Depth estimation is critical for autonomous vehicles (AVs) to perceive their surrounding environment. However, the majority of current approaches rely on costly sensors, making wide-scale deployment or integration with present-day transportation difficult. This issue highlights the camera as the most affordable and readily available sensor for AVs. To overcome this limitation, this paper uses monocular depth estimation as a low-cost, data-driven strategy for approximating depth from an RGB image. To achieve low complexity, we approximate the distance of vehicles within the frontal view in two stages: firstly, the YOLOv7 algorithm is utilized to detect vehicles and their front and rear lights; secondly, a nonlinear model maps this detection to the corresponding radial depth information. It is also demonstrated how the attention mechanism can be used to enhance detection precision. Our simulation results show an excellent blend of accuracy and speed, with the mean squared error converging to 0.1. The results of defined distance metrics on the KITTI dataset show that our approach is highly competitive with existing models and outperforms current state-of-the-art approaches that only use the detected vehicle’s height to determine depth.

Energy Harvesting Wireless Sensor Networks (EH-WSNs) are widely adopted for their ability to harvest ambient energy. However, these networks face significant challenges due to the limited and continuously varying energy availability at individual nodes, which depends on unpredictable environmental sources. To operate effectively in such conditions, energy fluctuations need to be regulated. This requires continuous monitoring of each node’s energy level over time and adaptively adjusting operations. State-of-the-art mechanisms often categorize nodes or discretize energy levels, leading to issues such as the inability to select appropriate actions based on the actual energy states of the nodes. This discretization simplifies the representation of energy states and reduces complexity, making it easier to design and implement. However, it overlooks subtle variations in energy levels, leading to inaccurate assessments and suboptimal performance. To overcome this limitation, this paper proposes an energy-aware transmission method based on the Deep Reinforcement Learning (DRL) algorithm that integrates Q-learning with Deep Neural Networks (DNNs). This method enables each node to adaptively select transmission actions based on its real-time energy state, improving responsiveness to dynamic network conditions. Simulation results show that the proposed method improves throughput by 11.79% compared to traditional methods. These findings demonstrate the effectiveness of DRL-based control in enhancing performance and energy efficiency in EH-WSNs.

The Wireless Body Area Networks (WBANs) are a set of sensors on the human s body that are designed in very small sizes. These sensors are faced with the exchange of a huge amount of data, which causes them to run out of energy consumption. One of the most effective methods to save the sensors’ energy is the use of data compression. However, the compression methods in WBANs are inadequate for compressing large amounts of duplicate data. In this regard, a new method called Efficient Data Compression for Energy Reduction (EDC-ER) is presented. EDC-ER method uses Recurrent Neural Network (RNN) and Run Length Encoding (RLE) which involves four key steps: 1- create and fit the LSTM network, 2- prediction, 3- calculate the error, and 4- compress by the lossless procedure. The presented method has a very good performance in energy consumption, data volume reduction by removing unimportant and repetitive data in the exchange of information between sensors and sink, high accuracy in data prediction, and achieving a high compression rate due to low error. The EDC-ER method is implemented on the data set received from body sensors including blood pressure systolic, blood pressure diastolic, heart rate, respiration, and SPO2. In the last step, the differences between predictions and original signals are coded by four lossless codes: RLE, Huffman, Limpel Ziv Welch (LZW), and Arithmetic. Three measurements of Compression Ratio (CR), Energy Remaining (ER), and Root Mean Square Error (RMSE) after data compression have been measured. Our results compared with state-of-art lossless coding methods. Results show the EDC-ER method with RNN and RLE has the highest energy saving on average of 98% by maintaining the appropriate compression ratio.