In recent years, all attention has been directed to the mobile robots (MRs) which are becoming increasingly popular across different sectors. They are used to assist work processes and accomplish tasks that are impossible or dangerous for human workers such as earthquakes, floods, active volcanos, or nuclear disasters. MRs have many applications in different fields such as commercial, recreational, agricultural sectors, hospital, policing, welding, surveillance, product deliveries, and aerial photography. The MR encounters difficult circumstances in its complex environment which may have a high density of obstacles, either static or dynamic or both, erratic sensor data, numerous robots doing distinct duties, and unpredictability conditions. These challenging conditions limit its capacity to choose the most appropriate path. Technology for MRs has advanced more lately, and a variety of autonomous navigation algorithms have made it possible for these MRs to navigate in dynamic and complex environments. This study aims to present a thorough and current review of the autonomous mobility of MRs which enable safe and effective navigation with a single or multi-robot. Furthermore, it provides a review for various automatic AI techniques for getting the optimal path planning for the MRs. A systematic analysis demonstrates the contributions and limitations of each technique to show the effectiveness of the presented work. Accordingly, this paper offers valuable guidance and reference for further investigations to enhance the autonomy of MRs.
Artificial Intelligence (AI) applications involved in all human- life activies. AI applications should be used in repetitive activities like inventory and supplies however many people use the AI applications in creative and human cantered actions. Many previous researchers discussed the importance of using AI in different fields like Education, supply chain, marketing, medical and engineering. Limited research focuses on using AI applications like ChatGPT in creating academic articles through idea creation, writing, proofreading, collecting data and analysing. It is very interesting to understand the academics opinions in using ChatGPT not only in learning and education but also in creating academic articles and whether ChatGPT can increase the productivity of the writing and help academics who are involved in many other tasks like teaching, examining, preparing curriculums, assisting projects and managing quality procedures. The paper will propose Academics Emotion Analysis Model that will analyse the sentiments of academics whether they agree to use ChatGPT in writing articles or not. Word2vec and Term Frequency Inverse Document Frequency (TFIDF) and word2vec feature selection methods will be used and three machine learning techniques which are Naive Bayes (NB), Support Vector Machine (SVM) and Decision Tree (DT) on 17,000 sentiments. Academics emotion analysis model will start with the processing academics sentiments and using feature selection method then will use three-machine learning. Results including precision, recall and accuracy of all these classifiers will be described in this paper with a highest accuracy equivalent to 94
Automated traffic monitoring is an essential system in our daily life offering numerous benefits. It helps drivers stay aware of their speed, reducing the risk of accidents and saving lives, while also aiding law enforcement in effectively regulating traffic. The goal of this research aims to compare the evaluation of the car detection while estimating the speed of both Haar Cascade and Yolov8 methods. Experimental results demonstrated that our proposed one outperformed with the accuracy MAE is about 0.77, along with the precision 93
Customer churn prediction is one of the most critical problems an e-commerce firm faces, particularly in the B2C segment, due to increasing customer acquisition cost. In this regard, the paper proposes a novelty churn prediction model using XGBoost as a supervised learning technique based on the gradient boosting algorithm to find out who all the potential customers that can be identified as churning and strategies can be provided to retain them. A model uses the myriad amount of customer data created at e-commerce businesses, such as searches, purchases, reviews, and comments, to analyse customer behaviour in searching for potential opportunities of attrition. For execution speed and performance of the model, XGBoost will be used, which allows big datasets to be processed without restriction. The proposed algorithm creates a series of models and then combines them into an overall model which is better than the individual model in the sequence. The performance of the proposed model looks very promising in comparison with other models of churn prediction based on accuracy and Kappa metrics. Concerning this, an accuracy rate of 97.80
Global Routing (GR) is a critical step in the VLSI design process. With the ever increasing number of components on a single chip, there is great need of better routing algorithms to produce efficient, congestion free routing. We propose a hybrid Biogeography-based Optimization (BBO)/Maze Routing (MR) algorithm which focuses on producing zero overflow routing solutions. MR is used to generate initial routing of all nets and then a novel BBO based routing algorithm is used to iteratively perform the Rip-up and Reroute (R R) of congested nets. Lower and upper bounds on the 3D wirelength were computed using the 2-D routing solution generated by the proposed algorithm. The performance of the proposed router was evaluated on ISPD 2007 benchmarks and the results were found to be comparable with some of the state-of-the-art academic global routers and considerably less total overflow was achieved.
