Recently,to build a smart factory,research has been conducted to perform fault diagnosis and defect detection based on vibration and noise signals generated when a mechanical system is driven using deep-learning techn...Recently,to build a smart factory,research has been conducted to perform fault diagnosis and defect detection based on vibration and noise signals generated when a mechanical system is driven using deep-learning technology,a field of artificial intelligence.Most of the related studies apply various audio-feature extraction techniques to one-dimensional raw data to extract sound-specific features and then classify the sound by using the derived spectral image as a training dataset.However,compared to numerical raw data,learning based on image data has the disadvantage that creating a training dataset is very time-consuming.Therefore,we devised a two-step data preprocessing method that efficiently detects machine anomalies in numerical raw data.In the first preprocessing process,sound signal information is analyzed to extract features,and in the second preprocessing process,data filtering is performed by applying the proposed algorithm.An efficient dataset was built formodel learning through a total of two steps of data preprocessing.In addition,both showed excellent performance in the training accuracy of the model that entered each dataset,but it can be seen that the time required to build the dataset was 203 s compared to 39 s,which is about 5.2 times than when building the image dataset.展开更多
Networks based on backscatter communication provide wireless data transmission in the absence of a power source.A backscatter device receives a radio frequency(RF)source and creates a backscattered signal that deliver...Networks based on backscatter communication provide wireless data transmission in the absence of a power source.A backscatter device receives a radio frequency(RF)source and creates a backscattered signal that delivers data;this enables new services in battery-less domains with massive Internet-of-Things(IoT)devices.Connectivity is highly energy-efficient in the context of massive IoT applications.Outdoors,long-range(LoRa)backscattering facilitates large IoT services.A backscatter network guarantees timeslot-and contention-based transmission.Timeslot-based transmission ensures data transmission,but is not scalable to different numbers of transmission devices.If contention-based transmission is used,collisions are unavoidable.To reduce collisions and increase transmission efficiency,the number of devices transmitting data must be controlled.To control device activation,the RF source range can be modulated by adjusting the RF source power during LoRa backscatter.This reduces the number of transmitting devices,and thus collisions and retransmission,thereby improving transmission efficiency.We performed extensive simulations to evaluate the performance of our method.展开更多
As the Internet of Things(IoT)advances,machine-type devices are densely deployed and massive networks such as ultra-dense networks(UDNs)are formed.Various devices attend to the network to transmit data using machine-t...As the Internet of Things(IoT)advances,machine-type devices are densely deployed and massive networks such as ultra-dense networks(UDNs)are formed.Various devices attend to the network to transmit data using machine-type communication(MTC),whereby numerous,various are generated.MTC devices generally have resource constraints and use wireless communication.In this kind of network,data aggregation is a key function to provide transmission efficiency.It can reduce the number of transmitted data in the network,and this leads to energy saving and reducing transmission delays.In order to effectively operate data aggregation in UDNs,it is important to select an aggregation point well.The total number of transmitted data may vary,depending on the aggregation point to which the data are delivered.Therefore,in this paper,we propose a novel data aggregation scheme to select the appropriate aggregation point and describe the data transmission method applying the proposed aggregation scheme.In addition,we evaluate the proposed scheme with extensive computer simulations.Better performances in the proposed scheme are achieved compared to the conventional approach.展开更多
In many IIoT architectures,various devices connect to the edge cloud via gateway systems.For data processing,numerous data are delivered to the edge cloud.Delivering data to an appropriate edge cloud is critical to im...In many IIoT architectures,various devices connect to the edge cloud via gateway systems.For data processing,numerous data are delivered to the edge cloud.Delivering data to an appropriate edge cloud is critical to improve IIoT service efficiency.There are two types of costs for this kind of IoT network:a communication cost and a computing cost.For service efficiency,the communication cost of data transmission should be minimized,and the computing cost in the edge cloud should be also minimized.Therefore,in this paper,the communication cost for data transmission is defined as the delay factor,and the computing cost in the edge cloud is defined as the waiting time of the computing intensity.The proposed method selects an edge cloud that minimizes the total cost of the communication and computing costs.That is,a device chooses a routing path to the selected edge cloud based on the costs.The proposed method controls the data flows in a mesh-structured network and appropriately distributes the data processing load.The performance of the proposed method is validated through extensive computer simulation.When the transition probability from good to bad is 0.3 and the transition probability from bad to good is 0.7 in wireless and edge cloud states,the proposed method reduced both the average delay and the service pause counts to about 25%of the existing method.展开更多
Background: The nutritional support after hematopoietic stem cell transplantation (HSCT) has not been well established due to the scarcity of clinical trials. To conduct international clinical trials in Asia, we perfo...Background: The nutritional support after hematopoietic stem cell transplantation (HSCT) has not been well established due to the scarcity of clinical trials. To conduct international clinical trials in Asia, we performed the questionnaire survey to investigate the current standard of nutritional support after HSCT. Method: We sent the questionnaire to the physicians nominated by the Asia Pacific Blood and Marrow Transplantation (APBMT) members of each country/ region. Result: We received 15 responses from 7 different countries/regions. The target calorie amount is 1.0 - 1.3 × basal energy expenditure (BEE) in 11 institutes when partial parenteral nutrition is used. When total parenteral nutrition (TPN) is used, the target calorie amount is 1.0 - 1.3 × BEE in 9 institutes and 1.3 - 1.5 × BEE in 4 institutes. Lipid emulsion is routinely used in 12 institutes. Multivitamins and trace elements are routinely added to TPN used in most institutes. It is still uncommon to use the immunonutrition. Blood glucose levels are routinely monitored in all institutes, but the target range varies (<110 in 2 institutes, <150 in 4 institutes, and <200 in 8 institutes). Conclusions: Basic nutritional support is similar in participating institutes. However, the target glucose level varies and the use of immunonutrition is rather rare. These points can be the theme of future clinical trials.展开更多
AIM: To study the distributions and frequencies of intestinal endocrine cells in the C57BL/6 mouse with immunohistochemical method using seven types of specific antisera against chromogranin A (CGA), serotonin,somatos...AIM: To study the distributions and frequencies of intestinal endocrine cells in the C57BL/6 mouse with immunohistochemical method using seven types of specific antisera against chromogranin A (CGA), serotonin,somatostatin, glucagons, gastrin, cholecystokinin (CCK)-8 and human pancreatic polypeptide (hPP) after abdominal subcutaneous implantation of murine lung carcinoma (3LL).METHODS: The experimental animals were divided into two groups, one is non-implanted Sham and the other is 3LL-implanted group. Samples were collected from six regions of intestinal tract at 28th d after implantation of 3LL cells (1×105 cell/mouse).RESULTS: In this study, five types of immunoreactive (IR) cells were identified except for gastrin and hPP. The regional distributions of the intestinal endocrine cells in the 3LL-implanted group were similar to those of the non-implanted Sham. However, significant decreases of IR cells were detected in 3LL-implanted group compared to those of non-implanted Sham. CGA- and serotonin-IR cells significantly decreased in 3LL-implanted groups compared to that of non-implanted Sham. Somatostatin-IR cells in the jejunum and ileum and CCK-8-IR cells in the jejunum of 3LL-implanted groups significantly decreased compared to that of non-implanted Sham. In addition,glucagon-IR cells were restricted to the ileum and colon of non-implanted Sham.CONCLUSION: Implantation of tumor cell mass (3LL)induced severe quantifiable changes of intestinal endocrine cell density and the abnormality in density of intestinal endocrine cells may contribute to the development of gastrointestinal symptoms such as anorexia and indigestion, frequently encountered in patients with cancer.展开更多
Communication is important for providing intelligent services in connected vehicles.Vehicles must be able to communicate with different places and exchange information while driving.For service operation,connected veh...Communication is important for providing intelligent services in connected vehicles.Vehicles must be able to communicate with different places and exchange information while driving.For service operation,connected vehicles frequently attempt to download large amounts of data.They can request data downloading to a road side unit(RSU),which provides infrastructure for connected vehicles.The RSU is a data bottleneck in a transportation system because data traffic is concentrated on the RSU.Therefore,it is not appropriate for a connected vehicle to always attempt a high speed download from the RSU.If the mobile network between a connected vehicle and an RSU has poor connection quality,the efficiency and speed of the data download from the RSU is decreased.This problem affects the quality of the user experience.Therefore,it is important for a connected vehicle to connect to an RSU with consideration of the network conditions in order to try to maximize download speed.The proposed method maximizes download speed from an RSU using a machine learning algorithm.To collect and learn from network data,fog computing is used.A fog server is integrated with the RSU to perform computing.If the algorithm recognizes that conditions are not good for mass data download,it will not attempt to download at high speed.Thus,the proposed method can improve the efficiency of high speed downloads.This conclusion was validated using extensive computer simulations.展开更多
Air pollution caused by fine dust is a big problem all over the world and fine dust has a fatal impact on human health.But there are too few fine dust measuring stations and the installation cost of fine dust measurin...Air pollution caused by fine dust is a big problem all over the world and fine dust has a fatal impact on human health.But there are too few fine dust measuring stations and the installation cost of fine dust measuring station is very expensive.In this paper,we propose Cloud-based air pollution information system using R.To measure fine dust,we have developed an inexpensive measuring device and studied the technique to accurately measure the concentration of fine dust at the user’s location.And we have developed the smartphone application to provide air pollution information.In our system,we provide collected data based analytical results through effective data modeling.Our system provides information on fine dust value and action tips through the air pollution information application.And it supports visualization on the map using the statistical program R.The user can check the fine dust statistics map and cope with fine dust accordingly.展开更多
Recently,the fifth generation(5G)of mobile networks has been deployed and various ranges of mobile services have been provided.The 5G mobile network supports improved mobile broadband,ultra-low latency and densely dep...Recently,the fifth generation(5G)of mobile networks has been deployed and various ranges of mobile services have been provided.The 5G mobile network supports improved mobile broadband,ultra-low latency and densely deployed massive devices.It allows multiple radio access technologies and interworks them for services.5G mobile systems employ traffic steering techniques to efficiently use multiple radio access technologies.However,conventional traffic steering techniques do not consider dynamic network conditions efficiently.In this paper,we propose a network aided traffic steering technique in 5G mobile network architecture.5G mobile systems monitor network conditions and learn with network data.Through a machine learning algorithm such as a feed-forward neural network,it recognizes dynamic network conditions and then performs traffic steering.The proposed scheme controls traffic for multiple radio access according to the ratio of measured throughput.Thus,it can be expected to improve traffic steering efficiency.The performance of the proposed traffic steering scheme is evaluated using extensive computer simulations.展开更多
The Internet of Things(IoT)has enabled various intelligent services,and IoT service range has been steadily extended through long range wide area communication technologies,which enable very long distance wireless dat...The Internet of Things(IoT)has enabled various intelligent services,and IoT service range has been steadily extended through long range wide area communication technologies,which enable very long distance wireless data transmission.End-nodes are connected to a gateway with a single hop.They consume very low-power,using very low data rate to deliver data.Since long transmission time is consequently needed for each data packet transmission in long range wide area networks,data transmission should be efficiently performed.Therefore,this paper proposes a multicast uplink data transmission mechanism particularly for bad network conditions.Transmission delay will be increased if only retransmissions are used under bad network conditions.However,employing multicast techniques in bad network conditions can significantly increase packet delivery rate.Thus,retransmission can be reduced and hence transmission efficiency increased.Therefore,the proposed method adopts multicast uplink after network condition prediction.To predict network conditions,the proposed method uses a deep neural network algorithm.The proposed method performance was verified by comparison with uplink unicast transmission only,confirming significantly improved performance.展开更多
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea Government(MSIT)(No.2021R1C1C1013133)funded by BK21 FOUR(Fostering Outstanding Universities for Research)(No.5199990914048)supported by the Soonchunhyang University Research Fund.
文摘Recently,to build a smart factory,research has been conducted to perform fault diagnosis and defect detection based on vibration and noise signals generated when a mechanical system is driven using deep-learning technology,a field of artificial intelligence.Most of the related studies apply various audio-feature extraction techniques to one-dimensional raw data to extract sound-specific features and then classify the sound by using the derived spectral image as a training dataset.However,compared to numerical raw data,learning based on image data has the disadvantage that creating a training dataset is very time-consuming.Therefore,we devised a two-step data preprocessing method that efficiently detects machine anomalies in numerical raw data.In the first preprocessing process,sound signal information is analyzed to extract features,and in the second preprocessing process,data filtering is performed by applying the proposed algorithm.An efficient dataset was built formodel learning through a total of two steps of data preprocessing.In addition,both showed excellent performance in the training accuracy of the model that entered each dataset,but it can be seen that the time required to build the dataset was 203 s compared to 39 s,which is about 5.2 times than when building the image dataset.
基金the National Research Foundation of Korea(NRF)grant funded by theKoreaGovernment(MSIT)(No.2021R1C1C1013133)Basic ScienceResearch Programthrough the NationalResearch Foundation ofKorea(NRF)funded by the Ministry of Education(NRF-2020R1I1A3066543)the Soonchunhyang University Research Fund.
文摘Networks based on backscatter communication provide wireless data transmission in the absence of a power source.A backscatter device receives a radio frequency(RF)source and creates a backscattered signal that delivers data;this enables new services in battery-less domains with massive Internet-of-Things(IoT)devices.Connectivity is highly energy-efficient in the context of massive IoT applications.Outdoors,long-range(LoRa)backscattering facilitates large IoT services.A backscatter network guarantees timeslot-and contention-based transmission.Timeslot-based transmission ensures data transmission,but is not scalable to different numbers of transmission devices.If contention-based transmission is used,collisions are unavoidable.To reduce collisions and increase transmission efficiency,the number of devices transmitting data must be controlled.To control device activation,the RF source range can be modulated by adjusting the RF source power during LoRa backscatter.This reduces the number of transmitting devices,and thus collisions and retransmission,thereby improving transmission efficiency.We performed extensive simulations to evaluate the performance of our method.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea Government(MSIT)(No.2021R1C1C1013133)this work was supported by the Soonchunhyang University Research Fund(No.20210442).
文摘As the Internet of Things(IoT)advances,machine-type devices are densely deployed and massive networks such as ultra-dense networks(UDNs)are formed.Various devices attend to the network to transmit data using machine-type communication(MTC),whereby numerous,various are generated.MTC devices generally have resource constraints and use wireless communication.In this kind of network,data aggregation is a key function to provide transmission efficiency.It can reduce the number of transmitted data in the network,and this leads to energy saving and reducing transmission delays.In order to effectively operate data aggregation in UDNs,it is important to select an aggregation point well.The total number of transmitted data may vary,depending on the aggregation point to which the data are delivered.Therefore,in this paper,we propose a novel data aggregation scheme to select the appropriate aggregation point and describe the data transmission method applying the proposed aggregation scheme.In addition,we evaluate the proposed scheme with extensive computer simulations.Better performances in the proposed scheme are achieved compared to the conventional approach.
基金supported by the National Research Foundation of Korea (NRF) grant funded by the Korea Government (MSIT) (No.2021R1C1C1013133)supported by the Institute of Information and Communications Technology Planning and Evaluation (IITP)grant funded by the Korea Government (MSIT) (RS-2022-00167197,Development of Intelligent 5G/6G Infrastructure Technology for The Smart City)supported by the Soonchunhyang University Research Fund.
文摘In many IIoT architectures,various devices connect to the edge cloud via gateway systems.For data processing,numerous data are delivered to the edge cloud.Delivering data to an appropriate edge cloud is critical to improve IIoT service efficiency.There are two types of costs for this kind of IoT network:a communication cost and a computing cost.For service efficiency,the communication cost of data transmission should be minimized,and the computing cost in the edge cloud should be also minimized.Therefore,in this paper,the communication cost for data transmission is defined as the delay factor,and the computing cost in the edge cloud is defined as the waiting time of the computing intensity.The proposed method selects an edge cloud that minimizes the total cost of the communication and computing costs.That is,a device chooses a routing path to the selected edge cloud based on the costs.The proposed method controls the data flows in a mesh-structured network and appropriately distributes the data processing load.The performance of the proposed method is validated through extensive computer simulation.When the transition probability from good to bad is 0.3 and the transition probability from bad to good is 0.7 in wireless and edge cloud states,the proposed method reduced both the average delay and the service pause counts to about 25%of the existing method.
文摘Background: The nutritional support after hematopoietic stem cell transplantation (HSCT) has not been well established due to the scarcity of clinical trials. To conduct international clinical trials in Asia, we performed the questionnaire survey to investigate the current standard of nutritional support after HSCT. Method: We sent the questionnaire to the physicians nominated by the Asia Pacific Blood and Marrow Transplantation (APBMT) members of each country/ region. Result: We received 15 responses from 7 different countries/regions. The target calorie amount is 1.0 - 1.3 × basal energy expenditure (BEE) in 11 institutes when partial parenteral nutrition is used. When total parenteral nutrition (TPN) is used, the target calorie amount is 1.0 - 1.3 × BEE in 9 institutes and 1.3 - 1.5 × BEE in 4 institutes. Lipid emulsion is routinely used in 12 institutes. Multivitamins and trace elements are routinely added to TPN used in most institutes. It is still uncommon to use the immunonutrition. Blood glucose levels are routinely monitored in all institutes, but the target range varies (<110 in 2 institutes, <150 in 4 institutes, and <200 in 8 institutes). Conclusions: Basic nutritional support is similar in participating institutes. However, the target glucose level varies and the use of immunonutrition is rather rare. These points can be the theme of future clinical trials.
文摘AIM: To study the distributions and frequencies of intestinal endocrine cells in the C57BL/6 mouse with immunohistochemical method using seven types of specific antisera against chromogranin A (CGA), serotonin,somatostatin, glucagons, gastrin, cholecystokinin (CCK)-8 and human pancreatic polypeptide (hPP) after abdominal subcutaneous implantation of murine lung carcinoma (3LL).METHODS: The experimental animals were divided into two groups, one is non-implanted Sham and the other is 3LL-implanted group. Samples were collected from six regions of intestinal tract at 28th d after implantation of 3LL cells (1×105 cell/mouse).RESULTS: In this study, five types of immunoreactive (IR) cells were identified except for gastrin and hPP. The regional distributions of the intestinal endocrine cells in the 3LL-implanted group were similar to those of the non-implanted Sham. However, significant decreases of IR cells were detected in 3LL-implanted group compared to those of non-implanted Sham. CGA- and serotonin-IR cells significantly decreased in 3LL-implanted groups compared to that of non-implanted Sham. Somatostatin-IR cells in the jejunum and ileum and CCK-8-IR cells in the jejunum of 3LL-implanted groups significantly decreased compared to that of non-implanted Sham. In addition,glucagon-IR cells were restricted to the ileum and colon of non-implanted Sham.CONCLUSION: Implantation of tumor cell mass (3LL)induced severe quantifiable changes of intestinal endocrine cell density and the abnormality in density of intestinal endocrine cells may contribute to the development of gastrointestinal symptoms such as anorexia and indigestion, frequently encountered in patients with cancer.
文摘Communication is important for providing intelligent services in connected vehicles.Vehicles must be able to communicate with different places and exchange information while driving.For service operation,connected vehicles frequently attempt to download large amounts of data.They can request data downloading to a road side unit(RSU),which provides infrastructure for connected vehicles.The RSU is a data bottleneck in a transportation system because data traffic is concentrated on the RSU.Therefore,it is not appropriate for a connected vehicle to always attempt a high speed download from the RSU.If the mobile network between a connected vehicle and an RSU has poor connection quality,the efficiency and speed of the data download from the RSU is decreased.This problem affects the quality of the user experience.Therefore,it is important for a connected vehicle to connect to an RSU with consideration of the network conditions in order to try to maximize download speed.The proposed method maximizes download speed from an RSU using a machine learning algorithm.To collect and learn from network data,fog computing is used.A fog server is integrated with the RSU to perform computing.If the algorithm recognizes that conditions are not good for mass data download,it will not attempt to download at high speed.Thus,the proposed method can improve the efficiency of high speed downloads.This conclusion was validated using extensive computer simulations.
文摘Air pollution caused by fine dust is a big problem all over the world and fine dust has a fatal impact on human health.But there are too few fine dust measuring stations and the installation cost of fine dust measuring station is very expensive.In this paper,we propose Cloud-based air pollution information system using R.To measure fine dust,we have developed an inexpensive measuring device and studied the technique to accurately measure the concentration of fine dust at the user’s location.And we have developed the smartphone application to provide air pollution information.In our system,we provide collected data based analytical results through effective data modeling.Our system provides information on fine dust value and action tips through the air pollution information application.And it supports visualization on the map using the statistical program R.The user can check the fine dust statistics map and cope with fine dust accordingly.
基金This research was supported by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)support program(IITP-2020-2015-0-00403)supervised by the IITP(Institute for Information&communications Technology Planning&Evaluation)this work was supported by the Soonchunhyang University Research Fund.
文摘Recently,the fifth generation(5G)of mobile networks has been deployed and various ranges of mobile services have been provided.The 5G mobile network supports improved mobile broadband,ultra-low latency and densely deployed massive devices.It allows multiple radio access technologies and interworks them for services.5G mobile systems employ traffic steering techniques to efficiently use multiple radio access technologies.However,conventional traffic steering techniques do not consider dynamic network conditions efficiently.In this paper,we propose a network aided traffic steering technique in 5G mobile network architecture.5G mobile systems monitor network conditions and learn with network data.Through a machine learning algorithm such as a feed-forward neural network,it recognizes dynamic network conditions and then performs traffic steering.The proposed scheme controls traffic for multiple radio access according to the ratio of measured throughput.Thus,it can be expected to improve traffic steering efficiency.The performance of the proposed traffic steering scheme is evaluated using extensive computer simulations.
基金This research was supported by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)support program(IITP-2019-2015-0-00403)supervised by the IITP(Institute for Information&communications Technology Planning&Evaluation)this work was supported by the Soonchunhyang University Research Fund.
文摘The Internet of Things(IoT)has enabled various intelligent services,and IoT service range has been steadily extended through long range wide area communication technologies,which enable very long distance wireless data transmission.End-nodes are connected to a gateway with a single hop.They consume very low-power,using very low data rate to deliver data.Since long transmission time is consequently needed for each data packet transmission in long range wide area networks,data transmission should be efficiently performed.Therefore,this paper proposes a multicast uplink data transmission mechanism particularly for bad network conditions.Transmission delay will be increased if only retransmissions are used under bad network conditions.However,employing multicast techniques in bad network conditions can significantly increase packet delivery rate.Thus,retransmission can be reduced and hence transmission efficiency increased.Therefore,the proposed method adopts multicast uplink after network condition prediction.To predict network conditions,the proposed method uses a deep neural network algorithm.The proposed method performance was verified by comparison with uplink unicast transmission only,confirming significantly improved performance.