http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
오늘 본 자료
Beamforming in Vehicle to Infrastructure Scenario with Respect to LSTM and NAR Method
Bhadauria Prateek,Kumar Ravi,Sharma Sanjay 대한전기학회 2024 Journal of Electrical Engineering & Technology Vol.19 No.1
The application of deep learning for adaptive beamforming is a necessary and disruptive advancement in wireless communication technology. It has the potential to satisfy the continuous need for data trafc in a highly dense network created by the vehicle to infrastructure (V2I) scenario. Due to excessive usage of data in V2I scenario interference is a pertinent problem. It is essential to adaptively predict and nullify the interference for V2I scenarios. Practical V2I network implementation is limited because of the inevitability of interference due to the random nature of the wireless channel. This paper proposes an adaptive beamforming (ABF) technique for mitigation of interference in V2I networks, especially in a multiuser environment. In this work, LSTM based deep learning and Non-Linear Auto Regressive (NAR) based regressor have been employed to predict the angles between the RSU’s and UE. Simulation results have confrmed that the proposed LSTM model achieves comparable performance in terms of system throughput when compared with the non-linear auto regressive (NAR) method implemented as an artifcial neural network (ANN).
Nitish P. Gokhale,Prateek Kala,Varun Sharma,Murali Palla 대한기계학회 2020 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.34 No.2
Welding-based additive manufacturing can potentially produce a cost-effective process for the production of dense metallic parts. Tungsten inert gas (TIG) welding-based additive manufacturing process uses wire as a filler material and offers a high deposition rate with low spattering. In this study, different orientations of wire feeding nozzle and TIG welding torch, such as front wire feeding (FWF), back wire feeding (BWF), and side wire feeding (SWF), were investigated for thin-walled metal deposition with enhanced dimensional accuracy and mechanical properties. The dimensional accuracy of thin-walls deposited at four different orientations were investigated in terms of deposition height and deposition width. The FWF orientation with higher wire feeding angle and SWF orientation produced poor dimensional accuracy in the deposition. FWF orientation with normal wire feeding angle and BWF orientation provided a decent dimensional accuracy and surface appearance. The deposited samples exhibited a similar trend for Vickers microhardness, residual stress, and microstructure for the four different wire feeding orientations.
Cesare Hassan,Alessandro Repici,Angelo Zullo,Prateek Sharma 대한소화기내시경학회 2013 Clinical Endoscopy Vol.46 No.2
The possibility to predict in vivo the histology of colorectal polyps by advanced endoscopic imaging has resulted in the implementation of a more conservative management for diminutive lesions detected at colonoscopy. In detail, a predict-and-do-not-resect strategy has been proposed for diminutive lesions located in the rectosigmoid tract, whilst a predict-resect-and-discard policy has been advocated for nonrectosigmoid diminutive polyps. Recently, the American Society for Gastrointestinal Endoscopy set required thresholds to be met, before allowing the adoption of these policies in the clinical field. The ability of current endoscopic imaging in reaching these thresholds would depend on a complex interaction among the accuracy of advanced endoscopic imaging in differentiating between ad-enomatous and hyperplastic lesions, the prevalence of (advanced) neoplasia within diminutive lesions, and the type of surveillance in-tervals recommended. Aim of this review is to summarize the data supporting the application of both a predict-and-do-not-resect and a predict-resect-and-discard policies, also addressing the potential pitfalls associated with these strategies.