Differentially Private Support Vector Machines with Knowledge Aggregation

With the widespread data collection and processing,privacy-preserving machine learning has become increasingly important in addressing privacy risks related to individuals.Support vector machine(SVM)is one of the most elementary learning models of machine learning.Privacy issues surrounding SVM classifier training have attracted increasing attention.In this paper,we investigate Differential Privacy-compliant Federated Machine Learning with Dimensionality Reduction,called FedDPDR-DPML,which greatly improves data utility while providing strong privacy guarantees.Considering in distributed learning scenarios,multiple participants usually hold unbalanced or small amounts of data.Therefore,FedDPDR-DPML enables multiple participants to collaboratively learn a global model based on weighted model averaging and knowledge aggregation and then the server distributes the global model to each participant to improve local data utility.Aiming at high-dimensional data,we adopt differential privacy in both the principal component analysis(PCA)-based dimensionality reduction phase and SVM classifiers training phase,which improves model accuracy while achieving strict differential privacy protection.Besides,we train Differential privacy(DP)-compliant SVM classifiers by adding noise to the objective function itself,thus leading to better data utility.Extensive experiments on three high-dimensional datasets demonstrate that FedDPDR-DPML can achieve high accuracy while ensuring strong privacy protection.

A Knowledge Model-and Growth Model-Based Decision Support System for Wheat Management

By applying the system analysis principle and mathematical modeling technique to knowledge expression system for crop cultural management, the fundamental relationships and quantitative algorithms of wheat growth and management indices to variety types, ecological environments and production levels were analysed and extracted, and a dynamic knowledge model with temporal and spatial characters for wheat management(WheatKnow)was developed. By adopting the soft component characteristics as non language relevance , re-utilization and portable system maintenance. and by further integrating the wheat growth simulation model(WheatGrow)and intelligent system for wheat management, a comprehensive and digital knowledge model, growth model and component-based decision support system for wheat management(MBDSSWM)was established on the platforms of Visual C++ and Visual Basic. The MBDSSWM realized the effective integration and coupling of the prediction and decision-making functions for digital crop management.

Basic life support:knowledge and attitude of medical/paramedical professionals

BACKGROUND:Basic life support(BLS),a key component of the chain of survival decreases the arrest-cardiopulmonary resuscitation interval and increases the rate of hospital discharge.The study aimed to explore the knowledge of and attitude towards basic life support(BLS)among medical/paramedical professionals.METHODS:An observational study was conducted by assessing response to self prepared questionnaire consisting of the demographic information of the medical/paramedical staff,their personnel experience/attitude and knowledge of BLS based on the 2005 BLS Guidelines of European Resuscitation Council.RESULTS:After excluding incomplete questionnaires,the data from 121 responders(27 clinical faculty members,21 dental and basic sciences faculty members,29 house officers and 44 nurses and health assistants)were analyzed.Only 9(7.4%)of the 121 responders answered≥11,53(43%)answered 7-10,and 58(48%)answered<7 of 15 questions correctly.The clinical faculty members,house officers and nurses/HA had a mean score of 7.4±3.15,7.37±2.02 and 6.63±2.16 respectively,while dental/basic sciences faculty members attained a least mean score of 4.52±2.13(P<0.001).Those who had received cardiopulmonary resuscitation(CPR)training within 5 years obtained a highest mean score of 8.62±2.49,whereas those who had the training more than 5 years back or no training obtained a mean score of 5.54±2.38 and 6.1±2.29 respectively(P=0.001).Those who were involved in resuscitation frequently had a higher median score of 8 in comparison to those who were seldom involved or not involved at all(P<0.001).CONCLUSIONS:The average health personnel in our hospital lack adequate knowledge in CPR/BLS.Training and experience can enhance knowledge of CPR of these personnel.Thus standard of CPR/BLS training and assessment are recommended at our hospital.

Assessment of knowledge and attitude about basic life support among dental interns and postgraduate students in Bangalore city,India

BACKGROUND: Life-threatening emergencies can occur at anytime, at anywhere and in anyone. Effective management of an emergency situation in the dental office is ultimately the dentist's responsibility. The lack of training and inability to cope with medical emergencies can lead to tragic consequences and sometimes legal complications. Therefore, health professionals including dentists must be well prepared to deal with medical emergencies. This study was undertaken to assess the knowledge about and attitude towards basic life support(BLS) among dental interns and postgraduate students in Bangalore city, India.METHODS: A cross sectional survey was conducted among dental interns and postgraduate students from May 2014 to June 2014 since few studies have been conducted in Bangalore city. A questionnaire with 17 questions regarding the knowledge about and attitude towards BLS was distributed to 202 study participants.RESULTS: The data analyzed using the Chi-square test showed that dental interns and postgraduate students had average knowledge about BLS. In the 201 participants, 121(59.9%) had a positive attitude and 81(40.1%) had a negative attitude towards BLS.CONCLUSIONS: Cardiopulmonary resuscitation should be considered as part of the dental curriculum. Workshops on a regular basis should be focused on skills of cardiopulmonary resuscitation for dental students.

Computer Support for Concept Engineering Design：Enabling Interaction with Design Knowledge

This paper addresses the question of how to support the designer with appropriate knowledge during conceptual design. It begins with a discussion of knowledge-based support for design and is followed by a scenario account of the use of a Knowledge Support System. A system is described that demonstrates interaction with different forms of knowledge in concept vehicle design.It supports the creation of new designs by way of a solution generation and evaluation process that relies upon co-operation between the designer and the knowledge system. The results of user evaluation gave rise to a current research agenda which addresses the requirements of a multi-user platform for a design knowledge support environment for collaborative team work.

Integration of Decision-Support and Knowledge-Based Techniques in a Problem-Solving Strategy for Selection Problems

The limitations of traditional approaches to selection problems are examined. A problemsolving strategy is presented in which decision-support and knowledge-based techniques play complementary roles. An approach to the representation of knowledge to support the problem-solving strategy is presented which avoids commitment to a specific programming language or implementation environment. The problem of choosing a home is used to illustrate the representation of knowledge in a specific problem domain. Techniques for implementation of the problem-solving strategy are described. Knowledge elicitation techniques and their implementation in a development shell for application of the problem-solving strategy to any selection problem are also described.

Assessment of Knowledge, Attitudes and Support of Health Professionals towards Biobanks in Eastern Morocco

Background: Health professionals play a key role in increasing the rate of biobanking participation. Here, we assessed the knowledge and attitude of health professionals in Eastern Morocco towards biobanks and their willingness to recruit patients into biobanks. Methods: A cross-sectional study carried out among health professionals working in various public and private health centers in Eastern Morocco. The data were obtained using a self-administered anonymous questionnaire. Results: 600 health professionals were included in the study. Only 37.5% of them had knowledge of biobanks. Associations analysis showed that among health professionals, physicians had more knowledge of biobanks (OR = 2.50, p = 0.000), and health professionals working at the University Hospital had more knowledge of biobanks compared to those working in the other participating health centers (p Conclusions: This study indicates that health professionals in Eastern Morocco showed a notable lack of knowledge about biobanks. However, the majority were willing to donate their own biospecimens and supported the recruitment of patients into biobanks. This study was a good opportunity to raise awareness among health professionals about the interest of biobanks in the development of biomedical research in Eastern Morocco.

Correlation of long-term medication behaviour self-efficacy with social support and medication knowledge of kidney transplant recipients

Aim:This study aimed to explore the correlation of long-term medication behaviour self-efficacy with social support and medication knowledge of kidney transplant recipients.Methods:A convenient sample of kidney transplant recipients in a general hospital in Guangzhou was recruited from November 2016 to January 2017.Self-reported survey data were provided by the kidney transplant recipients using long-term medication behaviour self-efficacy scale(LTMBSES),perceived social support scale(PSSS)and scale for patient-perceived medication knowledge in medication usage.Descriptive statistics and Spearman's correlation analysis were used for data analysis.Results:A total of 195 kidney transplant recipients(132 men and 63 women)were recruited for this study.The mean scores of all LTMBSES dimensions,namely personal attitudes,environmental and taskrelated and behavioural factors,were 32.49±4.34,60.90±7.56 and 32.32±4.40,respectively.The mean scores of three PSSS dimensions,namely,family,friends and significant others,were 24.91±3.42,22.71±4.66 and 22.15±4.26,correspondingly.The mean scores of two five-item knowledge subscale dimensions,namely,general and interaction knowledge,were 9.56±1.07 and 13.02±2.67,respectively.Spearman's correlation analysis showed that social support(rs=0.232,P<0.01)and medication knowledge(rs=0.352,P<0.01)were positively associated with long-term medication self-efficacy in the kidney transplant recipients.Conclusion:The levels of long-term medication self-efficacy,perceived social support and medication knowledge of the kidney transplant recipients were high.Social support and medication knowledge were correlated with self-efficacy.

Use of Data Mining to Support the Development of Knowledge Intensive CAD

In order to compete in the global manufacturing mar ke t, agility is the only possible solution to response to the fragmented market se gments and frequently changed customer requirements. However, manufacturing agil ity can only be attained through the deployment of knowledge. To embed knowledge into a CAD system to form a knowledge intensive CAD (KIC) system is one of way to enhance the design compatibility of a manufacturing company. The most difficu lt phase to develop a KIC system is to capitalize a huge amount of legacy data t o form a knowledge database. In the past, such capitalization process could only be done solely manually or semi-automatic. In this paper, a five step model fo r automatic design knowledge capitalization through the use of data mining is pr oposed whilst details of how to select, verify and performance benchmarking an a ppropriate data mining algorithm for a specific design task will also be discuss ed. A case study concerning the design of a plastic toaster casing was used as an illustration for the proposed methodology and it was found that the avera ge absolute error of the predictions for the most appropriate algorithm is withi n 17%.

A knowledge-based decision support system for engineering design

A knowledge-based decision supporting system, used for engineering design is introduced by describing the architecture, function, workflow of the system and its way of implementation. Based upon information composed of knowledge, models, data, cases, methods, etc, the system is designed to use such methods as knowledge-based reasoning, case-based reasoning, and multi-criteria evaluation techniques to provide effective tools to support the decision-making process.

Research on and implementation of a knowledge-reasoning based evaluation support system

An evaluation support system involving complicated decision making problems during engineering design of products is introduced by first describng and modeling complicated decision making problems, and then constructing and describing the architecture and functional structure of an evaluation support system, based on knowledge-based reasoning. Knowledge contains important experience of field-expert and can be classified and stored in knowledge bases, and therefore, the system suggests information-processing tools based on information resources including data knowledge bases and methods bases, which can be used to evaluate the designs against the multi-criteria decision framework thereby providing decision-makers with rational and scientific information.

Integrating Knowledge－Based Simulation with Aspiration－Directed Model－based Decision Support System

This paper reports an aspiration-directed, model-based decision support system (AMDSS) integrated with a knowledge-based simulation system. The system is designed to study China's mid-range economic development strategy. The capacity of the system is enhanced by the knowledge-based component which provides a knowledge-based simulation environment for model management. Currently the system has passed the stage of prototype and achieves its implementation capacity. The paper first presents the mathematical aspects of decision making including aspiration-directed decision making, then discusses the architecture of the system. The purpose of the paper is to provide insights into how such an integrated system could provide decision support for complex decision analysis.

Construction and realization of the knowledge base and inference engine of an IDSS model for air-conditioning cooling/heating sources selection

The knowledge representation mode and inference control strategy were analyzed according to the specialties of air-conditioning cooling/heating sources selection. The constructing idea and working procedure for knowledge base and inference engine were proposed while the realization technique of the C language was discussed. An intelligent decision support system (IDSS) model based on such knowledge representation and inference mechanism was developed by domain engineers. The model was verified to have a small kernel and powerful capability in list processing and data driving, which was successfully used in the design of a cooling/heating sources system for a large-sized office building.

New Knowledge Network Evaluation Method for Design Rationale Management

Current design rationale （DR） systems have not demonstrated the value of the approach in practice since little attention is put to the evaluation method of DR knowledge. To systematize knowledge management process for future computer-aided DR applications, a prerequisite is to provide the measure for the DR knowledge. In this paper, a new knowledge network evaluation method for DR management is presented. The method characterizes the DR knowledge value from four perspectives, namely, the design rationale structure scale, association knowledge and reasoning ability, degree of design justification support and degree of knowledge representation conciseness. The DR knowledge comprehensive value is also measured by the proposed method. To validate the proposed method, different style of DR knowledge network and the performance of the proposed measure are discussed. The evaluation method has been applied in two realistic design cases and compared with the structural measures. The research proposes the DR knowledge evaluation method which can provide object metric and selection basis for the DR knowledge reuse during the product design process. In addition, the method is proved to be more effective guidance and support for the application and management of DR knowledge.

Knowledge mining collaborative DESVM correction method in short-term load forecasting

Short-term forecasting is a difficult problem because of the influence of non-linear factors and irregular events.A novel short-term forecasting method named TIK was proposed,in which ARMA forecasting model was used to consider the load time series trend forecasting,intelligence forecasting DESVR model was applied to estimate the non-linear influence,and knowledge mining methods were applied to correct the errors caused by irregular events.In order to prove the effectiveness of the proposed model,an application of the daily maximum load forecasting was evaluated.The experimental results show that the DESVR model improves the mean absolute percentage error(MAPE) from 2.82% to 2.55%,and the knowledge rules can improve the MAPE from 2.55% to 2.30%.Compared with the single ARMA forecasting method and ARMA combined SVR forecasting method,it can be proved that TIK method gains the best performance in short-term load forecasting.

Knowledge representation and rule-based solution system for dynamic programming model

A knowledge representation has been proposed using the state space theory of Artificial Intelligence for Dynamic Programming Model, in which a model can be defined as a six tuple M=(I,G,O,T,D,S). A building block modeling method uses the modules of a six tuple to form a rule based solution model. Moreover, a rule based system has been designed and set up to solve the Dynamic Programming Model. This knowledge based representation can be easily used to express symbolical knowledge and dynamic characteristics for Dynamic Programming Model, and the inference based on the knowledge in the process of solving Dynamic Programming Model can also be conveniently realized in computer.

To design and construct an embedded knowledge integration service platform:Taking ISCAS subject group platform as an example

Purpose:As scientific resources are widely distributed,researchers often have difficulties in acquiring information from different individual sources.This paper intends to present a new approach to construct a subject-knowledge-based integration platform which was carried out by the Institute of Software,Chinese Academy of Sciences(ISCAS).Our aim is to use technique tools to strengthen the library service by combining a variety of information service resources with knowledge tools.Design/methodology/approach:Based on the analysis of users’ needs,we established a collaborative team across ISCAS Library,National Science Library of CAS(NSL CAS),and ISCAS’ research groups or research labs.With the service tools developed by ISCAS Library,we embedded other multipurpose utility tools of knowledge integration into the platform as to make full use of software tools in knowledge integration,knowledge fusion,and intelligent push of library services to end users.Findings:With a hard effort of the construction team,the ISCAS subject group platform(hereinafter as ISCAS Platform) has integrated such information resources as institutional repository(IR) of ISCAS,open resources from websites and subject resources of computer sciences.Up to date,ISCAS platform can provide integrated information services including data collection for computer science and intelligent generation of citation reports,by means of embedding self-developed discovering tools for domain experts and subject content,and generation tools for scientific citation reports.Research limitations:Knowledge organization need be further improved in the ISCAS subject group platform.In addition,functions for academic exchanges need be maximized as to meet the individual demands of researchers for library services at the Platform.Practical implications:Since we Platform has been put into use through the Library website of the ISCAS in June 2012,many academic libraries from both domestic universities and CAS institutes have showed their strong interest for our self-developed tools,among which more than 10 cooperation partnerships have been formed.Originality/value:Through self-developed service tools and the integration of multiple-type resources,our Platform has solved such key problems as timely access and update of the trusted resources from a third party,and the rapid fusion and extension of library resources while establishing subject knowledge environment.So the ISCAS library can provide a flexible customization of library services according to the need of different users.

Knowledge Creation Systems in Seven-Eleven Japan

Japanese convenience store chain Seven-Eleven Japan (hereinafter 'SEJ') has been profitable for 30 years by constantly anticipating changing trends regardless of the severe business environment. In this paper, the knowledge creation process and its supportive systems in SEJ to examine how information system can support knowledge creation are described. Using case study method, the knowledge creation theory is applied to SEJ, and the results show that facilitating 'dialogue' and reinforcing 'creative routine' might be the most important functions of information system to support knowledge creation.

A Motivation Framework to Promote Knowledge Translation in Healthcare

Globally,there is a great gulf between medical knowledge and clinical practice.Translating knowledge into clinical decision support(CDS) application has become the biggest challenge faced by evidence based medicine.This paper proposed a comprehensive motivation framework to facilitate knowledge translation in healthcare.Based on a unified medical knowledge ontology and knowledge base,the framework provides an infrastructure of fundamental services,such as inference service and data acquisition,to support development of knowledge-driven CDS applications and integration into clinical workflow.The framework has been implemented in a 2600-bed Chinese hospital,and is able to reduce the time and cost of developing typical CDS applications.

中医药知识服务的理论探索和平台化实践

中医药知识服务以中医药学科知识体系为基础,通过搜集、整理、分析和重组中医药领域的各种知识资源,提供有效的中医药知识检索、知识挖掘、决策支持、问题解决方案,帮助用户解决中医药领域的实际问题,提高业务技能水平,促进中医药领域的知识传承、创新和发展。知识服务具有定制化、个性化、差异化、互动性、场景化特征,并体现出领域垂直整合的平台化发展趋势。本文结合知识服务领域研究成果和该系统的建设经验,阐述中医药知识服务的理论框架和平台化实践,探讨服务模式和未来趋势。