Search

A smart grid is a modern electrical system that uses information technology, including sensors, measurement tools and communication devices, to monitor and improve the efficiency of the power system. However, real-time forecasting remains a challenge due to its complexity. This paper presents a forecasting framework that combines Convolutional Neural Networks (CNN) and Bidirectional LongShort Term Memory (BiLSTM) for real-time load forecasting in smart grids. Compared to traditional methods like ARMA and Decision Trees (DTs), the proposed CNN-BiLSTM model demonstrates superior performance in terms of prediction accuracy, reaching up to 99% - higher than Long-Short Term Memory (LSTM) (93%) and Support Vector Machine (SVM) (84%). Additionally, the CNN-BiLSTM model requires fewer computational resources, with 90 Gigaflops (G) and 94 Million (M) parameters, compared to 151 (G) and 120 (G) for ARIMA and CNN-LSTM, respectively. These results indicate the proposed model's ability to accurately predict power system loads in real time with high computational efficiency. [ABSTRACT FROM AUTHOR]

The global COVID-19 pandemic has led to an urgent need for government intervention to prevent its spread. Scientific evidence has confirmed the effectiveness of mask-wearing in reducing virus spread. However, enforcing mask mandates in public spaces presents notable monitoring hurdles, particularly as facial recognition technology is impeded by face coverings. With many organizations relying on facial recognition for employee authentication, security and authentication become critical, especially for IoT systems. This article uses a Convolutional Neural Network (CNN) model to accurately identify mask- wearing individuals and introduces a secure user authentication mechanism between the node and the access point. This authentication mechanism consists of three phases. (i) Identification Phase at the Access Point Level: A novel hybrid biometric pattern, merging password and image features, is employed to strengthen user authentication security through a fusion approach. (ii) Secure Communication: Utilizing blockchain technology and AES cryptography ensures the secure transmission of these patterns between the node and the access point. (iii) Matching Phase at the Node Level: A newly proposed method verifies authenticity by comparing the combined image and password features with database records during the development phase. The experimental results demonstrate its outstanding performance, achieving 99% accuracy, 99% recall, 100% precision, and 98.9% F1 score. These results suggest that the proposed approach holds promise as an effective and secure solution for identifying individuals wearing masks while ensuring reliable authentication in various environments. [ABSTRACT FROM AUTHOR]

We are witnessing an explosion in the concept of the Internet of Things (IoT) as smart objects become more important in our daily lives to make it easier to achieve our goals. It is obvious that the application areas of IoT are extremely diverse. Indeed, several sectors will be deeply impacted by IoT applications. Of which, security in the Internet of Things (IoT) has become a major concern due to increasing vulnerabilities and threats. Connected devices, often with limited security capabilities, have become attractive targets for attackers. Vulnerabilities in IoT devices, whether resulting from unmodified default configurations, lack of regular updates, or insecure communication protocols, expose these systems to potential risks. Cryptography, as a discipline dedicated to securing communications, uses advanced mathematical techniques to guarantee the confidentiality of electronic exchanges by making the data incomprehensible to unauthorized persons. In this paper, we show an in-depth exploration of the generation of new S-boxes using the genetic algorithm. These new S-boxes are dynamically generated with the new genetic algorithm-based approach. This new method offers adaptive optimization, iteratively exploring the solution space to identify robust S-boxes, thereby strengthening the security of the encryption system. The study continues with the evaluation of these S-boxes through dedicated metrics, allowing an in-depth analysis of their performance in terms of resistance to cryptographic attacks and preservation of substitution properties. Finally, this evaluation extends to the incorporation of these newly generated S-boxes into the AES encryption algorithm, where different dimensions, such as cryptanalysis resistance, scene visibility, and other performance levels, will be examined. [ABSTRACT FROM AUTHOR]

Summary: In the present situation, there is a huge research gap and development present in the creation and utilization of smart environment due to the development of wireless sensor network (WSN) and Internet of Things (IoT). The disadvantage of the earlier models and present systems is it consumes more power and there is a presence of network monitoring issues. Here, there is a need of developing a model which solves both this issues for the real time environment. So, in this paper, we developed a novel model which is a cross‐layered energy optimization‐based Medium Access Control (CEO‐MAC) protocol to overcome those issues. Our model considers the optimal design of the network and MAC layer. Its focus is on the CEO‐MAC routing model, cross‐layer MAC model, cross‐layer energy optimization model, and intercluster/intracluster MAC operational model. This model is briefly analyzed and simulated using Network Simulator 2 (NS2) software, which is the discrete event simulator that works using C++ and Tcl languages. Our protocol is simulated and compared with the present models such as TDL, CMISO, and PCL‐IDA protocols. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) have attracted a lot of interests over last years in security to ensure integrity, authenticity and data confidentiality. WSN applications are numerous, which range from smart home in indoor deployment offices to smart agriculture in outdoor deployments. Due to the deployment of nodes in remote areas, the solution brought to the wireless sensor network to increase the information security consists in protecting the messages exchanged between nodes. In the paper, modifications in the key management scheme are presented. Due to resource constraints in the sensor nodes, the proposed scheme ensures a distribution of the secured keys between nodes. New session keys transmitted between sensor nodes are defined during the discovery and path key phases. The experimental results prove that the proposed scheme is adapted to the WSN applications in terms of connectivity and resiliency. [ABSTRACT FROM AUTHOR]