2692-2967ISSN (Online)
2770-0216ISSN (Print)
Determining web services according to Quality of Service (QoS) restrictions is the topic of discussion in this section. Decision tree classifiers are used to accomplish this classification. Because of the ever-changing and expanding nature of online services, it is necessary to accurately categorize them in order to make choosing them more efficient for consumers. It makes use of decision tree techniques, more especially the C5.0 classifier, this is an advancement over older approaches such as the C4.5 classifiers. It incorporates characteristics like as noisy handling, incomplete information administration, and improved decision-making correctness. Web services are classified into four distinct groups: Outstanding, Good, Average, and Poor. These classifications are determined by QoS metrics that include time to response, accessibility, performance, dependability, and success rate. The choice of features is accomplished utilizing an evolutionary algorithm with a wrapper technique with the goal to maximize the effectiveness of this category. This method minimizes the number of repetitive features and improves the method of classification for the purpose of optimization. The resilience and predicted reliability of the algorithm are ensured by additional approaches like as cross-validation and error reduction. These approaches also address difficulties such as overfitting and redundant characteristics. The construction of integrated web services for complicated corporate operations is a particularly valuable use of this technology, which also considerably improves the procedure for making choices for identifying services and consumption. Service 7 stands out with an impressive 98% performance, while Service 6 and Service 3 are also among the top-performing services. Compared to the others, Service 1, Service 2, Service 5, and Service 4 all exhibit comparatively poor results.
Read MoreDoi: https://doi.org/10.54216/AJBOR.120201
Vol. 12 Issue. 2 PP. 01-14, (2025)
The suggested models for the spread of technical breakthroughs make use of a phase structure to illustrate the steps involved in becoming familiar with the problem and making a choice. For it to portray genuine adopting conduct, a time-lag factor is included into the dispersion process. Depicts a two-step dissemination process by taking into account the reliance of adopting on the informed group of potential purchasers. Assuming that a prospective customer first becomes intrigued by an upcoming the item's availability and then accepts the novel idea at an ulterior point, a method of analysis for sales functions that incorporates time delay is proposed. The efficient propagation method for invention is shown using the various lag factors. Applying nonlinear regression modelling to worldwide shipping data of Acer PCs and Samsung smartphones experimentally validates the suggested models for mathematics. Several comparison models are used to evaluate the predicting abilities of the suggested models. By integrating a distributed time delay function into the implementation manage, a theoretical intergenerational diffusion model is created. To measure how long it takes for innovation to be eventually accepted, the distributed time lag function that follows the Erlang distributions is used. This framework incorporates switch and substituting, two forms of pragmatist shift behaviour. Using real shipping data of LCD (Liquid Crystal Display) computer monitors from consecutive generations, the predicted effectiveness of the suggested methods is examined and contrasted with well-established research. Here is the total accuracy of the approaches that have been proposed: When contrasted with more conventional models, MGDM 1 achieves a 99.33% accuracy rate, MGDM 2 a 99.81% rate, and MGDM 3 a 99.91% accuracy rate.
Read MoreDoi: https://doi.org/10.54216/AJBOR.120202
Vol. 12 Issue. 2 PP. 15-31, (2025)
This paper presents a multi-server Markovian queuing-inventory system (MQIS) that incorporates attractionretention (AR) mechanisms for impatient customers and models catastrophic inventory losses within a warehouse setting. The system consists of C identical servers, a limited waiting area, and a storage capacity of Q items. Periodic disruptions may destroy all inventory in the system, compelling waiting customers either to remain until stock is replenished or to exit the system. A subset of servers may take joint vacations when no customers are waiting. To analyze this queuing-inventory system (QIS), we derive balance equations using a three-dimensional continuous-time Markov chain framework, solving for steady-state solutions through a recursive method. We then derive performance metrics and identify special-case queuing-inventory models within the broader system. A cost-loss model is formulated to optimize the service rate and server vacation strategies, minimizing overall costs. A genetic algorithm is employed to conduct a cost analysis. We collected primary data from the Ethio Telecom district head office in Arba Minch, Ethiopia to validate our theoretical findings. The empirical analysis serves a dual purpose: to investigate performance measure sensitivity to parameter variations and to discuss an optimization problem aimed at minimizing expected total cost (ETC) while assessing the impacts of AR mechanisms and catastrophic events on ETC.
Read MoreDoi: https://doi.org/10.54216/AJBOR.120203
Vol. 12 Issue. 2 PP. 32-51, (2025)