Cybernetics and Information Technologies

Abstract Recent advances in path-planning algorithms have transformed robotics. The Rapidly exploring Random Tree (RRT) algorithm underpins autonomous robot navigation. This paper systematically examines the uses and development of RRT algorithms in single and multiple robots to demonstrate their importance in modern robotics studies. To do this, we have reviewed 70 works on RRT algorithms in single and multiple robot path planning from 2015 to 2023. RRT algorithm evolution, including crucial turning points and innovative techniques, have been examined. A detailed comparison of the RRT Algorithm versions reveals their merits, limitations, and development potential. The review’s identification of developing regions and future research initiatives will enable roboticists to use RRT algorithms. This thorough review is essential to the robotics community, inspiring new ideas, helping problem-solving, and expediting single- and multi-robot system development. This highlights the necessity of RRT algorithms for autonomous and collaborative robotics advancement.

Dena Kadhim Muhsen

Firas Abdulrazzaq Raheem

Ahmed T. Sadiq

A Systematic Review of Rapidly Exploring Random Tree RRT Algorithm for Single and Multiple Robots

单机器人和多机器人快速探索随机树RRT算法的系统综述

Abstract Nowadays, being in digital era the data generated by various applications are increasing drastically both row-wise and column wise; this creates a bottleneck for analytics and also increases the burden of machine learning algorithms that work for pattern recognition. This cause of dimensionality can be handled through reduction techniques. The Dimensionality Reduction (DR) can be handled in two ways namely Feature Selection (FS) and Feature Extraction (FE). This paper focuses on a survey of feature selection methods, from this extensive survey we can conclude that most of the FS methods use static data. However, after the emergence of IoT and web-based applications, the data are generated dynamically and grow in a fast rate, so it is likely to have noisy data, it also hinders the performance of the algorithm. With the increase in the size of the data set, the scalability of the FS methods becomes jeopardized. So the existing DR algorithms do not address the issues with the dynamic data. Using FS methods not only reduces the burden of the data but also avoids overfitting of the model.

B. Venkatesh

J. Anuradha

A Review of Feature Selection and Its Methods

特征选择及其方法综述

Abstract In this work, we build upon an implementation of a peer-to-peer image encryption algorithm: “Rubik’s cube algorithm”. The algorithm utilizes pixel-level scrambling and XOR-based diffusion, facilitated through the symmetric key. Empirical analysis has proven this algorithm to have the advantage of large key space, high-level security, high obscurity level, and high speed, aiding in secure image transmission over insecure channels. However, the base approach has drawbacks of key generation being handled client-side (at nodes) and the process is time-consuming due to dynamically generating keys. Our work solves these issues by introducing a Key Distribution Center (KDC) to distribute symmetric keys for transmission, increasing confidentiality, and reducing key-generation overhead on nodes. Three approaches utilizing the KDC are presented, communicating the dimensions with KDC to generate keys, standardizing any image to fixed dimensions to standardize key-generation, and lastly, using a single session key which is cyclically iterated over, emulating different dimensions.

Aswani Kumar Cherukuri

Shria Sannuthi

Neha Elagandula

Rishita Gadamsetty

Neha Singh

Arnav Jain

I. Sumaiya Thaseen

V. Priya

Annapurna Jonnalagadda

Firuz Kamalov

A Secure Peer-to-Peer Image Sharing Using Rubik’s Cube Algorithm and Key Distribution Centre

使用魔方算法和密钥分发中心的点对点图像安全共享

Abstract This study presents design of traffic light system with feedback control that considers a crossroad in an urban area. Two types of controllers are designed – fuzzy and analytical, which have been tested separately on Aimsun platform through a simulation. The aim of the study is to compare the performance of both controllers in terms of increasing traffic flow and decreasing queue length. The controllers manage the duration of the green light according to the traffic flow. Two different formal models are designed, tested, and compared. They have produced adequate solutions in terms of developing controllers for modeling and simulation of transportation tasks.

Boriana Vatchova

Yordanka Boneva

Alexander Gegov

Modelling and Simulation of Traffic Light Control

交通信号灯控制的建模与仿真

Abstract Wireless Sensor Networks (WSN) aggregate data from multiple sensors and transfer it to a central node. Sensor nodes should use as little energy as possible to aggregate data. This work has focused on optimal clustering and cluster head node selection to save energy. HyperGraphs (HGC) and cluster head selection based on distance and energy consumption are unique approaches to spectral clustering. GRA computes a relational matrix to select the cluster head. The network’s Moving Agent (MA) may use Hypergraphed Particle Swarm Optimization (HGPSO) to collect data from cluster heads. Compared to the clustering algorithm without agent movement, the HGC-GRA-HGPSO approach has increased residual energy by 5.59% and packets by 2.44%. It also has improved residual energy by 2.45% compared to Grey Wolf Optimizer-based Clustering (GWO-C).

Shailendra Pushkin

None Ranvijay

A Novel Hypergraph Clustered Gray Relational Analysis HGPSO Algorithm for Data Aggregation in WSN

一种用于WSN数据聚合的新型超图聚类灰色关联分析HGPSO算法

Abstract Penetration Testing (PT), which mimics actual cyber attacks, has become an essential procedure for assessing the security posture of network infrastructures in recent years. Automated PT reduces human labor, increases scalability, and allows for more frequent evaluations. Real-world exploitation still challenges RL-based penetration testing because the agent’s many possible actions make it hard for the algorithm to converge. To resolve these shortcomings, a deep learning- model named Adaptive Hunt Tuner algorithm optimized Q-learning based deep Convolutional neural Network (AHT-QCN) is developed for efficient PT. Specifically, the Q-learning employed in this model improves its efficiency by enabling optimal policy learning for decision-making. In addition, the Adaptive Hunt Tuner (AHT) algorithm enhances the model’s performance by tuning its parameters with reduced computational time. The experimental outcomes demonstrate that the developed model attains 95.25% accuracy, 97.66% precision, and 93.81% F1 score.

Dipali Railkar

Shubhalaxmi Joshi

AHT-QCN: Adaptive Hunt Tuner Algorithm Optimized Q-learning Based Deep Convolutional Neural Network for the Penetration Testing

AHT-QCN：基于自适应狩猎调谐算法优化Q学习的深度卷积神经网络用于渗透测试

Abstract This study presents a novel multi-level Stacking model designed to enhance the accuracy of customer churn prediction in the banking sector, a critical aspect for improving customer retention. Our approach integrates four distinct machine-learning algorithms – K-Nearest Neighbor (KNN), XGBoost, Random Forest (RF), and Support Vector Machine (SVM) – at the first level (Level 0). These algorithms generate initial predictions, which are then combined and fed into higher-level models (Level 1) comprising Logistic Regression, Recurrent Neural Network (RNN), and Deep Neural Network (DNN). We evaluated the model through three scenarios: Scenario 1 uses Logistic Regression at Level 1, Scenario 2 employs a Deep Convolutional Neural Network (DNN), and Scenario 3 utilizes a Deep Recurrent Neural Network (RNN). Our experiments on multiple datasets demonstrate significant improvements over traditional methods. In particular, Scenario 1 achieved an accuracy of 91.08%, a ROC-AUC of 98%, and an AUC-PR of 98.15%. Comparisons with existing research further underscore the enhanced performance of our proposed model.

Van-Binh Ngo

Van-Hieu Vu

Multi-Level Machine Learning Model to Improve the Effectiveness of Predicting Customers Churn Banks

多层次机器学习模型提升银行客户流失预测效果

Abstract Real-time Hand Gesture Recognition (HGR) has emerged as a vital technology in human-computer interaction, offering intuitive and natural ways for users to interact with computer-vision systems. This comprehensive review explores the advancements, challenges, and future directions in real-time HGR. Various HGR-related technologies have also been investigated, including sensors and vision technologies, which are utilized as a preliminary step in acquiring data in HGR systems. This paper discusses different recognition approaches, from traditional handcrafted feature methods to state-of-the-art deep learning techniques. Learning paradigms have been analyzed such as supervised, unsupervised, transfer, and adaptive learning in the context of HGR. A wide range of applications has been covered, from sign language recognition to healthcare and security systems. Despite significant developments in the computer vision domain, challenges remain in areas such as environmental robustness, gesture complexity, computational efficiency, and user adaptability. Lastly, this paper concludes by highlighting potential solutions and future research directions trying to develop more robust, efficient, and user-friendly real-time HGR systems.

Aws Saood Mohamed

Nidaa Flaih Hassan

Abeer Salim Jamil

Real-Time Hand Gesture Recognition: A Comprehensive Review of Techniques, Applications, and Challenges

实时手势识别：技术、应用与挑战的综合评述

Abstract Next Generation Wireless Networks (NGWNs) have two main components: Network Slicing and Open Radio Access Networks (O-RAN). NS is needed to handle various Quality of Services (QoS). O-RAN adopts an open environment for network vendors and Mobile Network Operators (MNOs). In recent years, Deep Reinforcement Learning (DRL) approaches have been proposed to solve some key issues in NGWNs. The primary obstacles preventing the DRL deployment are being slowly converged and unstable. Additionally, these algorithms have enormous carbon emissions that negatively impact climate change. This paper tackles the dynamic allocation problem of O-RAN radio resources for better QoS, faster convergence, stability, lower energy and power consumption, and reduced carbon emissions. Firstly, we develop an agent with a newly designed latency-based reward function and a top-k filtration mechanism for actions. Then, we propose a policy Transfer Learning approach to accelerate agent convergence. We compared our model to another two models.

Heba Sherif

Eman Ahmed

Amira M. Kotb

Energy-Efficient and Accelerated Resource Allocation in O-RAN Slicing Using Deep Reinforcement Learning and Transfer Learning

使用深度强化学习和迁移学习的O-RAN切片中高效能和加速资源分配

Abstract The rapid growth of Internet-enabled applications, such as social media platforms, e-commerce sites, and blogs, has led to a surge in user-generated content. This vast amount of data has made sentiment analysis increasingly valuable. Modern Aspect-Based Sentiment Analysis (ABSA) offers a more detailed approach by identifying sentiment trends related to specific aspects within the text. However, the challenge lies in analyzing reviews that are often short, unstructured, and filled with slang and emotive language, making it difficult to gauge customer opinions accurately. To address these issues, we proposed an effective hybrid approach “RoBERTa-1D-CNN-BiLSTM” for ABSA. Initially, the pre-trained Robustly Optimized BERT approach (RoBERTa) and One Dimensional Convolutional Neural Network (1D-CNN) models are used to extract features at the aspect level from the context of the review, following which classification is performed using Bidirectional Long Short-Term Memory (BiLSTM). The approach is evaluated on three cross-domain standards datasets, yielding an accuracy of 92.33%. The results of the experiments show that it surpasses the current leading methods in sentiment analysis and product recommendation.

Muhammad Rizwan Rashid Rana

Asif Nawaz

Tariq Ali

Ahmed Saleh Alattas

Diaa Salama AbdElminaam

Sentiment Analysis of Product Reviews Using Transformer Enhanced 1D-CNN and BiLSTM

使用Transformer增强的1D-CNN和BiLSTM进行产品评论情感分析

短名	Cybern. Inf. Technol.
Journal Impact	1.27
国际分区	COMPUTER SCIENCE, INFORMATION SYSTEMS(Q4)

ISSN	1311-9702, 1314-4081
h-index	24

涉及主题	计算机科学数学人工智能工程类操作系统程序设计语言物理经济哲学生物机器学习算法统计量子力学计算机网络语言学政治学法学数据挖掘计算机安全计算机视觉管理地理
出版信息	出版商: Institute of Information and Communication Technologies, Bulgarian Academy of Sciences，出版周期: ，期刊类型: journal，开源期刊: 否
基本数据	创刊年份: 2011，原创研究文献占比: 100.00%，自引率:41.70%， Gold OA占比: 100.00%
平均审稿周期	网友分享经验：12 Weeks

Cybernetics and Information Technologies

期刊引文格式

有 1 位以上作者的期刊

有 2 位作者的期刊

有 3 位作者的期刊

有 5 位以上作者的期刊

书籍引用格式

学位论文引用格式

网页引用格式

专利引用格式

手工熬夜修改参考文献？研飞自动匹配期刊，一键轻松成稿，支持 Word/WPS

投稿经验分享