The pace of information technology growth in the modern day is so rapid that financial fraud has now spread to renewable technologies. The only approach to guarantee future financial security is to invest. However, the vast array of investment options—including stocks, gold, and other investments—often makes it difficult for people to make the best decision. Many millennials are still apprehensive about investing. This results from a lack of understanding about effective investing. A machine learning information system is necessary to assist in the selection of investment products in order to boost the community's and millennials' interest in investing. The Markowitz and K-Nearest Neighbor algorithms were used in the system's construction. Finding recommendations for investment portfolios that match the risk profile can be aided using the K-Nearest Neighbor approach, which is a machine learning technique. Based on a comparison of the sharpe ratio findings from system calculations and manual calculations, the accuracy level of the Markowitz and KNN approaches, which was set at 99.15%, was established.
Electronic products are goods that are really needed at this time, because electronic goods really help humans in carrying out various daily activities, such as television, computers, cellphones, etc. The problem is how to apply the Fuzzy C-means method with Optimize Parameter Grid in the form of grouping electronic goods data for the needs of consumers used, and how to determine the optimum number of clusters from the use of the method used in grouping electronic goods data sets to find the best accuracy value. The purpose of this study was to apply the use of the fuzzy c-means algorithm in the case of grouping electronic data and produce an output to find out the best value of the electronic data used. While this research uses one method, namely the fuzzy cmeans algorithm with Optimize grid parameters which are included in the grouping rules in data mining. The research results are expected to be able to find the best electronic data set grouping based on the Davies Bouldin Index value resulting from the analysis of the fuzzy c-means algorithm at measure_type : NumericalMeasure, Dbi = 0.516 and measure_type : MixedMeasure, Dbi = 0.627.
Betta fish are one of the favorite ornamental fish which is much loved because of its beauty. This is the reason why so many people want to cultivate it. During the cultivation period, farmers are often negligent in providing fish with a feeding schedule. Quite a few cultivators also pay less attention to dosage, feed size, temperature and pH levels when feeding baby betta fish, which results in waste and neglect of the environmental health of cultivation ponds. Controlling the correct dosage, size and feeding schedule according to the age of the baby fish, temperature and water pH will be able to increase the success of cultivation. Controlling the dosage, size and schedule of feed can actually be done automatically with the realization of IoT devices. This device was built through co-create, ideate, Q&A IoT OSI, and prototype so that this device can run well. This device uses an Arduino Uno R3 SMD as a microcontroller, a DS18B20 sensor as a temperature sensor, and a pH sensor connected to a servo motor to control the feed dispenser. The Arduino Uno R3 was chosen because of its wide compatibility with various sensors as well as the flexibility to write our own program code. Water temperature and pH sensors are used to monitor environmental conditions in real-time which will be used to make intelligent decisions regarding feeding. This device will put food into the pond according to the schedule, dosage and size of the food based on the water temperature and pH conditions. As a monitoring screen, thingspeak is used as a dashboard which can be accessed online via a web browser. Based on several experiments carried out, this IoT device is able to provide good feed dosage accuracy according to the needs of young fish, making it easier for farmers to care for fish without their physical presence. This research contributes to the development of IoT in the context of fish farming which can increase the success of cultivation and the welfare of farmers.
Multimedia-based learning media is one of the essential tools in supporting the learning process, especially for early childhood education, such as children aged 4-6 years old. The issue with conventional teaching methods is the lack of visualization during material delivery, which hinders the effectiveness of the teaching and learning process. This leads to a decrease in children's interest and a sense of boredom during the learning process. The utilization of multimedia-based literacy learning media in the teaching and learning process can greatly assist in delivering educational materials in a more engaging and interactive manner. This is because multimedia-based learning media is equipped with features such as images, sound, text, and animations that enhance children's learning experiences in understanding the subject matter. Furthermore, multimedia-based learning media can also help reduce boredom levels among children during the teaching and learning process. This is because children are more likely to engage and stay focused on the learning process when they use interesting and interactive media. The development method of multimedia drills and practice used by the author in creating multimedia-based literacy learning media is highly effective. This method allows children to practice and review the subject matter repeatedly until they truly understand and master it. Overall, the utilization of multimedia-based learning media in literacy education can provide numerous benefits for children aged 4-6 years old. This media can enhance children's learning experiences in understanding educational materials, expedite the learning process, and help reduce boredom levels among children during the learning process. Therefore, it is essential for educators to leverage multimedia-based learning media as a tool to enhance the quality of education for early childhood learners.
The swarm intelligence optimization algorithm has strong adaptability to optimization problems, fast computational speed, and the ability to quickly find the optimal solution, demonstrating a momentum of rapid development. As a type of swarm intelligence optimization algorithm, artificial bee colony algorithm obtains the optimal solution through the cyclic foraging and iteration of hired bees, observation bees, and reconnaissance bees, and has now been widely applied in various fields, But the artificial bee colony algorithm has the shortcomings of slow Rate of convergence and easy to fall into the local optimal solution. To overcome these shortcomings, this paper proposes an artificial bee colony algorithm based on the quantum Bloch spherical optimization mechanism. The effectiveness of the algorithm is proved through six benchmark test functions. The experimental results of the convergence curve graph can show that the Rate of convergence is greatly accelerated, and the global optimal solution can be obtained quickly.
