The use of reinforcement learning (RL) for dynamic obstacle avoidance (DOA) algorithms and path planning (PP) has become increasingly popular in recent years. Despite the importance of RL in this growing technological era, few studies have systematically reviewed this research concept. Therefore, this study provides a comprehensive review of the literature on dynamic reinforcement learning-based path planning and obstacle avoidance. Furthermore, this research reviews publications from the last 5 years (2018–2022) to include 34 studies to evaluate the latest trends in autonomous mobile robot development with RL. In the end, this review shed light on dynamic obstacle avoidance in reinforcement learning. Likewise, the propagation model and performance evaluation metrics and approaches that have been employed in previous research were synthesized by this study. Ultimately, this article’s major objective is to aid scholars in their understanding of the present and future applications of deep reinforcement learning for dynamic obstacle avoidance.

In most communication systems, when transmitting or receiving a signal, some unwanted signals may get introduced into the communications, making the quality of the communication poor. This disturbance, referred to as noise, can affect the reliability and quality of a digital communication system by corrupting or getting a message scrambled whenever it is transmitted. To prevent these errors, error-correction codes help detect and correct these errors arising during data transmission within digital communication systems. In communication systems, such error-correcting codes are essential for ensuring the efficient and reliable exchange of information over noisy channels like satellite links, optical fibers, and wireless networks. As such, the work presented in this paper delves into the issue of noisy data in communication systems and how error-correcting codes can be used to solve the problem. To achieve this, a review of different relevant literature by various scholars is done to present authentic and verifiable data on error-correcting codes for communication systems. On top of that, this paper introduces a novel approach by integrating advanced machine learning techniques, particularly artificial neural networks, to enhance the effectiveness and adaptability of error-correcting codes in diverse and dynamically changing communication environments, significantly surpassing traditional error correction methods.

Image Scenario classification is widespread for many IoT applications. Classifying scenario helps in making proper decisions. The study aims at classifying six different scenarios using a deep neural network algorithm. The proposed InceptionV3 classification algorithm could predict the scenarios and achieve 92.00% accuracy. A quick comparison is shown with the traditional machine learning algorithms, SVM and MLP. The study shows the power of the deep neural algorithm and classifies the scene image dataset with higher precision.