Advanced Intrusion Detection in Vehicular Networks: Empowering Security through Hybrid Off-loading Techniques and Enhanced Radial Bias Neural Network

Prashant Kumar; Ratish

doi:https://doi.org/10.54216/JISIoT.110205

Fusion: Practice and Applications | 2024

Enhanced Recognition of Handwritten Marathi Compound Characters using CNN-SVM Hybrid Approach

This study presents a hybrid recognition system for multi-class compound Marathi characters, which addresses the problem of handwritten Marathi character recognition. The methodology efficiently bridges the gap between feature extraction and classification by integrating a Convolutional Neural Network (CNN) and Support Vector Machine (SVM). The first step is gathering and preprocessing a wide range of handwritten Marathi compound characters that are written in different styles. Using conventional supervised learning methods, the CNN is trained on this dataset, paying special attention to data augmentation and validation in order to reduce overfitting. High-level features taken from the final fully connected layer of the CNN are fed into an SVM classifier in the next step. By using these features in its training, the SVM improves prediction accuracy. For multi-class classification, the one-vs-all method is used. The hybrid CNN-SVM algorithm demonstrates its effectiveness in the crucial phases of feature extraction and classification by identifying handwritten compound Marathi characters with remarkable accuracy. Evaluation metrics, such as accuracy, precision, recall, F1-score, and confusion matrix analysis, are employed in the process of evaluating the effectiveness of the model. This assessment is carried out on a different testing dataset, offering a thorough examination of the model's functionality. The proposed algorithm demonstrates its superior performance and potential for improved character recognition by achieving training accuracy of 98.60% and validation accuracy of 97.69%. The development of handwriting recognition systems has benefited greatly from this research, especially when it comes to intricate scripts like Marathi. The suggested hybrid algorithm shows encouraging outcomes and has a great deal of potential for use in document processing, natural language comprehension, and character recognition in languages that use the Marathi script. Subsequent efforts will centre on refining the model and investigating ensemble methods to increase the robustness and accuracy of recognition.

groups

Ashwini Patil mail -

Puneet Dwivedi mail

link https://doi.org/10.54216/FPA.140202

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2024

Analysis of EEG signals with the use of wavelet transform for accurate classification of Alzheimer Disease, Frontotemporal Dementia and healthy subjects using Machine Learning Models

Dementia is a brain disorder, if not prevented; takes the form of various types of diseases that have no cure yet. Accurate classification of multiple types of dementia diseases is required to provide proper medication to the patient so that growth of that disease can be delayed. This study analyzes EEG signal for the classification of multiple dementia diseases such as Alzheimer’s disease (AD), Fronto-temporal dementia (FTD) and control normal (CN) subjects using machine learning (ML) algorithms. Each of the 19 channels of EEG dataset is analyzed separately in this work to perform the classification. Combination of parameters like Hjorth Activity, Mobility and Complexity along with kurtosis value of the data has been extracted in time-frequency domain for each EEG frequency band (Delta, Theta, Alpha, Beta and Gamma) is applied to the machine learning algorithms. This research is focused on classification of multiple dementia classes (ADvsFTD) as well as three-way (ADvsFTDvsCN) classification. This research is validated using public EEG dataset with 23 participants of each category. Best classification result is achieved using random forest classifier and leave-one-subject-out (LOSO) cross validation method. The three-way classification i.e., ADvsCNvsFTD achieved best accuracy of 75.29%, whereas binary classifications i.e. ADvsCN, ADvsFTD and CNvsFTD achieved best accuracy of 88.90%, 88.44% and 84.10% respectively. The proposed framework shows better results than existing work on dementia classification using machine learning. The results obtained from proposed framework showed that combination of EEG frequency band features can be utilized for the classification of multiple dementia diseases with greater accuracy.

groups

Akanksha Parihar mail -

Preety D Swami mail

link https://doi.org/10.54216/FPA.140203

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2024

Performance Evaluation and Real-world Challenges of IoT-Based Smart Fuel Filling Systems with Embedded Intelligence

Integrating the Internet of Things (IoT) with smart fueling systems has the potential to revolutionize the fuel industry, leading to better resource management and increased operational efficiency. With the increasing integration of machine learning techniques, these systems are capable of self-learning, adaptation, and predictive decision making. However, the effectiveness of these advanced systems in real-life situations remains an area of intense interest and research. in operational efficiency and reduces resource waste by 10% compared to conventional systems. Additionally, system bottlenecks were identified mainly in data trans- mission  (delayed by up to 20% in high  traffic cases) and hardware malfunctions due  to environmental factors. End user feedback  indicates a satisfaction level of 85%, with an emphasis on system responsiveness and fuel prediction recommendations. Challenges mainly come from software issues, unwanted environmental interference and  ’some initial resistance from users accustomed to conventional systems. However, with data in hand, the benefits of integrating intelligence into IoT-based fueling systems offer a sustainable and efficient future for the fuel industry. Recommendations are made to improve data transmission channels, develop  robust hardware for extreme conditions, and conduct targeted user education campaigns.

groups

Muneer Sadeq ALqazan mail -

Mohamed Ben Ammar mail -

Monji Kherallah mail -

Fahmi Kammoun mail

link https://doi.org/10.54216/FPA.140204

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2024

An ICT-based Framework for Innovative Integration between BIM and Lean Practices Obtaining Smart Sustainable Cities

Smart sustainable cities rely on the latest technologies and apply recent knowledge like Information and Communication Technologies (ICT), BIM, and lean construction to expand people's eminence of life, smooth urban maneuvers and facilities more competent, and develop their competitiveness while confirming that they achieve the economic, social, environmental, and cultural demands of current and forthcoming generations. This paper explores the synergies between Building Information Modelling (BIM) visualisation and Lean construction practices to enhance Architecture, Engineering, and Construction (AEC) industry performance. A structured questionnaire was distributed among BIM and lean experts and analysed by SPSS. The study uses descriptive and correlation analyses to assess ten key lean practices, revealing high industry adoption and favorable mean scores. Notably, BIM-enhanced clash detection and coordination lead with a score of 4.4 out of 5. Correlation analysis establishes significant positive associations between BIM visualisation and practices such as just-in-time production, value stream mapping, lean pull systems, work sequencing, standardised work, and continuous improvement. The findings accentuate the pivotal role of BIM in optimising lean practices, offering valuable insights for practitioners seeking to elevate AEC industry performance through strategic integration. Future studies endeavors are recommended to investigate several alternative avenues to enhance the integration between BIM and Lean practices in the AEC industry. Furthermore, the forthcoming researchers are advised to validate the proposed framework.

groups

Fawaz Saleh mail -

Ashraf Elhendawi mail -

Abdul Salam Darwish mail -

Peter Farrell mail

link https://doi.org/10.54216/FPA.140205

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2024

Leveraging Advanced Machine Learning Methods to Enhance Multilevel Fusion Score Level Computations

This research introduces a novel technique for determining numerous fusion score levels that works with many datasets and purposes. Each of the four system pieces works together. These are Feature Engineering, Ensemble Learning, deep neural networks (DNNs), and Transfer Learning. In feature engineering, raw data is totally transformed. This stage stresses the importance of PCA and MI for predictive power. AdaBoost is added during ensemble learning. It repeatedly teaches weak learners and adjusts weights depending on errors to create a strong ensemble model. Weighted input processing, ReLU activation, and dropout layers smoothly integrate DNNs. These reveal minor data patterns and correlations. In transfer learning (fine-tuning), a trained model is modified for the feature-engineered dataset. In comparative testing, the recommended technique had greater accuracy, precision, recall, F1 score, AUC-ROC, and training duration. Efficiency measures reduce reasoning time, memory, parameter count, model size, and energy utilization. Visualizations demonstrate resource consumption, method scores, and reasoning time distribution in research. This mathematical framework improves multilayer fusion score level computations, performs well, and is versatile in many scenarios, making it a good choice for large and diverse datasets.

groups

Rajesh Tiwari mail -

Satyanand Singh mail -

G. Shanmugaraj mail -

Suresh Kumar Mandala mail -

Ch. L. N. Deepika mail -

Bhanu Pratap Soni mail -

Jiuliasi V. Uluiburotu mail

link https://doi.org/10.54216/FPA.140206

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

Energy Efficient Cluster Head Selection Using Hybrid RL-PSO Approach

Wireless Sensor Networks (WSNs) are crucial in several applications, highlighting the need of effective clustering and fault detection systems.  This paper introduces a novel approach that uses Reinforcement Learning (RL) and Particle Swarm Optimization (PSO) to optimize cluster head selection and enhance fault detection capabilities within WSNs. The proposed hybrid algorithm operates in two phases, combining the explorative capabilities of RL with the optimization process of PSO to select cluster heads based on residual energy and connectivity considerations. By continuously monitoring the network's residual energy state and the number of active nodes, the proposed method ensures prolonged network lifetime and improved overall performance. Our experimental results demonstrate the superior performance of the hybrid RL-PSO approach compared to traditional clustering algorithms, showcasing significant improvements in optimizer accuracy, residual energy preservation, and fault detection efficiency.

groups

Arpita Choudhary mail -

N. C. Barwar mail -

Vikas Chouhan mail

link https://doi.org/10.54216/JISIoT.110201

Volume & Issue

Vol. Volume 11 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

Improving Support vector machine for Imbalanced big data classification

A significant proportion of one type of pattern and a relatively small quantity of another type of pattern can be found in many unbalanced real data sets. In addition, finding significant observations and excluding influential observations is effectively accomplished through diagnostic analysis. Support vector machines (SVM), a common classification technique, perform poorly on imbalanced datasets and when influential observations exist. In this research, the pigeon optimization algorithm as a metaheuristic algorithm is employed to address the influence observation issues in SVM. Experiments are done on three real sets of data. Our approach provides higher classification accuracy compared to other widely used algorithms. This approach could be used for further biological, chemical, and medical datasets.

groups

Alaa Abdulazeez Qanbar mail -

Zakariya Yahya Algamal mail

link https://doi.org/10.54216/JISIoT.110202

Volume & Issue

Vol. Volume 11 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

Unraveling the Complexity: A DEMATEL Analysis of the Negative Impact of Artificial Intelligence (AI) Adoption among Students in Higher Education

This research employs DEMATEL analysis as a methodological approach to thoroughly examine the adverse consequences of implementing Artificial Intelligence (AI) among students enrolled at Universiti Teknologi MARA (UiTM) Negeri Sembilan, Malaysia. The analysis encompasses three distinct professional cohorts: student representatives, academic staff, and upper management. Through a systematic analysis of causal relationships between multiple factors, this study aims to identify and prioritize the fundamental elements contributing to the negative consequences associated with integrating artificial intelligence. The prominence of privacy and security concerns as a causal factor highlights the importance of implementing strong data protection measures and adhering to ethical practices related to AI. Furthermore, various factors connected with personal disconnection, restricted adaptability, dependance on technology, and insufficient emotional intelligence influence the adverse outcomes of artificial intelligence implementation among students. The results underscore the necessity of implementing focused interventions and strategies to tackle these difficulties and guarantee a harmonious and advantageous integration of artificial intelligence in students' educational journeys. Higher education institutions can effectively harness the advantages of AI while ensuring their students' welfare and educational achievements by recognizing and proactively addressing any potential limitations.

groups

Zahari Md Rodzi mail -

Wan Normila Mohamad mail -

Zhang Lu mail -

Faisal Al-Sharqi mail -

Rawan A. shlaka mail -

Ashraf Al-Quran mail -

Ali M. Alorsan Bany Awad mail

link https://doi.org/10.54216/JISIoT.110203

Volume & Issue

Vol. Volume 11 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

Adaptive feature selection based on machine learning algorithms for Lung tumors diagnosis and the COVID-19 index

Early detection of Lung tumors, which is lethal and equally affects men and women, is challenging. In order to decrease mortality rates and raise survival rates, early detection and classification of Lung tumors is essential. However, at the start of 2020, the entire planet would be afflicted with a coronavirus that causes a fatal sickness (COVID-19). CT imaging is a good tool to detect illness among the various COVID-19 screening techniques available. On the other hand, alternative methods of disease detection take a lot of time. Deep learning, a type of machine learning, opens up a wealth of opportunities for investigating and assessing tumor features using CT scans, allowing for improved disease prediction, diagnosis, and classification. Using CNN, DNN, and VGG-16 models, the suggested approach in this research gives unambiguous and accurate categorization.

groups

Bashar Talib Al-Nuaimi mail -

Ruaa Azzah Suhail mail -

Sanaa adnan abbas mail -

El-Sayed M. El-Kenawy mail

link https://doi.org/10.54216/JISIoT.110204

Volume & Issue

Vol. Volume 11 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

Advanced Intrusion Detection in Vehicular Networks: Empowering Security through Hybrid Off-loading Techniques and Enhanced Radial Bias Neural Network

Over the last several decades, the implementation of ITS has shown to be the most efficient and successful strategy for expanding the variety of current transportation networks. Vehicle-based offloading of data going to be essential for forthcoming networking innovations like D2D and 5G due to the substantial contribution it makes to efficiently using network capability while wasting minimal power. Information transmissions that would normally need a cellular network's infrastructure may instead be made using alternative networking mechanisms including Bluetooth, WiFi, and opportunistic communications. Data offloading has the ability to significantly increase the efficiency with which network resources are used. The offloading of data from vehicles has a considerable impact on the strain on cellular networks. It helps the network achieve higher throughput by facilitating the simultaneous reception of data by a large number of users. First, we must establish that the problem of Vehicular data offloading is an NP-hard target set selection (TSS) issue before we can even begin to characterize it. Using a combination of Hybrid PSO and GWO, TSS selects a small group of nodes to do the redundant data exchange (Particle Swarm Optimization with Gray Wolf Optimization). Collaboration between individuals and ISPs to identify effective aim sets may provide useful insights. If malicious users are present in the target group, they may slow down network activity by spoofing or by reducing the network's offloading capacity. It is possible that the whole network's performance would suffer as a direct result of these malicious users. In this study, we suggest a hybrid approach to communication for specifying the intended audience. We take use of the characteristics of opinion dynamics amongst users to get around the issue of overlapping community detection. Trust-based metrics inferred from users' activities are used to ensure the safety of the target set. In order to call 911, the suggested work additionally incorporates a method of sorting and classifying the offload limitations through Radial Bias Neural Network (RBNN). The following may be determined with the use of the proposed work's performance indicators: precision, entropy, and delay.

groups

Prashant Kumar Shukla mail -

Ratish Agarwal mail

link https://doi.org/10.54216/JISIoT.110205

Volume & Issue

Vol. Volume 11 / Iss. Issue 2

Details open_in_new