Malaysians generate 15,000 tons of food waste per day and dispose of it in the landfill, contributing to greenhouse gas emissions. As a solution for the stated problem, this research aims to produce an excellent quality bokashi compost from household organic waste using a smart composting bin. The bokashi composting method is conducted, whereby banana peels are composted with three types of bokashi brans prepared using 12, 22, and 32 mL of EM-1 mother cultured. During the 14 days composting process, the smart composting bin collected the temperature, air humidity, and moisture content produced by the bokashi-composting process. With the ATmega328 microcontroller, these data were uploaded and synchronized to Google Sheet via WIFI. After the bokashi-composting process was completed, three of each bokashi compost and a control sample were buried in separate black soil for three weeks to determine each compost’s effectiveness. NPK values and the C/N ratio were analyzed on the soil compost. From the research, 12 mL of EM-1 shows the most effective ratio to the bokashi composting, as it resulted in a faster decomposition rate and has an optimum C/N ratio. Bokashi composting can help to reduce household food wastes. An optimum amount of the EM-1 used during the bokashi-composting process will produce good quality soil without contributing to environmental issues.

Drones are unmanned aerial vehicles that can be remotely operated to perform a variety of tasks. They have been used in search and rescue operations since the early 2000s and have proven to be invaluable tools for quickly locating missing persons in difficult terrain and environment. In certain cases, automated human detection on drone camera feed can help the responder to locate the victims more effectively. In this work, we propose the use of a deep learning method called You Only Look Once version 5, or YOLOv5. The YOLOv5 model is trained using data collected during a simulation of search and rescue operations, where mannequins were used to represent human victims. Video was acquired using DJI Matrice 300 drone with Zenmuse H20T camera which flew around an area with various terrains such as farms, ravines, and river of more than 15,000 m2, at a height of 40 meters. The drone used grid, circular and zigzag flying patterns, with three different levels of camera zooms, and the data was captured on different days and times. The total duration of the video collected at 1080p@30fps is 148 minutes 26 seconds. Five pretrained models of YOLOv5 with different complexities were trained and tested using this dataset. Results showed that pretrained yolov5l6 model delivered the best precision, recall and mAP50 rate at 0.668, 0.303 and 0.346 respectively. Besides, the experiment also showed that we can improve the overall performance by using images acquired at 6x zoom magnification level where precision, recall, and mAP50 rate are increased to 0.846, 0.543, and 0.591 respectively. yolov5l6 model also delivered an acceptable inference time of 43ms per 1920x1080 resolution image, thus it can run at a respectable 23fps.

Water quality is one of the most highly debated issues worldwide at the moment. Inadequate water supplies affect human health, hinder food production, and degrade the environment. Using contemporary technology to analyze pollution statistics can help solve pollution issues. One option is to take advantage of advancements in intelligent data processing to conduct hydrological parameter analysis. To perform conclusive water quality studies, a lot of data is necessary. Unfilled data (information gaps) in the long-term hydrological data set may be due to equipment faults, collection schedule delays, or the data collection officer’s absence. The lack of hydrological data skews its interpretation. Therefore, interpolation is used to recreate and fill missing hydrological data. From 2012 to 2017, the Klang River’s biochemical oxygen demand (BOD) in Selangor, Malaysia, was sampled. This study examined three methods of interpolation for their effectiveness using the MATLAB software: piecewise cubic hermite interpolating polynomial (PCHIP), cubic Spline data interpolation (Spline), and modified Akima partitioned cubic hermite interpolation (Makima). The accuracy is assessed using root mean square error (RMSE). All interpolation algorithms offer excellent results with low RMSE. However, PCHIP delivers the best match between interpolated and original data.

Autonomous quadrocopter recently has shown a significant usages and potentials to be used widely in the commercial market. This caused the aircraft to become a well-liked subject among the researchers and research organizations. With good controllability and stability on its motions will make the usability of the quadrocopter to perform a task reliably. For this to happen, clean signals from accelerometer and gyroscope sensors appreciably play an essential role. However, the sensor's signals are routinely encounter problems with noise and drift. Hence, a filter is required to correct this imperfectness. In this paper, a simplified algorithm for Kalman's filter appropriates to be used by a low-cost microcontroller is presented. The research mainly focuses on filtering noisy outputs from the accelerometer so that the output is necessarily clean to be used for real-time quadrocopter pitch and roll angles estimation. Experimental results on assessment of the algorithm by varying the process and measurement noises are provided. The results reveal with correct tuning on the noise parameters; the filter algorithm is satisfying to give stable angles values with fine accuracy.

Telemedicine diabetes mellitus (Tele-DM) mobile health (mHealth) tool functionality, usefulness, and user feedback were examined in this study. Data from nine distinct users of type-2 diabetes (T2D) patients, healthcare professionals (HCPs), and administrators was analyzed to determine functionality. Data retrieval times increased with database user data amount, according to the study. A 3-month program with five T2D patients reduced weight (0.98 kg) and Hemoglobin A1c (HbA1c) (0.34%). This shows that Tele-DM helps manage diabetes, but more participants are needed to confirm. Nine Tele-DM customers were satisfied with the app's reception, according to 14 online questionnaires. Overall, Tele-DM simplifies diabetic self-management in a novel way. This study shows its potential to transform diabetes management and address major healthcare issues.

Water quality plays a major role in issues related to public health and marine life. Hence, monitoring river for contaminations is vital for ensuring safe and sustainable water resources. Conventional method for assessing water quality index is costly as it requires considerable amount of time and laboratory resources. Therefore, this study proposes a water quality index model based on artificial neural network. A six-year data for Air Busuk River is obtained from the Department of Environment. Dissolved oxygen, biological oxygen demand, and ammoniacal nitrogen has shown high correlation with water quality index. The water quality index model is then developed based on these parameters, employing the non-linear autoregressive with exogeneous input structure. Generally, the model which is based on three chemical parameters has shown satisfactory performance with overall regression of 0.8767 and passed the correlation function tests. The model offers a potentially efficient method for assessing water quality with cost-saving benefits for government agencies and monitoring authorities.