A5060039893- Metaheuristic Optimization Algorithms Research
- Evolutionary Algorithms and Applications
- Scheduling and Timetabling Solutions
- Vehicle Routing Optimization Methods
- Advanced Multi-Objective Optimization Algorithms
- Constraint Satisfaction and Optimization
- Optimization and Packing Problems
- Reinforcement Learning in Robotics
- Teaching and Learning Programming
- Advanced Manufacturing and Logistics Optimization
- Intelligent Tutoring Systems and Adaptive Learning
- Scheduling and Optimization Algorithms
- Machine Learning and Data Classification
- Neural Networks and Applications
- Viral Infectious Diseases and Gene Expression in Insects
- Artificial Intelligence in Games
- Robotic Path Planning Algorithms
- Smart Agriculture and AI
- Online Learning and Analytics
- Optimization and Search Problems
- AI-based Problem Solving and Planning
- Data Stream Mining Techniques
- Software Engineering Research
- AI in cancer detection
- Anomaly Detection Techniques and Applications
University of Pretoria
2017-2024
IEEE Computer Society
2023
Zimmer Biomet (United States)
2023
University of Nottingham
2020
University of KwaZulu-Natal
2010-2019
John Wiley & Sons (United Kingdom)
2017
Umkhuseli Innovation and Research Management
2007-2008
Abstract The use of genetic algorithms (GAs) to evolve neural network (NN) weights has risen in popularity recent years, particularly when used together with gradient descent as a mutation operator. However, crossover operators are often omitted from such GAs they seen being highly destructive and detrimental the performance GA. Designing that can effectively be applied NNs been an active area research success limited specific problem domains. focus this study is programming (GP)...
This paper defines a new combinatorial optimization problem, namely General Combinatorial Optimization Problem (GCOP), whose decision variables are set of parametric algorithmic components, i.e. algorithm design decisions. The solutions GCOP, compositions thus represent different generic search algorithms. objective GCOP is to find the optimal for solving given problems. Solving equivalent automatically designing best algorithms Despite recent advances, evolutionary computation and research...
Maize yields worldwide are limited by foliar diseases that could be fungal, oomycete, bacterial, or viral in origin. Correct disease identification is critical for farmers to apply the correct control measures, such as fungicide sprays. Deep learning has potential automated classification from images of leaf symptoms. We aimed develop a classifier identify gray spot (GLS) maize field where mixed were present (18,656 after augmentation). In this study, we compare deep models trained on with...
Novice programmers usually experience difficulties when programming for the first time. The main aim of study presented in this paper is to identify those characteristics that negatively effect procedural performance, so additional support can be provided instruction courses students possessing these characteristics. Investigations were conducted at two South African tertiary institutions. At both institutions a course Java programming, focussing on aspects, was used purposes study....
We present the progress on benchmarking project for high school timetabling that was introduced at PATAT 2008. In particular, we announce High School Timetabling Archive XHSTT-2011 with 21 instances from 8 countries and an evaluator capable of checking syntax evaluating solutions.
Metaheuristics have become a widely used approach for solving variety of practical problems. The literature is full diverse metaheuristics based on outstanding ideas and with proven excellent capabilities. Nonetheless, oftentimes claim novelty when they are just recombining elements from other methods. Hence, the need standard metaheuristic model vital to stop current frenetic tendency proposing methods chiefly their inspirational source. This work introduces first step generalised...
First year Computer Science students often encounter difficulties when learning to write procedural and object-oriented programs for the first time. This is also true of being exposed a new programming paradigm. One-on-one tutoring has proven be most effective means assisting time programmers overcome difficulties. However, due large class numbers funding constraints provision one-on-one not usually possible. Intelligent systems (ITSs) have successfully been used tutor novice on basis....
Artificial intelligence will play an imperative role in meeting the challenges posed by fourth industrial revolution. This paper discusses how artificial can be incorporated into engineering and computer science education to prepare for revolution South Africa. The firstly examines curriculum equip engineers scientists with necessary skills solve complex problems that bring. These range from online courses short certification taken practitioners, degrees data science. also used teaching...