Journal of Intelligent & Fuzzy Systems - Volume 43, issue 4

Authors: Zhang, Wei | Wang, Zhiming

Article Type: Research Article

Abstract: Deep Convolutional Neural Networks (CNNs) have been widely used in various domains due to their outstanding performance. However, they simultaneously bring enormous computational overhead, making it difficult to deploy to mobile and edge devices. Therefore, researchers use network compression techniques such as quantization, knowledge distillation and neural network pruning to alleviate this problem. Among network pruning, filter pruning has received broad attention. At present, most of the filter pruning methods need to define pruning rates manually, which is a trial-and-error process and requires rich experimental experience. Some methods obtain global optimal network parameters by Neural Architecture Search (NAS) or Evolutionary …Algorithms (EA) to overcome this difficulty. However, they also introduce huge computational burden. To mitigate the above problems, this study proposes a pruning strategy based on Principal Component Analysis (PCA) called PCA-Pruner. Filter weights of a layer is regarded as a set of features, and the number of filters responding to feature dimension. Then, the number of reserved filters in each layer can be determined by PCA which is a classical dimensionality reduction technology. After that, we calculate the L1 norm of each filter in each layer and use it as an importance measurement to prune filters. Experimental results show that PCA-Pruner achieve performance improvements over the state-of-the-arts algorithms. For example, we compress the FLOPs and parameters of ResNet-56 on CIFA-10 by 45.8% and 47.1%, with an increase in accuracy of 0.27%. For ResNet-110 on CIFAR-10, we improve the accuracy by 0.58% and reduce the FLOPs and Params of the model by 58.3% and 56.2%, respectively. Towards ResNet-56 on CIFAR-100 dataset, we achieve a 38.8% FLOPs decrease and 38.0% Params reduction with only 0.69% accuracy loss. Show more

Keywords: Network compression, neural network pruning, dimensionality reduction, PCA

DOI: 10.3233/JIFS-211555

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 4, pp. 4803-4813, 2022

Authors: Xuan, Cho Do | Huong, DT | Duong, Duc

Article Type: Research Article

Abstract: The Advanced Persistent Threat (APT) attack is a form of dangerous, intentionally and clearly targeted attack. Currently, the APT attack trend is through the end-users and then escalating privileges in the system by spreading malware which is widely used by attackers. Therefore, the problem of early detection and warning of the APT attack malware on workstations is urgent. In this paper, we propose a new approach to APT malware detection on workstations based on the technique of analyzing and evaluating process profiles. The characteristics and principles of our proposed method are as follows: Firstly, processes are collected and aggregated into …process profiles of APT malware; Secondly, these process profiles are used by Graph2Vec graph analysis algorithm to extract the characteristics of the process profile. Finally, in order to conclude about the sign of malicious APT, this paper proposes to use Long short-term memory (LSTM) and bidirectional LSTM (BiLSTM) algorithm. With the proposed approach in the paper, we have not only succeeded in building and synthesizing APT malware behavior on Workstations as a basis to improve the efficiency of predicting APT malware, but also have opened up a new approach to the task of synthesizing and analyzing anomalous behavior of malware. Show more

Keywords: APT, APT malware detection on Workstation, Event ID, deeplearning, process profile, Graph2Vec

DOI: 10.3233/JIFS-212880

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 4, pp. 4815-4834, 2022

Authors: Wang, Yongqiao | Ni, He

Article Type: Research Article

Abstract: This paper studies nonparametric estimation of the discount curve, which should be decreasing and positive over the entire maturity domain. Very few papers explicitly impose these shape requirements for removing the possibility of obtaining a shape-violating estimation. No matter how small the approximating error is, a shape-violating discount curve can never be accepted by the financial industry. Since these shape requirements are continuously constrained and involve an infinite number of inequality constraints, it is hard to provide a necessary and sufficient implementation that is computationally tractable. Existing parametric and nonparametric methods fail to achieve universal flexibility and shape compliance simultaneously. …This paper proposes a nonparametric method that approximates the discount curve with algebraic polynomials and ensures the discount function is decreasing and positive over the entire domain. This estimation problem can be reformulated equivalently as a semidefinite program that is convex and computationally tractable. The proposed method is the first one which not only has asymptotic universal fitting flexibility, but also fully complies with shape requirements. Experimental results on one artificial data, one US Gilt STRIPS data, and one US Treasury bonds data demonstrate its superiority over state-of-the-art methods in terms of both the compliance of shape requirements and out-of-sample fitting measures. Show more

Keywords: Curve fitting, term structure of interest rates, shape restriction, nonparametric regression, function approximation

DOI: 10.3233/JIFS-213432

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 4, pp. 4835-4847, 2022

Authors: Yu, Chun-Min | Chen, Kuen-Suan

Article Type: Research Article

Abstract: As the Internet of Things (IoT) becomes more and more popular and full-grown, diverse technologies for measurement and collection of business data continually improve as well. Effective data analysis of and applications can be helpful to stores to make smart and quick decisions in a jiffy, so that the percentage of customer satisfaction and in-store shopping can increase to raise the total revenue. Some researchers have suggested that the number of customers who enter a store refers to a Poisson process. Based on previous research, an attribute service performance index was proposed in this paper. This paper reviewed the fuzzy …one-tailed testing model of the attribute service performance index and put forward a fuzzy two-tailed testing model of two indices based on the confidence interval to verify whether the improvement had a significant effect. Now that this fuzzy evaluation model is built on the confidence interval of the index, we can diminish the chance of misjudgment caused by sampling error. Its design can incorporate the past data or expert experience. Thus, the evaluation accuracy can be retained in the case of small-sized samples. Show more

Keywords: Attribute service performance index, Poisson process, confidence interval, membership function of fuzzy number, fuzzy testing

DOI: 10.3233/JIFS-220090

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 4, pp. 4849-4857, 2022

Authors: Xu, Chang | Li, Bo | Zhang, Lingxian

Article Type: Research Article

Abstract: Asymmetric ν -twin Support vector regression (Asy-ν -TSVR) is an effective regression model in price prediction. However, there is a matrix inverse operation when solving its dual problem. It is well known that it may be not reversible, therefore a regularized asymmetric ν -TSVR (RAsy-ν -TSVR) is proposed in this paper to avoid above problem. Numerical experiments on eight Benchmark datasets are conducted to demonstrate the validity of our proposed RAsy-ν -TSVR. Moreover, a statistical test is to further show the effectiveness. Before we apply it to Chinese soybean price forecasting, we firstly employ the Lasso to analyze the influence …factors of soybean price, and select 21 important factors from the original 25 factors. And then RAsy-ν -TSVR is used to forecast the Chinese soybean price. It yields the lowest prediction error compared with other four models in both the training and testing phases. Meanwhile it produces lower prediction error after the feature selection than before. So the combined Lasso and RAsy-ν -TSVR model is effective for the Chinese soybean price. Show more

Keywords: Soybean, price forecast, TSVR, pinball loss, lasso

DOI: 10.3233/JIFS-212525

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 4, pp. 4859-4872, 2022

Authors: Shunmuga Priya, M.C. | Karthika Renuka, D. | Ashok Kumar, L.

Article Type: Research Article

Abstract: Speech recognition has now become ubiquitous and plays an inevitable role in almost all sectors. Numerous works have been proposed on speech recognition; however, more accurate transcriptions are not possible. Exploration of various studies related to spell correction implies that several kinds of research have been carried out in this field but still it is a very challenging problem. This led to the need for a new spell corrector framework capable of leveraging the performance of the automatic speech recognition (ASR) system. The proposed work unveils state-of-the-art Bidirectional Encoder Representations from Transformers (BERT) based spell correction module developed on top …of the deep recurrent neural network (RNN) based ASR system. The impact of BERT-based spell correction on the ASR system is evaluated on three different accent datasets in the perspective of word error rate (WER), character error rate (CER), and Bilingual evaluation understudy (BLEU) score. The experimental results inferred that the enhanced spell correction module is efficacious in detecting and correcting spell errors, by achieving the WER of 5.025% on librispeech corpus, 6.35% on voxforge, and 7.05% on NPTEL corpus. Show more

Keywords: Deep learning, natural language processing, spell error correction, word error rate, BERT

DOI: 10.3233/JIFS-213332

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 4, pp. 4873-4882, 2022

Authors: Işık, Gürkan | Kaya, İhsan

Article Type: Research Article

Abstract: As a combining concept of Pythagorean fuzzy sets (PFSs) and linguistic fuzzy sets (FSs), linguistic PFSs (LPFSs) has been suggested in the literature to deal with the uncertain and inconsistent information in multi-criteria decision making (MCDM) process. The LPFSs based procedure has been built by assuming that the experts make assessments suitable with PFS. It does not provide a mechanism to ensure the suitability of the assessments with theory of PFSs but there are other type of non-standard fuzzy sets such as Neutrosophic sets (NSs) used for modeling with inconsistent information. The main motivation of this study is to offer …an assessment collection method to guarantee that the input statements will be Pythagorean fuzzy linguistic expressions. As a second motivation, it is aimed to extend the PFS method for the fuzzy modeling of the other type of decision-making problems apart from MCDM which do not require aggregation and comparison operations and continue with precise fuzzy modeling (PFM). The third motivation of this study is to offer enhancements on the LPFSs method to increase the sensitivity of the modeling while protecting the interpretability. For these purposes, a new methodology based on LPFSs has been proposed and applied on a decision-making problem in a comparative way. Show more

Keywords: Fuzzy modifiers, fuzzy sets, linguistic terms, linguistic 2-tuple statements, pythagorean fuzzy sets

DOI: 10.3233/JIFS-213384

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 4, pp. 4883-4894, 2022

Authors: Dobrović, Željko | Tomičić-Pupek, Katarina

Article Type: Research Article

Abstract: Defense organizations, like the ministry of defense, the armed forces, the general staff of the armed forces, the army, the navy, or the air force units, use a specific business technology. What makes their business technology specific is a predictable changeability of their business processes. Namely, these organizations function in more than one state, each having its own business processes. An organization transits from one state to another in a predictable manner, thus changing its business processes. This kind of business technology is not exclusively restricted to defense organizations, as it also applies to police as well as crisis management …organizations. In order to develop information systems (IS) supporting these organizations properly, the complexity of their future IS should be assessed first. This assessment can be performed by relying on existing genetic taxonomies, i.e., by situating the planned defense IS inside the IS genetic taxonomy space, with regard of relevant characteristics of organizational processes supported by the IS. A behavioral dimension described in this paper addresses the dynamics of states defense systems operate in, offering to contribute to the understanding of defense systems’ response to changes in dynamic ecosystems, assisting thereby researchers and practitioners in describing dynamic properties of investigated systems. Show more

Keywords: Genetic taxonomy space, information systems, complexity, defense organizations

DOI: 10.3233/JIFS-220370

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 4, pp. 4895-4909, 2022

Authors: Yang, Yaliu | Wu, Xue | Liu, Fan | Zhang, Yingyan | Liu, Conghu

Article Type: Research Article

Abstract: With the increasing severity of the global energy crisis and environmental pollution, there is an urgent need to change the economic development model driven by certain factors and the investment scale and pursue science- and technology-driven innovative development. This study aims to improve the efficiency of scientific and technological innovation and promote the high-quality development of regional industrial enterprises. It constructs a data-driven DEA-Malmquist evaluation model to evaluate and optimize regional industrial enterprises’ scientific and technological innovation efficiency. First, we collect the panel data of regional industrial enterprises’ scientific and technological innovation input-output indexes. Second, we use the Pearson correlation …coefficient method to identify and construct the evaluation index system of regional industrial enterprises’ scientific and technological innovation efficiency. Third, we build a DEA-Malmquist evaluation model to quantitatively evaluate regional industrial enterprises’ scientific and technological innovation efficiency from static and dynamic aspects. Finally, we verify the feasibility and effectiveness of the method using statistical data on scientific and technological innovation and development of Anhui industrial enterprises from 2011 to 2019 and put forth targeted countermeasures and suggestions. This study provides theoretical and methodological support for the sustainable development of industrial enterprises. Show more

Keywords: Data-driven, DEA-Malmquist evaluation model, Anhui Province, industrial enterprise, scientific and technological innovation efficiency

DOI: 10.3233/JIFS-220491

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 4, pp. 4911-4928, 2022

Authors: Wang, Yufei | Dong, Xiaoshe | Wang, Longxiang | Chen, Weiduo | Chen, Heng

Article Type: Research Article

Abstract: In recent years, with the development of flash memory technology, storage systems in large data centers are typically built upon thousands or even millions of solid-state drives (SSDs). Therefore, the failure of SSDs is inevitable. An SSD failure may cause unrecoverable data loss or unavailable system service, resulting in catastrophic results. Active fault detection technologies are able to detect device problems in advance, so it is gaining popularity. Recent trends have turned toward applying AI algorithms based on SSD SMART data for fault detection. However, SMART data of new SSDs contains a large number of features, and the high dimension …of data features results in poor accuracy of AI algorithms for fault detection. To tackle the above problems, we improve the structure of traditional Auto-Encoder (AE) based on GRU and propose an SSD fault detection method – GAL based on dimensionality reduction with Gated Recurrent Unit (GRU) sparse autoencoder (GRUAE) by combining the temporal characteristics of SSD SMART data. The proposed method trains the GRUAE model with SSD SMART data firstly, and then adopts the encoder of GRUAE model as the dimensionality reduction tool to reduce the original high-dimensional SSD SMART data, aiming at reducing the influence of noise features in original SSD SAMRT data and highlight the features more relevant to data characteristics to improve the accuracy of fault detection. Finally, LSTM is adopted for fault detection with low-dimensional SSD SMART data. Experimental results on real SSD dataset from Alibaba show that the fault detection accuracy of various AI algorithms can be improved by varying degrees after dimensionality reduction with the proposed method, and GAL performs best among all methods. Show more

Keywords: Fault detection, dimensionality reduction, sparse auto-encoder, solid state drives, gated recurrent unit

DOI: 10.3233/JIFS-220590

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 4, pp. 4929-4946, 2022