Face Detection and Localization in Video Using HOG with CNN

Faqeda Hassen; Mohammed Abdullah

doi:https://doi.org/10.54216/FPA.170117

Journal of Intelligent Systems and Internet of Things | 2025

Efficient Routing and Lifetime Prolongation in IoT founded Wireless Sensor Network Performance with Bee Colony-Inspired Lifetime Enhancement

To extend the lifespan of Wireless Sensor Networks (WSNs), effective routing protocols are required to provide communication channels between the sources and sink. While nodes are arbitrarily distributed in a substantially unsafe situation, these steering protocols are susceptible to an extensive range of assaults. For WSNs, trust-based routing protocols are created, which employ a trusted route rather than the quickest path, to prevent these attacks. The artificial bee colony-based clustering technique is utilized because the conventional clustering algorithm reduces the energy usage of nodes. This allows it to increase the lifespan of the sensor network by evenly dividing energy use among all nodes. The artificial bee colony (ABC)-based grouping method was developed because the typical grouping technique minimizes the energy usage of nodes. By integrating diverse sensors and devices, Internet of Things (IoT) enhances the performance of WSN, by enabling efficient data collection, analysis, and communication. The creation of such traditional protocols does not guarantee the best global optimization for the lengthening of WSN life. Through simulation analysis, the suggested Artificial Bee Algorithm (ABC)-based Traffic-Aware Energy Efficient Routing (TEER) protocol's performance was evaluated and contrasted with the TEER protocols. The ABC-based TEER protocol's lifetime analysis, active node analysis is achieved and contrasted with those of other protocols. In terms of the number of rounds, the network performance for the ABC-based TEER scheme performs better than the TEER schemes. The Analysis of throughput of the ABC-TEER method, which reveals a 9.5% increase in performance in comparison to the TEER protocol.

groups

Megha Gupta mail -

Sunil Kr Pandey mail -

Piyush Kumar Pareek mail -

Prashant Kumar Shukla mail -

Puneet Kumar Aggarwal mail -

P. Venkateswarlu Reddy mail

link https://doi.org/10.54216/JISIoT.140117

Volume & Issue

Vol. Volume 14 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

The Future of Personalized Medicine and Internet of Things Reshaping Healthcare Treatment Plans and Patient Experiences

The article "The Future of Personalized Medicine and How the Healthcare Internet of Things is Reshaping Treatment Plans and Patient Experiences" offers a comprehensive exploration of the transformative landscape of healthcare. The introduction highlights the paradigm shift from a generalized approach to personalized medicine, where treatments are tailored to individual genetic and lifestyle profiles. Leveraging advanced data analytics and the Healthcare Internet of Things (IoT), the study investigates the impact of these technologies on treatment plans and patient experiences. Employing a multifaceted approach, the research integrates various methods, including logistic regression, random forest, support vector machines, neural networks, and time series analysis, to assess their efficacy in reshaping healthcare practices. Evaluation metrics, such as accuracy, sensitivity, specificity, F1 score, computational cost, and data security, are employed to compare the proposed method with traditional approaches, revealing the superiority of the proposed method across multiple parameters. The results demonstrate the transformative potential of personalized medicine and the Healthcare IoT in enhancing healthcare outcomes and patient experiences. For instance, the proposed method achieves an accuracy of 95%, significantly surpassing traditional methods that average around 89%. Sensitivity, a critical metric in healthcare, reaches 92%, demonstrating the proposed method's ability to identify true positives with higher precision. Additionally, the computational cost of the proposed method, at 0.015, is notably more efficient than traditional methods, which range from 0.020 to 0.022. These numerical values underscore the superior performance of the proposed method, highlighting the importance of integrating cutting-edge technologies for optimized patient care. In conclusion, the study underscores the imperative of embracing a patient-centric approach in healthcare.

groups

Tan lan Hong mail -

Yagnik Dave mail -

Ankur Khant mail -

Lokesh Verma mail -

Megha Chauhan mail -

S. Parthasarathy mail

link https://doi.org/10.54216/JISIoT.140118

Volume & Issue

Vol. Volume 14 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

The Integration and Implementation of the Healthcare Internet of Things and Its Comprehensive Analysis

The Healthcare Internet of Things (HIoT) is driving a paradigm shift in the healthcare business by providing safe, fast, and networked healthcare solutions. We examined the advantages, disadvantages, and potential future of the Internet of Things (IoT) in the medical industry. Scalability, accuracy, real-time monitoring, data security, and interoperability were among the top priorities. The study employed strict assessment criteria to compare the proposed HIoT technology to existing approaches. This article begins with an overview of the IoT in healthcare. This study compares and contrasts the proposed HIoT strategy with more conventional approaches. We applied both methodologies in this study, each with its own benefits and drawbacks. We evaluated the responses using the F1-score, recall, accuracy, and precision. The inquiry uncovered an interesting story. The proposed HIoT method outperformed traditional techniques in all assessment parameters. In terms of accuracy, the recommended solution outperformed "Block chain Encryption" (8.4) and "Data Validation" (7.9). Additionally, it received an 8.9 for real-time monitoring and an 8.8 for interoperability. Another benefit of the strategy was a reduction in medical errors. The high data accuracy score of 9.1 demonstrates this. The findings illustrate the potential transformation of healthcare delivery through the Internet of Things. According to the study, the proposed strategy might increase healthcare's efficacy, efficiency, and patient-centeredness. The Internet of Things has opened up exciting new opportunities in healthcare. These options may transform medical care and patient outcomes.

groups

Adilakshmamma .T mail -

Meharunnisa S. P. mail -

Anusha Sreeram mail -

Rajat Saini mail -

Maryanka mail -

Shikhar Gupta mail

link https://doi.org/10.54216/JISIoT.140119

Volume & Issue

Vol. Volume 14 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

IoT based Wireless Networks in Hospitals: Ensuring Seamless Communication in Critical Situations

The heading "Wireless Networks in Hospitals: Ensuring Seamless Communication in Critical Situations" examines hospital wireless network enhancement. When patient well-being is at stake, this strategy encourages honest conversation. Service quality, resource efficiency, and network security are crucial. These mathematical models increase hospital wireless network stability based on Internet of Thing (IoT). Service management effectiveness influences who gets vital medical information quickly. Information and crucial messages are delivered faster. A mathematical technique considers the relevance and transmission time of each data payload to estimate its priority factor (P(i)). Network performance determines QoS settings. Priority data is transmitted first to ensure quick delivery to the intended recipients. This technology is essential for updating hospital WiFi networks, especially in critical situations where it can transmit accurate and timely information and save lives. WiFi reliability is essential for building operations. Compare failure frequency and MTBF to assess each network point's reliability. An exponential reliability function determines network dependability. The mean time between failures is used. This method maintains network functionality despite its complexity. Determine which pieces are crucial and how they influences network health. This simplifies network backups and maintenance. Load balancing distributes network tasks among entry points. This strategy helps the network function smoothly and minimize congestion during peak demand. The weighted round-robin timing algorithm determines how busy each access point is to send fresh network traffic to the proper areas. By equally distributing load and prioritizing underutilized access points, this method maintains network stability and keeps critical lines available. These three approaches form a full healthcare WiFi network strengthening plan. Mission-critical data is prioritized, the network is more robust, and resources may be allocated quickly. Our solution often outperforms the existing standard in network stability, communication, and cost.

groups

Madhura .K mail -

Rahul Yadav mail -

Yuvraj Parmar mail -

Tressa Michael mail -

Kiran Sanjay Degan mail -

Prakriti Kapoor mail

link https://doi.org/10.54216/JISIoT.140120

Volume & Issue

Vol. Volume 14 / Iss. Issue 1

Details open_in_new

International Journal of Advances in Applied Computational Intelligence | 2024

Hybrid Stochastic-Deterministic Path Planning Based Robotic Navigation Analysis

A capability that is indispensable in robotic navigation when it comes to planning paths through dynamic and uncertain environments efficiently and accurately. This work aims at a hybrid stochastic-deterministic path planning by combining the best of both worlds in order to improve robotic navigation. This hybrid model uses stochastic techniques to employ the robustness of uncertainly models, but offers efficient execution with deterministic algorithms for our optimum path solution. The method combines a highly exploratory stochastic sampling-based planner for environmental search with a deterministic optimization component that refines paths generated by the former, enforcing constraints such as minimal traversal distance (energy efficiency), while avoiding obstacles. The integration of those methods targets to override the disadvantages that each purely stochastic or solely deterministic model required, giving a more flexible and robust solution for autonomous vehicle guidance. We use simulation analysis and real-life experimental data to validate the algorithm in comparison with traditional algorithms. The approach performs significantly better, up to an order of magnitude in terms of accuracy and efficiency on navigation as well as robustness against cluttered or dynamic disturbances. These results indicate that the proposed hybrid stochastic-deterministic path-planning algorithm has strong potential to contribute to improving autonomy of robotic navigation systems, especially in highly dynamic and precise applications. The post provides a new framework to improve autonomous navigation of robots for complex environments that can support more efficient, reliable and high-level robotic systems in industrial, household or exploratory settings.

groups

Ahmed Hatip mail -

Karla Zayood mail -

Rabah Scharif mail

link https://doi.org/10.54216/IJAACI.060207

Volume & Issue

Vol. Volume 6 / Iss. Issue 2

Details open_in_new

International Journal of Advances in Applied Computational Intelligence | 2024

Realtime Traffic Enhancement using Intelligent Route Optimization for Dynamic Logistics

Software defect prediction is a technique that may foretell when and where software errors will manifest. It should be the aim of every software development project to provide a product devoid of bugs. Software defect prediction (SDP) is a crucial aspect of software repair that involves predicting potential code locations for problems. Software of excellent quality need to be bug-free. Software metrics are assessments of the program or its needs that are either quantitative or qualitative in nature. The Lévy flying patterns of various birds and fruit flies, together with the flight patterns of some cuckoo species, served as inspiration for Cuckoo Search (CS), a population-based algorithm that was developed relatively recently. Computer science satisfies the requirements for global convergence. Among the many supervised learning methods that do not need parameters, KNN stands out. This study provides a social metaphorical overview of Stochastic Diffusion Search (SDS) to show how SDS distributes resources. Using a new probabilistic approach, SDS solved the problems of best-fit pattern recognition and matching. Using interactions amongst basic agents, SDS is a distributed computing paradigm that employs multiagent population-based global search and optimization. An optimization approach that combines CS and SDS methods is suggested in this work. This hybridization proposal seeks to improve the cuckoo bird's search strategy for the ideal host nest by using the global search strategy solution of the SDS algorithm. So, to find the best spot for the cuckoo egg, the SDS approach would be used. One possible explanation for PC2's superior performance when compared to other classifiers is its greater recall values. Specifically, KNN outperforms Radial Bias Neural Network (2.20% improvement) and Naive Bayes (7.54% improvement) classifiers.

groups

Ahmed Abdelaziz mail -

Alia N. Mahmoud Nova mail

link https://doi.org/10.54216/IJAACI.060208

Volume & Issue

Vol. Volume 6 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

Enhancing Stock Price Prediction Using Mutual Information, PCA, and LSTM: A Deep Learning Approach

The stock price exhibits quick and extremely nonlinear fluctuations in the financial market. A prominent worry among scholars and investors is the correct prediction of short-term stock prices and the corresponding upward and downward trends. Financial organizations have successfully incorporated machine learning and deep learning techniques to anticipate time series data accurately. Nevertheless, the precision of these models' predictions still needs improvement. Most current studies employ single prediction algorithms that cannot overcome intrinsic limitations. This paper proposes a methodology that utilizes the MUTUAL, principal component analysis (PCA), and Long Short-Term Memory (LSTM) model to accurately simulate and predict the variations in stock prices. The technology is utilized for the three global stock market datasets: TSLA, S&P500, and NASDAQ. The highest level of improvement achieved is a correlation of 99%. Furthermore, there is a reduction in error for the metrics MSE, MAPE, and RMSE, with improvements of 0.0001, 0.009, and 0.01 correspondingly.

groups

Zinah Kareem Mansoor mail -

Ali Yakoob Al-Sultan mail

link https://doi.org/10.54216/FPA.170114

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2025

Leveraging LSTM and Attention for High-Accuracy Credit Card Fraud Detection

The increasing use of credit cards, especially for online payments, has led to a significant increase in fraud involving credit card payment technologies. Financial companies must enhance fraud detection systems to mitigate significant losses. This study introduces a methodology for developing a credit card fraud detection system that uses the Synthetic Minority Oversampling Technique (SMOTE) to address an imbalanced dataset problem and an attention layer to identify important features in the input sequence, two long short-term memory (LSTM) layers modeling long-run dependencies within a sequence of transactions, a dropout layer that neglects values lower than 0.3, and two dense layers, which allows enhancing the accuracy of prediction of fraudulent transactions. When implemented, the proposed system achieves an accuracy of 0.9434% on the IEEE dataset, 0.9850% on the Banksim dataset, and 0.9757% on the European dataset. This methodology shows improvements in fraud detection, emphasizing its ability to enhance financial security systems and reduce misclassification in credit card transactions.

groups

Ola Imran Obaid mail -

Ali Yakoob Al-Sultan mail

link https://doi.org/10.54216/FPA.170115

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2025

Enhancing Network Performance in Wireless Sensor and Anonymous Networks

In Wireless Sensor Networks (WSN), congestion control plays a crucial role as the traffic load surpasses the capacity of each major channel. The WSN constrained resources must be taken in consideration while devising such strategies to get the best throughput. Various factors are contributed in the congestion; the primary factor is the over flowing buffer, packet loss, reduce network throughput and loss of energy. This research, studies path load distribution in novel networks, including anonymous communication. Initially there is a chance that the public Wi-current Fi approach will result in notable imbalances. We next modify an optimal path-selection algorithm and use flow level visualization to show that this results in a substantially improved network load balance. Web-based Congestion Control (WCC) needs to make it possible to give WCC channel flows a distinct quality of service (QoS) in order to overcome this difficulty.

groups

Zaynab Saeed Hameed mail -

Mohammed Arif Nadhom Obaid Al-agar mail -

Israa Ali Al-Neami mail

link https://doi.org/10.54216/FPA.170116

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2025

Face Detection and Localization in Video Using HOG with CNN

Face detection is important in computer vision and image processing, particularly in surveillance, security systems, video analytics, and facial recognition applications. However, face detection algorithms face challenges like position variations, lighting fluctuations, size and resolution differences, facial expressions, and background clutter. This research aims to develop a system that achieves high accuracy in detecting and localizing faces using local descriptors and spatial feature extraction techniques, specifically the Histogram of Oriented Gradients method (HOG). Using videos from the YouTube Face database, features were extracted from frames and trained using a convolutional neural network (CNN). The HOG technique achieved a 94% accuracy rate and good localization compared to CNN without feature extraction.

groups

Faqeda Hassen Kareem mail -

Mohammed Abdullah Naser mail

link https://doi.org/10.54216/FPA.170117

Volume & Issue

Vol. Volume 17 / Iss. Issue 1

Details open_in_new