Arman Process Journal (APJ)

Abstract Background and Objectives: With the advancement of vehicular networks and the increasing demand for accurate and timely data, challenges such as data retrieval delays and security concerns have garnered significant attention. Traditional cloud-based storage methods are unable to meet temporal and security requirements due to the considerable distance between vehicles and servers. Although edge computing offers a solution for reducing latency, it requires improvements due to limitations in storage and distributed management. Previous research has primarily focused on one aspect of optimization (reducing delay or enhancing security), with less attention paid to combining these two objectives. This paper aims to propose an innovative hybrid optimization model using deep learning and blockchain that considers both security and delay reduction. This is achieved by optimizing caching locations, storage, retrieval processes, and storing critical information on the blockchain, ensuring a scalable and flexible model adaptable to traffic changes and user demands.

Methods: The study population and sample include mobile vehicular networks (VANETs), considering edge servers and vehicular nodes. An LSTM model was used to predict traffic patterns and data popularity, while blockchain with a Proof of Authority (PoA) consensus mechanism and smart contracts was employed for secure data storage. Performance was evaluated based on delay, security, and scalability metrics, and compared with existing methods such as Tabu Search, CCS-AGP, and Random Caching in terms of delay and security.

Findings: The proposed model significantly reduced delay (by 10% to 30% compared to baseline methods). The use of blockchain introduced only an 8% additional delay while elevating security to a "very high" level. The system demonstrated stability and scalability under increasing numbers of nodes and data volume. Simulation results indicated that the combination of deep learning and blockchain achieves an optimal balance between performance and security.

Conclusion: The proposed model, integrating deep learning and blockchain, not only reduces delay but also ensures data security and integrity. This framework can serve as a foundation for developing intelligent systems in domains such as the Internet of Things (IoT), smart cities, and next-generation transportation.

Abstract Wireless Sensor Networks (WSNs) have emerged as one of the key technologies in recent decades due to their rapid deployability, low cost, and wide range of applications in fields such as the Internet of Things (IoT), environmental monitoring, smart agriculture, and critical systems. However, the hardware and software limitations of sensor nodes — including low processing power and limited energy resources — make these networks vulnerable to failures and disruptions, turning reliability into a fundamental challenge.



In this study, a novel framework based on Tiny Machine Learning (TinyML) is proposed to enhance reliability and optimize energy consumption in WSNs. The proposed architecture consists of four key modules — anomaly detection, failure prediction, intelligent data compression, and adaptive routing — which are deployed locally at the node level to enable fast processing, reduce communication overhead, and enable intelligent resource management.



Simulation results demonstrated that the proposed method not only increases the network lifetime and significantly reduces energy consumption but also improves data quality, communication stability, and responsiveness to abnormal events.



The findings of this research indicate that leveraging TinyML can open new horizons in the design of intelligent WSNs and provide a solid foundation for developing future large-scale applications in dynamic environments.

Abstract Background and Objectives: in this research, a novel method for detecting Iranian license plates and simultaneously recognizing letters and digits is introduced. Various approaches have been proposed for license plate detection, which have progressively improved over time. Traditional methods involve classical image processing techniques such as grayscale conversion, thresholding, and binary morphology. With advancements in machine learning, artificial neural network algorithms have been employed for license plate identification and recognition. Today, deep neural networks, particularly convolutional neural networks and recurrent neural networks, are recognized as leading methods in vehicle license plate detection. The objective of this study is to propose an efficient approach that includes locating the license plate using machine vision algorithms and segmenting the identifiers. Challenges such as variations in lighting conditions and vehicle speed have been examined in this research, and solutions to enhance detection accuracy and speed have been presented.



Methods: To improve the accuracy and robustness of the proposed model, a dataset consisting of 844 real Iranian license plate images captured under diverse lighting conditions and viewing angles was collected and expanded to 2024 images using data augmentation techniques. After fine-tuning, the model is capable of localizing license plate regions and extracting Persian characters using a CRNN-based architecture. The proposed system demonstrates a significant performance improvement over YOLOv8 and YOLOS models by reducing recognition errors in challenging scenarios such as strong illumination, shadows, high vehicle speed, and font variations

Findings: Ultimately, an accurate and efficient license plate recognition method based on the YOLOv9 architecture is proposed, achieving an overall accuracy of 98%. Quantitative evaluation results, including precision, recall, and F1-score, indicate that the proposed model is well suited for real-time applications in visual surveillance, traffic monitoring, and intelligent transportation systems.

Conclusion: The experimental results demonstrate that the proposed approach significantly enhances license plate detection accuracy and can effectively support intelligent transportation systems and automated traffic management applications.

Abstract Background and Objectives: Fault of power distribution networks is based on the ‎uncontorable factors. Rapid approache to identidtification and localization of power ‎network fault is ctritical to maintain system riable. While traditional approaches use ‎measurements from current and voltage transformers, this study proposes an ‎artificial intelligence-driven approach for enhanced fault detection and analysis in ‎power distribution networks. A custom-designed sensing prototype captured voltage ‎and current data under simulated fault conditions, including short-circuit and open-‎circuit faults. The presented approach includes fundamental variables, such as fault ‎type, sensor placement topology, and line distance, were rigorously controlled during ‎data acquisition.‎

Methods: This paper presentes two algorithms: an Artificial Neural Network (ANN) ‎and an Adaptive Neuro-Fuzzy Inference System (ANFIS). Both used algorithms have ‎many parmeters that rquire to be tune While the values of these parameters effect ‎on the performance, but the major target of this study is using of these algorithms. ‎Steps of algorithms are described in the paper. The redults of algorithms are showed ‎with the used data. Performance was validated under variable load conditions across ‎line distances of 200–800 meters. ‎

Finding: Simulation results demonstrate that the ANFIS classifier achieved superior ‎accuracy in fault classification (99.7%) and minimal distance estimation error (0.5%). ‎Both ANN and ANFIS delivered high precision in fault detection, localisation, and ‎classification, with ANFIS exhibiting significantly faster training convergence (1 ms). ‎Indeed ANFIS has more consistency. ‎

Cnclusion: The framework presents a robust, computationally efficient solution for ‎real-time fault management (modeling), recommending (analysis) the integration of ‎dedicated sensors by power distribution network utilities to enable targeted grid ‎interventions.‎

Abstract  Mobile commerce, as a new achievement of e-commerce services, has numerous and unique advantages such as accessibility, positioning, immediacy, capability, personalization and identification. Today, most businesses have considered the use of mobile phone social advertising as the main way to help connect with customers in order to obtain information and promote it. Business-oriented companies use Internet services and social networks as a new option to support their products or provide customer service. Placing real-time and up-to-date advertisements on social networking websites will be a competitive advantage in increasing the volume of customer visits. Mobile commerce has various dimensions, operational components, functions and adoption models, which we intend to address in this article.

Abstract  Nowadays, cloud computing is the preferred choice of any organization based on information and communication technology due to its flexible services and outstanding pay-as-you-go features. Some cloud-based networks face various security challenges due to the lack of fixed infrastructure and centralized management. However, the security and privacy of cloud computing systems is a fundamental problem of cloud computing due to their distributed architecture and vulnerability to unwanted inputs. The role of unwanted attack detection systems in cloud security is very important because it acts as a preventive security layer and, in addition to identifying known attacks, can detect many unknown attacks. In this article, we intend to review these systems and describe approaches to deal with the challenge of intrusion into cloud computing services.