Nowadays,ensuring thequality of networkserviceshas become increasingly vital.Experts are turning toknowledge graph technology,with a significant emphasis on entity extraction in the identification of device configurat...Nowadays,ensuring thequality of networkserviceshas become increasingly vital.Experts are turning toknowledge graph technology,with a significant emphasis on entity extraction in the identification of device configurations.This research paper presents a novel entity extraction method that leverages a combination of active learning and attention mechanisms.Initially,an improved active learning approach is employed to select the most valuable unlabeled samples,which are subsequently submitted for expert labeling.This approach successfully addresses the problems of isolated points and sample redundancy within the network configuration sample set.Then the labeled samples are utilized to train the model for network configuration entity extraction.Furthermore,the multi-head self-attention of the transformer model is enhanced by introducing the Adaptive Weighting method based on the Laplace mixture distribution.This enhancement enables the transformer model to dynamically adapt its focus to words in various positions,displaying exceptional adaptability to abnormal data and further elevating the accuracy of the proposed model.Through comparisons with Random Sampling(RANDOM),Maximum Normalized Log-Probability(MNLP),Least Confidence(LC),Token Entrop(TE),and Entropy Query by Bagging(EQB),the proposed method,Entropy Query by Bagging and Maximum Influence Active Learning(EQBMIAL),achieves comparable performance with only 40% of the samples on both datasets,while other algorithms require 50% of the samples.Furthermore,the entity extraction algorithm with the Adaptive Weighted Multi-head Attention mechanism(AW-MHA)is compared with BILSTM-CRF,Mutil_Attention-Bilstm-Crf,Deep_Neural_Model_NER and BERT_Transformer,achieving precision rates of 75.98% and 98.32% on the two datasets,respectively.Statistical tests demonstrate the statistical significance and effectiveness of the proposed algorithms in this paper.展开更多
The outbreak and subsequent recurring waves of COVID−19 pose threats on the emergency management and people's daily life,while the large-scale spatio-temporal epidemiological data have sure come in handy in epidem...The outbreak and subsequent recurring waves of COVID−19 pose threats on the emergency management and people's daily life,while the large-scale spatio-temporal epidemiological data have sure come in handy in epidemic surveillance.Nonetheless,some challenges remain to be addressed in terms of multi-source heterogeneous data fusion,deep mining,and comprehensive applications.The Spatio-Temporal Artificial Intelligence(STAI)technology,which focuses on integrating spatial related time-series data,artificial intelligence models,and digital tools to provide intelligent computing platforms and applications,opens up new opportunities for scientific epidemic control.To this end,we leverage STAI and long-term experience in location-based intelligent services in the work.Specifically,we devise and develop a STAI-driven digital infrastructure,namely,WAYZ Disease Control Intelligent Platform(WDCIP),which consists of a systematic framework for building pipelines from automatic spatio-temporal data collection,processing to AI-based analysis and inference implementation for providing appropriate applications serving various epidemic scenarios.According to the platform implementation logic,our work can be performed and summarized from three aspects:(1)a STAI-driven integrated system;(2)a hybrid GNN-based approach for hierarchical risk assessment(as the core algorithm of WDCIP);and(3)comprehensive applications for social epidemic containment.This work makes a pivotal contribution to facilitating the aggregation and full utilization of spatio-temporal epidemic data from multiple sources,where the real-time human mobility data generated by high-precision mobile positioning plays a vital role in sensing the spread of the epidemic.So far,WDCIP has accumulated more than 200 million users who have been served in life convenience and decision-making during the pandemic.展开更多
Chlorella residues are currently underutilized. Therefore, in this study, we analyzed the nutritional components of Chlorella residue, and investigated its potential use as an organic fertilizer/bio-stimulant. Composi...Chlorella residues are currently underutilized. Therefore, in this study, we analyzed the nutritional components of Chlorella residue, and investigated its potential use as an organic fertilizer/bio-stimulant. Composition analyses revealed that the Chlorella residue contained a substantial amount of nitrogen (97,910 mg/kg), and significant quantities of secondary macronutrients, such as calcium (4300 mg/kg) and magnesium (9700 mg/kg), and micronutrients, such as iron (1850 mg/L) and manganese (359 mg/kg). The application of Chlorella residue to soil resulted in increased soil bacterial biomass. When Chlorella residue was added to the soil at a rate of 0.5% or 1.0% (w/w), the fresh weights of Brassica rapa and Spinacia oleracea were significantly increased. Furthermore, the application of Chlorella residue to the soil of B. rapa suppressed the reduction of the microbiome caused by clubroot disease and decreased the clubroot disease index. Therefore, Chlorella residue can be included in organic fertilizers that effectively improve soil nutrient contents, promote plant growth, and reduce the incidence of disease.展开更多
Rats suffering from adjuvant arthritis (AA) were used to examine the effect of a static magnetic field (SMF) upon pain relief. Rats were divided into SMF- treated AA rats, non-SMF treated AA rats and control rats. Fol...Rats suffering from adjuvant arthritis (AA) were used to examine the effect of a static magnetic field (SMF) upon pain relief. Rats were divided into SMF- treated AA rats, non-SMF treated AA rats and control rats. Following SMF stimulation, we measured blood flow volume in the paw and then reactive speed response to thermal stimulation. The AA groups exhibited significantly lower blood volume and reactivity to thermal stimulation compared to the control group. Compared to non-SMF, SMF exhibited increased blood flow volume in both the tail and paw, along with an increased reactive speed response to thermal stimulation. Our findings suggest that an improved of blood flow and reactive speed response, induced by SMF, appears to be effective for the relief of pain induced by chronic inflammation.展开更多
Frequent bathtub bathing (BB) improves the mental health of middle-aged and older Japanese in-dividuals. This study investigated the chronic mental health effects of BB, maintaining warmth using an insulating sheet an...Frequent bathtub bathing (BB) improves the mental health of middle-aged and older Japanese in-dividuals. This study investigated the chronic mental health effects of BB, maintaining warmth using an insulating sheet and sleeping bag after bathtub bathing (BBW), and bathtub bathing with herbal extracts (BBH) in healthy young adults. The study involved healthy young adults who habitually showered, as opposed to bathing. In the first experiment, 18 participants were randomly assigned to either the BB or BBW groups for 14 consecutive nights. After a 2-week washout period, the participants were asked to switch their bathing styles (a cross-over design). In the second experiment, 20 participants were randomly assigned to the BB or BBH group. The herbal extracts for the BBH group contained angelicae radix, aurantii nobilis pericarpium, chamomile, and zingiberis rhizoma. After a 2-week washout period, these participants also switched to the other bathing style. The participants’ mental conditions pre- and post-intervention were assessed using the Profile of Mood States-Brief Form questionnaire, Japanese version, and were statistically analyzed. The participants’ Anger-Hostility score converged to an average (50 points) in the post-BBW and post-BBH participants, and there were no significant differences in BB. The Confusion change rate was significantly different in the first experiment (BB versus BBW). The Depression-Dejection and Fatigue change rates were significantly different in the second experiment (BB versus BBH). Our findings suggest that changing bathing style from showering to BBW or BBH improves the POMS Anger-Hostility scores of healthy young adults.展开更多
The objective of this article is to uncover benefits and risks of Integrated Product Service Offering （IPSO） in a systematic manner. To do so, it adopts an explorative longitudinal in-depth case study （development ...The objective of this article is to uncover benefits and risks of Integrated Product Service Offering （IPSO） in a systematic manner. To do so, it adopts an explorative longitudinal in-depth case study （development of an IPSO based on a new technology） and adds insights to the existing literature. The article first proposes a theoretical and generic framework termed the PCP （Provider - Customer - Product） triangle with associated information flow and uncertainty. Second, various types of benefits and risks are presented based on the framework. Among others, the benefit of keeping IPR （Intellectual Property Rights） with the provider and the risk of regulation change are new findings from the case study. In addition, the case study reveals that IPSO is regarded as a positive contributor to innovation. Applying the framework and classification of benefits and risks as norms to other cases has yet to be done for verification. However, the framework contributes scientifically to a better understanding of the benefits and risks of IPSO. In addition, this framework is advantageous with its easiness to understand, which contributes practically to the dissemination of IPS0 insight to industry.展开更多
Investigation of the vertical vibration characteristics of the seated human body is beneficial for the design and development of vehicle ride comfort.In this study,we first established models of the seated human body ...Investigation of the vertical vibration characteristics of the seated human body is beneficial for the design and development of vehicle ride comfort.In this study,we first established models of the seated human body with two,three and four degrees of freedom(DOF).Then,the vibration characteristics of 30 volunteers were tested under standard conditions with a vibration test rig to obtain data for the apparent mass,driving point mechanical impedance,and seat-to-head transfer function.Based on the experimental data,the parameters of these models are identified and the results show that the four-DOF model can simulate the vertical vibration characteristics of the seated human body more comprehensively.Then,different seated human body models were applied to optimize the damping of shock absorber.The results show that the optimized damping with the four-DOF Chinese seated human body model is 27%more than that with rigid mass and 7%less than that with ISO 5982:2001 seated human body model.展开更多
Listwise approaches are an important class of learning to rank, which utilizes automatic learning techniques to discover useful information. Most previous research on listwise approaches has focused on optimizing rank...Listwise approaches are an important class of learning to rank, which utilizes automatic learning techniques to discover useful information. Most previous research on listwise approaches has focused on optimizing ranking models using weights and has used imprecisely labeled training data; optimizing ranking models using features was largely ignored thus the continuous performance improvement of these approaches was hindered. To address the limitations of previous listwise work, we propose a quasi-KNN model to discover the ranking of features and employ rank addition rule to calculate the weight of combination. On the basis of this, we propose three listwise algorithms, FeatureRank, BL-FeatureRank, and DiffRank. The experimental results show that our proposed algorithms can be applied to a strict ordered ranking training set and gain better performance than state-of-the-art listwise algorithms.展开更多
基金supported by the National Key R&D Program of China(2019YFB2103202).
文摘Nowadays,ensuring thequality of networkserviceshas become increasingly vital.Experts are turning toknowledge graph technology,with a significant emphasis on entity extraction in the identification of device configurations.This research paper presents a novel entity extraction method that leverages a combination of active learning and attention mechanisms.Initially,an improved active learning approach is employed to select the most valuable unlabeled samples,which are subsequently submitted for expert labeling.This approach successfully addresses the problems of isolated points and sample redundancy within the network configuration sample set.Then the labeled samples are utilized to train the model for network configuration entity extraction.Furthermore,the multi-head self-attention of the transformer model is enhanced by introducing the Adaptive Weighting method based on the Laplace mixture distribution.This enhancement enables the transformer model to dynamically adapt its focus to words in various positions,displaying exceptional adaptability to abnormal data and further elevating the accuracy of the proposed model.Through comparisons with Random Sampling(RANDOM),Maximum Normalized Log-Probability(MNLP),Least Confidence(LC),Token Entrop(TE),and Entropy Query by Bagging(EQB),the proposed method,Entropy Query by Bagging and Maximum Influence Active Learning(EQBMIAL),achieves comparable performance with only 40% of the samples on both datasets,while other algorithms require 50% of the samples.Furthermore,the entity extraction algorithm with the Adaptive Weighted Multi-head Attention mechanism(AW-MHA)is compared with BILSTM-CRF,Mutil_Attention-Bilstm-Crf,Deep_Neural_Model_NER and BERT_Transformer,achieving precision rates of 75.98% and 98.32% on the two datasets,respectively.Statistical tests demonstrate the statistical significance and effectiveness of the proposed algorithms in this paper.
基金supported by the Shanghai Municipal Science and Technology Major Project[grant number 2021SHZD ZX0100]the Fundamental Research Funds for the Central Universities[grant number 2021SHZDZX0100].
文摘The outbreak and subsequent recurring waves of COVID−19 pose threats on the emergency management and people's daily life,while the large-scale spatio-temporal epidemiological data have sure come in handy in epidemic surveillance.Nonetheless,some challenges remain to be addressed in terms of multi-source heterogeneous data fusion,deep mining,and comprehensive applications.The Spatio-Temporal Artificial Intelligence(STAI)technology,which focuses on integrating spatial related time-series data,artificial intelligence models,and digital tools to provide intelligent computing platforms and applications,opens up new opportunities for scientific epidemic control.To this end,we leverage STAI and long-term experience in location-based intelligent services in the work.Specifically,we devise and develop a STAI-driven digital infrastructure,namely,WAYZ Disease Control Intelligent Platform(WDCIP),which consists of a systematic framework for building pipelines from automatic spatio-temporal data collection,processing to AI-based analysis and inference implementation for providing appropriate applications serving various epidemic scenarios.According to the platform implementation logic,our work can be performed and summarized from three aspects:(1)a STAI-driven integrated system;(2)a hybrid GNN-based approach for hierarchical risk assessment(as the core algorithm of WDCIP);and(3)comprehensive applications for social epidemic containment.This work makes a pivotal contribution to facilitating the aggregation and full utilization of spatio-temporal epidemic data from multiple sources,where the real-time human mobility data generated by high-precision mobile positioning plays a vital role in sensing the spread of the epidemic.So far,WDCIP has accumulated more than 200 million users who have been served in life convenience and decision-making during the pandemic.
文摘Chlorella residues are currently underutilized. Therefore, in this study, we analyzed the nutritional components of Chlorella residue, and investigated its potential use as an organic fertilizer/bio-stimulant. Composition analyses revealed that the Chlorella residue contained a substantial amount of nitrogen (97,910 mg/kg), and significant quantities of secondary macronutrients, such as calcium (4300 mg/kg) and magnesium (9700 mg/kg), and micronutrients, such as iron (1850 mg/L) and manganese (359 mg/kg). The application of Chlorella residue to soil resulted in increased soil bacterial biomass. When Chlorella residue was added to the soil at a rate of 0.5% or 1.0% (w/w), the fresh weights of Brassica rapa and Spinacia oleracea were significantly increased. Furthermore, the application of Chlorella residue to the soil of B. rapa suppressed the reduction of the microbiome caused by clubroot disease and decreased the clubroot disease index. Therefore, Chlorella residue can be included in organic fertilizers that effectively improve soil nutrient contents, promote plant growth, and reduce the incidence of disease.
文摘Rats suffering from adjuvant arthritis (AA) were used to examine the effect of a static magnetic field (SMF) upon pain relief. Rats were divided into SMF- treated AA rats, non-SMF treated AA rats and control rats. Following SMF stimulation, we measured blood flow volume in the paw and then reactive speed response to thermal stimulation. The AA groups exhibited significantly lower blood volume and reactivity to thermal stimulation compared to the control group. Compared to non-SMF, SMF exhibited increased blood flow volume in both the tail and paw, along with an increased reactive speed response to thermal stimulation. Our findings suggest that an improved of blood flow and reactive speed response, induced by SMF, appears to be effective for the relief of pain induced by chronic inflammation.
文摘Frequent bathtub bathing (BB) improves the mental health of middle-aged and older Japanese in-dividuals. This study investigated the chronic mental health effects of BB, maintaining warmth using an insulating sheet and sleeping bag after bathtub bathing (BBW), and bathtub bathing with herbal extracts (BBH) in healthy young adults. The study involved healthy young adults who habitually showered, as opposed to bathing. In the first experiment, 18 participants were randomly assigned to either the BB or BBW groups for 14 consecutive nights. After a 2-week washout period, the participants were asked to switch their bathing styles (a cross-over design). In the second experiment, 20 participants were randomly assigned to the BB or BBH group. The herbal extracts for the BBH group contained angelicae radix, aurantii nobilis pericarpium, chamomile, and zingiberis rhizoma. After a 2-week washout period, these participants also switched to the other bathing style. The participants’ mental conditions pre- and post-intervention were assessed using the Profile of Mood States-Brief Form questionnaire, Japanese version, and were statistically analyzed. The participants’ Anger-Hostility score converged to an average (50 points) in the post-BBW and post-BBH participants, and there were no significant differences in BB. The Confusion change rate was significantly different in the first experiment (BB versus BBW). The Depression-Dejection and Fatigue change rates were significantly different in the second experiment (BB versus BBH). Our findings suggest that changing bathing style from showering to BBW or BBH improves the POMS Anger-Hostility scores of healthy young adults.
基金supported by the project Management of Innovation Processes for Business Driven Networksfunded by VINNOVA(The Swedish Governmental Agency for Innovation Systems)
文摘The objective of this article is to uncover benefits and risks of Integrated Product Service Offering （IPSO） in a systematic manner. To do so, it adopts an explorative longitudinal in-depth case study （development of an IPSO based on a new technology） and adds insights to the existing literature. The article first proposes a theoretical and generic framework termed the PCP （Provider - Customer - Product） triangle with associated information flow and uncertainty. Second, various types of benefits and risks are presented based on the framework. Among others, the benefit of keeping IPR （Intellectual Property Rights） with the provider and the risk of regulation change are new findings from the case study. In addition, the case study reveals that IPSO is regarded as a positive contributor to innovation. Applying the framework and classification of benefits and risks as norms to other cases has yet to be done for verification. However, the framework contributes scientifically to a better understanding of the benefits and risks of IPSO. In addition, this framework is advantageous with its easiness to understand, which contributes practically to the dissemination of IPS0 insight to industry.
文摘Investigation of the vertical vibration characteristics of the seated human body is beneficial for the design and development of vehicle ride comfort.In this study,we first established models of the seated human body with two,three and four degrees of freedom(DOF).Then,the vibration characteristics of 30 volunteers were tested under standard conditions with a vibration test rig to obtain data for the apparent mass,driving point mechanical impedance,and seat-to-head transfer function.Based on the experimental data,the parameters of these models are identified and the results show that the four-DOF model can simulate the vertical vibration characteristics of the seated human body more comprehensively.Then,different seated human body models were applied to optimize the damping of shock absorber.The results show that the optimized damping with the four-DOF Chinese seated human body model is 27%more than that with rigid mass and 7%less than that with ISO 5982:2001 seated human body model.
文摘Listwise approaches are an important class of learning to rank, which utilizes automatic learning techniques to discover useful information. Most previous research on listwise approaches has focused on optimizing ranking models using weights and has used imprecisely labeled training data; optimizing ranking models using features was largely ignored thus the continuous performance improvement of these approaches was hindered. To address the limitations of previous listwise work, we propose a quasi-KNN model to discover the ranking of features and employ rank addition rule to calculate the weight of combination. On the basis of this, we propose three listwise algorithms, FeatureRank, BL-FeatureRank, and DiffRank. The experimental results show that our proposed algorithms can be applied to a strict ordered ranking training set and gain better performance than state-of-the-art listwise algorithms.
