In the rehabilitation process for patients with motor disabilities, measuring and identifying source location brain activity using multi-channel EEG is feedback information. In the study, a processing scheme was propo...
详细信息
Electrical Impedance Tomography or EIT is a tomography technique that can be used to determine the internal object by reconstructing the object's physical parameters in the boundary plane. EIT is widely applied in...
详细信息
The Human Activity Recognition (HAR) System endeavors to proficiently categorize input data acquired from sensors affixed to the human body, meticulously measuring movement and assigning it to specific activity catego...
The Human Activity Recognition (HAR) System endeavors to proficiently categorize input data acquired from sensors affixed to the human body, meticulously measuring movement and assigning it to specific activity categories. While traditional techniques have long struggled to capture the intricacies of HAR, especially in instances with subtle microactivity sequences, the integration of machine learning within the realm of Artificial Intelligence has proven itself adept at handling such complex data-related challenges. This article considers the utilization of machine learning techniques to enhance human activities by examining datasets for HAR classification on realtime applications. A carefully curated dataset is chosen as the primary input for the processes of training, testing, and evaluation, facilitated by sophisticated models that include Long Short-Term Memory (LSTM), 1D Convolution Neural Network (CNN) for time series data, 1D CNN for the frequency domain, and 2D Image CNN models. These models are meticulously scrutinized, with their performance metrics meticulously compared to determine the most suitable HAR model for the task at hand. Through comprehensive simulations, the results affirm the supremacy of the 1D CNN frequency domain model in terms of performance with 93.28% accuracy, meanwhile the LSTM model showing the best results in term of the computation cost with the lowest time/step of 0.505ms/step. This outcome underscores the potential of advanced machine learning techniques in revolutionizing the field of HAR, particularly when confronted with nuanced and intricate movement sequences.
Batik production in home industries needs support wastewater treatment in a limited space. Therefore, a modular-type, lab-scale wastewater treatment plant (WWTP) with a capacity of 87.75 liters and a dimension of 1.5 ...
详细信息
The Simple Network Management Protocol (SNMP) is a networking protocol used for the management and monitoring of all connected devices in internet standard protocol networks. Recently, the utilization and capability o...
The Simple Network Management Protocol (SNMP) is a networking protocol used for the management and monitoring of all connected devices in internet standard protocol networks. Recently, the utilization and capability of SNMP has been enhanced to be able to handle data exchange across a network from the control level to the human machine interface level. Some controllers, including micro-controllers, have upgraded their features and coverage to include SNMP in their communications protocol. The utilization of SNMP is also supported by Open Platform Communications (OPC) Server, which plays an important role as data exchange server for various controllers or systems with different gateways and drivers. This paper presents the performance assessment of SNMP implementation in a network, from controller to OPC server, comparing hardwired and wireless automation architectures. The results show that in both cases the round-trip times (RTT) of SNMP were acceptable according to network criteria, with an average of less than 100 ms. Hence, SNMP is suitable as an industrial automation protocol.
This study focuses on improving multiple drones' trajectory tracking accuracy and completion time in mapping assignments. A centralized control system is applied to drones to achieve such performance. The system t...
详细信息
ISBN:
(数字)9798350355314
ISBN:
(纸本)9798350355321
This study focuses on improving multiple drones' trajectory tracking accuracy and completion time in mapping assignments. A centralized control system is applied to drones to achieve such performance. The system tracking accuracy is supported by dense square fiducial markers (SFM) as positioning media. The drone's position is assumed to be at the camera's center, leading to more precise calculations. Detecting multiple markers also ensures that the drones do not lose positional information over long distances, resulting in more accurate position estimation. The test is conducted indoors with two drones, with trajectory tracking tests performed along the x-axis and y-axis within a
$5\times 4\ \mathrm{m}^{2}$
area. The test shows that the root means squared tracking error (RMSTE) when the drones moved along the positive x-axis was 5.2 cm, less than 20% of the drone's diameter. During the mapping assignment, the drones traced an S-shaped route and obtained RMSTE values of 12.3 cm for drone A and 22.5 cm for drone B, with a travel time of 51 seconds from takeoff to landing. Therefore, detecting multiple markers improves trajectory tracking capabilities, enabling drones to perform mapping tasks efficiently, even in confined areas.
Simple Network Management Protocol (SNMP) has moved from being used only as a tool to monitor a network to becoming one of the standard data communication protocols. SNMP is supported by Open Platform Communication (O...
详细信息
During the restoration of the hydropower system, it is necessary to maintain a frequency response at the set-point and the system can withstand interference from external inputs and noise measurements. In this paper, ...
详细信息
The Automatic Weather Station (AWS) is an automated instrument designed to gather meteorological parameters within a given environment. The dataset obtained from AWS often contains missing values due to various factor...
详细信息
To understand typical features that could be imaged using ultrasonography (USG) in the training phases of medical students or practitioners, a lung phantom is required. The research team suggests using a gelatine-base...
详细信息
暂无评论