Journal of Intelligent & Fuzzy Systems - Volume 38, issue 1

Authors: Deng, Leilei | Wang, Zhenghao | Wang, Chuang | He, Yifan | Huang, Tao | Dong, Yue | Zhang, Xian

Article Type: Research Article

Abstract: Image segmentation technology is a basic technology for image processing and analysis. As a typical interactive color image segmentation algorithm, grabbing segmentation has high precision, interactive operation and better segmentation effect in processing complex background segmentation, and has broad prospects in the field of agriculture. In this paper, the image segmentation algorithm of maize smut, Maize Head Smut and maize rust, which are three main diseases and insect pests, is studied by taking the high-yield crop Maize in Northeast China as an example. The image background in the static image editing is replaced by an improved one-time cutting algorithm. Through …the adaptive combination of weights, the depth information and saliency information are combined into the grabbing color model. The improved image segmentation algorithm greatly improves the efficiency and accuracy of image segmentation, and achieves a good spot segmentation effect in the static image of corn pests and diseases, and has a high recognition. Do not rate. And it plays a predictive research effect in practical verification. Show more

Keywords: Threshold segmentation, graph segmentation, grab cut algorithm, saliency, maize diseases and pests

DOI: 10.3233/JIFS-179413

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 1, pp. 379-389, 2020

Authors: Fei, Rong | Li, Shasha | Hei, Xinhong | Xu, Qingzheng | Zhao, Jiayu | Guo, Yuling

Article Type: Research Article

Abstract: Using the Semi-Markov decision model, we start with the real road map datum with a constructed logic network and construct the complex road network with random moving characteristics. First we translate the crowdsoured map datum into the vectorgraph in road network by the ArcGIS with the conversion of longitudinal and Latitude Coordinates to planar coordinates. In the motion simulation model all objects are sorted by the time of state change, and the moving object with the closest state change time to the current time are set at the front of the queue. And then, the moving object motion model based …crowdsourced map datum is simulated. The experimental results for fitting and analysing the distribution rules of in-degree and out-degree show that the designed model can satisfy the Poission Distribution Rule on the cross node of Road Network based Uniform Distribution of moving object random motion, which conform to the characteristics of Distance Space and small-world network. Show more

Keywords: Semi-markov model, real road map, moving object, distribution rule, motion simulation model

DOI: 10.3233/JIFS-179414

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 1, pp. 391-407, 2020

Authors: Hu, Yun | Zhou, Zuojian | Hu, Kongfa | Li, Hui

Article Type: Research Article

Abstract: Detecting community structure is critical in analysing social networks which are flourishing and influencing every aspect of people’s social life. Most social network systems are composed with complicated entity relations such and social interests, user relationships and their interactions. To understand how users interact with each other under the community level, its not enough to consider one kind of these relations while ignore the other. An united network model that can comprehensively integrate these relations is essential for community detection. Focusing on such kind of problem when dealing with social network with multiple relations, this paper proposes a heterogeneous network …model which characterizes and constructs user similarity relations by combining both of users’ interests and their interactions attributes. Based on the heterogeneous similarity model, an additive spectral decomposition algorithm is applied to detect overlapped communities from the network. The remarkable effect of our heterogeneous model is the ability to reveal most important attributes of the blog network. And, comparing to crisp clustering method, the additive spectral decomposition algorithm proposed is effective for finding overlapped user groups which is more reasonable among social networks where users tend to join multiple social groups. Results of experimental studies on real-world and synthetic datasets demonstrate the effectiveness of the algorithm with respect to the size, the distributive structure and the high dimensionality of the datasets. Show more

Keywords: Community detection, micro blog network, user interest, user interaction, heterogeneous network model, user similarity modelling

DOI: 10.3233/JIFS-179415

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 1, pp. 409-416, 2020

Authors: Wang, Yuanyuan | Wang, Zhijian | Jiang, Mingxin | Chen, Liqi | Shen, Tianhao | Zhang, Wenyang

Article Type: Research Article

Abstract: Person re-identification (ReID) is a critical work in the field of intelligent image processing and deep learning, which has attracted the attention of industry application. Person ReID focuses on matching person images obtained from non-overlapping camera views and finding the person-of-interest. An important unresolved problem is to obtain efficient metric for measuring the similarity among pedestrian images. Lately, deep learning with metric learning has become a general method for person ReID. Yet, previous methods mainly used a variety of distance to measure the similarity among samples. The way of distance measure is more sensitive when the scale changes. In this …paper, we propose angular loss with hard sample mining (ALHSM) to learn better similarity metric for the person ReID. Our work uses the angular relationship in triangles as a measure of similarity, minimizing the angle at the negative point of the triangle. ALHSM combines with hard negative mining strategies, which learn better similarity metric and achieve advanced performance on several benchmark datasets. The experimental results show that our work is competitive compared to the state-of-the-art. Show more

Keywords: Person re-identification, deep learning, angular loss, intelligent image processing

DOI: 10.3233/JIFS-179416

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 1, pp. 417-426, 2020

Authors: Wei, Dongping | Tang, Niansheng | lei, Tianli | Wen, Shouwen

Article Type: Research Article

Abstract:  Language Model is used to describe and calculate the probability of a reasonable sentence occurrence in natural language. In practical applications, language model as the core of natural language processing is often used in machine translation, information indexing, voice recognition, context processing such as sentiment recognition and other tasks. We will discuss advantages and weaknesses of traditional statistical language models and neural Network Language Models such as CBOW and Skip-gram. Keeping in view the traditional statistical language model and neural network model, we will try to put forward the word vector model based on part of speech and sentiment information …(PSWV-model) in order to use more natural language information such as word order features, part of speech features, and sentiment polarity information under the framework of Mikolov’s model. And finally we will present our deliberations on some advantages of PSWV model and other models including CBOW and Skip-Gram, CDNV in the NLP tasks including named entities recognition and sentiment polarity analysis. Show more

Keywords: Deep learning, word vector, sentiment analysis, named entity recognition

DOI: 10.3233/JIFS-179417

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 1, pp. 427-440, 2020

Authors: Han, Hongmu | Dong, Xinhua | Zuo, Cuihua

Article Type: Research Article

Abstract: Recommender systems are widely used to provide users with items they may be interested in without explicitly searching. However, they suffer from low accuracy and scalability problems. Although existing clustering techniques have been incorporated to solve these inherent problems, most of them fail to achieve further improvement in recommendation accuracy because of ignoring the correlations between items and the different effects of item attributes on recommendation results. In this article, we propose a novel recommendation algorithm to alleviate these issues to a large extent. First of all, users and items are clustered into multiple cluster subsets based on user-item rating …matrix and item attribute deriving from domain experts, respectively. Then we use a selection method relying on item attribute to mine candidate items and only their predictions will be calculated in the next step, which can save the computation time greatly. Furthermore, by weighting the predictions with TF-IDF (Term Frequency-Inverse Document Frequency) weights, the top-N recommendations are generated to the target user for return. Finally, comparative experiments on two real datasets demonstrate that this algorithm provides superior recommendation accuracy in terms of MAE (Mean Absolute Error) and RMSE (Root Mean Square Error). Show more

Keywords: Recommender systems, clustering, item attribute, weight, recommendation accuracy

DOI: 10.3233/JIFS-179418

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 1, pp. 441-451, 2020

Authors: Wang, Sheng | Yu, Yongchang | Yang, Chen | Liu, Long | Zhang, Yahui | Zhang, Zhi | Li, He

Article Type: Research Article

Abstract: Traditional soybean seeders are driven by land wheels, which are easy to slip in complex operating conditions, resulting in the increased miss-seeding index and row-spacing coefficient of variation, etc. In order to solve these problems, a soybean electrical-control seeding system was designed in this paper. For improving the control accuracy of the electrical seeding system and achieving precise control of soybean seeding, the closed-loop control was adopted in the electric-driven Soybean Seeding system, the motor model of the electric-driven soybean seeding system was established and the transfer function of the motor was obtained. The PID control parameters were obtained by …the Ziegler-Nichols PID tuning method, and the corresponding parameters were substituted into the control system simulation model established in MATLAB/SIMULINK. The conventional PID control system and the fuzzy PID control system were simulated respectively. Field trial results show that seeding with fuzzy PID control is better. Show more

Keywords: Seed metering device, electronic control, fuzzy control

DOI: 10.3233/JIFS-179419

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 1, pp. 453-462, 2020

Authors: Zhang, Xian | Wang, Fengxian | Han, Dawen | Meng, Hao | Wei, Bin | Wang, Songcen | Li, Yang | Xue, Ming | Yang, Qingxin

Article Type: Research Article

Abstract: Wireless power transmission technology avoids the problem of towed wires in the process of using electric energy, and increases the flexibility of using electricity. It is a hot research topic at present. In order to improve the system performance, a field-circuit coupling algorithm is proposed to analyze the system performance, with the help of the concept of supercomputing. Frequency splitting is a phenomenon in wireless power transfer (WPT) system when the coupling distance is less than the splitting point, the load power changes from a single-peak curve to a double-peak curve driven by two non-intrinsic resonant frequencies. Asymptotic coupled mode …theory (CMT) method is used to analyse the frequency splitting phenomena in WPT system. It provides detailed information about interaction of field strength under different coupling states through coupled solution of FEM and CMT. Over coupling, critical coupling and under coupling are three typical states classified by frequency splitting. Experimental results are acquired by two helical resonators. The overall system reaches the critical coupling state when resonators space 1.5 m and the total power on the load is 110 W. Therefore, it is an efficient way to forecast transmission characteristics by using this method. Show more

Keywords: magnetic resonant coupling, frequency splitting, coupled mode theory, critical coupling, coupled solution

DOI: 10.3233/JIFS-179420

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 1, pp. 463-469, 2020

Authors: Wang, Yajun | Sun, Fuming | Li, Xiaohui

Article Type: Research Article

Abstract:  To reduce and eliminate the three problems for large-scale data sets that include high computational complexity, large storage space, and long time-consuming in complex batch process with inherent dynamics and nonlinearity, a novel approach based on multi-dynamic kernel principal component analysis (MDKPCA) by exploiting compound dimensionality reduction for fault detection is proposed. The method firstly uses discrete cosine transform (DCT) having strong energy aggregation and distance preserving property to realize dimensionality reduction without changing the essential characteristics of data. Then after the reduced dimension data is processed by inverse transformation, the dynamic kernel principal component analysis (DKPCA) model is established …by combining the autoregressive moving average time series (ARMAX) model and kernel principal component analysis (KPCA) to handle the nonlinearity and dynamics in industrial process. Finally, one penicillin fermentation process case for fault monitoring is provided to test the effectiveness of the proposed method, where the comparison with multiway kernel principal component analysis (MKPCA) results is covered. Show more

Keywords: Compound dimensionality reduction, discrete cosine transform, multi-dynamic kernel principal component analysis, large-scale data set, penicillin fermentation process

DOI: 10.3233/JIFS-179421

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 1, pp. 471-480, 2020

Authors: Wang, Yang | Zhang, Shengyu | Cen, Hongjie | Zou, Bo

Article Type: Research Article

Abstract:  The explosive growth of wireless data services, especially more and more requirement for high-definition videos, demands higher capacity of future wireless communication systems to meet this trend. One efficient solution to this problem is to improve the spectral efficiency. This paper analyzes the basic principles of large-scale antenna array system, whose performance is verified by simulation. Key technologies on large-scale antenna array system, such as channel state information acquisition, antenna array design, code book design, are also studied. The results show that large-scale antenna array system can greatly improve spectral efficiency and reduce system energy consumption.

Keywords: Large-scale antenna array system, massive MIMO, spectral efficiency, interference mitigation

DOI: 10.3233/JIFS-179422

Citation: Journal of Intelligent & Fuzzy Systems, vol. 38, no. 1, pp. 481-486, 2020