International Journal of Internet Manufacturing and Services (27 papers in press)
The Equilibrium Model of Dual Channel Closed-loop Supply Chain Network Based on Carbon Trading and Carbon Tax
by Chunfang Guo
Abstract: In this paper, on the basis that carbon trading and carbon tax are brought into the category of the carbon management, an equilibrium model of a dual channel closed-loop supply chain network is developed. Many decision-makers and their independent behaviors are fully processed based on the variational inequality theory and Lagrange duality theory. Based on the above analysis, a finite-dimensional variational inequality formulation is established. Besides, qualitative properties of the equilibrium model and a modified projection algorithm are given.
Keywords: dual channel; carbon trading; carbon tax; closed-loop supply chain network;.
Research on the development of agricultural products logistics in China based on ISM model
by Yuhan Wang, Wenbing Wu, Shuxiang Wang
Abstract: Agricultural products logistics is of great significance to regulating the supply and demand, protecting the income of peasant households, and increasing the added value of agricultural products. The agricultural products logistics in China has the characteristics of long chain, multiple nodes, and many influencing factors, which makes it difficult for the government and enterprises to find the effective focus of resource allocation. In view of this situation, this paper summarizes 13 key factors that affect the development of agricultural products logistics in China on basis of the connotation of agricultural products logistics, in combination with actual development and expert opinions. Then, the paper establishes 5-level hierarchical structure of those factors in the use of interpretive structural modelling (ISM), which intuitively reflects the hierarchical association among the influencing factors. Finally, according to the 5-level hierarchical structure, this paper puts forward targeted development suggestions for relevant departments and enterprises.
Keywords: agricultural products logistics; interpretive structural modelling; influencing factors; China.
The Production Strategy for 2 Products Considering Stochastic Demand under Cap-and-Trade Regulation
by Hua He, Changsong Ma, Zhenyu Luo, Xiangchao Liu
Abstract: This paper deals with a production model involving 1 manufacturer who produces 2 products. One product adopts green technology and we term the product as green product, and the other product, with regular production technique, termed regular product. In this paper, we formulate models to examine the impact of production for 2 products under cap-and-trade policy. Analytical results are obtained: With cap-and-trade policy, the manufactures maximum quantity for product 1 and product 2 is lower than the case without carbon emission constraint, and the expected profit of the manufacturer under this situation depends on initial allowance. To cope with the increasing awareness of environmental protection, firms are required to apply some green technologies to produce greener products. General economics concepts are achieved. That is, the green technology input could improve the manufactures normal product quantities and expected profit to some degree.
Keywords: 2 products; cap-and-trade; stochastic demand; production strategy.
Enabling cutting tool services based on in-process machining condition monitoring
by Guohai Zhang, Huibin Sun
Abstract: The cutting tool industrial product-service system (ct-iPSS) integrates intangible cutting services with physical cutting tools to satisfy consumers cutting/machining requirements. It realizes a win-win situation for cutting tool service consumers, cutting tool manufacturers and the third-party cutting tool service providers. However, the study on ct-iPSS is insufficient when some significant topics are still pending. In this paper, the in-process cutting tool condition monitoring service is integrated in the improved ct-iPSS model. A more precise cutting tool demand service is enabled on the basis of in-process cutting tool reaming useful life prediction service. The used cutting tool collection routes are optimized together with the new cutting tool delivery routes. The total delivery/collection cost is minimized systematically to enable a more feasible ct-iPSS. A scenario is presented to verify these services. The ct-iPSSs feasibility and practicality are enhanced by the improved ct-iPSS model.
Keywords: industrial product-service system; cutting tool service; machining condition monitoring.
A Novel Improvement on Rank Reversal in TOPSIS Based on the Efficacy Coefficient Method
by Houxing Tang, Fang Fang
Abstract: Some papers present a simple and intuitive method for eliminating rank reversal in TOPSIS by replacing the relative ideal solution with the absolute ideal solution. Unfortunately, this method has some defects, because it creates new constraints on the initial data. Consequently, it will still result in rank reversal. However, these new constraints are neglected in present studies. In this paper, the efficacy coefficient method is introduced to deal with these problems. Firstly, the merits and drawbacks of the absolute ideal solution are presented. Secondly, the efficacy coefficient method is used to restructure the initial data in order to eliminate these new constraints. Thirdly, it is proved that selecting a different preference weight coefficient in the efficacy coefficient method does not affect the relative rank, and can increase the discrimination degree of alternatives. Finally, based on an illustrative example, the results show that the novel improved method is valid and stable.
Keywords: TOPSIS; rank reversal; efficacy coefficient method; novel improvement; multi-criteria decision-making.
Key stakeholders governance research based on SNA for green building projects whole life cycle
by Zhu Qiao, Yisheng Liu
Abstract: Relationship between green building project stakeholders at different stages in the whole life cycle constitutes a complex network, and the stakeholders relationship at different stages can be coordinated through project governance at the organization level, so as to promote green building large-scale popularization and application. This paper, firstly, screens the green building projects stakeholders through the literature research, and then identifies green building projects key stakeholders at different stages in the whole life cycle, in order to project governance more targeted. Secondly, this paper uses social network analysis to measure green building project key stakeholders network organization relations, to analyze the mutual influence among key stakeholders. Finally, combining with social network analysis results, this paper puts forward different governance solution at the decision-making phase, implementation phase and usage phase of green building projects.
Keywords: green building; whole life cycle; project governance; social network analysis (SNA).
The impacts of system neglect effect on emergency resource replenishment
by Zhiru Juan, Weidong Huang, Haiyan Wang, Jie Cao
Abstract: Aiming at preparedness and response to emergency events, this paper studies emergency resource replenishment decisions made by an irrational decision maker. The decision maker would exhibit system neglect effect, in the sense that the decision maker reacts primarily to signals they received and secondarily to the underlying system that produced the signals. By comparing the performances of threshold methods and smoothing strategies, we identify the impacts of system neglect effect on the resource replenishment decisions and offer insight into when high-consequence, low-probability events may occur. The results show that threshold method is more attractive than smoothing method in emergency management and the existence of system neglect may improve the efficiency of the replenishment decisions generated by smoothing strategies. The findings are meaningful to preparedness and response to emergency events and help manage the influence of system neglect effect when replenishing emergency resources.
Keywords: forecasting; system neglect; smoothing strategy; threshold method.
MBAN-MLC: a multi-label classification method and its application in automating fault diagnosis
by Shijun Chen
Abstract: With increasing competition in the mobile telecom network market, the network quality becomes one of the key factors for competitions between network operators. At the work site of drive-testing in the mobile radio communication network, drive-testing experts needed to tag the fault causes manually based on their experience for fault diagnosis, and there were always multiple causes. Traditional single-label classification method cannot be used here to automatically tag the multiple fault causes. In this paper such kind of fault diagnosis problem is transformed to the multi-label classification problem, and a multi-label classification method (MBAN-MLC) is proposed for fault diagnosis automation. MBAN-MLC is based on a Bayesian network-augmented Na
Keywords: multi-label classification; multi-label learning; Bayesian network; Bayesian network-augmented Naive Bayes; multiple classifying nodes; fault diagnosis.
Naïve Bayes regression model and its application in Collaborative filtering recommendation algorithm
by Shiqi Wen
Abstract: Aiming at the problem that the general Bayes classification model cannot be applied to regression prediction，a Naïve Bayes regression model is proposed. Firstly, in order to simplify the complexity of model, attribute values and decision values are discretized from continuous value to discrete value. By summing the probability of Bayesian classification and using the mathematical expectation value as the regression value, the process of regression problem is turned into a classification problem and the Naive Bayes classification model was modified into Bayesian regression model.
Keywords: Naïve Bayes regression model; discretization; expectation; model-based collaborative filtering; time efficiency; recommendation accuracy.
Dynamic Data Source Selection for Humanistic Culture Integrated Information Retrieval
by Song Deng
Abstract: There are hundreds of data sources in tourism, and the quality of data in data sources is quite different. How to obtain high-quality integrated information from a few data sources has become an important research direction, so the technology of data source selection arises at the historic moment. One of the core technologies of data source selection is to construct data source summary. When the data source content updates, it will inevitably lead to changes in the data source summary. The calculation work load to completely update the summary is huge, so a partial update strategy is used to improve the efficiency. In order to enhance the efficiency of tourism cultural information integration, we propose a new dynamic data source selection strategy. Firstly, we build a data source summary based on the relationship between people and characteristic words. Then, We design a local summary updating algorithm based on sampling technique. Finally, we propose a scoring method of data source base on the gain of cultural content of a single or synthetic character for integration purposes. We conduct a number of experiments based on field data collection, and the results showed that compared with the existing update algorithms, our method has higher accuracy. Therefore, it can provide effective support to character or attraction integration.
Keywords: Data Source Selection; Cultural Integration; Dynamic; Information Retrieval.
Time Series Difference of Collaborative Evolution of Industrial Structure of the Urban Agglomeration along the Middle Reaches of the Yangtze River
by Zhenyuan Liu, Shuhua Hu, Renyan Mu, Lijun Wang, Zheng Wang
Abstract: The City Cluster along the Middle Reaches of the Yangtze River is an important regional economic pole, and its industrial structure is the key to the economic growth of this region. Based on the methodology of system theory and synergy, the paper constructs the concentration-deviation measure system of industrial collaborative development. According to the concentration-deviation assessment of the evolution of industrial structure of the City Cluster along the Middle Reaches of the Yangtze River from 2004 to 2014, the paper points out the features and problems concerning optimization of industrial structure, and then offers strategies accordingly.
Keywords: industrial structure; collaborative evolution; the City Cluster along the Middle Reaches of the Yangtze River.
Railway route optimization from Romania to Poland based on an analysis of Chinas "One Belt and One Road" initiative
by Yang Wang, Xiaochun Lu
Abstract: With the proposal of the "One Belt and One Road" initiative, a new strategic route is underway. It travels from China to Afghanistan, Iran, Turkey, Romania, Poland, and Western Europe. This is a new rail route, and the exact path is unknown. This paper focuses on the railway route between Romania and Poland. Railway lines between two countries can be two different gauge rails, which can lead to transshipment problems. A dynamic programming model is established to find optimized railway routes between these countries. In the optimization model, the transshipment stations on country borders are set as constraints. First, four shorter routes from the hundreds of railway lines are obtained by the Dijkstra-based dynamic programming algorithm. Next, by accounting for the transit service abilities of railway stations, we estimate the total transportation time using Monte Carlo simulations. Finally, we obtain the two best routes. The first one passes Bucharest, Nevetlenfolu, Brest and Warsaw, and the second route is from Bucharest, Nevetlenfolu and Medyka to Warsaw. However, these two routes are not the shortest paths. We found that the line from Bucharest to Nevetlenfolu is the common section of two routes. The Nevelenfolu railway station may become a bottleneck of the two routes. Therefore, future upgrades of the Nevetlenfolu railway station will be vital. At present, these railway lines have not played role in trade between China and Europe, but they may become important transportation lines in the future.
Keywords: One Belt and One Road; Transshipment service ability; Shortest path algorithm.
THE TWO-STAGE DELAY DISTRIBUTION METHOD BASED ON COMPENSATION MECHANISM UNDER RANDOM ENVIRONMENT
by Jianjun Wang, Lei Zhou, Fachao Li
Abstract: The two-stage delay distribution problem is a class of special programming problem. In real life, the supply, demand and transportation environment are with uncertainty. If the random customer demand dose not reached full load, we will choose the decision of the delay delivery or delivery on schedule based on minimize expectation cost. In this paper, based on the analysis of the random distribution characteristics and deficiencies, a class of two-stage delay distribution stochastic programming model with compensation mechanism is put forward. Through synthesizing the expectation, variance and probability distribution of cost factors, stochastic programming model can be converted into a class of crisp programming models. Finally, combined with the case of the vehicle distribution, using the analytical method, the proposed model is applied to get the optimal solution which can reduce transportation costs and improve the profitability.
Keywords: Compensation mechanism; Minimize expectation cost; Non load distribution; Synthesizing effect.
Special Issue on: ICSS 2017 Big Data and Big Services for Internet-based Enterprises
The optimization design of cooling water channel for calibrator based on Kriging and NSGA-II
by Jianjing Jin, Yibing Li, Donglin Song, Lei Wang
Abstract: Abstract: Calibrator plays an important role in the shaping of the cooling in the plastic profile production. In this paper, a simplified model with the specific length was used as the analysis example. The multi-objective optimization for the water channel position of the model was carried out based on the modern intelligent algorithm. In order to realize the uniform distribution of the surface temperature of the profile, the position parameters and the diameter of the cooling water channel were taken as the design variables. Then Kriging model was established on the basis of Latin hypercube sampling, and the above variables were optimized based on NSGA-II. Finally, the optimized channel parameters were obtained. Compared with the initial scheme, the temperature distribution of the profile surface was uniform. Finally, the effectiveness and applicability of the design method of the chilled water channel parameters of the calibrator based on NSGA-II were verified.
Keywords: Calibrator; Kriging model; NSGA-II; Optimization.
Mining QoS benchmark of resource-service chain for collaborative tasks
by Haibo Li, Yafeng Gao
Abstract: To improve the efficiency and quality of resource services selection in collaborative task systems, the temporal relationship between the resource services should be taken into account. At the same time, the changing market requires a dynamic selection benchmark. QoS (Quality of Service) as the main basis for the selection of resource services, mining the business data set to develop the QoS benchmark has a good objectivity and dynamic. Taking Manufacturing as a typical collaborative process, based on the resource service chain (RSC, Resource Service Chain) formed by the scheduling order of resource services, an approach called the QoSB-RSC (mining method for QoS Benchmark of RSC) is proposed to obtain the QoS benchmark of RSC. By comparing the QoS similarity between scheduling instances of RSC, mining the cluster centers from business data set as the QoS benchmark. The performance of the QoSB-RSC is verified by experiment and case analysis, indicating that it has positive significance to improve the efficiency and quality of resource services selection.
Keywords: collaborative tasks; QoS benchmark; resource service chain; mining.
Testing Job Characteristics Model: Empirical Research on Service-Oriented Organizations in China
by Xueliang Pei, Yang Yang, Yingying Su, Longfang Xue
Abstract: In service-oriented organizations, employees job characteristics and motivations are important to improving organizational performance. The job characteristics model is a classical model that links job characteristics, job motivation, and organizational performance; however, theoretical and empirical research on this model is insufficient. Therefore, a theoretical model of relationships among employees job characteristics, job motivation, and work outcomes is proposed. We took service-oriented organizations in China as our sample and conducted empirical research on data from 209 valid samples. The results showed the following: (1) job autonomy and task significance positively affected personal outcomes, and skill variety and job autonomy positively affected work-related outcomes; (2) skill variety, job feedback, and task significance were positively related to inner psychological needs, while skill variety, job autonomy, and task significance were positively related to work interest; and (3) job motivation had different mediating effects on the relationship between employees job characteristics and work outcomes.
Keywords: Service-oriented organization; job characteristics model; job characteristics; job motivation; work outcomes; skill variety; task identity; task significance; autonomy; feedback; inner psychological needs; work interest; personal outcomes; work-related outcomes.
Time-slot based Point of Interest Recommendation on Location-Based Social Network
by Jun Zeng, Yinghua Li, Feng Li, Xin He, Junhao Wen
Abstract: Point-of-Interest (POI) recommendation on Location-Based Social Network (LBSN) is an important service in mobile environment. POI recommendation recommend places that users have not visited before. In this paper, we introduce time slot to describe the feature vector of locations. We consider that the locations that user has visited may reflect users preference. Hence, we calculate the similarity between the visited locations and the unvisited locations. Meanwhile, we consider the influence of the physical distance and the weight of the visited locations. We conduct an experiment, the experimental results show that our method has better precision and recall than other two methods.
Keywords: location-based social networks; point-of-interest recommendation; time-slot; temporal information.
Resource Selection Method Based on Service Capability in Cloud Manufacturing
by Zhuling Zhang
Abstract: The cooperation among enterprises becomes more popular than before as the manufacturing industry tends to be globalized. How to transform a production-oriented manufacturing industry to a service-oriented one still remains a problem. Cloud Manufacturing, which is a new manufacturing model based on the network, responds to the proper time and conditions. It collects unevenly distributed physical manufacturing resources of the world into virtual resources and provides services outward by providing services. When a large number of resources accumulate, it is difficult to select optimal resources objectively and a good resource selection method is needed. Service capability is the attribute of resources to provide external services. It represents performance indicators of resources or user's evaluation of resource services. It plays an extremely important role in measuring the quality of resources. This paper performs analysis in two contexts: the business system and manufacturing process. It uses workflow log mining technology to provide a favourable environment for resource selection. The paper proposes a resource selection method based on service capability and applies it to experimental analysis of a citys the research and development project named manufacturing service platform for small and medium-sized enterprises. The results show that the method proposed is feasible.
Keywords: cloud manufacturing; workflow; service capability; resource selection; physical manufacturing resource; virtual manufacturing resource.
A Compound Operation Method of Model Transformation Rule based on OWL
by Li Jin, Cheng Xuhong, Bai Yu
Abstract: With the wide application of MDA, many similar or identical business models and software models have subsequently accumulated. The transformation rules for these business models and software models are often similar. Reusing similar transformation rules can improve the efficiency of model transformation. Therefore, it is important to solve the problem of how to use similar constructs and reuse the model transformation rules for improving the precision and efficiency of model transformation. The paper proposes a method based on OWL for the compound operation of model transformation rules. First, the transformation rule space and transformation rules are defined by OWL. Second, the similarity between the business model and software model element is analyzed, and the compound operation of the five transformation rules is defined. Finally, to apply the paradigm, a support tool is realized, which can help users implement five compound operations for constructing large granularity model transformation rule.
Keywords: model transformation rule; compound operation; OWL; model similarity.
Cloud manufacturing service evaluation based on modular neural network
by Shenghui Liu, Shuli Zhang, Chao Ma, Hongguo Zhang, Xing Zhang
Abstract: In order to solve the evaluation problem of cloud manufacturing service and then minimize the time of choosing the best service, a comprehensive evaluation index system of cloud manufacturing services is constructed in the light of the characteristics of cloud manufacturing service. The service attributes, manufacturing attributes and network attributes are taken into account from two views of the online characteristics and the offline characteristics of cloud manufacturing service in the evaluation index system. And on this basis, a quantitative evaluation model based on modular neural network (MNN) is proposed. Firstly, the clustering algorithm subtractive-k-means is introduced and used to divide the task into several subtasks based on the idea of modularization. Then, the subtasks are processed through the trained BP network. Finally, the self-adaptive genetic algorithm is used to optimize the integration weights of each subtask processing module. Combining with the cloud manufacturing evaluation index system, this modular neural network model can be used to effectively evaluate the cloud manufacturing service and help customers quickly select the best cloud manufacturing service.
Keywords: Cloud Manufacturing; Evaluation Model; Modular Neural Network; Clustering Algorithm; Self-adaptive Genetic Algorithm.
Approach to Manufacturing Resource Description Based on Metadata in Cloud Manufacturing
by Xiaocheng Lin
Abstract: Cloud manufacturing is a new model of service-oriented networked manufacturing. Encapsulating the physical manufacturing resources to virtual resources and completing the description of manufacturing resources are the keys and the basis to realize comprehensive sharing of resources, but there is no uniform method at present. Metadata is the basic tool to organize the data information, and is the data set which is used to describe the information resources online, to strengthen the search, development, organization and utilization of network resources. In combination with the special characteristics of manufacturing resources and the advantages of metadata, the paper offers the definition and category of manufacturing resources, proposes the description method of manufacturing resources based on metadata, XML markup language is used to define in detail. In the end, the effectiveness of this method is verified through cases.
Keywords: cloud manufacturing; metadata; physical manufacturing resource; virtual manufacturing resource.
The design and implementation of data collection middleware for logistics traceability
by Can Tian, Hongzhen Zheng, Fanchao Meng
Abstract: Logistics traceability system has complicate business logic, while the underlying RFID reader has distributed and heterogeneous characteristics. In order to simplify the business logic and facilitate the data processing, this paper extracts the general characteristics of logistics traceability, and establishes a logistics traceability model. A dynamic plug-in mechanism based on XML is introduced to solve the heterogeneity problem. To summarize, the data collection middleware framework for logistics traceability is designed, the diversity and complexity of RFID reader is shielded and the collection interface is standardized. The data collection middleware for logistics traceability is confirmed to integrate the reader and the application effectively.
Keywords: RFID; logistics traceability; data collection middleware.
User-based collaborative filtering algorithm fusing the local and global nearest neighbour
by Cheng Wang, Shiqi Wen, Fangfang Su, Yewang Chen, Yiwen Zhang, Guoqi Zheng
Abstract: Collaborative filtering method is one of the most successful used recommendation algorithm. It can be divided into the global nearest neighbour based method and the local nearest neighbour based method. The global neatest neighbour based method has high stability but the recommended results are not sufficiently personalized. The local nearest neighbour based method is more accurate and personalized than the global neatest neighbour based method, but the prediction failure rate is high and its not stable. Aiming at these problems, a new user-based collaborative filtering algorithm fusing the local and global nearest neighbour is proposed. Firstly, the max-min K-medoids clustering algorithm is applied for clustering items into several clusters. The local similarity of users is calculated in each item cluster. Secondly, the factor of correlation-weighted is introduced to improve the accuracy of the global similarity among users. By using the contribution proportion of the nearest neighbour as fusion weights, the global similarity and the local similarity are fusion as the new similarity measurement and the nearest neighbour can be found in this new similarity measurement. Finally, this new similarity among users is presented to optimize the selection of neighbours of target user. The user-based collaborative filtering algorithm fusing the local and global nearest neighbour increases the recommendation precision while avoiding the shortcoming of instability. The experimental results on EachMovie and MovieLens-100K show that the prediction reliability and accuracy of this new method are better than traditional ones.
Keywords: user-based collaborative filtering; max-min K-medoids clustering algorithm; local nearest neighbor; global nearest neighbor; linear weighting fusion algorithm.
Research on humanoid head robot system based on interactive visual expression analysis
by Guoliang Zhang
Abstract: A humanoid head robot system with some specific expression was comprehensively modelled in this paper by interactive visual expression analysis between the operator and the robot. Firstly, based on the open source hardware of Fritz humanoid head robot, an integrated emotional expression mapping model was proposed by extending the functional module of voice, vision and so on. Secondly, to achieve a natural interaction between the expression robot and the operator, the integrated visual analysis is mainly utilized for emotion calculation. Haar-like featured cascade classified algorithm is utilized for automatic face location. Gabor feature is filtered and down-sampled as the emotional expression feature. To deal with unreasonable samples distribution in traditional Eigenface, an optimized eigenvectorss selection is built by comparing projection reconstructed images with original image. Finally, the classification of with-in class PCA with energy dimension is served as expression recognition. The experimental results on JAFFE database and real-time video image demonstrate the feasibility and effectiveness of the proposed modelling scheme.
Keywords: expression robot; humanoid head robot; Gabor Feature; Eigenface; feature reconstruction.
Predictive Maintenance Strategy of Running Fault Based on ELM Algorithm for Power Transformer
by Qian Wu, Xiaoyi Yang, Renming Deng
Abstract: Transformer is the most important core equipment of power system, and once the fault happened, the economic losses and adverse social impacts resulted in faults by the twinkling of eye are difficult to estimate. In order to prevent transformer fault happened, the paper explored a sort of predictive maintenance strategy of transformer fault power transformer supported by the ELM algorithm. In this paper, it made the anatomy of the drawbacks in BM and PM maintenance system, pointed out the advantage of PRM maintenance system, studied on prediction of the fault diagnosis and predictive algorithm based on ELM, discussed the dynamic fault diagnosis model of power transformer in smart grid environment. A comparative study of different fault pattern prediction algorithms confirmed the rationality and feasibility of the fault prediction algorithm based on ELM. Transformer operation experience shows that the ELM algorithm can provide powerful technical support for the maintenance strategy of transformer fault prediction.
Keywords: equipment of power system; fault happened; transformer fault; predictive maintenance strategy; ELM algorithm; powerful technical support; Transformer operation; fault prediction algorithm; powerful technical support; maintenance strategy; transformer fault prediction.
A process planning method based on firefly algorithm
by Xianbang Yang, Ting He
Abstract: In the modern manufacturing system, process planning is an essential function. Generally, a part has many alternative process plans since there are many other viable processing methods and techniques. Therefore, optimization of the process plan in manufacturing is an important task of flexible process planning. In this paper, the flexible process planning method based on firefly algorithm is developed for improving production efficiency and reducing production cost. Firstly, a hierarchical evaluation index system for the process plan is presented and a multi-objective nonlinear optimization model of process planning is formulated. This model is based on the evaluation index system in which the quality, cost, efficiency, and environmental consumption of parts processing can be optimized. Next, the improved firefly algorithm is proposed to solve the multi-objective nonlinear optimization model. Finally, an example is given to prove the validity of the model and algorithm.
Keywords: flexible process planning; multi-objective; optimization; firefly algorithm.
IEDPS: Intelligent Elderly Disease Prediction System
by Guoru Li, Hongzhen Zheng, Dianhui Chu
Abstract: This article implements the intelligent elderly disease prediction system in
order to solve the problem that the existing disease prediction systems lack
pertinence for the elderly. The elderly disease prediction model is optimized
by adding specific attributes of the elderly based on the attributes selected by
automatic attribute selection methods. We use accuracy, sensitivity and specificity
to evaluate models comprehensive performance. The results show that Naive
Bayes is better than Logistic Regression, which is more suitable for the intelligent
elderly disease prediction system. The structure and class diagram of the system is
designed. The intelligent elderly disease prediction system is implemented using
the elderly disease prediction model based on Naive Bayes.
Keywords: elderly disease prediction; specific attributes of the elderly; Naive
Bayes; Logistic Regression.