning techniques with IoT, aiming to offer a holistic understanding of the state-of-the-art research and practical implementations. The key motivations include handling complex IoT data and enabling smart applications across domains like healthcare, transportation, and industry 4.0. Real-world case studies demonstrate significant improvements on metrics like prediction accuracy, operational efficiency, and energy savings. The adoption of edge computing is further driven by the need to reduce latency in data processing and enhance real-time decisionmaking capabilities in these critical sectors. However, challenges remain around model interpretation, robustness, and computational complexity. Future IoT systems must focus on lightweight deep learning architectures tailored for edge devices, distributed and privacy-preserving analytics, and improved model transparency and fairness. Additionally, these future IoT systems should prioritize robust security measures to protect sensitive data and ensure the reliability and integrity of connected devices and networks. A systematic framework is proposed covering data curation, model development, deployment, and monitoring to guide adoption. The comprehensive nature of this survey aims to bridge the gap between theoretical knowledge and practical deployment, enabling a smoother integration of deep learning into IoT systems. By offering a structured overview of best practices and emerging trends, it empowers professionals to make informed decisions in their IoT projects.
