18 June 2025 in IEEE Access
Traffic flow prediction is critical for Intelligent Transportation Systems to alleviate congestion and optimize traffic management. The existing basic Encoder-Decoder Transformer model for multi-step prediction requires high computational complexity, making them less efficient for real-time applications. Therefore, this paper presents an Encoder-Only Transformer that eliminates the decoder component while evaluating the model’s ability to capture long-term spatial-temporal dependencies. This simplification was found to reduce computational overhead while maintaining a reasonable predictive accuracy comparable to the basic Encoder-Decoder Transformer and Long Short-Term Memory (LSTM) models. Experimental evaluations on two real-world datasets, Minnesota and California, for hourly prediction of 6, 12, and 24-hour horizon tasks, demonstrate the proposed model’s effectiveness. The proposed Encoder-Only Transformer outperforms LSTM networks across all horizons task for the Minnesota dataset, achieving up to 17.33% improvement in Mean Absolute Error. The proposed model excels in 24-hour horizon task for the California dataset but underperforms for shorter horizons compared to the LSTM and basic Encoder-Decoder Transformer models. These findings highlight the Encoder-Only Transformer’s application for multi-step traffic flow prediction while emphasizing dataset-specific variations in model performance.
31 October 2014 in Applied Mechanics and Materials
Product disassembly is a vital strategy for industrial recycling and remanufacturing which generates the desired parts and/or subassemblies by means of separation of a product into its elements. In order to increase disassembly capacity while maintaining the parts quality, new standards had to be established. Manual disassembly work perform by human will create inconsistency in the quality, efficiency, as well as time consuming, whereby it is believe that those weaknesses can be overcome by an automated performance. Therefore, this research work will re-evaluate the existing approach of disassembly process; reverse-assembly method in disassemble a mini toy car. The design methodology is conducted to verify the disassembly process performance and identify factors affecting the performance. The disassembly process experiment will be conducted in two ways; manual and semi-automated disassembly. This paper reviews the design process of the proposed experimental methodology. The important components of the experimental methodology are discussed in this paper.
6 October 2021 in Journal of Advanced Research in Fluid Mechanics and Thermal Sciences
Thermal energy transfer (TET) is the main performance of contact interfaces which has been studied at a molecular level. Several investigations on TET were accomplished, however, the influences of liquid film thickness on TET have not been sufficiently examined. Thus, this paper analyses the influences of liquid film thickness on TET across solid–liquid (S-L) interfaces. Two liquid film thicknesses (Lz) of 30 Å and 60 Å have been evaluated, and two shear directions (x- and y-directions) have been tested in the simulation system. It has been found that there is no significant difference in the density distribution of liquid regardless of the shear directions for the same Lz. However, there are differences in the density distribution of liquid between Lz of 30 Å and 60 Å. Based on the results its suggests that, the cut-off of the temperature and velocity at the contact interfaces of solid and liquid is substantially influences by the liquid thickness of the simulation system. It is found that, there are a significant different in the thermal boundary resistance (TBR) for Lz of 30 Å and 60 Å for cases liquid sheared in the x-direction. Whereas TBR for Lz of 30 Å and 60 Å sheared in the y-direction have no significant difference. In conclusion, the TET is affected by the velocity cut-off at the contact interfaces of solid and liquid where larger velocity discontinuity exhibits higher TBR.
18 May 2015 in Applied Mechanics and Materials
MRMuhamad Arfauz A. Rahman
+1
This paper presents the development of the system identification (SI) for the highly nonlinear piezoelectric patch actuator. The transfer function is determined by using the nonlinear least square (NLS) method after the direct measurements of input-output data are taken from the actuator that is installed on a well-equipped platform. The results were validated to ensure that the transfer function derived fits well with the experimental output.