The Wingsuit Flying Search (WFS) algorithm is a newly developed global meta-heuristic algorithm. It is efficient and easy to implement, requiring no parameter tuning apart from the population size and the maximum number of iterations. Recently, WFS has been developed based on applying t-way strategies, where t represents the interaction strength. Despite the encouraging results, WFS's search strategy leans more toward local optima due to the narrowing of the boundary search space and the increased value of the search sharpness. Hybridising two or more algorithms enhances search performance by effectively balancing the strengths and mitigating the weaknesses of each method. Thus, this paper proposes a new hybrid Lévy Flight with Wingsuit Flying Search (WFS) algorithm called Enhanced Wingsuit Flying Search Algorithm (EWFS). EWFS uses a control mechanism to identify the best dynamic solution during runtime. The Lévy Flight motion helps the solution escape from local optima and improves the searching process when it gets stuck. Comparison between EWFS and WFS uses the benchmarking configuration of CA(N; 2, 5⁷), while the comparison with other metaheuristic algorithms is based on the following covering array configurations: CA(N; t, 3p), CA(N; t, v7), CA(N; 2, 2p), and CA(N; t, 210). The experimental result shows that EWFS is statistically better regarding test suite size reduction than the recent t-way strategies. It also offers improved results of 65% over the original WFS and resolves the issues of excessive exploitation and getting stuck in local minima or maxima.

Power system is considered one of the most complicated infrastructures. The main components of the system are generation, transmission and distribution. The main function of the system is to supply consumers with electricity as economically and reliably as possible. In order to provide uninterrupted power supply to the consumers, the reliability of distribution system needs to be improved. Several strategies are in place in order to enhance the reliability of the distribution networks. The distribution system could encounter the challenges of aging infrastructure, environmental factors, and the rising in demand power which can cause frequent power interruptions. This paper aims to enhance the reliability of distribution networks by utilizing network reconfiguration techniques to improve voltage profiles, reduce power losses, and restore power to interrupt sections as quickly as possible in the event of a failure. Additionally, the study incorporates the use of fault passage indicator devices installed along the lines. These devices are intended to swiftly identify fault locations, thereby minimizing outage durations and further improving network reliability. An investment in these measures, can obtain significant reliability improvements in the network which at the end lead to consumer satisfaction and huge economic advantages for the system operator.

Plant diseases are a serious problem in agriculture that affects both the quantity and quality of the harvest. To address this issue, authors developed a mobile software capable of detecting diseases in plants by analyzing their leaves using a smartphone camera. This research used the Convolutional Neural Networks (CNN) method for this purpose. In the initial experiments, authors compared the performance of four deep learning architectures: VGG-19, Xception, ResNet-50, and InceptionV3. Based on the results of the experiments, authors decided to use the CNN Xception as it yielded good performance. However, the CNN algorithm does not attain its maximum potential when using default parameters. Hence, authors goal is to enhance its performance by implementing parameter optimization using the grid search algorithm to determine the optimal combination of learning rate and epoch values. The experimental results demonstrated that the implementation of parameter optimization in CNN significantly improved accuracy in potato plants from 96.3% to 97.9% and in maize plants from 87.6% to 93.4%.

When the COVID-19 pandemic hit, the use of vaccines was advertised as the end of the pandemic by the entire world. However, the chances of vaccination depended on the sentiments of society and individuals about the vaccine. People's acceptance of vaccines can change depending on conditions and events. Social media platforms such as Twitter can be used as a source of information to find out the conditions and attitudes of the community toward the program. By implementing a machine learning technique on the COVID-19 vaccine dataset, we hope to impact the classification result with text. This study suggests three distinct machine learning models for classifying texts of the COVID-19 vaccination, namely a model based on the first lexicon using the feature extraction method; second, using the word insertion technique to utilize distribution representation; and third, a combination model of distribution representation and feature extraction based on the lexicon. From the evaluation that has been carried out, we found that a combination of lexicon-based and distributional representation methods succeeded in giving the best results for classifying the level of acceptance of the COVID-19 vaccine in Indonesia with an accuracy score of 71.44% and an F1-score of 71.43%.

Drum transcription is the task of transcribing audio or music into drum notation. Drum notation is helpful to help drummers as instruction in playing drums and could also be useful for students to learn about drum music theories. Unfortunately, transcribing music is not an easy task. A good transcription can usually be obtained only by an experienced musician. On the other side, musical notation is beneficial not only for professionals but also for amateurs. This study develops an Automatic Drum Transcription (ADT) application using the segment and classify method with Deep Learning as the classification method. The segment and classify method is divided into two steps. First, the segmentation step achieved a score of 76.14% in macro F1 after doing a grid search to tune the parameters. Second, the spectrogram feature is extracted on the detected onsets as the input for the classification models. The models are evaluated using the multi-objective optimization (MOO) of macro F1 score and time consumption for prediction. The result shows that the LSTM model outperformed the other models with MOO scores of 77.42%, 86.97%, and 82.87% on MDB Drums, IDMT-SMT Drums, and combined datasets, respectively. The model is then used in the ADT application. The application is built using the FastAPI framework, which delivers the transcription result as a drum tab.

In human-robot interaction, human mental states in dialogue have attracted attention to human-friendly robots that support educational use. Although estimating mental states using speech and visual information has been conducted, it is still challenging to estimate mental states more precisely in the educational scene. In this paper, we proposed a method to estimate human mental state based on participants’ eye gaze and head movement information. Estimated participants’ confidence levels in their answers to the miscellaneous knowledge question as a human mental state. The participants’ non-verbal information, such as eye gaze and head movements during dialog with a robot, were collected in our experiment using an eye-tracking device. Then we collect participants’ confidence levels and analyze the relationship between human mental state and non-verbal information. Furthermore, we also applied a machine learning technique to estimate participants’ confidence levels from extracted features of gaze and head movement information. As a result, the performance of a machine learning technique using gaze and head movements information achieved over 80 % accuracy in estimating confidence levels. Our research provides insight into developing a human-friendly robot considering human mental states in the dialogue.

One of the most commonly faced tasks in industrial robots is bin picking. Much work has been done in this related topic is about grasping and picking an object from the piled bin but ignoring the recognition step in their pipeline. In this paper, a recognition pipeline for industrial bin picking is proposed. Begin with obtaining point cloud data from different manner of stacking objects there are well separated, well piled, and arbitrary piled. Then followed by segmentation using Density-based Spatial Clustering Application with Noise (DBSCAN) to obtain individual object data. The systems then use Convolutional Neural Network (CNN) that consume raw point cloud data. Performance of the segmentation reaches an impressive result in separating objects and network is evaluated under the varying style of stacking objects and give the result with average Accuracy, Recall, Precision, and F1-Score on 98.72%, 95.45%, 99.39%, and 97.33% respectively. Then the obtained model can be used for multiple objects recognition in one scene.

A steam turbine is the most critical component in a thermal power plant. Due to its crucial function, it should be maintained to be able to operate without failure. This paper aims to develop an application that can be used to analyze the reliability and synchronization of vibrations in a single evaluation through the application. The application is helpful to decide the proper time the maintenance should be performed in order to provide a better maintenance strategy. In this paper, the application was used to make an ease in evaluating the reliability and vibration of a 670 MW power plant steam turbine. The reliability was analyzed by qualitative and quantitative methods. The vibration evaluation using Fast Fourier Transform (FFT) was done by diagnosing the failure symptoms from vibration spectrum. The analysis of synchronization of vibrations conducted by comparing the vibration frequency and the natural frequency of the system which can be calculated easily using the application. The algorithm program of both evaluations was built using GNU Octave software to make a friendly user interface. From the evaluation result, the most critical components of the steam turbine are coupling, labyrinth seals, bearing, diaphragm, turbine control valve, and turbine stop valve. The maintenance interval based on the expected reliability of 90% produces the highest reliability improvement. Based on the vibration analysis, there is no failure symptoms detected in the turbine bearings. Furthermore, the dominant frequencies of vibration are distant from the natural frequency. Therefore, the steam turbine condition is acceptable to operate.

Students have different learning styles when studying online. Meanwhile, lecturers use the same method for all students who take their online lectures. These different learning styles can affect the level of understanding and the results obtained by students. By knowing student learning styles, lecturers are expected to be able to use the right way in delivering material. In this research, we developed a student behavior analysis feature on self-developed Virtual Learning Environment (VLE) called Enterprise Hybrid Online Learning (ETHOL). Students’ data collected includes data on online activities, personal data, and survey data on student learning styles. User behavior analysis was carried out by dividing into three clusters: average scores, time to collect assignments, and student learning styles. The clustering method used is the Hierarchical K-Means. The results obtained are students who have the habit of collecting assignments on time have higher scores than others. In addition, the lecturer is able to see the results of the analysis of the behavior and learning styles of each student. These results can be used as information in delivering lecture material.