{"title":"Medical Image Retrieval Based on Attention Triplet Hashing","authors":"Shangrui Guo, Kai Yang, Zhijun Zhang, Xijie Li","doi":"10.1109/ICPSE56329.2022.9935433","DOIUrl":"https://doi.org/10.1109/ICPSE56329.2022.9935433","url":null,"abstract":"With the wide application of X-ray, Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) methods in clinical practice, massive information retrieval and utilization of medical images has become a hot topic. Although traditional methods have shown good results in many specific medical applications, there are still many problems in large-scale medical applications. Deep hash method has been proved to be the most efficient approximate nearest neighbor search technique for large-scale image retrieval. To this end, Attention Triplet Hashing (ATH) network is proposed in this paper, which can further improve retrieval performance and ranking performance of small samples by learning low-dimensional hash codes that retain classification, ROI, and small sample information. We add channel attention to this end-to-end framework to focus on ROI information. And we add label smoothing regularization to distinguish small sample images. Finally, the validity of my framework is tested on a case-based medical dataset.","PeriodicalId":421812,"journal":{"name":"2022 11th International Conference on Power Science and Engineering (ICPSE)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126854566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Patrick Cuyubamba, Joel Asto-Evangelista, Jean R. Almerco-Ataucusi, Yadhira S. Valenzuela-Lino, Deyby Huamanchahua, N. Moggiano
{"title":"Design and Performance Study of the Heat Exchanger of a Fin-Based Thermoelectric Generator via Numerical Simulations","authors":"Patrick Cuyubamba, Joel Asto-Evangelista, Jean R. Almerco-Ataucusi, Yadhira S. Valenzuela-Lino, Deyby Huamanchahua, N. Moggiano","doi":"10.1109/ICPSE56329.2022.9935347","DOIUrl":"https://doi.org/10.1109/ICPSE56329.2022.9935347","url":null,"abstract":"Climate change is a latent concern nowadays, so the ONU proposed to adopt new alternatives for obtaining energy through clean and renewable energies; that is why the TEG (Thermoelectric Generator) have been used in different industries and vehicles as they are a system that recovers and uses the waste heat from automobile exhaust gases for waste heat recovery; therefore, it is a method that allows improving energy efficiency. The present study aims to design and study the performance of the heat exchanger of a fin-based thermoelectric generator via numerical simulations. In this way, the geometry was performed using SolidWorks software. In addition, the meshing and boundary conditions were established in ANSYS Fluent to obtain the initial temperature distributions. Additionally, these initial temperature distributions serve as boundary conditions for ANSYS Thermal-Electric to obtain the semiconductor’s final temperature distributions, voltage distributions, and electric current distributions. It was obtained as a result that the semiconductor’s temperature distributions reached a voltage of 80 mV in 1 second of heat transfer. Also, the droplets fin-base TEG had an average temperature of 36.85 °C on the cold side and 163.3 °C on the hot side. Finally, it was concluded that the semiconductor’s final temperature distributions of the hot and cold side for the droplets fin-base TEG presented higher uniformity than the parallel plate fin-base TEG.","PeriodicalId":421812,"journal":{"name":"2022 11th International Conference on Power Science and Engineering (ICPSE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127872352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"System Dynamics Analysis of Green Power Grid Price Compensation","authors":"Kaikai Chen, Yunfeng Ti, Lun Li, Zhenghua Zhang","doi":"10.1109/ICPSE56329.2022.9935430","DOIUrl":"https://doi.org/10.1109/ICPSE56329.2022.9935430","url":null,"abstract":"With the gradual implementation of power grid energy conservation and emission reduction policies, the factors affecting the price compensation of green power grid are becoming more and more complex. The green power grid price compensation system is divided into technology research and development subsystem, design subsystem, production subsystem, construction subsystem and operation subsystem. Applying the theory of system dynamics to establish the system dynamics model of green power grid price compensation. Through the analysis of causality diagram, the interaction mechanism between various factors is clearly shown, and the price compensation mechanism of green power grid is established.","PeriodicalId":421812,"journal":{"name":"2022 11th International Conference on Power Science and Engineering (ICPSE)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134270367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Efficient Method of Finding the Best Time Interval for Predicting Short Term Solar Radiation Using CNN-LSTM Model","authors":"Chibuzor N Obiora, Ahmed Ali, Ali N. Hasan","doi":"10.1109/ICPSE56329.2022.9935441","DOIUrl":"https://doi.org/10.1109/ICPSE56329.2022.9935441","url":null,"abstract":"Even though the application of solar energy for electric power production is rapidly growing throughout the world, its unpredictability continues to provide significant difficulties. The primary source of this issue is the fluctuation of the solar radiative power, which the Photovoltaic (PV) cells convert into electrical energy at the power plants. In determining the best time interval or horizon for solar irradiance forecasting, the CNN-LSTM hybrid model was used. The input data consisted of historical solar irradiance obtained at five different time intervals over two years period. The dataset was created using historical meteorological data for Cape Town for two years. Eighty percent of the whole dataset was used to train the model for up to 1,000 epochs. The metric deployed to assess the model’s performance was Root Mean Squared Error (RMSE). Results from this experiment were compared with those from the Support Vector Regression (SVR) model that was fitted independently using a similar volume of data. From the performance metrics analyzed, the CNN-LSTM achieved better results than the SVR model. It recorded an RMSE of 6.2 percent using training data collected at 5-minute intervals. This result was best when contrasted with others obtained when the models were trained with data obtained from other different horizons. Adopting the data produced by the CNN-LSTM hybrid model at the five-minute horizon in Cape Town is suggested to improve control over the issues caused by fluctuating solar radiative power on the power system smart grid.","PeriodicalId":421812,"journal":{"name":"2022 11th International Conference on Power Science and Engineering (ICPSE)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132794636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Significance of Mutual Coupling on the Lightning Transient Voltage and Current of Typical Wind Turbine under Different Lightning Strokes","authors":"Tserensambuu Chinges, Qingmin Li, Jiyao Zhao","doi":"10.1109/ICPSE56329.2022.9935353","DOIUrl":"https://doi.org/10.1109/ICPSE56329.2022.9935353","url":null,"abstract":"This paper described a computation of lightning electromagnetic transient of the wind turbine lightning protection system using PSCAD/EMTDC software. Blade grounding wire and wind turbine tower were modelled by circuit approach considering their mutual coupling of vertical and horizontal wires using the codes available in PSCAD. The comparison analysis has been performed between models with and without accounting the inductive/capacitive coupling for estimating transient overvoltage at the blade, tower top, and tower base under two distinct lightning current strokes. Also, wind turbine grounding system configuration with an equipotential grounding cable is analyzed to determine discharge current through the low voltage surge arrester under different grounding characteristics. The simulation results show that the mutual coupling significantly affects the tower top/nacelle overvoltage. Moreover, it was found that double peaked lightning current produces strong negative oscillations than standard 2.6/50 $mu$s lightning. Depending on the uses of the model, the accuracy is enough to compute lightning overvoltage and currents through surge arresters.","PeriodicalId":421812,"journal":{"name":"2022 11th International Conference on Power Science and Engineering (ICPSE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132156638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Research and Application of Material Storage and Inspection Integration System","authors":"Jun Zhang, Dongliang Wang, Junxin Wu","doi":"10.1109/ICPSE56329.2022.9935489","DOIUrl":"https://doi.org/10.1109/ICPSE56329.2022.9935489","url":null,"abstract":"The construction of an integrated base for inspection, storage and distribution of power materials is an effective measure to optimize the efficiency of the power supply chain and reduce transportation costs and time costs. However, significant challenges were encountered in building such an integrated base due to the poor shape regularity of power materials, large weight span, and low utilization rate of warehouses. This paper designs an integrated system of inspection, storage, and distribution of power materials by studying and solving the construction problem and gives its implementation, which provides a reference for the research and construction of an integrated power material base and development of supporting systems.","PeriodicalId":421812,"journal":{"name":"2022 11th International Conference on Power Science and Engineering (ICPSE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124493243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sitra Muhaba, M. Darun, Freselam Mulubrhan, S. Chin
{"title":"Improving the Quality of Petrochemical Wastewater via a Medium-Sized Industrial-Scale Treatment Plant","authors":"Sitra Muhaba, M. Darun, Freselam Mulubrhan, S. Chin","doi":"10.1109/ICPSE56329.2022.9935348","DOIUrl":"https://doi.org/10.1109/ICPSE56329.2022.9935348","url":null,"abstract":"This paper aims to investigate the performance of a petrochemical wastewater treatment plant with a daily capacity of 450 $mathrm{m}^{3}$ of wastewater influent that has an average Chemical Oxygen Demand (COD) concentration of 12021.6 mg/L and pH of 3.02-11.17. The data were registered twice a day at 9:00 am and 9:00 pm and the daily average data was calculated. The wastewater quality data indicated that the COD removal rate during the primary treatment stage was only 50.29%. When the biological treatment was used the COD removal efficiency of the plant increased to 81.78%. The high efficiency of removal was evident in the Upflow Anaerobic Sludge Blanket (UASB) reactors that normally contain high concentrations of solid hydrocarbon; hence the removal of COD is possible even in cases involving highly concentrated influents. Moreover, the average pH of the effluent was 6.8 and the average concentrations of other pollutants such as suspended solids (SS), Oxidation-reduction potential, (ORP), ammonium-nitrogen ($mathrm{NH}_{4-}mathrm{N}$), and orthophosphate were 217.1 mg/L, 146.85 mV, 4.46 mg/L and 2.88 mg/L, respectively. The results indicate that the construction of a UASB reactor could result in higher removal efficiency of petrochemical wastewater pollutants. However, the effluent from the biological treatment needs further treatment before it can be discharged into the ocean.","PeriodicalId":421812,"journal":{"name":"2022 11th International Conference on Power Science and Engineering (ICPSE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126693047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cybersecurity of Prognostic Control Algorithms of Distributed Generation Plants","authors":"Yu. N. Bulatov, A. Kryukov, K. Suslov","doi":"10.1109/ICPSE56329.2022.9935355","DOIUrl":"https://doi.org/10.1109/ICPSE56329.2022.9935355","url":null,"abstract":"The introduction of distributed generation (DG) plants entails the solution of multiple tasks. optimization of the settings of automatic voltage controllers (AVC) and speed controllers (ASC) of synchronous generators in all possible operating modes is one of these tasks. This requires the application of complex power supply system (PSS) models, DG plants and their controllers, as well as labor-intensive calculations that take into account a large number of interrelated parameters. However, there is another approach associated with the use of prognostic controllers, the tuning of which requires only one parameter for linear prognostic models. The article describes a method for constructing and configuring a predictive ASC, as well as computer models of DG plants to conduct studies, the purpose of which was to determine the cybersecurity level of power supply systems equipped with DG plants with prognostic controllers. Research was carried out in the MATLAB system on DG plants computer models with one turbogenerator and a set of generators. The simulation results indicated that the cubersecurity of the proposed prognostic control algorithms can be calculated by the introduction of hardware restrictions on the range of the time constant of the prognostic link.","PeriodicalId":421812,"journal":{"name":"2022 11th International Conference on Power Science and Engineering (ICPSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129264873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}