Journal of Intelligent & Fuzzy Systems - Volume Preprint, issue Preprint

Authors: Jiang, Ping | Dou, Quansheng | Hu, Xiaoying

Article Type: Research Article

Abstract: This paper presents a supervised method for blood vessel segmentation in digital retinal images by a combination of learning and classification. For an image, the method defines and computes pixel strength as primary features for conservatively computing vessel and background pixels as preliminary segmentation, from which the main segmentation selects training data to learn a neutral network (NN) classifier on the fly. Each pixel in the training data set is represented by an 8-D vector composed of intensity descriptor and pixel strength features, and the learned classifier for the image is next applied to classify the undetermined pixels. The segmentation …results are further refined by filtering out the outliers. The method was evaluated on the publicly available DRIVE database, and the results showed better or comparable performance when comparing with other existing solutions in literature. The much better sensitivity and robustness of our approach with different image conditions make it potentially suitable for clinical applications such as automated screening for early diabetic retinopathy detection, and auto- and semi-automatic grading of diabetic retinopathy. Show more

Keywords: Vessel segmentation, learning and classification, pixel strength, neural network

DOI: 10.3233/IFS-151812

Citation: Journal of Intelligent & Fuzzy Systems, vol. Preprint, no. Preprint, pp. 1-11, 2015

Authors: Karaşan, Ali | Kahraman, Cengiz

Article Type: Research Article

Abstract: Location selection for a freight village is extremely important since it has strong impacts on quality of life such as reduction of traffic congestion, reduction of carbon emission, and effective use of lands. The inclusion of such criteria in a location selection requires the fuzzy sets to be used in the decision making methodology. In this paper, we propose a novel integrated fuzzy decision model for the location selection of freight villages. In this integrated methodology, we use DEMATEL for determining the most effective criteria and their inner and outer dependencies; ANP for weighting the determined criteria; and TOPSIS for …finding the best location alternative. The proposed model is applied to a case study for the city of Istanbul in Turkey. Show more

Keywords: Intuitionistic fuzzy sets, DEMATEL, ANP, TOPSIS, freight village

DOI: 10.3233/JIFS-17169

Citation: Journal of Intelligent & Fuzzy Systems, vol. Preprint, no. Preprint, pp. 1-18, 2017

Authors: Li, Xiaofei

Article Type: Research Article

Abstract: Existing fuzzy KANO model has the defect that respondents should judge tendency on satisfaction degree at all levels. A KANO quality attribute classification method based on trapezoidal fuzzy number similarity measures is established, which is applied in practice of quality attribute classification of mobile classrooms. Fuzzy questionnaire is not adopted for investigation in the method. Fuzzy treatment is implemented on questionnaire data in the calculation process only. The questionnaire filling difficulty is reduced greatly, thereby it is more operational.

Keywords: Trapezoidal fuzzy number, similarity measures, KANO model

DOI: 10.3233/JIFS-169336

Citation: Journal of Intelligent & Fuzzy Systems, vol. Preprint, no. Preprint, pp. 1-8, 2017

Authors: Minjing, Peng | Xinglin, Liu | Ximing, Luo | Mingliang, Zhu | Xianyong, Zhang | Xiangming, Deng | Mingfen, Wu

Article Type: Research Article

Abstract: Identification of a consumer’s intent has a vital impact on commodity recommendation, selection of hot drainage commodity, website layout, and link settings. Most of the present studies on user intent are considered static. Specific intent is accompanied by a specific environment. Thus, intent is static when the environment does not change. However, the uncertainty of user access and purchase in e-commerce activities indicates that user intent can assume multiple forms and has multiple developmental stages. Therefore, this study draws support from the core ideas of an ant colony algorithm. Ants represent users, and pheromones represent user intent. User intents of …browsing, collection, cart shopping, and purchasing behavior are obtained from ant responses to pheromones. Pheromone is expressed as the inner product of the objective attribute of commodity and user perception ability, because user intent is the matching result of objective attributes of commodity and subjective feelings of users, and its value is the concentration of user intent pheromone. Thus, the dynamics and uncertainty of user intention development can be presented by the ant colony algorithm. In this study, data were obtained from a NetLogo simulation experiment. We used neural networks to identify and verify user intentions of browsing, collection, cart shopping, and purchasing. The experimental results showed that the accuracy of intention prediction increased from 48% to 67% , and a level of the 11–20% accuracy improvement shows good, realistic predictions. Show more

Keywords: Intent, browsing, purchasing, pheromone, ant colony optimization

DOI: 10.3233/JIFS-169318

Citation: Journal of Intelligent & Fuzzy Systems, vol. Preprint, no. Preprint, pp. 1-11, 2017

Authors: Luo, Yuyan | Wang, Zhong | Wang, Jun | Liao, Zhixue | Hu, Mingming

Article Type: Research Article

Abstract: The more and more significant the global ecological environment problems highlight, putting forward new requirements on the development of tourism and the transformation way of economic growth. So it indicates that tourism economy development and environmental protection should coexist, which is the base for measuring decarbonated development in the system of tourist attractions (DDSTA). Due to the complicated system of a tourist attraction, it not only contains connection between tourist activities and tourism resources, but also includes the relationships between human activity and ecological economy as well as the interaction of various factors in tourist attractions. This paper concentrates on …how to measure decarbonated development of tourist attractions using the organic combination of qualitative and quantitative approach, proposing M2 DL measurement mode associated with management entropy, measuring indicator reference set and application set for DDSTA and taking Jiuzhai Valley as a case study to apply management-entropy-based measurement system for DDSTA and extend previous research on low-carbon tourist attraction and tourism. Show more

Keywords: Decarbonated development, ecological environment, management entropy, M2DL, Jiuzhai Valley

DOI: 10.3233/JIFS-169338

Citation: Journal of Intelligent & Fuzzy Systems, vol. Preprint, no. Preprint, pp. 1-10, 2017

Authors: Xiao, Shuo | Li, Wei | Shang, Tao

Article Type: Research Article

Abstract: Wireless sensor networks (WSNs), with self-organizing and high fault tolerant characteristics, have great advantages for target tracking. But the sensor nodes are battery powered and in most of the cases, it is impossible to charge or replace batteries. Therefore, energy efficiency to extende the life of the network has become an important design criterion for wireless sensor networks. At the same time, high communication speed is also an important issue in the target tracking application. In order to overcome these problems, we propose a novel fuzzy logic model which provides high communication speed to fulfil the tracking task of wireless …sensor networks. The proposed algorithm is evaluated in MATLAB. The results show that the our algorithm performs better than the other algorithms in terms of data transmission rate and system lifetime. Show more

Keywords: Wireless sensor networks, fuzzy logic, target tracking, high speed, data transmission

DOI: 10.3233/JIFS-169339

Citation: Journal of Intelligent & Fuzzy Systems, vol. Preprint, no. Preprint, pp. 1-7, 2017

Authors: Lu, Chengjiang | Zhu, Hongming | Li, Shuang

Article Type: Research Article

Abstract: The paper studies the initial form-finding problem, includes the initial configuration and stress distribution, of deployable tensegrity structures. The stress distributions in bars are preset as prestressing forces, the configuration of the structure and the stress distributions in cables are searched by a presented dynamic relaxation method. In the method, mechanical characteristics of the deployable tensegrity structures are considered. The compatibility of the configuration and stress distribution of the structure is achieved in an iterative process by continuous modification of the bar lengths while keeping the initial stress in bars and the cable lengths with constant values. The effects of …the dummy nodal mass, iteration time step length, and cable stiffness on the calculated results and the convergence performances are investigated and rational selection of these parameters are advised. Several numerical examples are provided to verify the applicability and accuracy of the presented method. Show more

Keywords: Deployable tensegrity structures, form-founding, dynamic relaxation, iterative process, selection of parameter

DOI: 10.3233/JIFS-169335

Citation: Journal of Intelligent & Fuzzy Systems, vol. Preprint, no. Preprint, pp. 1-8, 2017

Authors: sun, Shunyuan | sun, Li | chen, Shu

Article Type: Research Article

Abstract: Energy-Efficient Uneven Clustering (EEUC) protocol is applied to low-redundancy Wireless Sensor Network (WSN), the uneven consumption of sensor node energy leads to nodes’ early death which will seriously affect the network quality. This paper proposes the Chinese Remainder Theorem (CRT) division algorithm for EEUC Energy-Efficient Uneven Clustering routing protocol optimization. The nodes split the packets before forwarding and balance the energy consumption of the nodes forward packets which results in alleviating hot problems of wireless sensor networks. We also add energy and distance parameters to the threshold function in the cluster heads selection mechanism, and optimize the cluster semidiameter to …make the cluster head election distribution more reasonable which will help to optimize the network energy consumption. The result of simulation indicates that the algorithm we propose can make energy consumption of lower redundant sensor network nodes more balanced and delay the first death time of node as well as prolong the network life time effectively. Show more

Keywords: LEACH protocol, Uneven Cluster-Based, energy balance, competitive cluster radius, low redundancy

DOI: 10.3233/JIFS-169326

Citation: Journal of Intelligent & Fuzzy Systems, vol. Preprint, no. Preprint, pp. 1-8, 2017

Authors: Zhu, Yungang | Duan, Hongying | Wang, Xinhua | Zhou, Baokui | Wang, Guodong | Grosu, Radu

Article Type: Research Article

Abstract: Convex evidence theory is the only way to handle ordered and fuzzy evidence fusion, however, conventional convex evidence theory has some drawbacks that make the fusion results are unreasonable in some cases, and not efficient in the scenario of massive data. To overcome above issues, in this article we proposed a novel convex evidence theory based on Gaussian function, we modified Gaussian function and use it to combine mass function of ordered propositions, we designed the formula of the parameters of Gaussian function, and proposed a more accurate method to find the most likely true proposition. We also proved the …effectiveness of the proposed method. Theoretical analysis and experimental results demonstrate that the proposed method has lower time complexity and higher accuracy than state-of-the-art method. Show more

Keywords: Evidence theory, data fusion, gaussian function, convex function

DOI: 10.3233/JIFS-169333

Citation: Journal of Intelligent & Fuzzy Systems, vol. Preprint, no. Preprint, pp. 1-7, 2017

Authors: Xiong, Yipeng | Xiong, Zhengde | Huang, Rui

Article Type: Research Article

Abstract: This paper investigates the impact of service constraints on the retailer’s optimal ordering strategy under supply disruptions. Considering a single-period supply chain that consists of one supplier and one retailer, we first establish a non-binding profit function model and proved the existence of an optimal order quantity at which the retailer’s expected profit can achieve optimal value. We then formulate the profit model with service constraints, i.e. fill rate and service level constraints, respectively. Through the analysis, we find that the expected value of the retailer’s profit is a convex function of the order quantity and there exists a unique …order quantity that makes retailer’s expected profit maximum under each service constraint. In numerical analysis we explain how the retailer can achieve the desired profit by changing the order quantity. Show more

Keywords: Ordering strategy, supply disruption, service constraint, lagrange multiplier

DOI: 10.3233/JIFS-169341

Citation: Journal of Intelligent & Fuzzy Systems, vol. Preprint, no. Preprint, pp. 1-9, 2017