From the view of both objective and subjective factors,the indoor air quality(IAQ)evaluation was considered.Carbon dioxide(CO_(2))and formaldehyde(HCHO)were selected as the typical contaminants of indoor air,and the e...From the view of both objective and subjective factors,the indoor air quality(IAQ)evaluation was considered.Carbon dioxide(CO_(2))and formaldehyde(HCHO)were selected as the typical contaminants of indoor air,and the evaluation method of logarithmic index was adopted as the evaluation means of IAQ.Then the recommended limits(RL)of typical contaminants CO_(2)and HCHO were given through analysis and calculation.The limits of CO_(2)and HCHO in Indoor Air Quality Standard of China or other existing standards probably correspond to the level of PD=25(%).The result shows that the existing standards fail to meet the requirement of the definition of"acceptable indoor air quality",that is to say,less than 20%of the people express dissatisfaction.When PD=20%,RL of CO_(2)and HCHO are 728×10-6 and 0.068×10-6 respectively,which are stricter than the limits in the existing standards.The method proposed in this paper is applicable to 13.1%≤PD≤86.7%.展开更多
Objective To explore the possible preventive mechanism of Hunan expert group recommended Chinese medicine prescription of No.2(Pre-No.2)against coronavirus disease 2019(COVID-19)by network pharmacology method.Methods ...Objective To explore the possible preventive mechanism of Hunan expert group recommended Chinese medicine prescription of No.2(Pre-No.2)against coronavirus disease 2019(COVID-19)by network pharmacology method.Methods The target proteins of effective components and active compounds in Pre-No.2 were screened by searching the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform(TCMSP).A component-target-disease interaction network of Pre-No.2 was constructed by Cytoscape 3.7.2,gene ontology(GO)analysis,and Kyoto encyclopedia of genes and genomes(KEGG)analysis of target protein pathway by DAVID.Results A total of 163 compounds and 278 target protein targets in Pre-No.2 were collected from the TCMSP database.Kaempferol,wogonin,7-methoxy-2-methyl isoflavone,formononetin,isorhamnetin,and licochalcone A were the most frequent targets in the regulatory network.GO enrichment analysis showed that Pre-No.2 regulated response to virus,viral processes,humoral immune responses,defense responses to virus and viral entry into host cells.KEGG enrichment analysis showed that the formula regulated the NF-κB signaling pathway,B cell receptor signaling pathway,viral carcinogenesis,T cell signaling pathway and FcγR-mediated phagocytosis signaling pathway.Conclusions Pre-No.2 may play a preventive role against COVID-19 through regulation of the Toll-like signaling,T cell signaling,B cell signaling and other signaling pathways.It may regulate the immune system to protect against anti-influenza virus.展开更多
Book 1: (Editor-in-Chief: Shi Yafeng; Published by Elsevier and Science Press Beijing in 2008, 539 pages) Glaciers and Related Environments in China Since the professional institution for glaciology attached to the Ch...Book 1: (Editor-in-Chief: Shi Yafeng; Published by Elsevier and Science Press Beijing in 2008, 539 pages) Glaciers and Related Environments in China Since the professional institution for glaciology attached to the Chinese Academy of Sciences was established in 1958, studies of glaciers in alpine regions, and of Quaternary glaciations throughout展开更多
Closer sino-African relations have encouraged more Chinese enterprises to invest in African countries.Statistics show that more than 2,000 Chinese enterprises had invested in the continent by 2012.
The response of rice to N fertilizer applicationhas shown that high rates of N application donot always ensure a proportional increase inyield due to high N losses. A model, ORYZA-0 was developed by ten Berge for desi...The response of rice to N fertilizer applicationhas shown that high rates of N application donot always ensure a proportional increase inyield due to high N losses. A model, ORYZA-0 was developed by ten Berge for designingoptimum N fertilizer management strategy inrice. We evaluated the performance ofORYZA-0 in Jinhua, Zhejiang Province. ORYZA-0 includes N uptakes, partition-ing of N among the organs, and utilization ofleaf N in converting solar energy to dry mat-ter. It can predict the amount and time of Nfertilizer application to achieve a maximumbiomass or yield combining with Price algo-rithm optimization procedure.展开更多
Current guidelines for treating asymptomatic common bile duct stones(CBDS)recommend stone removal,with endoscopic retrograde cholangiopan-creatography(ERCP)being the first treatment choice.When deciding on ERCP treatm...Current guidelines for treating asymptomatic common bile duct stones(CBDS)recommend stone removal,with endoscopic retrograde cholangiopan-creatography(ERCP)being the first treatment choice.When deciding on ERCP treatment for asymptomatic CBDS,the risk of ERCP-related complications and outcome of natural history of asymptomatic CBDS should be compared.The incidence rate of ERCP-related complications,particularly of post-ERCP pancreatitis for asymptomatic CBDS,was reportedly higher than that of symptomatic CBDS,increasing the risk of ERCP-related complications for asymptomatic CBDS compared with that previously reported for biliopancreatic diseases.Although studies have reported short-to middle-term outcomes of natural history of asymptomatic CBDS,its long-term natural history is not well known.Till date,there are no prospective studies that determined whether ERCP has a better outcome than no treatment in patients with asymptomatic CBDS or not.No randomized controlled trial has evaluated the risk of early and late ERCP-related complications vs the risk of biliary complications in the wait-and-see approach,suggesting that a change is needed in our perspective on endoscopic treatment for asymptomatic CBDS.Further studies examining long-term complication risks of ERCP and wait-and-see groups for asymptomatic CBDS are warranted to discuss whether routine endoscopic treatment for asymptomatic CBDS is justified or not.展开更多
A new collaborative filtered recommendation strategy oriented to trajectory data is proposed for communication bottlenecks and vulnerability in centralized system structure location services. In the strategy based on ...A new collaborative filtered recommendation strategy oriented to trajectory data is proposed for communication bottlenecks and vulnerability in centralized system structure location services. In the strategy based on distributed system architecture, individual user information profiles were established using daily trajectory information and neighboring user groups were established using density measure. Then the trajectory similarity and profile similarity were calculated to recommend appropriate location services using collaborative filtering recommendation method. The strategy was verified on real position data set. The proposed strategy provides higher quality location services to ensure the privacy of user position information.展开更多
With the rapid development of electric vehicles,the requirements for charging stations are getting higher and higher.In this study,we constructed a charging station topology network inNanjing through the Space-L metho...With the rapid development of electric vehicles,the requirements for charging stations are getting higher and higher.In this study,we constructed a charging station topology network inNanjing through the Space-L method,mapping charging stations as network nodes and constructing edges through road relationships.The experiment introduced five EV charging recommendation strategies(based on distance,number of fast charging piles,user preference,price,and overall rating)used to simulate disordered charging caused by different user preferences,and the impact of the networkdynamic robustness in case of node failure is exploredby simulating the load-capacity cascade failure model.In this paper,two important metrics for evaluating network robustness are selected:the relative size of the maximum connected subgraph and the network efficiency.The experimental results point out that in the price recommendation strategy,the network stability significantly decreases when the node failure ratio reaches 75.4%,while the fast charging quantity recommendation strategy significantly decreases when the node failure ratio is 62.3%.Therefore,the robustness of the charging station network is best under the price recommendation,while the network robustness is poor under the fast charging quantity recommendation.While the network robustness is poor under preference recommendation.Based on this finding,this study particularly emphasizes that in the process of improving the robustness of the charging station network,it is necessary to comprehensively consider the market demand and guide users to charge in an orderly manner by reasonably adjusting the price strategy.This strategy not only effectively prevents network stability problems that may result fromdisorderly charging behavior,but also enhances the ability of the charging network to resist node failure and improves the overall dynamic robustness of the network.展开更多
The performance of deep recommendation models degrades significantly under data poisoning attacks.While adversarial training methods such as Vulnerability-Aware Training(VAT)enhance robustness by injecting perturbatio...The performance of deep recommendation models degrades significantly under data poisoning attacks.While adversarial training methods such as Vulnerability-Aware Training(VAT)enhance robustness by injecting perturbations into embeddings,they remain limited by coarse-grained noise and a static defense strategy,leaving models susceptible to adaptive attacks.This study proposes a novel framework,Self-Purification Data Sanitization(SPD),which integrates vulnerability-aware adversarial training with dynamic label correction.Specifically,SPD first identifies high-risk users through a fragility scoring mechanism,then applies self-purification by replacing suspicious interactions with model-predicted high-confidence labels during training.This closed-loop process continuously sanitizes the training data and breaks the protection ceiling of conventional adversarial training.Experiments demonstrate that SPD significantly improves the robustness of both Matrix Factorization(MF)and LightGCN models against various poisoning attacks.We show that SPD effectively suppresses malicious gradient propagation and maintains recommendation accuracy.Evaluations on Gowalla and Yelp2018 confirmthat SPD-trainedmodels withstandmultiple attack strategies—including Random,Bandwagon,DP,and Rev attacks—while preserving performance.展开更多
The Internet of Things(IoT)and cloud computing have significantly contributed to the development of smart cities,enabling real-time monitoring,intelligent decision-making,and efficient resource management.These system...The Internet of Things(IoT)and cloud computing have significantly contributed to the development of smart cities,enabling real-time monitoring,intelligent decision-making,and efficient resource management.These systems,particularly in IoT networks,rely on numerous interconnected devices that handle time-sensitive data for critical applications.In related approaches,trusted communication and reliable device interaction have been overlooked,thereby lowering security when sharing sensitive IoT data.Moreover,it incurs additional energy consumption and overhead while addressing potential threats in the dynamic environment.In this research,an Artificial Intelligence(AI)recommended fault-tolerant framework is proposed that leverages blockchain technology,aiming to enhance device trustworthiness and ensure data privacy.In addition,the intelligence of the proposed framework enables more authentic and authorized device involvement in data routing,thereby enabling seamless transmission in smart cities integrated with lightweight computing.To evaluate dynamic network conditions,the proposed framework offers a timely decision-making system to ensure robust delivery of IoT-assisted services.Using simulations,the efficacy of the proposed framework is validated by comparing it with existing approaches across various network metrics,demonstrating remarkable performance while achieving energy efficiency and optimizing network resources.展开更多
Recommendation systems are an integral and indispensable part of every digital platform,as they can suggest content or items to users based on their respective needs.Collaborative filtering is a technique often used i...Recommendation systems are an integral and indispensable part of every digital platform,as they can suggest content or items to users based on their respective needs.Collaborative filtering is a technique often used in various studies,which produces recommendations by analyzing similarities between users and items based on their behavior.Although often used,traditional collaborative filtering techniques still face the main challenge of sparsity.Sparsity problems occur when the data in the system is sparse,meaning that only a portion of users provide feedback on some items,resulting in inaccurate recommendations generated by the system.To overcome this problem,we developed aHybrid Collaborative Filtering model based onMatrix Factorization andGradient Boosting(HCF-MFGB),a new hybrid approach.Our proposed model integrates SVD++,the XGBoost ensemble learning algorithm,and utilizes user demographic data and meta items.We utilize information,both explicitly and implicitly,to learn user preference patterns using SVD++.The XGBoost algorithm is used to create hundreds of decision trees incrementally,thereby improving model accuracy.Meanwhile,user demographic and meta-item data are clustered using the K-Means Clustering algorithm to capture similarities in user and item characteristics.This combination is designed to improve rating prediction accuracy by reducing reliance on minimal explicit rating data,while addressing sparsity issues in movie recommendation systems.The results of experiments on the MovieLens 100K,MovieLens 1M,and CiaoDVD datasets show significant improvements,outperforming various other baselinemodels in terms of RMSE and MAE.On theMovieLens 100K dataset,the HCF-MFGB model obtained an RMSE value of 0.853 and an MAE value of 0.674.On theMovieLens 1M dataset,the HCF-MFGB model obtained an RMSE value of 0.763 and an MAE value of 0.61.On the CiaoDCD dataset,the HCF-MFGB model achieved an RMSE value of 0.718 and an MAE value of 0.495.These results confirm a significant improvement in movie recommendation accuracy with the proposed approach.展开更多
Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interact...Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interactions to predict future items of interest.However,many current methods rely on unique user and item IDs,limiting their ability to represent users and items effectively,especially in zero-shot learning scenarios where training data is scarce.With the rapid development of Large Language Models(LLMs),researchers are exploring their potential to enhance recommendation systems.However,there is a semantic gap between the linguistic semantics of LLMs and the collaborative semantics of recommendation systems,where items are typically indexed by IDs.Moreover,most research focuses on item representations,neglecting personalized user modeling.To address these issues,we propose a sequential recommendation framework using LLMs,called CIT-Rec,a model that integrates Collaborative semantics for user representation and Image and Text information for item representation to enhance Recommendations.Specifically,by aligning intuitive image information with text containing semantic features,we can more accurately represent items,improving item representation quality.We focus not only on item representations but also on user representations.To more precisely capture users’personalized preferences,we use traditional sequential recommendation models to train on users’historical interaction data,effectively capturing behavioral patterns.Finally,by combining LLMs and traditional sequential recommendation models,we allow the LLM to understand linguistic semantics while capturing collaborative semantics.Extensive evaluations on real-world datasets show that our model outperforms baseline methods,effectively combining user interaction history with item visual and textual modalities to provide personalized recommendations.展开更多
Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of...Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of user preferences.To address this,we propose a Conditional Generative Adversarial Network(CGAN)that generates diverse and highly relevant itineraries.Our approach begins by constructing a conditional vector that encapsulates a user’s profile.This vector uniquely fuses embeddings from a Heterogeneous Information Network(HIN)to model complex user-place-route relationships,a Recurrent Neural Network(RNN)to capture sequential path dynamics,and Neural Collaborative Filtering(NCF)to incorporate collaborative signals from the wider user base.This comprehensive condition,further enhanced with features representing user interaction confidence and uncertainty,steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations,effectively mitigating the data sparsity problem.Recommendations are then formulated using an Anchor-and-Expand algorithm,which selects relevant starting Points of Interest(POI)based on user history,then expands routes through latent similarity matching and geographic coherence optimization,culminating in Traveling Salesman Problem(TSP)-based route optimization for practical travel distances.Experiments on a real-world check-in dataset validate our model’s unique generative capability,achieving F1 scores ranging from 0.163 to 0.305,and near-zero pairs−F1 scores between 0.002 and 0.022.These results confirm the model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’past itineraries.This work provides a robust solution for personalized travel planning,capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence.展开更多
Recommendation systems have become indispensable for providing tailored suggestions and capturing evolving user preferences based on interaction histories.The collaborative filtering(CF)model,which depends exclusively...Recommendation systems have become indispensable for providing tailored suggestions and capturing evolving user preferences based on interaction histories.The collaborative filtering(CF)model,which depends exclusively on user-item interactions,commonly encounters challenges,including the cold-start problem and an inability to effectively capture the sequential and temporal characteristics of user behavior.This paper introduces a personalized recommendation system that combines deep learning techniques with Bayesian Personalized Ranking(BPR)optimization to address these limitations.With the strong support of Long Short-Term Memory(LSTM)networks,we apply it to identify sequential dependencies of user behavior and then incorporate an attention mechanism to improve the prioritization of relevant items,thereby enhancing recommendations based on the hybrid feedback of the user and its interaction patterns.The proposed system is empirically evaluated using publicly available datasets from movie and music,and we evaluate the performance against standard recommendation models,including Popularity,BPR,ItemKNN,FPMC,LightGCN,GRU4Rec,NARM,SASRec,and BERT4Rec.The results demonstrate that our proposed framework consistently achieves high outcomes in terms of HitRate,NDCG,MRR,and Precision at K=100,with scores of(0.6763,0.1892,0.0796,0.0068)on MovieLens-100K,(0.6826,0.1920,0.0813,0.0068)on MovieLens-1M,and(0.7937,0.3701,0.2756,0.0078)on Last.fm.The results show an average improvement of around 15%across all metrics compared to existing sequence models,proving that our framework ranks and recommends items more accurately.展开更多
Conversational recommender systems(CRSs)focus on refining preferences and providing personalized recommendations through natural language interactions and dialogue history.Large language models(LLMs)have shown outstan...Conversational recommender systems(CRSs)focus on refining preferences and providing personalized recommendations through natural language interactions and dialogue history.Large language models(LLMs)have shown outstanding performance across various domains,thereby prompting researchers to investigate their applicability in recommendation systems.However,due to the lack of task-specific knowledge and an inefficient feature extraction process,LLMs still have suboptimal performance in recommendation tasks.Therefore,external knowledge sources,such as knowledge graphs(KGs)and knowledge bases(KBs),are often introduced to address the issue of data sparsity.Compared to KGs,KBs possess higher retrieval efficiency,making them more suitable for scenarios where LLMs serve as recommenders.To this end,we introduce a novel framework integrating LLMs with KBs for enhanced retrieval generation,namely LLMKB.LLMKB initially leverages structured knowledge to create mapping dictionaries,extracting entity-relation information from heterogeneous knowledge to construct KBs.Then,LLMKB achieves the embedding calibration between user information representations and documents in KBs through retrieval model fine-tuning.Finally,LLMKB employs retrievalaugmented generation to produce recommendations based on fused text inputs,followed by post-processing.Experiment results on two public CRS datasets demonstrate the effectiveness of our framework.Our code is publicly available at the link:https://anonymous.4open.science/r/LLMKB-6FD0.展开更多
1.Introduction The COVID-19 pandemic is affecting the lives of the world population in various ways and has resulted in an unforeseen scale of disruption of activities across the globe.Its emergence has health and eco...1.Introduction The COVID-19 pandemic is affecting the lives of the world population in various ways and has resulted in an unforeseen scale of disruption of activities across the globe.Its emergence has health and economic implications that impact individuals,organizations and sovereign states which is inclusive of the stakeholders in a tax system.Thus,revenue authorities need to take actions to protect and ease the burden on its external and internal stakeholders.展开更多
Objective This study aimed to reexplore minimum iodine excretion and to build a dietary iodine recommendation for Chinese adults using the obligatory iodine loss hypothesis.Methods Data from 171 Chinese adults(19–21 ...Objective This study aimed to reexplore minimum iodine excretion and to build a dietary iodine recommendation for Chinese adults using the obligatory iodine loss hypothesis.Methods Data from 171 Chinese adults(19–21 years old)were collected and analyzed based on three balance studies in Shenzhen,Yinchuan,and Changzhi.The single exponential equation was accordingly used to simulate the trajectory of 24 h urinary iodine excretion as the low iodine experimental diets offered(iodine intake:11-26μg/day)and to further deduce the dietary reference intakes(DRIs)for iodine,including estimated average requirement(EAR)and recommended nutrient intake(RNI).Results The minimum iodine excretion was estimated as 57,58,and 51μg/day in three balance studies,respectively.Moreover,it was further suggested as 57,58,and 51μg/day for iodine EAR,and 80,81,and 71μg/day for iodine RNI or expressed as 1.42,1.41,and 1.20μg/(day·kg)of body weight.Conclusion The iodine DRIs for Chinese adults were established based on the obligatory iodine loss hypothesis,which provides scientific support for the amendment of nutrient requirements.展开更多
Azoospermia,defined as the absence of sperm in the ejaculate,is a well-documented consequence of exogenous testosterone(ET)and anabolic–androgenic steroid(AAS)use.These agents suppress the hypothalamic–pituitary–go...Azoospermia,defined as the absence of sperm in the ejaculate,is a well-documented consequence of exogenous testosterone(ET)and anabolic–androgenic steroid(AAS)use.These agents suppress the hypothalamic–pituitary–gonadal(HPG)axis,leading to reduced intratesticular testosterone levels and impaired spermatogenesis.This review examines the pathophysiological mechanisms underlying azoospermia and outlines therapeutic strategies for recovery.Azoospermia is categorized into pretesticular,testicular,and post-testicular types,with a focus on personalized treatment approaches based on the degree of HPG axis suppression and baseline testicular function.Key strategies include discontinuing ET and monitoring for spontaneous recovery,particularly in patients with shorter durations of ET use.For cases of persistent azoospermia,gonadotropins(human chorionic gonadotropin[hCG]and follicle-stimulating hormone[FSH])and selective estrogen receptor modulators(SERMs),such as clomiphene citrate,are recommended,either alone or in combination.The global increase in exogenous testosterone use,including testosterone replacement therapy and AAS,underscores the need for improved management of associated azoospermia,which can be temporary or permanent depending on individual factors and the type of testosterone used.Additionally,the manuscript discusses preventive strategies,such as transitioning to short-acting testosterone formulations or incorporating low-dose hCG to preserve fertility during ET therapy.While guidelines for managing testosterone-related azoospermia remain limited,emerging research indicates the potential efficacy of hormonal stimulation therapies.However,there is a notable lack of well-structured,controlled,and long-term studies addressing the management of azoospermia related to exogenous testosterone use,highlighting the need for such studies to inform evidence-based recommendations.展开更多
文摘From the view of both objective and subjective factors,the indoor air quality(IAQ)evaluation was considered.Carbon dioxide(CO_(2))and formaldehyde(HCHO)were selected as the typical contaminants of indoor air,and the evaluation method of logarithmic index was adopted as the evaluation means of IAQ.Then the recommended limits(RL)of typical contaminants CO_(2)and HCHO were given through analysis and calculation.The limits of CO_(2)and HCHO in Indoor Air Quality Standard of China or other existing standards probably correspond to the level of PD=25(%).The result shows that the existing standards fail to meet the requirement of the definition of"acceptable indoor air quality",that is to say,less than 20%of the people express dissatisfaction.When PD=20%,RL of CO_(2)and HCHO are 728×10-6 and 0.068×10-6 respectively,which are stricter than the limits in the existing standards.The method proposed in this paper is applicable to 13.1%≤PD≤86.7%.
基金funding support from the Scientific Research Fund of Hunan Administration of TCM(No.KYGG06,No.KYGG07)。
文摘Objective To explore the possible preventive mechanism of Hunan expert group recommended Chinese medicine prescription of No.2(Pre-No.2)against coronavirus disease 2019(COVID-19)by network pharmacology method.Methods The target proteins of effective components and active compounds in Pre-No.2 were screened by searching the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform(TCMSP).A component-target-disease interaction network of Pre-No.2 was constructed by Cytoscape 3.7.2,gene ontology(GO)analysis,and Kyoto encyclopedia of genes and genomes(KEGG)analysis of target protein pathway by DAVID.Results A total of 163 compounds and 278 target protein targets in Pre-No.2 were collected from the TCMSP database.Kaempferol,wogonin,7-methoxy-2-methyl isoflavone,formononetin,isorhamnetin,and licochalcone A were the most frequent targets in the regulatory network.GO enrichment analysis showed that Pre-No.2 regulated response to virus,viral processes,humoral immune responses,defense responses to virus and viral entry into host cells.KEGG enrichment analysis showed that the formula regulated the NF-κB signaling pathway,B cell receptor signaling pathway,viral carcinogenesis,T cell signaling pathway and FcγR-mediated phagocytosis signaling pathway.Conclusions Pre-No.2 may play a preventive role against COVID-19 through regulation of the Toll-like signaling,T cell signaling,B cell signaling and other signaling pathways.It may regulate the immune system to protect against anti-influenza virus.
文摘Book 1: (Editor-in-Chief: Shi Yafeng; Published by Elsevier and Science Press Beijing in 2008, 539 pages) Glaciers and Related Environments in China Since the professional institution for glaciology attached to the Chinese Academy of Sciences was established in 1958, studies of glaciers in alpine regions, and of Quaternary glaciations throughout
文摘Closer sino-African relations have encouraged more Chinese enterprises to invest in African countries.Statistics show that more than 2,000 Chinese enterprises had invested in the continent by 2012.
文摘The response of rice to N fertilizer applicationhas shown that high rates of N application donot always ensure a proportional increase inyield due to high N losses. A model, ORYZA-0 was developed by ten Berge for designingoptimum N fertilizer management strategy inrice. We evaluated the performance ofORYZA-0 in Jinhua, Zhejiang Province. ORYZA-0 includes N uptakes, partition-ing of N among the organs, and utilization ofleaf N in converting solar energy to dry mat-ter. It can predict the amount and time of Nfertilizer application to achieve a maximumbiomass or yield combining with Price algo-rithm optimization procedure.
文摘Current guidelines for treating asymptomatic common bile duct stones(CBDS)recommend stone removal,with endoscopic retrograde cholangiopan-creatography(ERCP)being the first treatment choice.When deciding on ERCP treatment for asymptomatic CBDS,the risk of ERCP-related complications and outcome of natural history of asymptomatic CBDS should be compared.The incidence rate of ERCP-related complications,particularly of post-ERCP pancreatitis for asymptomatic CBDS,was reportedly higher than that of symptomatic CBDS,increasing the risk of ERCP-related complications for asymptomatic CBDS compared with that previously reported for biliopancreatic diseases.Although studies have reported short-to middle-term outcomes of natural history of asymptomatic CBDS,its long-term natural history is not well known.Till date,there are no prospective studies that determined whether ERCP has a better outcome than no treatment in patients with asymptomatic CBDS or not.No randomized controlled trial has evaluated the risk of early and late ERCP-related complications vs the risk of biliary complications in the wait-and-see approach,suggesting that a change is needed in our perspective on endoscopic treatment for asymptomatic CBDS.Further studies examining long-term complication risks of ERCP and wait-and-see groups for asymptomatic CBDS are warranted to discuss whether routine endoscopic treatment for asymptomatic CBDS is justified or not.
文摘A new collaborative filtered recommendation strategy oriented to trajectory data is proposed for communication bottlenecks and vulnerability in centralized system structure location services. In the strategy based on distributed system architecture, individual user information profiles were established using daily trajectory information and neighboring user groups were established using density measure. Then the trajectory similarity and profile similarity were calculated to recommend appropriate location services using collaborative filtering recommendation method. The strategy was verified on real position data set. The proposed strategy provides higher quality location services to ensure the privacy of user position information.
基金supported by the Jiangsu Science and Technology Think Tank Program(Youth)Project(JSKX24085)the Jiangsu Provincial College Students Innovation and Entrepreneurship Training Plan Project(202311276097Y).
文摘With the rapid development of electric vehicles,the requirements for charging stations are getting higher and higher.In this study,we constructed a charging station topology network inNanjing through the Space-L method,mapping charging stations as network nodes and constructing edges through road relationships.The experiment introduced five EV charging recommendation strategies(based on distance,number of fast charging piles,user preference,price,and overall rating)used to simulate disordered charging caused by different user preferences,and the impact of the networkdynamic robustness in case of node failure is exploredby simulating the load-capacity cascade failure model.In this paper,two important metrics for evaluating network robustness are selected:the relative size of the maximum connected subgraph and the network efficiency.The experimental results point out that in the price recommendation strategy,the network stability significantly decreases when the node failure ratio reaches 75.4%,while the fast charging quantity recommendation strategy significantly decreases when the node failure ratio is 62.3%.Therefore,the robustness of the charging station network is best under the price recommendation,while the network robustness is poor under the fast charging quantity recommendation.While the network robustness is poor under preference recommendation.Based on this finding,this study particularly emphasizes that in the process of improving the robustness of the charging station network,it is necessary to comprehensively consider the market demand and guide users to charge in an orderly manner by reasonably adjusting the price strategy.This strategy not only effectively prevents network stability problems that may result fromdisorderly charging behavior,but also enhances the ability of the charging network to resist node failure and improves the overall dynamic robustness of the network.
文摘The performance of deep recommendation models degrades significantly under data poisoning attacks.While adversarial training methods such as Vulnerability-Aware Training(VAT)enhance robustness by injecting perturbations into embeddings,they remain limited by coarse-grained noise and a static defense strategy,leaving models susceptible to adaptive attacks.This study proposes a novel framework,Self-Purification Data Sanitization(SPD),which integrates vulnerability-aware adversarial training with dynamic label correction.Specifically,SPD first identifies high-risk users through a fragility scoring mechanism,then applies self-purification by replacing suspicious interactions with model-predicted high-confidence labels during training.This closed-loop process continuously sanitizes the training data and breaks the protection ceiling of conventional adversarial training.Experiments demonstrate that SPD significantly improves the robustness of both Matrix Factorization(MF)and LightGCN models against various poisoning attacks.We show that SPD effectively suppresses malicious gradient propagation and maintains recommendation accuracy.Evaluations on Gowalla and Yelp2018 confirmthat SPD-trainedmodels withstandmultiple attack strategies—including Random,Bandwagon,DP,and Rev attacks—while preserving performance.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2024-02-02152).
文摘The Internet of Things(IoT)and cloud computing have significantly contributed to the development of smart cities,enabling real-time monitoring,intelligent decision-making,and efficient resource management.These systems,particularly in IoT networks,rely on numerous interconnected devices that handle time-sensitive data for critical applications.In related approaches,trusted communication and reliable device interaction have been overlooked,thereby lowering security when sharing sensitive IoT data.Moreover,it incurs additional energy consumption and overhead while addressing potential threats in the dynamic environment.In this research,an Artificial Intelligence(AI)recommended fault-tolerant framework is proposed that leverages blockchain technology,aiming to enhance device trustworthiness and ensure data privacy.In addition,the intelligence of the proposed framework enables more authentic and authorized device involvement in data routing,thereby enabling seamless transmission in smart cities integrated with lightweight computing.To evaluate dynamic network conditions,the proposed framework offers a timely decision-making system to ensure robust delivery of IoT-assisted services.Using simulations,the efficacy of the proposed framework is validated by comparing it with existing approaches across various network metrics,demonstrating remarkable performance while achieving energy efficiency and optimizing network resources.
基金funded by the Directorate General of Research and Development,Ministry of Higher Education,Science and Technology of the Republic of Indonesia,with grant number 2.6.63/UN32.14.1/LT/2025.
文摘Recommendation systems are an integral and indispensable part of every digital platform,as they can suggest content or items to users based on their respective needs.Collaborative filtering is a technique often used in various studies,which produces recommendations by analyzing similarities between users and items based on their behavior.Although often used,traditional collaborative filtering techniques still face the main challenge of sparsity.Sparsity problems occur when the data in the system is sparse,meaning that only a portion of users provide feedback on some items,resulting in inaccurate recommendations generated by the system.To overcome this problem,we developed aHybrid Collaborative Filtering model based onMatrix Factorization andGradient Boosting(HCF-MFGB),a new hybrid approach.Our proposed model integrates SVD++,the XGBoost ensemble learning algorithm,and utilizes user demographic data and meta items.We utilize information,both explicitly and implicitly,to learn user preference patterns using SVD++.The XGBoost algorithm is used to create hundreds of decision trees incrementally,thereby improving model accuracy.Meanwhile,user demographic and meta-item data are clustered using the K-Means Clustering algorithm to capture similarities in user and item characteristics.This combination is designed to improve rating prediction accuracy by reducing reliance on minimal explicit rating data,while addressing sparsity issues in movie recommendation systems.The results of experiments on the MovieLens 100K,MovieLens 1M,and CiaoDVD datasets show significant improvements,outperforming various other baselinemodels in terms of RMSE and MAE.On theMovieLens 100K dataset,the HCF-MFGB model obtained an RMSE value of 0.853 and an MAE value of 0.674.On theMovieLens 1M dataset,the HCF-MFGB model obtained an RMSE value of 0.763 and an MAE value of 0.61.On the CiaoDCD dataset,the HCF-MFGB model achieved an RMSE value of 0.718 and an MAE value of 0.495.These results confirm a significant improvement in movie recommendation accuracy with the proposed approach.
基金supported by the National Key R&D Program of China[2022YFF0902703]the State Administration for Market Regulation Science and Technology Plan Project(2024MK033).
文摘Recommendation systems are key to boosting user engagement,satisfaction,and retention,particularly on media platforms where personalized content is vital.Sequential recommendation systems learn from user-item interactions to predict future items of interest.However,many current methods rely on unique user and item IDs,limiting their ability to represent users and items effectively,especially in zero-shot learning scenarios where training data is scarce.With the rapid development of Large Language Models(LLMs),researchers are exploring their potential to enhance recommendation systems.However,there is a semantic gap between the linguistic semantics of LLMs and the collaborative semantics of recommendation systems,where items are typically indexed by IDs.Moreover,most research focuses on item representations,neglecting personalized user modeling.To address these issues,we propose a sequential recommendation framework using LLMs,called CIT-Rec,a model that integrates Collaborative semantics for user representation and Image and Text information for item representation to enhance Recommendations.Specifically,by aligning intuitive image information with text containing semantic features,we can more accurately represent items,improving item representation quality.We focus not only on item representations but also on user representations.To more precisely capture users’personalized preferences,we use traditional sequential recommendation models to train on users’historical interaction data,effectively capturing behavioral patterns.Finally,by combining LLMs and traditional sequential recommendation models,we allow the LLM to understand linguistic semantics while capturing collaborative semantics.Extensive evaluations on real-world datasets show that our model outperforms baseline methods,effectively combining user interaction history with item visual and textual modalities to provide personalized recommendations.
基金supported by the Chung-Ang University Research Grants in 2023.Alsothe work is supported by the ELLIIT Excellence Center at Linköping–Lund in Information Technology in Sweden.
文摘Recommending personalized travel routes from sparse,implicit feedback poses a significant challenge,as conventional systems often struggle with information overload and fail to capture the complex,sequential nature of user preferences.To address this,we propose a Conditional Generative Adversarial Network(CGAN)that generates diverse and highly relevant itineraries.Our approach begins by constructing a conditional vector that encapsulates a user’s profile.This vector uniquely fuses embeddings from a Heterogeneous Information Network(HIN)to model complex user-place-route relationships,a Recurrent Neural Network(RNN)to capture sequential path dynamics,and Neural Collaborative Filtering(NCF)to incorporate collaborative signals from the wider user base.This comprehensive condition,further enhanced with features representing user interaction confidence and uncertainty,steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations,effectively mitigating the data sparsity problem.Recommendations are then formulated using an Anchor-and-Expand algorithm,which selects relevant starting Points of Interest(POI)based on user history,then expands routes through latent similarity matching and geographic coherence optimization,culminating in Traveling Salesman Problem(TSP)-based route optimization for practical travel distances.Experiments on a real-world check-in dataset validate our model’s unique generative capability,achieving F1 scores ranging from 0.163 to 0.305,and near-zero pairs−F1 scores between 0.002 and 0.022.These results confirm the model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’past itineraries.This work provides a robust solution for personalized travel planning,capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence.
基金funded by Soonchunhyang University,Grant Number 20250029。
文摘Recommendation systems have become indispensable for providing tailored suggestions and capturing evolving user preferences based on interaction histories.The collaborative filtering(CF)model,which depends exclusively on user-item interactions,commonly encounters challenges,including the cold-start problem and an inability to effectively capture the sequential and temporal characteristics of user behavior.This paper introduces a personalized recommendation system that combines deep learning techniques with Bayesian Personalized Ranking(BPR)optimization to address these limitations.With the strong support of Long Short-Term Memory(LSTM)networks,we apply it to identify sequential dependencies of user behavior and then incorporate an attention mechanism to improve the prioritization of relevant items,thereby enhancing recommendations based on the hybrid feedback of the user and its interaction patterns.The proposed system is empirically evaluated using publicly available datasets from movie and music,and we evaluate the performance against standard recommendation models,including Popularity,BPR,ItemKNN,FPMC,LightGCN,GRU4Rec,NARM,SASRec,and BERT4Rec.The results demonstrate that our proposed framework consistently achieves high outcomes in terms of HitRate,NDCG,MRR,and Precision at K=100,with scores of(0.6763,0.1892,0.0796,0.0068)on MovieLens-100K,(0.6826,0.1920,0.0813,0.0068)on MovieLens-1M,and(0.7937,0.3701,0.2756,0.0078)on Last.fm.The results show an average improvement of around 15%across all metrics compared to existing sequence models,proving that our framework ranks and recommends items more accurately.
文摘Conversational recommender systems(CRSs)focus on refining preferences and providing personalized recommendations through natural language interactions and dialogue history.Large language models(LLMs)have shown outstanding performance across various domains,thereby prompting researchers to investigate their applicability in recommendation systems.However,due to the lack of task-specific knowledge and an inefficient feature extraction process,LLMs still have suboptimal performance in recommendation tasks.Therefore,external knowledge sources,such as knowledge graphs(KGs)and knowledge bases(KBs),are often introduced to address the issue of data sparsity.Compared to KGs,KBs possess higher retrieval efficiency,making them more suitable for scenarios where LLMs serve as recommenders.To this end,we introduce a novel framework integrating LLMs with KBs for enhanced retrieval generation,namely LLMKB.LLMKB initially leverages structured knowledge to create mapping dictionaries,extracting entity-relation information from heterogeneous knowledge to construct KBs.Then,LLMKB achieves the embedding calibration between user information representations and documents in KBs through retrieval model fine-tuning.Finally,LLMKB employs retrievalaugmented generation to produce recommendations based on fused text inputs,followed by post-processing.Experiment results on two public CRS datasets demonstrate the effectiveness of our framework.Our code is publicly available at the link:https://anonymous.4open.science/r/LLMKB-6FD0.
文摘1.Introduction The COVID-19 pandemic is affecting the lives of the world population in various ways and has resulted in an unforeseen scale of disruption of activities across the globe.Its emergence has health and economic implications that impact individuals,organizations and sovereign states which is inclusive of the stakeholders in a tax system.Thus,revenue authorities need to take actions to protect and ease the burden on its external and internal stakeholders.
基金supported by the National Natural Science Foundation of China(Grant No.81872624)Fundamental Research Program of Shanxi Province(Grant No.202403021211139).
文摘Objective This study aimed to reexplore minimum iodine excretion and to build a dietary iodine recommendation for Chinese adults using the obligatory iodine loss hypothesis.Methods Data from 171 Chinese adults(19–21 years old)were collected and analyzed based on three balance studies in Shenzhen,Yinchuan,and Changzhi.The single exponential equation was accordingly used to simulate the trajectory of 24 h urinary iodine excretion as the low iodine experimental diets offered(iodine intake:11-26μg/day)and to further deduce the dietary reference intakes(DRIs)for iodine,including estimated average requirement(EAR)and recommended nutrient intake(RNI).Results The minimum iodine excretion was estimated as 57,58,and 51μg/day in three balance studies,respectively.Moreover,it was further suggested as 57,58,and 51μg/day for iodine EAR,and 80,81,and 71μg/day for iodine RNI or expressed as 1.42,1.41,and 1.20μg/(day·kg)of body weight.Conclusion The iodine DRIs for Chinese adults were established based on the obligatory iodine loss hypothesis,which provides scientific support for the amendment of nutrient requirements.
文摘Azoospermia,defined as the absence of sperm in the ejaculate,is a well-documented consequence of exogenous testosterone(ET)and anabolic–androgenic steroid(AAS)use.These agents suppress the hypothalamic–pituitary–gonadal(HPG)axis,leading to reduced intratesticular testosterone levels and impaired spermatogenesis.This review examines the pathophysiological mechanisms underlying azoospermia and outlines therapeutic strategies for recovery.Azoospermia is categorized into pretesticular,testicular,and post-testicular types,with a focus on personalized treatment approaches based on the degree of HPG axis suppression and baseline testicular function.Key strategies include discontinuing ET and monitoring for spontaneous recovery,particularly in patients with shorter durations of ET use.For cases of persistent azoospermia,gonadotropins(human chorionic gonadotropin[hCG]and follicle-stimulating hormone[FSH])and selective estrogen receptor modulators(SERMs),such as clomiphene citrate,are recommended,either alone or in combination.The global increase in exogenous testosterone use,including testosterone replacement therapy and AAS,underscores the need for improved management of associated azoospermia,which can be temporary or permanent depending on individual factors and the type of testosterone used.Additionally,the manuscript discusses preventive strategies,such as transitioning to short-acting testosterone formulations or incorporating low-dose hCG to preserve fertility during ET therapy.While guidelines for managing testosterone-related azoospermia remain limited,emerging research indicates the potential efficacy of hormonal stimulation therapies.However,there is a notable lack of well-structured,controlled,and long-term studies addressing the management of azoospermia related to exogenous testosterone use,highlighting the need for such studies to inform evidence-based recommendations.
