The increasing misuse of drones poses significant safety and security risks, including illegal transportation of prohibited goods, interference with manned aircraft, and threats to public safety. This has raised concerns about the increased use of unmanned aerial vehicles (UAVs) due to their small size. Addressing these concerns has sparked significant research into developing effective drone detection systems. Deep learning, especially YOLO, is known as a lightweight model that offers real-time detection capabilities. Attention mechanisms have proven effective in many studies for detecting objects. This research focused on optimizing the YOLOv8n-based model by incorporating the Attention Module into the neck and improving the detection head by adding a tiny detection head, making the model work efficiently in detecting objects of tiny size. To obtain the most effective model, multiple training sets have been experimented with involving different types of attention modules, such as the Convolutional Block Attention Module (CBAM), ResBlock CBAM, Global Attention Mechanism (GAM), and Efficient Channel Attention (ECA). Therefore, based on the results, YOLOv8n + ResCBAM + high-resolution detection head, called P2-YOLOv8n-ResCBAM significantly improves the mean Average Accuracy (mAP) from 90.3% to 92.6%. Although the increased model complexity reduced frames per second (fps) from 263 to 166, the detection speed remains suitable for real-time applications. The proposed model effectively distinguishes drones from birds and recognizes them at long distances, demonstrating its potential for enhancing aerial surveillance and security measures.

The aquaculture industry has witnessed significant global growth, offering opportunities for sustainable fish production. This research delves into the application of data analytics to develop an appropriate predictive model, utilizing diverse machine learning and statistical techniques, to forecast marine fish production within Brunei Darussalam's aquaculture sector. Employing a machine learning-based algorithm, the study aims to achieve enhanced prediction accuracy, thereby providing novel insights into fish production dynamics. The primary objective of this research is to equip the industry with alternative decision-making tools, leveraging predictive modeling, to identify trends and bolster strategic planning in farm activities, ultimately optimizing marine fish aquaculture production in Brunei. The study employs various time series and machine learning techniques to generate a precise predictive model, effectively capturing the inherent seasonal and trend patterns within the time-series data. To construct the model, the research incorporates notable algorithms, including autoregressive integrated moving average (ARIMA), long short-term memory (LSTM), linear regression, random forest, multilayer perceptron (MLP), and Prophet, in conjunction with correlation analysis. Evaluation of the model's performance and selection of the optimal forecasting model are based on mean absolute percentage error (MAPE) and root mean squared error (RMSE) metrics, ensuring a robust analysis of time series data. Notably, this pioneering research stands as the first-ever attempt to forecast marine fish production in Brunei Darussalam, setting a benchmark unmatched by any existing baseline studies conducted in other countries. The experiment's results reveal that straightforward machine learning and statistical techniques, such as ARIMA, linear regression, and random forest, outperform deep learning methods like MLP and LSTM when forecasting univariate time series datasets.

This paper reports on our experiences with combining Heart of Gold and Language Grid technology to provide more language resources available on Web. Heart of Gold is known as middleware architecture for integrating deep and shallow natural language processing components. The language grid is an infrastructure built on top of the Internet to provide distributed language services. Having Heart of Gold available as Web services in the language grid environment would contribute to interoperability among language services.

The COVID-19 pandemic has affected day-to-day activities. Some families experienced a positive impact, such as an increase of bonding between family members. However, there are families that experienced a negative effect, such as the emergence of various conflicts that lead to a divorce. Based on the literature, it can be stated that the COVID-19 pandemic contributed to the increasing number of divorce rates. This paper proposes a convolutional neural network (CNN) classification algorithm in determining the dominant causes of the increase in divorce rate during the COVID-19 pandemic. CNN is considered suitable for classifying large amounts of data. The data used as research materials are available on the official website of the Indonesian Supreme Court. This research utilizes Supreme Court divorce decisions from March 2020 to July 2021, which constitutes 15,997 datasets. The proposed number of layers implemented during the classification is four. The results indicate that the classification using CNN is able to provide an accuracy value of 96% at the 100^th epoch. To provide a baseline comparison, the classical support vector machine (SVM) method was performed. The result confirms that CNN outweighs SVM. It is expected that the results will help any parties to provide a suitable anticipation based on the classified dominant causes of the divorce during the COVID-19 pandemic.

In e-Science, many scientific workflow management systems have been developed to integrate distributed computation resources, data sets, and mining algorithms. Users usually modify and rerun a workflow while repeating procedures: preprocess of data, selection of features, modification of data, selection of mining algorithms, generation of models, and evaluation of the models. These procedures are continued until the domain knowledge is acquired. However, as the size of the data increases, the execution time of the workflow becomes longer and longer, which drives up the cost of rerunning the modified workflow. As a result, it becomes hard to quickly obtain the analysis result. In this research, we avoided the rerun of the workflow by storing service invocation results on a platform and realized data-centered service composition by adding and deleting rules to be fired. To validate the effectiveness of our proposed platform, we created two rule-based services to analyze real-time data: stream message data and sensing data.