- Fractional Differential Equations Solutions
- Tactile and Sensory Interactions
- Interactive and Immersive Displays
- Caching and Content Delivery
- Color perception and design
- Metaheuristic Optimization Algorithms Research
- Online Learning and Analytics
- Data Visualization and Analytics
- IoT and Edge/Fog Computing
- Opportunistic and Delay-Tolerant Networks
- Context-Aware Activity Recognition Systems
- Cooperative Communication and Network Coding
- Safety Warnings and Signage
- Data Mining Algorithms and Applications
- Evolutionary Algorithms and Applications
- Impact of Technology on Adolescents
- Usability and User Interface Design
- Blockchain Technology Applications and Security
- Iterative Methods for Nonlinear Equations
- Water Quality Monitoring Technologies
- Indoor and Outdoor Localization Technologies
- Music Technology and Sound Studies
- IoT-based Smart Home Systems
- Advanced Clustering Algorithms Research
- Machine Learning in Bioinformatics
Universiti of Malaysia Sabah
2015-2024
Afe Babalola University
2024
Higher Colleges of Technology
2023
Federal University of Technology Minna
2022
University of Gujrat
2021
University of Malaya
2021
King Faisal University
2017
INTI International University
2013-2016
Mansoura University
2014
University of York
2006-2007
Metaheuristic algorithms have been widely used to solve diverse kinds of optimization problems. For an problem, population initialization plays a significant role in metaheuristic algorithms. These can influence the convergence find efficient optimal solution. Mainly, for recognizing importance diversity, several researchers worked on performance improvement Population is vital factor such as PSO and DE. Instead applying random distribution population, quasirandom sequences are more useful...
Ribonucleic acid Sequencing (RNA-Seq) analysis is particularly useful for obtaining insights into differentially expressed genes. However, it challenging because of its high-dimensional data. Such a tool with which to find underlying patterns in data, e.g., cancer specific biomarkers. In the past, analyses were performed on RNA-Seq data pertaining same class as positive and negative samples, i.e., without samples other types. To perform multiple type classification genes, types need be...
Healthcare, one of the most important industries, is data-oriented, but research in this industry focuses on incorporating internet things (IoT) or connecting medical equipment. Very few researchers are looking at data generated healthcare industry. Data very tools competitive world, as they can be integrated with artificial intelligence (AI) to promote sustainability. Healthcare include health records patients, drug-related data, clinical trials from various equipment, etc. Most management...
Facts can be exchanged in multiple fields with the help of disease-specific ontologies. A range diverse values produced by mining ontological approaches for demonstrating disease mechanisms. Alzheimer’s (AD) is an incurable neurological brain illness. An early diagnosis AD helpful better treatment and prevention tissue destruction. Researchers have used machine learning techniques to predict detection AD. However, disorders are still underexplored knowledge domain. In biomedical field,...
Challenges faced in network security have significantly steered the deployment timeline of Fifth Generation (5G) communication at a global level; therefore, research Sixth (6G) analysis is profoundly necessitated. The prerogative this paper to present survey on emerging 6G cellular paradigm highlight symmetry with legacy concepts along asymmetric innovative aspects such Artificial Intelligence (AI), Quantum Computing, Federated Learning, etc. We taxonomy threat model five concepts, including...
The aim of this study is to design a layer structure feed-forward artificial neural networks using the Morlet wavelet activation function for solving class pantograph differential Lane-Emden models. equation one important kind singular functional model. numerical solutions model are presented by approximation capability (MWNNs) accomplished with strength global and local search terminologies genetic algorithm (GA) interior-point (IPA), i.e., MWNN-GAIPA. Three different problems models have...
The aim of this study is to present the numerical solutions higher order singular nonlinear differential equations using an advanced intelligent computational approach by manipulating Morlet wavelet (MW) neural networks (NNs), global as genetic algorithm (GA) and quick local search interior-point method (IPM), i.e., GA-IPM. MWNNs applied discretize express activation function mean square error. performance designed GA-IPM observed solve three different variants based on model check...
Bat algorithm (BA) is an eminent meta-heuristic that has been widely used to solve diverse kinds of optimization problems. BA leverages the echolocation feature bats produced by imitating bats’ searching behavior. faces premature convergence due its local search capability. Instead using standard uniform walk, Torus walk viewed as a promising alternative improve In this work, we proposed improved variation applying torus diversity and convergence. The proposed. Modern Computerized Algorithm...
This review paper is based on Radio Frequency Identification (RFID) technology, Wireless Sensor Networks (WSNs) and wireless information & communication networks. RFID technology use for tags readers enclosed to shop-floor industrial stuffs such as operators, terminals, vessels, stocks Smart Home (SH) architecture that includes sensors, data integration. The system collect movement activities from the objects using technology. Passive can be deliver at a gap do not require Line of Sight...
The utmost advancements of artificial neural networks (ANNs), software-defined (SDNs) and internet things (IoT) technologies find beneficial in different applications the smart healthcare sector. Aiming at modern technology's use future development healthcare, this paper presents an advanced heuristic based on Morlet wavelet network for solving mosquito release ecosystem a heterogeneous atmosphere. is dependent six classes, eggs density, larvae pupae mosquitoes searching hosts resting...
Most Internet of Things (IoT) resources are exposed to security risks due their essential functionality. IoT devices, such as smartphones and tablets, have a limited network, computation, storage capacity, making them more vulnerable attacks. In addition, the huge volume data generated by devices remains an open challenge for existing platforms process, analyze, discover underlying trends create convenient environment. As result, deliver acceptable services, new solution is necessary secure...
Confidentiality and data integrity are essential paradigms in aggregation owing to the various cyberattacks wireless sensor networks (WSNs). This study proposes a novel technique named Lamport certificateless signcryption-based shift-invariant connectionist artificial deep neural (LCS-SICADNN) by using develop security model. model utilises input layer with several nodes, four hidden layers overcome different attacks (data injection, compromised node, Sybil black hole attacks) output analyse...
A Smart Home (SH) is a house or an apartment equipped with advanced automation technologies to provide the occupants intelligent monitoring and actionable information that can be situation specific. It allows for improvements in way we live work, improved energy efficiencies. The smart home especially relevant elderly because sensing systems would allow remote possibly control of health environmental parameters according their status living needs. burgeoning population rising costs...
In this work, a new heuristic computing design is presented with an artificial intelligence approach to exploit the models feed-forward (FF) Gudermannian neural networks (GNN) accomplished global search capability of genetic algorithms (GA) combined local convergence aptitude active-set method (ASM), i.e., FF-GNN-GAASM solve second kind Lane–Emden nonlinear singular (LE-NSM). The proposed based on intelligent kernel incorporated hidden layer configuration FF-GNN differential operatives...
In existing meta-heuristic algorithms, population initialization forms a huge part towards problem optimization. These calculations can impact variety and combination to locate productive ideal arrangement. Especially, for perceiving the significance of intermingling, different specialists have attempted improve presentation algorithms. Particle Swarm Optimization (PSO) algorithm is populace-based, shrewd stochastic inquiry strategy that motivated by inherent honey bee swarm food search...
Optimisation-based methods are enormously used in the field of data classification. Particle Swarm Optimization (PSO) is a metaheuristic algorithm based on swarm intelligence, widely to solve global optimisation problems throughout real world. The main problem PSO faces premature convergence due lack diversity, and it usually stuck local minima when dealing with complex real-world problems. In meta-heuristic algorithms, population initialisation an important factor affecting diversity speed....
To solve different kinds of optimization challenges, meta-heuristic algorithms have been extensively used. Population initialization plays a prominent role in for the problem optimization. These can affect convergence to identify robust optimum solution. investigate effectiveness diversity, many scholars focus on reliability and quality enhancement. initialize population search space, this dissertation proposes three new low discrepancy sequences instead uniform distribution called WELL...
This paper demonstrates a broad exploration of existing authentication and secure communication unmanned aerial vehicles (UAVs) in ‘6G network’. We begin with an overview surveys that deal UAV 6G beyond communications, standardization, applications security. In order to highlight the impact blockchain ‘UAV networks’ future systems, we categorize groups this review into two comprehensive groups. The first group, named Performance Group (PG), comprises performance-related needs on data rates,...
Scene recognition algorithm is crucial for landmark model development. Landmark one of the main modules in intelligent tour guide system architecture use smart tourism industry. However, recognizing tourist landmarks public places are challenging due to common structure and complexity scene objects such as building, monuments parks. Hence, this study proposes a super lightweight robust by using combination Convolutional Neural Network (CNN) Linear Discriminant Analysis (LDA) approaches. The...
Particle Swarm Optimization (PSO) has been widely used to solve various types of optimization problems. An efficient algorithm must have symmetry information between participating entities. Enhancing efficiency relative the symmetric concept is a critical challenge in field security. PSO also becomes trapped into local optima similarly other nature-inspired algorithms. The literature depicts that order pre-mature convergence for algorithms, researchers adopted parameters such as population...
Text summarization is a technique for shortening down or exacting long text document. It becomes critical when someone needs quick and accurate summary of very content. Manual can be expensive time-consuming. While summarizing, some important content, such as information, concepts, features the document, lost; therefore, retention ratio, which contains informative sentences, lost, if more information added, then lengthy texts produced, increasing compression ratio. Therefore, there tradeoff...
CSTR (Continuous stirred tank reactor) is employed in process control and chemical industries to improve response characteristics system efficiency. It has a highly nonlinear characteristic that includes complexities its design. Dynamic performance compassionate change parameters which need more effort for planning significant controller CSTR. The reactor temperature changes either direction from the defined reference value. important note intensity of actions inside dependent on various...
The task of analyzing and forecasting time-series data is very crucial as this Time Series Analysis (TSA) used for many applications such Economic Forecasting, Sales Budgetary Analysis, Stock Market Yield Projections, Process Quality Control, Inventory Studies, Workload Utility Census Network Monitoring more. techniques can be classified into two categories, namely statistical machine learning techniques. As a result, the selection several prediction methods will continue to an alternative...
Smart Home (SH) is a house or an apartment equipped with advanced automation technologies to provide the occupants intelligent monitoring and actionable information that can be situation specific. Recent research indicates population over age of 60 growing at alarming rate, which estimated by 2050 this particular group will have globally increased 50%. With such increase, sense eldercare being emphasized among nowadays undoubtedly promising solution problem. This paper involves SH...