http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Sujit Kumar Das,Pinki Roy,Arnab Kumar Mishra 한국통신학회 2022 ICT Express Vol.8 No.2
Diabetic Foot Ulcer (DFU) is a complication of diabetes that causes lower limb amputation. In this work, a unique stacked parallel convolution layers-based network (DFU_SPNet) is proposed to perform DFU vs. normal skin classification. The main objective of this work is to design an effective CNN-based classification model, along with proper fine-tuning of optimizer settings. DFU_SPNet consists of 3 blocks of parallel convolution layers with multiple kernel sizes, for local and global feature abstractions. The proposed DFU_SPNet, trained using SGD (with momentum) optimizer with learning rate on the DFUNet dataset, outperformed the current state-of-the-art results with an AUC of 0.974.
Dhar, Sujit,Dutta, Biswajit,Ghoshroy, Debasmita,Roy, Debabrata,Sadhu, Pradip Kumar,Ganguly, Ankur,Sanyal, Amar Nath,Das, Soumya Techno-Press 2017 Advances in computational design Vol.2 No.4
High frequency full bridge series resonant inverters have become increasingly popular among power supply designers. One of the most important parameter for a High Frequency Full Bridge Series Resonant Inverter is optimal coil design. The optimal coil designing procedure is not a easy task. This paper deals with the New Approach to Optimal Design Procedure for a Real-time High Frequency Full Bridge Series Resonant Inverter in Induction Heating Equipment devices. A new design to experimental modelling of the physical properties and a practical power input simulation process for the non-sinusoidal input waveform is accepted. The design sensitivity analysis with Levenberg-Marquardt technique is used for the optimal design process. The proposed technique is applied to an Induction Heating Equipment devices model and the result is verified by real-time experiment. The main advantages of this design technique is to achieve more accurate temperature control with a huge amount of power saving.
Anamika Roy,Mamun Mandal,Sujit Das,Manoj Kumar,Robert Popek,Amit Awasthi,Balendu Shekher Giri,Kartick Chandra Mondal,Abhijit Sarkar 대한환경공학회 2023 Environmental Engineering Research Vol.29 No.3
Recent regulations on exhaust emissions have led to an increase in non-exhaust emissions, which now surpasses exhaust emissions. Non-exhaust emissions are mainly generated from brake and tire particle abrasion, road wear, and re-suspended road dust. In Asia, non-exhaust emissions have increased significantly over the past 50 years, resulting in almost 92% of the population breathing polluted air, which accounts for 70% of air pollution related-deaths. Most Asian countries with poor air quality are developing or underdeveloped. Taking this into consideration, the current study aims to shed light on particulate pollution from non-exhaust emissions in the Asian context to assess the current status and its health consequences and provides technological solutions. The study is based on an in-depth analysis of existing reviews and research concerning non-exhaust emissions and their health impacts in Asia to pinpoint knowledge gaps. The study found that particulate pollutants had exceeded WHOs standards in many Asian countries, bringing deleterious health consequences among children and the elderly. The findings underscore the significance of future researchers efforts to devise solutions that curtail non-exhaust emissions, ultimately reducing air pollution, augmenting air quality, fostering better health outcomes, and paving way for a more sustainable future before it is too late.