In the quest to minimize energy waste,the energy performance of buildings(EPB)has been a focus because building appliances,such as heating,ventilation,and air conditioning,consume the highest energy.Therefore,effectiv...In the quest to minimize energy waste,the energy performance of buildings(EPB)has been a focus because building appliances,such as heating,ventilation,and air conditioning,consume the highest energy.Therefore,effective design and planning for estimating heating load(HL)and cooling load(CL)for energy saving have become paramount.In this vein,efforts have been made to predict the HL and CL using a univariate approach.However,this approach necessitates two models for learning HL and CL,requiring more computational time.Moreover,the one-dimensional(1D)convolutional neural network(CNN)has gained popularity due to its nominal computa-tional complexity,high performance,and low-cost hardware requirement.In this paper,we formulate the prediction as a multivariate regression problem in which the HL and CL are simultaneously predicted using the 1D CNN.Considering the building shape characteristics,one kernel size is adopted to create the receptive fields of the 1D CNN to extract the feature maps,a dense layer to interpret the maps,and an output layer with two neurons to predict the two real-valued responses,HL and CL.As the 1D data are not affected by excessive parameters,the pooling layer is not applied in this implementation.Besides,the use of pooling has been questioned by recent studies.The performance of the proposed model displays a comparative advantage over existing models in terms of the mean squared error(MSE).Thus,the proposed model is effective for EPB prediction because it reduces computational time and significantly lowers the MSE.展开更多
The key-value store can provide flexibility of data types because it does not need to specify the data types to be stored in advance and can store any types of data as the value of the key-value pair.Various types of ...The key-value store can provide flexibility of data types because it does not need to specify the data types to be stored in advance and can store any types of data as the value of the key-value pair.Various types of studies have been conducted to improve the performance of the key-value store while maintaining its flexibility.However,the research efforts storing the large-scale values such as multimedia data files(e.g.,images or videos)in the key-value store were limited.In this study,we propose a new key-value store,WR-Store++aiming to store the large-scale values stably.Specifically,it provides a new design of separating data and index by working with the built-in data structure of the Windows operating system and the file system.The utilization of the built-in data structure of the Windows operating system achieves the efficiency of the key-value store and that of the file system extends the limited space of the storage significantly.We also present chunk-based memory management and parallel processing of WR-Store++to further improve its performance in the GET operation.Through the experiments,we show that WR-Store++can store at least 32.74 times larger datasets than the existing baseline key-value store,WR-Store,which has the limitation in storing large-scale data sets.Furthermore,in terms of processing efficiency,we show that WR-Store++outperforms not only WR-Store but also the other state-ofthe-art key-value stores,LevelDB,RocksDB,and BerkeleyDB,for individual key-value operations and mixed workloads.展开更多
Question-answering(QA)models find answers to a given question.The necessity of automatically finding answers is increasing because it is very important and challenging from the large-scale QA data sets.In this paper,w...Question-answering(QA)models find answers to a given question.The necessity of automatically finding answers is increasing because it is very important and challenging from the large-scale QA data sets.In this paper,we deal with the QA pair matching approach in QA models,which finds the most relevant question and its recommended answer for a given question.Existing studies for the approach performed on the entire dataset or datasets within a category that the question writer manually specifies.In contrast,we aim to automatically find the category to which the question belongs by employing the text classification model and to find the answer corresponding to the question within the category.Due to the text classification model,we can effectively reduce the search space for finding the answers to a given question.Therefore,the proposed model improves the accuracy of the QA matching model and significantly reduces the model inference time.Furthermore,to improve the performance of finding similar sentences in each category,we present an ensemble embedding model for sentences,improving the performance compared to the individual embedding models.Using real-world QA data sets,we evaluate the performance of the proposed QA matching model.As a result,the accuracy of our final ensemble embedding model based on the text classification model is 81.18%,which outperforms the existing models by 9.81%∼14.16%point.Moreover,in terms of the model inference speed,our model is faster than the existing models by 2.61∼5.07 times due to the effective reduction of search spaces by the text classification model.展开更多
The uncontrolled spread of the coronavirus disease 2019(COVID-19)pandemic has led to the emergence of different severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)variants across the globe.The ongoing global v...The uncontrolled spread of the coronavirus disease 2019(COVID-19)pandemic has led to the emergence of different severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)variants across the globe.The ongoing global vaccination strategy to curtail the COVID-19 juggernaut is threatened by the rapidly spreading variants of concern(VOC)and other regional mutants,which are less responsive to neutralization by infection-or vaccine-derived antibodies(Gomez et al.,2021;Wang et al.,2021).展开更多
BACKGROUND Colonic diverticular bleeding(CDB)is a leading cause of gastrointestinal blee-ding-related hospitalizations in Japan and is increasingly recognized as a signifi-cant burden in the United States.Identifying ...BACKGROUND Colonic diverticular bleeding(CDB)is a leading cause of gastrointestinal blee-ding-related hospitalizations in Japan and is increasingly recognized as a signifi-cant burden in the United States.Identifying the stigmata of a recent hemorrhage(SRH)during colonoscopy enables targeted hemostasis and reduces rebleeding.However,no benchmark exists for an appropriate observation duration,resulting in operator-dependent variation.Short observation periods may lead to missed SRH,whereas unnecessarily prolonged procedures,particularly in older patients,can increase patient burden and limit endoscopy unit availability.METHODS We retrospectively analyzed patients with acute hematochezia who underwent an initial colonoscopy between January 2017 and December 2024 at a Japanese tertiary hospital.The Observation time was measured from scope insertion to SRH detection(excluding therapeutic time)or withdrawal.The primary outcome,the“5%plateau time”,was defined as the point when the proportion of patients newly identified with SRH in each 5-minute interval consistently dropped below 5%.Computed tomography(CT)-based stratified analyses were performed by endoscopists who conducted≥10%of procedures.RESULTS Of the 1039 patients who underwent colonoscopy,845(mean age 77±11 years;64.5%male)were included.Nine board-certified endoscopists performed the procedures.SRH was detected in 286 patients(33.8%),with a median detection time of 19 minutes(interquartile range,12-28 minutes).The overall 5%plateau time was 40 minutes and varied according to the CT findings:40,35,and 30 minutes for no extravasation,right-sided extravasation,and left-sided extravasation,respectively.This time point corresponded to when 80%-90%of SRH cases were detected.De-spite variations in SRH detection rates and observation durations among endoscopists,the 5%plateau time was consistently approximately 40 minutes.CONCLUSION Although it varied according to the CT findings,the overall 5%plateau time was 40 minutes.This offers a practical benchmark for the minimum observation time without SRH detection.展开更多
基金supported in part by the Institute of Information and Communications Technology Planning and Evaluation(IITP)Grant by the Korean Government Ministry of Science and ICT(MSITArtificial Intelligence Innovation Hub)under Grant 2021-0-02068in part by the NationalResearch Foundation of Korea(NRF)Grant by theKorean Government(MSIT)under Grant NRF-2021R1I1A3060565.
文摘In the quest to minimize energy waste,the energy performance of buildings(EPB)has been a focus because building appliances,such as heating,ventilation,and air conditioning,consume the highest energy.Therefore,effective design and planning for estimating heating load(HL)and cooling load(CL)for energy saving have become paramount.In this vein,efforts have been made to predict the HL and CL using a univariate approach.However,this approach necessitates two models for learning HL and CL,requiring more computational time.Moreover,the one-dimensional(1D)convolutional neural network(CNN)has gained popularity due to its nominal computa-tional complexity,high performance,and low-cost hardware requirement.In this paper,we formulate the prediction as a multivariate regression problem in which the HL and CL are simultaneously predicted using the 1D CNN.Considering the building shape characteristics,one kernel size is adopted to create the receptive fields of the 1D CNN to extract the feature maps,a dense layer to interpret the maps,and an output layer with two neurons to predict the two real-valued responses,HL and CL.As the 1D data are not affected by excessive parameters,the pooling layer is not applied in this implementation.Besides,the use of pooling has been questioned by recent studies.The performance of the proposed model displays a comparative advantage over existing models in terms of the mean squared error(MSE).Thus,the proposed model is effective for EPB prediction because it reduces computational time and significantly lowers the MSE.
文摘The key-value store can provide flexibility of data types because it does not need to specify the data types to be stored in advance and can store any types of data as the value of the key-value pair.Various types of studies have been conducted to improve the performance of the key-value store while maintaining its flexibility.However,the research efforts storing the large-scale values such as multimedia data files(e.g.,images or videos)in the key-value store were limited.In this study,we propose a new key-value store,WR-Store++aiming to store the large-scale values stably.Specifically,it provides a new design of separating data and index by working with the built-in data structure of the Windows operating system and the file system.The utilization of the built-in data structure of the Windows operating system achieves the efficiency of the key-value store and that of the file system extends the limited space of the storage significantly.We also present chunk-based memory management and parallel processing of WR-Store++to further improve its performance in the GET operation.Through the experiments,we show that WR-Store++can store at least 32.74 times larger datasets than the existing baseline key-value store,WR-Store,which has the limitation in storing large-scale data sets.Furthermore,in terms of processing efficiency,we show that WR-Store++outperforms not only WR-Store but also the other state-ofthe-art key-value stores,LevelDB,RocksDB,and BerkeleyDB,for individual key-value operations and mixed workloads.
基金This work was supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.2022R1F1A1067008)by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(No.2019R1A6A1A03032119).
文摘Question-answering(QA)models find answers to a given question.The necessity of automatically finding answers is increasing because it is very important and challenging from the large-scale QA data sets.In this paper,we deal with the QA pair matching approach in QA models,which finds the most relevant question and its recommended answer for a given question.Existing studies for the approach performed on the entire dataset or datasets within a category that the question writer manually specifies.In contrast,we aim to automatically find the category to which the question belongs by employing the text classification model and to find the answer corresponding to the question within the category.Due to the text classification model,we can effectively reduce the search space for finding the answers to a given question.Therefore,the proposed model improves the accuracy of the QA matching model and significantly reduces the model inference time.Furthermore,to improve the performance of finding similar sentences in each category,we present an ensemble embedding model for sentences,improving the performance compared to the individual embedding models.Using real-world QA data sets,we evaluate the performance of the proposed QA matching model.As a result,the accuracy of our final ensemble embedding model based on the text classification model is 81.18%,which outperforms the existing models by 9.81%∼14.16%point.Moreover,in terms of the model inference speed,our model is faster than the existing models by 2.61∼5.07 times due to the effective reduction of search spaces by the text classification model.
基金supported by a grant-in-aid fromthe Japan Agency for Medical Researchand Development (JP19fk0108110,JP20he0522001, and JP21fk0108104)。
文摘The uncontrolled spread of the coronavirus disease 2019(COVID-19)pandemic has led to the emergence of different severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)variants across the globe.The ongoing global vaccination strategy to curtail the COVID-19 juggernaut is threatened by the rapidly spreading variants of concern(VOC)and other regional mutants,which are less responsive to neutralization by infection-or vaccine-derived antibodies(Gomez et al.,2021;Wang et al.,2021).
文摘BACKGROUND Colonic diverticular bleeding(CDB)is a leading cause of gastrointestinal blee-ding-related hospitalizations in Japan and is increasingly recognized as a signifi-cant burden in the United States.Identifying the stigmata of a recent hemorrhage(SRH)during colonoscopy enables targeted hemostasis and reduces rebleeding.However,no benchmark exists for an appropriate observation duration,resulting in operator-dependent variation.Short observation periods may lead to missed SRH,whereas unnecessarily prolonged procedures,particularly in older patients,can increase patient burden and limit endoscopy unit availability.METHODS We retrospectively analyzed patients with acute hematochezia who underwent an initial colonoscopy between January 2017 and December 2024 at a Japanese tertiary hospital.The Observation time was measured from scope insertion to SRH detection(excluding therapeutic time)or withdrawal.The primary outcome,the“5%plateau time”,was defined as the point when the proportion of patients newly identified with SRH in each 5-minute interval consistently dropped below 5%.Computed tomography(CT)-based stratified analyses were performed by endoscopists who conducted≥10%of procedures.RESULTS Of the 1039 patients who underwent colonoscopy,845(mean age 77±11 years;64.5%male)were included.Nine board-certified endoscopists performed the procedures.SRH was detected in 286 patients(33.8%),with a median detection time of 19 minutes(interquartile range,12-28 minutes).The overall 5%plateau time was 40 minutes and varied according to the CT findings:40,35,and 30 minutes for no extravasation,right-sided extravasation,and left-sided extravasation,respectively.This time point corresponded to when 80%-90%of SRH cases were detected.De-spite variations in SRH detection rates and observation durations among endoscopists,the 5%plateau time was consistently approximately 40 minutes.CONCLUSION Although it varied according to the CT findings,the overall 5%plateau time was 40 minutes.This offers a practical benchmark for the minimum observation time without SRH detection.
