Browsing by Author "Mahenge, Michael Pendo John"

Now showing 1 - 4 of 4

Adaptive cache server selection and resource allocation strategy in mobile edge computing
(International journal of information communication technologies and human development (ijicthd), 2023) Mahenge, Michael Pendo John; Kitindi, Edvin Jonathan
The enormous increase of data traffic generated by mobile devices emanate challenges for both internet service providers (ISP) and content service provider (CSP). The objective of this paper is to propose the cost-efficient design for content delivery that selects the best cache server to store repeatedly accessed contents. The proposed strategy considers both caching and transmission costs. To achieve the equilibrium of transmission cost and caching cost, a weighted cost model based on entropy-weighting- method (EWM) is proposed. Then, an adaptive cache server selection and resource allocation strategy based on deep-reinforcement-learning (DRL) is proposed to place the cache on best edge server closer to end-user. The proposed method reduces the cost of service delivery under the constraints of meeting server storage capacity constraints and deadlines. The simulation experiments show that the proposed strategy can effectively improve the cache-hit rate and reduce the cache-miss rate and content access costs.
Artificial intelligence and deep learning based Technologies for emerging disease recognition and pest Prediction in beans (phaseolus vulgaris l.): A systematic review
(African Journal of Agricultural Research, 2023) Mahenge, Michael Pendo John; Mkwazu, Hussein; Madege, Richard Raphael; Mwaipopo, Beatrice; Maro, Caroline
Artificial Intelligence (AI) and deep learning have the capacity to reduce losses in crop production, such as low crop yields, food insecurity, and the negative impacts on a country’s economy caused by crop infections. This study aims to find the knowledge and technological gaps associated with the application of AI-based technologies for plant disease detection and pest prediction at an early stage and recommend suitable curative measures. An evidence-based framework known as the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) methodology was used to conduct systematic reviews of the state-of-the-art of AI and deep learning techniques for crop disease identification and pest prediction in developing countries. The results demonstrate that conventional methods for plant disease management face some challenges, such as being costly in terms of labour, having low detection and prediction accuracy, and some are not environmentally friendly. Also, the rapid increase in data-intensive and computational-intensive tasks needed for plant disease classification using traditional machine learning methods poses challenges such as high processing time and storage capacity. Consequently, this paper recommends a deep learning and AI-based strategy to enhance the detection, prediction and prevention of crop diseases. These recommendations will be the starting point for future research.
Energy-efficient task offloading strategy in mobile edge computing for resource-intensive mobile applications
(Science Direct, 2022) Mahenge, Michael Pendo John; Li, Chunlin; Sanga, Camilius A
Mobile Edge Computing (MEC) has been considered a promising solution that can address capacity and perfor- mance challenges in legacy systems such as Mobile Cloud Computing (MCC). In particular, such challenges include intolerable delay, congestion in the core network, insufficient Quality of Experience (QoE), high cost of resource utility, such as energy and bandwidth. The aforementioned challenges originate from limited resources in mobile devices, the multi-hop connection between end-users and the cloud, high pressure from computation- intensive and delay-critical applications. Considering the limited resource setting at the MEC, improving the efficiency of task offloading in terms of both energy and delay in MEC applications is an important and urgent problem to be solved. In this paper, the key objective is to propose a task offloading scheme that minimizes the overall energy consumption along with satisfying capacity and delay requirements. Thus, we propose a MEC- assisted energy-efficient task offloading scheme that leverages the cooperative MEC framework. To achieve en- ergy efficiency, we propose a novel hybrid approach established based on Particle Swarm Optimization (PSO) and Grey Wolf Optimizer (GWO) to solve the optimization problem. The proposed approach considers efficient resource allocation such as sub-carriers, power, and bandwidth for offloading to guarantee minimum energy consumption. The simulation results demonstrate that the proposed strategy is computational-efficient compared to benchmark methods. Moreover, it improves energy utilization, energy gain, response delay, and offloading utility.
Mobile based system for electronic learning content delivery and accessibility: a case of higher education institutions in Tanzania
(Nelson Mandela African Institution of Science and Technology, 2014) Mahenge, Michael Pendo John
The advancement in Information and Communication Technology (ICT) has brought new opportunities for learning. Tanzania is adopting the new technologies in Higher Education Institutions (HEIs) through e-learning. However, delivery of learning contents is becoming a challenge for HEIs due to the constraints in resources and network bandwidth. Although challenges exist, development of innovative and emerging mobile computing technologies have brought potential opportunities for enhancements of learning contents delivery and accessibility. The objective of this study was to develop a mobile application based system for e-Iearning content delivery and accessibility as a solution to high bandwidth costs of the conventional Web application based system. The proposed system can synchronize contents from some original servers to local database in mobile devices for offline use. The study was conducted in HEIs in Tanzania. Survey methodology was used to identify and assess ICTs for e-learning and system design requirements. During the survey different methods including interview, structured questionnaire and review of empirical literatures were used. Quantitative data were analysed using Statistical Package for Social Sciences (SPSS) while qualitative data were analysed through content analysis. A prototype for Mobile-LCDS was developed using UML, MySQL. PHP, XML, ANDROID and Java; and tested using a black box testing technique. Findings show that 85% of students own laptop, 65% own smartphone and 78% own mobile phone. The results provide empirical evidence that students own more than one mobile devices that can be used as tools for facilitating learning process. However, the results provide empirical evidence that the rate of adoption of mobile phones for mobile-learning in Tanzania has reached 20.3% which is still low due to fact that even though e-learning systems exist, they are not fully operational. This is caused by poor ICT infrastructures, constraints in resources and bandwidth. The results of numerical evaluation revealed that synchronizing learning contents locally in mobile devices is significant for bandwidth usage cost savings, alleviates network overload, alleviates servers’ workload and hence improves e-learning system performance. In conclusion, in order to improve e-learning content delivery and accessibility under limited resource settings, HEIs in developing countries should make an effective use of emerging mobile computing technologies which are relevant to their respective environments.