Journal of Intelligent & Fuzzy Systems - Volume 42, issue 3

Authors: Zhang, Yan | Yang, Gongping | Liu, Yikun | Wang, Chong | Yin, Yilong

Article Type: Research Article

Abstract: Detection of cotton bolls in the field environments is one of crucial techniques for many precision agriculture applications, including yield estimation, disease and pest recognition and automatic harvesting. Because of the complex conditions, such as different growth periods and occlusion among leaves and bolls, detection in the field environments is a task with considerable challenges. Despite this, the development of deep learning technologies have shown great potential to effectively solve this task. In this work, we propose an Improved YOLOv5 network to detect unopened cotton bolls in the field accurately and with lower cost, which combines DenseNet, attention mechanism and …Bi-FPN. Besides, we modify the architecture of the network to get larger feature maps from shallower network layers to enhance the ability of detecting bolls due to the size of cotton boll is generally small. We collect image data of cotton in Aodu Farm in Xinjiang Province, China and establish a dataset containing 616 high-resolution images. The experiment results show that the proposed method is superior to the original YOLOv5 model and other methods such as YOLOv3,SSD and FasterRCNN considering the detection accuracy, computational cost, model size and speed at the same time. The detection of cotton boll can be further applied for different purposes such as yield prediction and identification of diseases and pests in earlier stage which can effectively help farmers take effective approaches in time and reduce the crop losses and therefore increase production. Show more

Keywords: Unopened cotton boll detection, deep learning, improved YOLOv5, image data collection, Bi-FPN

DOI: 10.3233/JIFS-211514

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2193-2206, 2022

Authors: Shao, Dangguo | An, Qing | Huang, Kun | Xiang, Yan | Ma, Lei | Guo, Junjun | Yin, Runda

Article Type: Research Article

Abstract: The purpose of aspect-level sentiment analysis is to identify the contextual sentence expressions given by sentiment for some aspects. For previous works, many scholars have proved the importance of the interaction between aspects and contexts. However, most existing methods ignore or do not specifically capture the position information of the aspect targets in the sentence. Thus, we propose an aspect-level sentiment analysis based on joint aspect and position hierarchy attention mechanism network. At the same time, the model adopts a joint approach to make the model of the aspect features and the position features. On the one hand, this method …clearly captures the interaction between aspect words and context when inputting word vector information. On the other hand, this method can enhance the importance of position information in the sentence and boost the information retrieval ability of the model. Additionally, the model utilizes a hierarchical attention mechanism to extract feature information and to differentiate sentiment towards, which is similar to filtering useless information again. Experiment on the SemEval 2014 dataset represent that our model achieves better performance on aspect-level sentiment classification. Show more

Keywords: Aspect-level, position information, hierarchy attention mechanism, sentiment analysis, sentiment polarity

DOI: 10.3233/JIFS-211515

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2207-2218, 2022

Authors: Bai, Luyi | Cui, Zengmei | Duan, Xinyi | Fu, Hao

Article Type: Research Article

Abstract: With the increasing popularity of XML for data representations, there is a lot of interest in keyword query on XML. Many algorithms have been proposed for XML keyword queries. But the existing approaches fall short in their abilities to analyze the logical relationship between keywords of spatiotemporal data. To overcome this limitation, in this paper, we firstly propose the concept of query time series (QTS) according to the data revision degree. For the logical relationship of keywords in QTS, we study the intra-coupling logic relationship and the inter-coupling logic relationship separately. Then a calculation method of keyword similarity is proposed …and the best parameter in the method is found through experiment. Finally, we compare this method with others. Experimental results show that our method is superior to previous approaches. Show more

Keywords: Data revision degree, keyword search, spatiotemporal data, XML

DOI: 10.3233/JIFS-211537

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2219-2228, 2022

Authors: Shabbir, Wasif | Aijun, Li | Taimoor, Muhammad | Yuwei, Cui

Article Type: Research Article

Abstract: The problem of quick and accurate fault estimation in nonlinear systems is addressed in this article by combining the technique of radial basis function neural network (RBFNN) and global fast terminal sliding mode control (GFTSMC) concept. A new strategy to update the neural network weights, by using the global fast terminal sliding surface instead of conventional error back propagation method, is introduced to achieve real time, quick and accurate fault estimation which is critical for fault tolerant control system design. The combination of online learning ability of RBFNN, to approximate any nonlinear function, and finite time convergence property of GFTSMC …ensures quick detection and accurate estimation of faults in real time. The effectiveness of the proposed strategy is demonstrated through simulations using a nonlinear model of a commercial aircraft and considering a wide range of sensors and actuators faults. The simulation results show that the proposed method is capable of quick and accurate online fault estimation in nonlinear systems and shows improved performance as compared to conventional RBFNN and other techniques existing in literature. Show more

Keywords: Fault estimation, neural networks, global fast terminal sliding mode control

DOI: 10.3233/JIFS-211547

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2229-2245, 2022

Authors: Tan, Chao | Liu, Jie

Article Type: Research Article

Abstract: The prime focus of knowledge distillation (KD) seeks a light proxy termed student to mimic the outputs of its heavy neural networks termed teacher, and makes the student run real-time on the resource-limited devices. This paradigm requires aligning the soft logits of both teacher and student. However, few doubts whether the process of softening the logits truly give full play to the teacher-student paradigm. In this paper, we launch several analyses to delve into this issue from scratch. Subsequently, several simple yet effective functions are devised to replace the vanilla KD. The ultimate function can be an effective alternative to …its original counterparts and work well with other skills like FitNets. To claim this point, we conduct several visual tasks on individual benchmarks, and experimental results verify the potential of our proposed function in terms of performance gains. For example, when the teacher and student networks are ShuffleNetV2-1.0 and ShuffleNetV2-0.5, our proposed method achieves 40.88%top-1 error rate on Tiny ImageNet. Show more

Keywords: Neural network compression, knowledge distillation, knowledge transfer

DOI: 10.3233/JIFS-211549

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2247-2259, 2022

Authors: Zhou, Anmin | Huang, Tianyi | Huang, Cheng | Li, Dunhan | Song, Chuangchuang

Article Type: Research Article

Abstract: Python is a concise language which can be used to build lightweight tools or dynamic object-orientated applications. The various attributes of Python have made it attractive to numerous malware authors. Attackers often embed malicious shell commands into Python scripts for illegal operations. However, traditional static analysis methods are not feasible to detect this kind of attack because they focus on common features and failure in finding those malicious commands. On the other hand, dynamic analysis is not optimal in this case for its time-consuming and inefficient. In this paper, we propose PyComm, a model for detecting malicious commands in Python …scripts with multidimensional features based on machine learning, which considers both 12 statistical features and string sequences of Python source code. Meanwhile, three comparison experiments are designed to evaluate the validity of proposed method. Experimental results show that presented model has achieved an excellent performance based on those practical features and random forest (RF) algorithm, obtained an accuracy of 0.955 with a recall of 0.943. Show more

Keywords: Cyber security, malicious script detection, malicious command, machine learning, static analysis

DOI: 10.3233/JIFS-211557

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2261-2273, 2022

Authors: Li, Xiaofei | Ye, Binhua | Liu, Xinwang

Article Type: Research Article

Abstract: Linear programming is an important branch of operations research. The model is mature in theory and widely used in real life. However, various complex realistic scenarios involve fuzzy information. In this paper, we consider a fuzzy linear programming (FLP) model in which all parameters are trapezoidal interval type-2 fuzzy numbers (IT2FNs) and propose a solution method based on the nearest interval approximation and the best-worst cases (BWC) method. We prove the nearest interval approximation interval of trapezoidal IT2FNs, then the trapezoidal IT2FNs in the model are transformed into interval numbers which both upper and lower limits are interval numbers. With …the help of best-worst cases (BWC) method, the sub-models of the transformed interval linear programming model are proposed, and four sub-solutions with different specific meanings can be obtained by solving them respectively. Finally, an application example is presented to show the rationality and practical significance of the method. Show more

Keywords: Fuzzy linear programming (FLP), Trapezoidal interval type-2 fuzzy numbers (IT2FNs), Best-worst cases (BWC) method, The nearest interval approximation

DOI: 10.3233/JIFS-211568

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2275-2285, 2022

Authors: Li, Baolin | Yang, Lihua | Qian, Jie

Article Type: Research Article

Abstract: In practice, picture hesitant fuzzy sets (PHFSs) combining the picture fuzzy sets (PFSs) and hesitant fuzzy sets (HFSs) are suitable to represent more complex multi-criteria decision-making (MCDM) information. The power heronian (PH) operators, which have the merits of power average (PA) and heronian mean (HM) operators, are extended to the environment of PHFSs in this article. First, some algebraic operations of picture hesitant fuzzy numbers (PHFNs), comparative functions and distance measure are introduced. Second, two novel operators, called as picture hesitant fuzzy weighted power heronian (PHFWPH) operator and picture hesitant fuzzy weighted geometric power heronian (PHFWGPH) operator, are defined. Meanwhile, …some desirable characteristics and special instances of two operators are investigated as well. Third, a novel MCDM approach applying the proposed PH operators to handle PHFNs is explored. Lastly, to indicate the effectiveness of this novel method, an example regarding MCDM problem is conducted, as well as sensitivity and comparison analysis. Show more

Keywords: Multi-criteria decision-making, power heronian operators, picture hesitant fuzzy sets

DOI: 10.3233/JIFS-211569

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2287-2308, 2022

Authors: Zhou, Chang-Jie | Yao, Wei

Article Type: Research Article

Abstract: For a usual commutative quantale Q (does not necessarily have a unit), we propose a definition of Q -ordered sets by introducing a kind of self-adaptive self-reflexivity. We study their completeness and the related Q -modules of complete lattices. The main result is that, the complete Q -ordered sets and the Q -modules of complete lattices are categorical isomorphic.

Keywords: Commutative quantale, Q-order, Q-module, complete Q-ordered set

DOI: 10.3233/JIFS-211581

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2309-2316, 2022

Authors: Wang, Sha | Li, Teng | Liu, Zifeng | Pan, Dongbo | Zhang, Yu

Article Type: Research Article

Abstract: The embedding capacity and steganography quality are two important performance indicators of data hiding which has practical application value for copyright and intellectual property protection, public information protection and online elections. Many researches presented hiding methods to improve the performance. However, the existing data hiding methods have problems such as low embedding capacity or poor stego-image quality. This paper proposes a new method (Single Pixel Modification, SPM) to improve the performance further. The SPM (Single Pixel Modification) method embeds k secret bits into a cover-pixel with the idea that minimizing the change to cover-pixel and adopting modulus operation based …on 2k . The experimental results show that the proposed method has better performance than methods compared and the highest hiding capacity can reach 4 bits per pixel and the average PSNR of stego-images is 34.83 dB . The source code and related materials are made to public to make it easy for researchers to verify the work and stimulate further research. Show more

Keywords: Data hiding, modulus calculation, cover image, stego-image

DOI: 10.3233/JIFS-211606

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2317-2329, 2022