Search scope:
排序: Display mode:
A self-supervised method for treatment recommendation in sepsis Research Articles
Sihan Zhu, Jian Pu,jianpu@fudan.edu.cn
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 7, Pages 926-939 doi: 10.1631/FITEE.2000127
Keywords: 治疗推荐;脓毒症;自监督学习;强化学习;电子病历
Non-IID Recommender Systems: A Review and Framework of Recommendation Paradigm Shifting Artical
Longbing Cao
Engineering 2016, Volume 2, Issue 2, Pages 212-224 doi: 10.1016/J.ENG.2016.02.013
While recommendation plays an increasingly critical role in our living, study, work, and entertainment, the recommendations we receive are often for irrelevant, duplicate, or uninteresting products and services. A critical reason for such bad recommendations lies in the intrinsic assumption that recommended users and items are independent and identically distributed (IID) in existing theories and systems. Another phenomenon is that, while tremendous efforts have been made to model specific aspects of users or items, the overall user and item characteristics and their non-IIDness have been overlooked. In this paper, the non-IID nature and characteristics of recommendation are discussed, followed by the non-IID theoretical framework in order to build a deep and comprehensive understanding of the intrinsic nature of recommendation problems, from the perspective of both couplings and heterogeneity. This non-IID recommendation research triggers the paradigm shift from IID to non-IID recommendation research and can hopefully deliver informed, relevant, personalized, and actionable recommendations. It creates exciting new directions and fundamental solutions to address various complexities including cold-start, sparse data-based, cross-domain, group-based, and shilling attack-related issues.
Keywords: Independent and identically distributed (IID) Non-IID Heterogeneity Coupling relationship Coupling learning Relational learning IIDness learning Non-IIDness learning Recommender system Recommendation Non-IID recommendation
Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation
孙曦,吕志民
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 9, Pages 1273-1286 doi: 10.1631/FITEE.2200304
Keywords: Point-of-interest recommendation Spatiotemporal effects Long short-term memory (LSTM) Attention mechanism
DAN: a deep association neural network approach for personalization recommendation Research Articles
Xu-na Wang, Qing-mei Tan,Xuna@nuaa.edu.cn,tanchina@nuaa.edu.cn
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 7, Pages 963-980 doi: 10.1631/FITEE.1900236
Keywords: Neural network Deep learning Deep association neural network (DAN) Recommendation
Cohort-based personalized query auto-completion Regular Papers-Research Articles
Dan-yang JIANG, Hong-hui CHEN
Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 9, Pages 1246-1258 doi: 10.1631/FITEE.1800010
Keywords: Query auto-completion Cohort-based retrieval Topic models
Toward Privacy-Preserving Personalized Recommendation Services Review
Cong Wang, Yifeng Zheng, Jinghua Jiang, Kui Ren
Engineering 2018, Volume 4, Issue 1, Pages 21-28 doi: 10.1016/j.eng.2018.02.005
Recommendation systems are crucially important for the delivery of personalized services to users. With personalized recommendation services, users can enjoy a variety of targeted recommendations such as movies, books, ads, restaurants, and more. In addition, personalized recommendation services have become extremely effective revenue drivers for online business. Despite the great benefits, deploying personalized recommendation services typically requires the collection of users’ personal data for processing and analytics, which undesirably makes users susceptible to serious privacy violation issues. Therefore, it is of paramount importance to develop practical privacy-preserving techniques to maintain the intelligence of personalized recommendation services while respecting user privacy. In this paper, we provide a comprehensive survey of the literature related to personalized recommendation services with privacy protection. We present the general architecture of personalized recommendation systems, the privacy issues therein, and existing works that focus on privacy-preserving personalized recommendation services. We classify the existing works according to their underlying techniques for personalized recommendation and privacy protection, and thoroughly discuss and compare their merits and demerits, especially in terms of privacy and recommendation accuracy. We also identity some future research directions.
Keywords: Privacy protection Personalized recommendation services Targeted delivery Collaborative filtering Machine learning
Diagnosis and treatment for one case with advanced abdominal pregnancy
Shen Ying,Dai Shuyan
Strategic Study of CAE 2015, Volume 17, Issue 6, Pages 61-64
Objective:To explore the diagnosis and treatment of advanced abdominal pregnancy. Methods:A retrospective analysis and summary were performed about 1 case of advanced abdominal pregnancy diagnosis and treatment in our hospital. Results:The case was diagnosis by MRI,and surgical treatment was successful. Conclusion:Abdominal pregnancy is not a typical clinical symptom and early diagnosis is difficult,MRI is an effective diagnosis. Surgery is the most important treatment.
Keywords: abdominal pregnancy diagnosis treatment MRI
EncyCatalogRec: catalog recommendation for encyclopedia article completion Article
Wei-ming LU, Jia-hui LIU, Wei XU, Peng WANG, Bao-gang WEI
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 3, Pages 436-447 doi: 10.1631/FITEE.1800363
Keywords: Catalog recommendation Encyclopedia article completion Product graph Transductive learning
Medical Cyclotron Used for Diagnostic or Therapy
Fan Mingwu
Strategic Study of CAE 2000, Volume 2, Issue 12, Pages 9-15
Cyclotron operated within a hospital to deliver radiation to produce short life radioactive isotopes for diagnostic purpose is used in many hospitals. But cyclotron used for proton therapy is just at beginning. Proton beam therapy is a technologically advanced approach since it achieves precise radiation dose distribution. As the depth of penetration is a function of its energy, the point of energy release of the proton can be very precisely determined. The path of the proton beam is linear and causes very little secondary lateral scatter. Healthy tissues upstream from the tumor receive only a small dose and those located around the tumor and behind receive virtually none. Thus proton beam therapy is the most effective method. On the other hand, the cyclotron must be reliable, and the beam must be stable to ensure patient´s safety since the proton beam is used directly. Efficiency of beam delivery to the treatment rooms, raster scanning techniques to ensure the correct control of beam energy, intensity, and position stability, rapid and precise flexibility in changing beam parameter are also essential for satisfying clinical needs. The design efforts for developing a hsopital-based medical therapy cyclotron including the clinical beam delivery systems and integrated control system are really complex, and are less well developed than patients real need. A conception scheme for the purpose is proposed.
Keywords: cyclotron positron emission tomography short life radioisotope proton beam therapy
Fast code recommendation via approximate sub-tree matching Research Article
Yichao SHAO, Zhiqiu HUANG, Weiwei LI, Yaoshen YU,shaoyichao@nuaa.edu.cn,zqhuang@nuaa.edu.cn
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 8, Pages 1205-1216 doi: 10.1631/FITEE.2100379
Keywords: Code reuse Code recommendation Tree similarity Structure information
RepoLike: amulti-feature-based personalized recommendation approach for open-source repositories None
Cheng YANG, Qiang FAN, Tao WANG, Gang YIN, Xun-hui ZHANG, Yue YU, Hua-min WANG
Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 2, Pages 222-237 doi: 10.1631/FITEE.1700196
With the deep integration of software collaborative development and social networking, social coding represents a new style of software production and creation paradigm. Because of their good flexibility and openness, a large number of external contributors have been attracted to the open-source communities. They are playing a significant role in open-source development. However, the open-source development online is a globalized and distributed cooperative work. If left unsupervised, the contribution process may result in inefficiency. It takes contributors a lot of time to find suitable projects or tasks from thousands of open-source projects in the communities to work on. In this paper, we propose a new approach called “RepoLike,” to recommend repositories for developers based on linear combination and learning to rank. It uses the project popularity, technical dependencies among projects, and social connections among developers to measure the correlations between a developer and the given projects. Experimental results show that our approach can achieve over 25% of hit ratio when recommending 20 candidates, meaning that it can recommend closely correlated repositories to social developers.
Keywords: Social coding Open-source software Personal recommendation GitHub
A knowledge-guided and traditional Chinese medicine informed approach for herb recommendation Research Article
Zhe JIN, Yin ZHANG, Jiaxu MIAO, Yi YANG, Yueting ZHUANG, Yunhe PAN,11521043@zju.edu.cn,yinzh@zju.edu.cn
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 10, Pages 1416-1429 doi: 10.1631/FITEE.2200662
Keywords: Traditional Chinese medicine Herb recommendation Knowledge graph Graph attention network
Guan Rui,Liu Yuhuan,Xu Mingjuan,Zhang Junjie,Hui Ning,Cui Ying
Strategic Study of CAE 2015, Volume 17, Issue 6, Pages 45-49
To investigate the treatment methods of retaining reproductive function in cesarean scar pregnancy. Clinical datus of 46 casesSin our hospital during 2000―2014Swere analyzed retrospectively.SThere were 45 cases of first-trimesterSpregnancy andS1 case of second-trimester pregnancy. 13 casesS(28.9 %)Sof first-trimesteSpregnancy were misdiagnosed and had received artificial abortion before hospitalization. According to CSP classificationS,S19Scases were type I,S13 cases were Stype II,Sall cases wereSsuccessful inSretaining the uterus. 63.1 % of type IScases receivedSuterine curettage under ultrasoundSmonitoring,S21%Sof type I casesSreceivedSuterineScurettageSafter uterine artery embolizationS(UAE)S. 84.6 %Sof type IIScases received surgery in which lesion were resected and uterine scar were repaired. The csp patient of second-trimester pregnancy suffered from thrombosis of lower extremity and rebleeding 30 days after UAE, she received the surgery of resecting lesion. Conclusion: STheSkeySforStheSconservativeStreatmentSSofS CSPSSis early diagnosis and early treatment. TreatmentSshouldSbeSindividualizedSaccording to CSP clinicSclassification ,β-HCG and so on.Furthermore, there are still someSrisk of UAE.WeSshould be careful to select UAESfor patients.
Keywords: Scesarean scar pregnancy Sindividualized treatment Spreservation of fertility uterine artery embolization
Experimental Studies on Recombinant Hepatitis B Immunogenic Complex Therapeutic Vaccine (YIC)
Wenyu mei,He Lifang,Qu Di,Ma Zhangmei,Yao Xin
Strategic Study of CAE 1999, Volume 1, Issue 1, Pages 38-42
A therapeutic vaccine composed of HBsAg complexed to anti-HBs (IC) has been developed for viral hepatitis B. Enhanced immune response was induced in hosts immunized with this complex, and the mechanisms of this vaccine was studied in mice. It was shown that the Fc fragment of anti-HBs in the complex was critical for induction of potent immune responses. The Fc fragment of the anti-HBs in the complex could attach to the Fc receptors on the antigen presenting cells (APC), increasing the uptake of HBsAg into these cells. After being ingested, the antigen complexed to antibody could be more effectively processed and presented to T cells. After incubation with macrophages previously treated with IC, T cells showed higher proliferation rate, and higher level of interferon-7 mRNA was detected. Enhanced immune response in host has also been shown by comparing anti-HBs titer in mice immunized with antigen-antibody complex versus the anti-HBs titer in mice immunized only with HBsAg. More than tenfold increase in anti-HBs was observed in the latter group. In addi-tion, this complex was used to immunize an HBsAg low-responder mouse strain (B10.S). Compared to the normal responsive counterpart mouse strain (BIO), immunization with HBsAg induced low titer of antibody, whereas, immunization using HBsAg-anti-HBs complex, BIO.S mice responded by producing similar level of anti-HBs as that induced in the BIO mice. When the complex was used to immunize HBsAg positive transgenic mice (TgE),after four injections, in the female mice, 72% cleared HBsAg and developed anti-HBs (mean titer 1 • 1070 by EIA); while in the male mice, 54% cleared HBsAg and developed anti-HBs (mean titer 1:455 by EIA). Though some of non-immunized mice lost their HBsAg spontaneously during the experiment, none developed anti-HBs. Data showed that this immunogenic complex has promising potential to be used for the treatment of hepatitis B patients. For human use, a therapeutic vaccine composed of yeast-derived recombinant HBsAg complexed to human high-titer anti-HBs immunoglobulin (HBIG) has been developed. Standard procedure for manufacturing this complex, as well as in vitro assay for monitoring its effect were also established. This complex will be further optimized for mass production and application for clinical trial will be submitted.
Keywords: hepatitis B therapeutic vaccine antigen-antibody complex immune responses
Liu Li,Wu Chunlin,Hu Yajun
Strategic Study of CAE 2015, Volume 17, Issue 6, Pages 31-35
Objective:To find out the general clinical characteristics from patients with normal ovulation,small follicular ovulation and luteinized unruptured follicle and observe the result of ovulation detection repeatedly and the effect of ovarian stimulatioin for later two types. Methods:Retrospective analyzing the difference of the patients’age,basal serum gonadal steroid hormones and follicle size before ovulation in the groups of normal ovulation(n=258), small follicular ovulation(n=65)and luteinized unruptured follicle(n=27). Then we observed the result of ovulation detection repeatedly by transvaginal ultrasound in the latter two groups. Finally,the ovulation induction with clomiphene citrate was carried out in the 58 cases of small follicles ovulation and 25 cases of luteinizing unruptured follicle which obtained the consistent results during the twice ovulation detection,we observed the rates of normal ovulation and clinical pregnancy in the two types of ovulatory dysfunctions. Results:Average age and basal serum Gonadal steroid hormones levelsdid not have significant difference(P<0.01)in thegroups of normal ovulation,small follicular ovulation and luteinized unruptured follicle,average diameter of follicles before ovulation in the three groups had significant difference(F=117.9,P< 0.01). Incidence rates of small follicular ovulation and luteinized unruptured follicle were 18.5 % and 7.71 % respectively. Both were detected repeatedly,repetition rates were 89.23 % and 92.59 % respectively. After combined induced ovulation by clomiphene withluteal support, normal ovulation rates were 70.69 % and 80 % in the groups of small follicular ovulation and unruptured follicle ovulation luteinized respectively,clinical pregnancy rateswere 29.31 % and 48 % respectively. Conclusions:Small follicular ovulation and luteinized unruptured follicle are two special types of ovulatory dysfunctions,basal serum gonadal steroid hormones levels cannot predict ovulation,and transvaginal ultrasound is the most direct method to diagnosisthe small follicular ovulation and luteinized unruptured follicle. Without treatment,the repetition rate is high in thetwo types of ovulatory dysfunctions. Combined induced ovulation withluteal support is effective in the patients of the small follicular ovulation and luteinized unruptured follicle.
Keywords: transvaginalultrasound ovulation detection small follicular ovulation luteinized unruptured follicle ovulation induction
Title Author Date Type Operation
A self-supervised method for treatment recommendation in sepsis
Sihan Zhu, Jian Pu,jianpu@fudan.edu.cn
Journal Article
Non-IID Recommender Systems: A Review and Framework of Recommendation Paradigm Shifting
Longbing Cao
Journal Article
Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation
孙曦,吕志民
Journal Article
DAN: a deep association neural network approach for personalization recommendation
Xu-na Wang, Qing-mei Tan,Xuna@nuaa.edu.cn,tanchina@nuaa.edu.cn
Journal Article
Toward Privacy-Preserving Personalized Recommendation Services
Cong Wang, Yifeng Zheng, Jinghua Jiang, Kui Ren
Journal Article
Diagnosis and treatment for one case with advanced abdominal pregnancy
Shen Ying,Dai Shuyan
Journal Article
EncyCatalogRec: catalog recommendation for encyclopedia article completion
Wei-ming LU, Jia-hui LIU, Wei XU, Peng WANG, Bao-gang WEI
Journal Article
Fast code recommendation via approximate sub-tree matching
Yichao SHAO, Zhiqiu HUANG, Weiwei LI, Yaoshen YU,shaoyichao@nuaa.edu.cn,zqhuang@nuaa.edu.cn
Journal Article
RepoLike: amulti-feature-based personalized recommendation approach for open-source repositories
Cheng YANG, Qiang FAN, Tao WANG, Gang YIN, Xun-hui ZHANG, Yue YU, Hua-min WANG
Journal Article
A knowledge-guided and traditional Chinese medicine informed approach for herb recommendation
Zhe JIN, Yin ZHANG, Jiaxu MIAO, Yi YANG, Yueting ZHUANG, Yunhe PAN,11521043@zju.edu.cn,yinzh@zju.edu.cn
Journal Article
Treatment of retaining reproductive function?in cesarean scar pregnancy:A clinical analysis of 46 cases
Guan Rui,Liu Yuhuan,Xu Mingjuan,Zhang Junjie,Hui Ning,Cui Ying
Journal Article
Experimental Studies on Recombinant Hepatitis B Immunogenic Complex Therapeutic Vaccine (YIC)
Wenyu mei,He Lifang,Qu Di,Ma Zhangmei,Yao Xin
Journal Article