Clustering algorithms are attracting much application interest due to the significant growth in the rate of data generation. However, the high computational complexity of the existing clustering algorithms has rendered them ineffective in several ways. Therefore, this study proposes a novel parallel clustering algorithm that integrates Multi-Agent Systems (MAS) with the K-means algorithm; hence, the proposed novel algorithm is termed Multi-agent-K-means (MK-means). The MK-means is based on the concept of separating the activating agents to perform clustering while considering a different subset of features for each agent. This is aimed at the preservation of the dataset while improving the clustering accuracy. The cluster centers are calculated for each partition before being merged and clustered again. The statistical significance of the proposed approach is provided. The effectiveness of the proposed MK-means clustering algorithm was evaluated using Wine datasets, and the performance is compared with that of the traditional K-means algorithm. The results analysis proved the superiority of the proposed MK-mean clustering algorithm over the traditional version of the K-means algorithm. This suggests the suitability of the proposed algorithm as a clustering technique that can also be applied to other clustering algorithms that are based on the concept of initial cluster centroids selection.
In this paper, we designed and implemented a washing machine based on fuzzy logic rules. The washing machine fuzzy logic system is based on detecting four input parameters The amount of dust (dirt), the kind of dust, the sensitivity of the material, and the number of garments are all factors to consider. The washing speed, washing time, hot water temperature, and amount of detergent are applied to the output based on the parameters entered. Applying a fuzzy logic rule makes it easier to get a cleaner cloth compared to the traditional method of manually adjusting the output parameters. In addition, applying fuzzy logic saves the amount of water, detergent and electricity, and finally saves time, which is a big factor, reducing process costs. This project aims to design and implement a washing marching system. As well as to study the effect of applying fuzzy logic rules in enhancing washing machine control system. And to apply the proposed project using the Matlab software as well. This investigation was simulated using the MATLAB/Fuzzy logic toolbox. Finally, practically mechanical and electronic engineering concepts should be used to implement this system.
Aptitude become one of major problem to determine the specialization in college, that sometimes make some individual to choose poorly and causing them to choose the wrong specialization that didn't match their aptitude, however the specialization can be observed and determined from early stage using the help of technology. One of the method that can be used is psychological test, psychological test is used for determine the individual psychological state that can be seen from non-physical aspect such as intelligence, intelligence have a major role on individual's Aptitude. Basically aptitude test that implemented today is still using the conventional way, however with the advances of technology the aptitude test can be done online and updated periodically. With the aptitude test hopefully scholars can understand more about their motivation and aptitude so that they can choose the specialization that match their motivation and aptitude. And with the motivation and aptitude test hopefully can reduce the tuition fee of the scholar. The system accuracy is 100% with the number of respondents as many as 62 people
Nowadays, everyone is required to check the body temperature and record personal details whenever he arrives at a different place. However, there are some problems when the actions are performed. Therefore, this paper proposed an Internet of Things (IoT)-based contactless body temperature scanning system. The software and hardware used in this study were Microsoft Visual Studio, ThingSpeak, Arduino IDE, Radio Frequency Identification (RFID), and contactless body temperature sensor. A parallel development model was used as the project management methodology. The proposed system was tested through system testing, user acceptance testing, and accuracy testing. Based on the testing results, the proposed system was successfully implemented and ready to be deployed. The average accuracy of the proposed system was 99.86% compared to a standard device.
In competing with various sources of news made available in the digital economy, newspaper companies need to look into proactive way to direct and drive readers in their search for news. Agent-mediated recommender system may sound common to the artificial intelligence world. However, this research paper proposes a deployment of software agents with certain roles and tasks, adopting the Detect-Determine-Direct Model for news website users, based on the user navigation behavior analysis. In this proposed conceptual framework, software agents are assigned with the tasks of identify, drive, decide and method, that are proven computable in earlier research. Taking into account the flexibility of users who may change their behavior once a recommendation is made, this conceptual design of recommender system is expected to be self-sustainable as it improves itself by learning new knowledge retrieved from the change in its environment to support the capacity of its knowledge repository.
