Yazar "Pedrycz, Witold" seçeneğine göre listele
Listeleniyor 1 - 20 / 102
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Accelerated Fuzzy C-Means Clustering Based on New Affinity Filtering and Membership Scaling(Ieee Computer Soc, 2023) Li, Dong; Zhou, Shuisheng; Pedrycz, WitoldFuzzy C-Means (FCM) is a widely used clustering method. However, FCM and its many accelerated variants have low efficiency in the mid-to-late stage of the clustering process. In this stage, all samples are involved in updating their non-affinity centers, and the membership grades of most samples, whose assignments remain unchanged, are still updated by calculating the sample-center distances. All these factors lead to the algorithms converging slowly. In this paper, a new affinity filtering technique is developed to recognize a complete set of non-affinity centers for each sample with low computations. Then, a new membership scaling technique is suggested to set the membership grades between each sample and its non-affinity centers to 0 and maintain the fuzzy membership grades for others. By integrating these two techniques, FCM based on new affinity filtering and membership scaling (AMFCM) is proposed to accelerate the whole convergence process of FCM. Numerous experimental results performed on synthetic and real-world data sets have shown the feasibility and efficiency of the proposed algorithm. Compared with state-of-the-art algorithms, AMFCM is significantly faster and more effective. For example, AMFCM reduces the number of FCM iterations by 80% on average.Öğe Accelerating the integration of the metaverse into urban transportation using fuzzy trigonometric based decision making(Pergamon-Elsevier Science Ltd, 2024) Deveci, Muhammet; Pamucar, Dragan; Gokasar, Ilgin; Martinez, Luis; Koppen, Mario; Pedrycz, WitoldMetaverse is defined as a fictional universe that could serve as a simulation environment of reality. Beginning in the past with games, it becomes increasingly integrated into human life as time passes. Metaverse usage is inevitable in every aspect of life. One of its potential application areas could be urban transportation. A novel fuzzy trigonometric based on the combination of the Full Consistency Method (FUCOM) and Combined Compromise Solution (CoCoSo) is proposed to rank three alternatives with twelve criteria under four major aspects: managerial, safety, user, and urban mobility. In the first stage, fuzzy FUCOM methods are used to calculate the weights of the criteria. In the second stage, the fuzzy trigonometric based CoCoSo method is applied to evaluate and rank the alternatives. The proposed model enables the nonlinear processing of complex and uncertain information using fuzzy trigonometric functions. The findings demonstrate focusing on a particular age group can make it easier to integrate the metaverse with urban transportation. The findings of this study have the potential to serve as a guide for decision-makers. The metaverse-based applications could be started by policymakers, which is a promising opportunity with potential boundaries beyond human comprehension making this statement weaker.Öğe Adaptive Nonstationary Fuzzy Neural Network(Elsevier, 2024) Chang, Qin; Zhang, Zhen; Wei, Fanyue; Wang, Jian; Pedrycz, Witold; Pal, Nikhil R.Fuzzy neural network (FNN) plays an important role as an inference system in practical applications. To enhance its ability of handling uncertainty without invoking high computational cost, and to take variations in rules into consideration as well, we propose a new inference framework-nonstationary fuzzy neural network (NFNN). This NFNN is composed of a series of zero -order TSK FNNs with the same structure but using slightly perturbed fuzzy sets in the corresponding neurons, which is inspired from the non -stationary fuzzy sets and can mimic the variation in human's decision -making process. In order to obtain a concise and adaptive rule base for NFNN, a modified affinity propagation (MAP) clustering method is proposed. The MAP can determine the number of rules in an adaptive manner, and is used to initialize the rule parameters of NFNN, which we call Adaptive NFNN (ANFNN). Numerical experiments have been carried out over 17 classification datasets and three regression datasets. The experimental results demonstrate that ANFNN exhibits better accuracy, generalization ability, and fault -tolerance ability compared with the classical type -1 fuzzy neural network. In 15 of the 17 classification datasets, ANFNN achieves the same or better accuracy performance compared to interval type -2 FNNs with about half time consumed. This work confirms the feasibility of integrating simplestructured type -1 TSK FNNs to achieve the performance of interval type -2 FNNs, and proves that ANFNN can be a more accurate and reliable alternative to classical type -1 FNN.Öğe Advantage prioritization of digital carbon footprint awareness in optimized urban mobility using fuzzy Aczel Alsina based decision making(Elsevier, 2024) Deveci, Muhammet; Gokasar, Ilgin; Pamucar, Dragan; Zaidan, Aws Alaa; Wei, Wei; Pedrycz, WitoldCity governments prioritize mobility in urban planning and policy. Greater mobility in a city leads to happier citizens. Although enhanced urban mobility is helpful, it comes with costs, notably in terms of climate change. Transportation systems that enable urban mobility often emit greenhouse gases. Cities must prioritize digital carbon footprint awareness. Cities may reduce the environmental impact of urban mobility while keeping its benefits by close monitoring and reducing the carbon footprint of digital technologies like transportation applications, ride-sharing platforms, and smart traffic control systems. The aim is to advantage prioritize three alternatives, namely doing nothing, upgrading and optimizing data centers and networks, and using renewable energy sources for data centers and networks to minimize the digital carbon footprint using the proposed decision making tool. This study consists of two stages. In the first stage, fuzzy Aczel-Alsina functions (fuzzy Aczel-Alsina weighted assessment - ALWAS method) based Ordinal Priority Approach (OPA) is proposed to find the weights of criteria. Secondly, fuzzy ALWAS Combined Compromise Solution (CoCoSo) model improved to evaluate and choose the best alternative among the three alternatives. The improved ALWAS-CoCoSo model enables flexible nonlinear processing of uncertain information and simulation of different risk levels. Besides, we proposed the improved fuzzy OPA algorithm for processing uncertain and incomplete information. The case study is provided to the decision-makers to advantage prioritize the alternatives based twelve criteria organized into four aspects, including digital carbon footprint, externalities, technical capability, and economics. The ranking results reveal that A(3) = 2.445 is the best among the three alternative, while A(1) = 1.705 is the worst alternative. The results show that the best way to reduce the digital carbon footprint is to use renewable energy sources to power data centers and networks (A(3)).Öğe Aggregation of Basic Uncertain Information With Two-Step Aggregation Frame(Ieee-Inst Electrical Electronics Engineers Inc, 2024) Jin, Lesheng; Chen, Zhen-Song; Pedrycz, Witold; Senapati, Tapan; Yatsalo, Boris; Mesiar, Radko; Beliakov, GlebThere exist various categories of uncertain information, and their corresponding methods of aggregation may also vary. At present, there exists a dearth of specifically tailored techniques for aggregating basic uncertain information (BUI). The present study introduces a two-step aggregation frame that is applicable to inputs of both real-valued and BUI-valued inputs. In the process of constructing such a frame, several novel notions and definitions are introduced. These comprise of extended aggregation operators with respect to a finite set and to a collection of subsets of the set, some certainty independent BUI aggregation and some certainty dependent BUI aggregation, BUI merging operators and BUI aggregation operators, BUI-valued min operator, and BUI-valued Sugeno integral. Some corresponding deductions, necessary reasoning and numerical examples are presented.Öğe Analysis of power asymmetry conflict based on fuzzy options graph models(Elsevier, 2024) Chen, Lu; Pedrycz, Witold; Xu, HaiyanAsymmetric power conflicts occur frequently. Because of the complexity of the conflict as well as the vagueness of the decision makers' cognition, it becomes urgent and highly motivated to propose an appropriate method to solve power asymmetry conflict. In this study, we consider that decision makers provide option choices quantified by some degrees of membership. The choice of an option is determined by the thresholds of selection degree. At the same time, due to the influence of the power, the follower adjusts its degree of option choice to reach consensus with the leader. The computational rules determining fuzzy truth value are given, and a fuzzy truth value option prioritization method is proposed to calculate the ranking of the states, where the states ordering is related to the fuzzy degree of option selection. Different from the previous studies, this paper is the first one to study the asymmetric power conflict from the perspective of options, considering the psychological threshold of decision maker for option selection, and pointing out that the option choice is described with the fuzzy values rather than being treated as two-valued (Boolean). Furthermore, the introduced stability analysis also reflects the interaction of the options of different decision makers, which makes the proposal being more in rapport with real-world scenarios. Finally, a case study of carbon emission reduction power asymmetry conflict in supply chain is studied to demonstrate the performance of the proposed method.Öğe An Approach for Incremental Mining of Clickstream Patterns as a Service Application(Ieee Computer Soc, 2023) Huynh, Huy M.; Vo, Bay; Oplatkova, Zuzana K.; Pedrycz, WitoldSequential pattern mining in general and one particular form, clickstream pattern mining, are data mining topics that have recently attracted attention due to their potential applications of discovering useful patterns. However, in order to provide them as real-world service applications, one issue that needs to be addressed is that traditional algorithms often view databases as static. In reality, databases often grow over time and invalidate parts of the previous results after updates, forcing the algorithms to rerun from scratch on the updated databases to obtain updated frequent patterns. This can be inefficient as a service application due to the cost in terms of resources, and the returning of results to users can take longer when the databases get bigger. The response time can be shortened if the algorithms update the results based on incremental changes in databases. Thus, we propose PF-CUP (pre-frequent clickstream mining using pseudo-IDList), an approach towards incremental clickstream pattern mining as a service. The algorithm is based on the pre-large concept to maintain and update results and a data structure called a pre-frequent hash table to maintain the information about patterns. The experiments completed on different databases show that the proposed algorithm is efficient in incremental clickstream pattern mining.Öğe An Approach to Semantic-Aware Heterogeneous Network Embedding for Recommender Systems(Ieee-Inst Electrical Electronics Engineers Inc, 2023) Pham, Phu; Nguyen, Loan T. T.; Nguyen, Ngoc-Thanh; Pedrycz, Witold; Yun, Unil; Lin, Jerry Chun-Wei; Vo, BayRecent studies on heterogeneous information network (HIN) embedding-based recommendations have encountered challenges. These challenges are related to the data heterogeneity of the associated unstructured attribute or content (e.g., text-based summary/description) of users and items in the context of HIN. In order to address these challenges, in this article, we propose a novel approach of semantic-aware HIN embedding-based recommendation, called SemHE4Rec. In our proposed SemHE4Rec model, we define two embedding techniques for efficiently learning the representations of both users and items in the context of HIN. These rich-structural user and item representations are then used to facilitate the matrix factorization (MF) process. The first embedding technique is a traditional co-occurrence representation learning (CoRL) approach which aims to learn the co-occurrence of structural features of users and items. These structural features are represented for their interconnections in terms of meta-paths. In order to do that, we adopt the well-known meta-path-based random walk strategy and heterogeneous Skip-gram architecture. The second embedding approach is a semantic-aware representation learning (SRL) method. The SRL embedding technique is designed to focus on capturing the unstructured semantic relations between users and item content for the recommendation task. Finally, all the learned representations of users and items are then jointly combined and optimized while integrating with the extended MF for the recommendation task. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed SemHE4Rec in comparison with the recent state-of-the-art HIN embedding-based recommendation techniques, and reveal that the joint text-based and co-occurrence-based representation learning can help to improve the recommendation performance.Öğe Assessing alternatives of including social robots in urban transport using fuzzy trigonometric operators based decision-making model(Elsevier Science Inc, 2023) Deveci, Muhammet; Pamucar, Dragan; Gokasar, Ilgin; Zaidan, Bilal Bahaa; Martinez, Luis; Pedrycz, WitoldCurrent trends point to a not-too-distant future with qualitatively advanced interactions between humans and social robots. It is critical to consider the possibility of forming meaningful social relationships with robots when defining the future of human-robot interactions, as well as studying how these interactions will evolve to the point where humans are unable to distinguish between humans and robots in urban transportation. In this study, the advantages of using social robots in urban transportation are prioritized by using a multi-criteria decisionmaking tool, which consists of two consecutive stages, namely: i) a novel fuzzy sine trigonometry based on the logarithmic method of additive weights (fuzzy ST-LMAW) that is proposed to calculate the criteria weights; ii) a nonlinear fuzzy Aczel-Alsina function based the weighted aggregate sum product assessment (fuzzy ALWASWASPAS) that is developed to select and rank the alternatives. The proposed model enables flexible nonlinear processing of complex and uncertain information encountered in real applications. A case study is developed to rank three alternatives with twelve sub-criteria grouped into four aspects using the proposed method. The results show that the most advantageous alternative is to replace people with social robots as safety drivers in level four autonomous vehicles due to their possible impact on transportation.Öğe Assessing growth potential of careers with occupational mobility network and ensemble framework(Pergamon-Elsevier Science Ltd, 2024) Liu, Jiamin; Wang, Tao; Yao, Feng; Pedrycz, Witold; Song, Yanjie; He, RenjieThe growth potential of a career reflects its future prospects and is an important consideration for individuals and organizations when career planning. There is still a lack of quantitative assessment tools for growth potential of careers. In this study, considering the key role of human capital in human resource management, as well as the excellent performance of complex network and machine learning in big data analysis and prediction, a career growth potential assessment model with human capital ensemble is proposed through human capital-based occupational mobility network and ensemble learning. First, an occupational mobility network is constructed based on online professional dataset to associate occupations with each other. Then, five dimensions of human capital measurements are designed to quantify human capital in terms of education, experience, social capital, occupational size, and concentration. These are then combined with the occupational mobility network to create a new network that depicts human capital flows among occupations. Finally, an ensemble framework for assessing career growth potential is constructed to integrate multidimensional human capital information in the network and obtain quantitative scores of growth potential. This study is the original attempt to adopt a data-driven idea and an intelligent approach to understand career growth potential. The experimental results show that it also makes a useful exploration for modeling human capital flows and intelligent assessment of career prospects.Öğe Automated breast cancer detection in mammography using ensemble classifier and feature weighting algorithms(Pergamon-Elsevier Science Ltd, 2023) Yan, Fei; Huang, Hesheng; Pedrycz, Witold; Hirota, KaoruBreast cancer exhibits one of the highest incidence and mortality rates among all cancers affecting women. The early detection of breast cancer reduces mortality and is crucial for prolonging life expectancy. Although mammography is the most often used screening technique in clinical practice, previous studies reviewing mammograms diagnosed by radiologists have commonly revealed false negatives and false positives. Ongoing advances in machine learning techniques have triggered new motivation for the development of computer-aided diagnosis (CAD) systems, which could be applied to assist radiologists in improving final diagnostic accuracy. In this study, an automated methodology for detecting breast cancer in mammography images is proposed based on an ensemble classifier and feature weighting algorithms. First, a novel region extraction approach is proposed to constrain the search area for suspicious breast lesions and an original pectoral removal method is proposed to avoid interference when identifying a region of interest (ROI). In addition, an effective segmentation strategy is developed to automatically identify ROIs whose textural and morphological features are then fused and weighted to generate new feature vectors using a feature weighting algorithm. Finally, an ensemble classifier model is designed using k-nearest neighbor (KNN), bagging, and eigenvalue classification (EigenClass) to determine whether a mammogram contains normal, benign, or malignant tumors based on a majority voting rule. A series of experiments was conducted using the Digital Database for Screening Mammography (DDSM) and Mammographic Image Analysis Society (MIAS) datasets, the results of which demonstrated the proposed scheme outperformed comparable algorithms.Öğe Automatically Prioritizing Tasks in Software Development(Ieee-Inst Electrical Electronics Engineers Inc, 2023) Bugayenko, Yegor; Farina, Mirko; Kruglov, Artem; Pedrycz, Witold; Plaksin, Yaroslav; Succi, GiancarloWithin the domain of managing software development teams, effective task prioritization is a critical responsibility that should not be underestimated, particularly for larger organizations with significant backlogs. Current approaches primarily rely on predicting task priority without considering information about other tasks, potentially resulting in inaccurate priority predictions. This paper presents the benefits of considering the entire backlog when prioritizing tasks. We employ an iterative approach using Particle Swarm Optimization to optimize a linear model with various preprocessing methods to determine the optimal model for task prioritization within a backlog. The findings of our study demonstrate the usefulness of constructing a task prioritization model based on complete information from the backlog. The method proposed in our study can serve as a valuable resource for future researchers and can also facilitate the development of new tools to aid IT management teams.Öğe Center transfer for supervised domain adaptation(Springer, 2023) Huang, Xiuyu; Zhou, Nan; Huang, Jian; Zhang, Huaidong; Pedrycz, Witold; Choi, Kup-SzeDomain adaptation (DA) is a popular strategy for pattern recognition and classification tasks. It leverages a large amount of data from the source domain to help train the model applied in the target domain. Supervised domain adaptation (SDA) approaches are desirable when only few labeled samples from the target domain are available. They can be easily adopted in many real-world applications where data collection is expensive. In this study, we propose a new supervision signal, namely center transfer loss (CTL), to efficiently align features under the SDA setting in the deep learning (DL) field. Unlike most previous SDA methods that rely on pairing up training samples, the proposed loss is trainable only using one-stream input based on the mini-batch strategy. The CTL exhibits two main functionalities in training to increase the performance of DL models, i.e., domain alignment and increasing the feature's discriminative power. The hyper-parameter to balance these two functionalities is waived in CTL, which is the second improvement from the previous approaches. Extensive experiments completed on well-known public datasets show that the proposed method performs better than recent state-of-the-art approaches.Öğe Coding Method Based on Fuzzy C-Means Clustering for Spiking Neural Network With Triangular Spike Response Function(Ieee-Inst Electrical Electronics Engineers Inc, 2023) Liu, Fang; Pedrycz, Witold; Zhang, Chao; Yang, Jie; Wu, WeiAlthough spiking neural network (SNN) has the advantages of strong brain-likeness and low energy consumption due to the use of discrete spikes for information representation and transmission, its performance still needs to be improved. This article improves SNN in terms of the coding process and the spike response function by invoking fuzzy sets. In terms of coding, a new fuzzy C-means coding (FCMC) method is proposed, which breaks the limitation of uniformly distributed receptive fields of existing coding methods and automatically determines suitable receptive fields that reflect the density distribution of the input data for encoding through the fuzzy C-means clustering. In terms of spike response function, triangular fuzzy numbers instead of the commonly used alpha-type function are used as the spike response function. Different from other functions of fixed shape, width parameters of the proposed function are learnt in the iterative way like weights of synapses do. Experimental results obtained on seven benchmark datasets and two real-world datasets with eleven approaches demonstrate that SNN with triangular spike response functions (abbreviated as T-SNN) combining FCMC can achieve improved performance in terms of accuracy, F-measure, AUC, required epochs, running time, and stability.Öğe A comprehensive survey on applications of transformers for deep learning tasks(Pergamon-Elsevier Science Ltd, 2024) Islam, Saidul; Elmekki, Hanae; Elsebai, Ahmed; Bentahar, Jamal; Drawel, Nagat; Rjoub, Gaith; Pedrycz, WitoldTransformers are Deep Neural Networks (DNN) that utilize a self-attention mechanism to capture contextual relationships within sequential data. Unlike traditional neural networks and variants of Recurrent Neural Networks (RNNs), such as Long Short-Term Memory (LSTM), Transformer models excel at managing long dependencies among input sequence elements and facilitate parallel processing. Consequently, Transformer -based models have garnered significant attention from researchers in the field of artificial intelligence. This is due to their tremendous potential and impressive accomplishments, which extend beyond Natural Language Processing (NLP) tasks to encompass various domains, including Computer Vision (CV), audio and speech processing, healthcare, and the Internet of Things (IoT). Although several survey papers have been published, spotlighting the Transformer's contributions in specific fields, architectural disparities, or performance assessments, there remains a notable absence of a comprehensive survey paper that encompasses its major applications across diverse domains. Therefore, this paper addresses this gap by conducting an extensive survey of proposed Transformer models spanning from 2017 to 2022. Our survey encompasses the identification of the top five application domains for Transformer-based models, namely: NLP, CV, multi -modality, audio and speech processing, and signal processing. We analyze the influence of highly impactful Transformer-based models within these domains and subsequently categorize them according to their respective tasks, employing a novel taxonomy. Our primary objective is to illuminate the existing potential and future prospects of Transformers for researchers who are passionate about this area, thereby contributing to a more comprehensive understanding of this groundbreaking technology.Öğe Condition Recognition Strategy Based on Fuzzy Clustering With Information Granulation for Blast Furnace(Ieee-Inst Electrical Electronics Engineers Inc, 2023) Huang, Yuanfeng; Du, Sheng; Hu, Jie; Pedrycz, Witold; Wu, MinThe temperature of the cooling stave (TCS) is an important state parameter to indicate the states of the slag crust during the blast furnace ironmaking process. The state of the slag crust affects the quality and production of pig iron, and the gas flow distribution in the blast furnace. Thus, it is necessary to recognize the states of the slag crust. This article proposes a condition recognition strategy based on fuzzy clustering endowed with a novel distance with information granulation for recognizing the states of the slag crust. First, the raw TCS time-series data are split into segments according to the appropriate segmentation length, and the segments are represented in a granular form by the information granulation method. Then, information granules are clustered using fuzzy clustering endowed with a novel distance. After completing the data representation, each information granule is compounded of a lower bound and an upper bound that indicate the dynamic characteristics of the corresponding segments. In the fuzzy clustering, information granulation distance, a new distance, is established to measure the similarity between two information granules. Finally, the data experiments using the datasets from the UCR time-series database and actual industrial data from the blast furnace demonstrate the effectiveness and superiority of the proposed condition recognition strategy.Öğe Conflict analysis based on a novel three-way decisions graph model for conflict resolution method under hesitant fuzzy environment(Elsevier, 2023) Chen, Lu; Xu, Haiyan; Pedrycz, WitoldMulti-criteria decision aiding/making (MCDA/M) approach and three-way decisions (3WD) are embedded into the framework of graph model for conflict resolution (GMCR). The objective of this study is to develop more reasonable preference ranking for decision makers (DMs) produced from the perspective of options. This implies further simplification of the underlying computing behind conflict resolution. More specifically, DMs' original option statements are evaluated by hesitant fuzzy sets (HFSs), then a three-way decisions approach is used to screen out the infeasible and rank the feasible option statements, and the feasible option statements' loss values of three-way decisions approach are determined based on the hesitant fuzzy (HF) evaluation values. In addition, based on the value of conditional probability of the feasible option statements, an improved option prioritization technique with objective weights is developed to efficiently rank the conflict states, so that it can efficiently reflect the intensity of the ranking. Then, considering the preference thresholds of DMs, new definitions of threshold stabilities are proposed. As demonstrated by the case study in the problem of a carbon emission conflict in supply chain under 3060 carbon peak and neutrality goal in China, the proposed novel three-way decisions graph model for conflict resolution (3WD-GMCR) framework can be widely applied to the realistic scenarios of decision-making. Compared with previous studies, the proposed approach can not only obtain the intensity ranking of conflict states, but also resolve complex large-scale conflicts effectively.Öğe Conjunctive and disjunctive combination rules in random permutation set theory: A layer-2 belief structure perspective(Elsevier, 2024) Zhou, Qianli; Cui, Ye; Pedrycz, Witold; Deng, YongIn uncertainty reasoning, conjunctive and disjunctive combination rules are the core tools for information updates. As an extension of evidential reasoning, random permutation set reasoning models uncertain information based on ordered focal sets. Existing combination rules in random permutation set theory, orthogonal sums, do not satisfy the commutativity of one of the original distributions and overly obey its order information. In this paper, the random permutation set theory is interpreted as an refined extension of Dempster-Shafer theory, and a layer-2 belief structure is proposed to describe the permutation event space. Compared with the traditional belief structure, the proposed structure can model both symbolic and numerical uncertainty. Based on the above, the conjunctive and disjunctive combination rules in Dempster-Shafer theory are extended to random permutation set theory. Through properties analysis and simulation demonstration, we demonstrate that the proposed methods can not only resolve the counter-intuitive results of orthogonal sums, but make full use of order information in distributions as well. In addition, we also extend the product space operations and discounting methods based on the proposed methods, and give a general framework of multi-source information fusion under the random permutation set theory.Öğe Convolutional Features-Based Broad Learning With LSTM for Multidimensional Facial Emotion Recognition in Human-Robot Interaction(Ieee-Inst Electrical Electronics Engineers Inc, 2024) Chen, Luefeng; Li, Min; Wu, Min; Pedrycz, Witold; Hirota, KaoruConvolutional feature-based broad learning with long short-term memory (CBLSTM) is proposed to recognize multidimensional facial emotions in human-robot interaction. The CBLSTM model consists of convolution and pooling layers, broad learning (BL), and long-and short-term memory network. It aims to obtain the depth, width, and time scale information of facial emotion through three parts of the model, so as to realize multidimensional facial emotion recognition. CBLSTM adopts the structure of BL after processing was done at the convolution and pooling layer to replace the original random mapping method and extract features with more representation ability, which significantly reduces the computational time of the facial emotion recognition network. Moreover, we adopted incremental learning, which can quickly reconstruct the model without a complete retraining process. Experiments on three databases are developed, including CK+, MMI, and SFEW2.0 databases. The experimental results show that the proposed CBLSTM model using multidimensional information produces higher recognition accuracy than that without time scale information. It is 1.30% higher on the CK+ database and 1.06% higher on the MMI database. The computation time is 9.065 s, which is significantly shorter than the time reported for the convolutional neural network (CNN). In addition, the proposed method obtains improvement compared to the state-of-the-art methods. It improves the recognition rate by 3.97%, 1.77%, and 0.17% compared to that of CNN-SIPS, HOG-TOP, and CMACNN in the CK+ database, 5.17%, 5.14%, and 3.56% compared to TLMOS, ALAW, and DAUGN in the MMI database, and 7.08% and 2.98% compared to CNNVA and QCNN in the SFEW2.0 database.Öğe Convolutional Fuzzy Neural Networks With Random Weights for Image Classification(Ieee-Inst Electrical Electronics Engineers Inc, 2024) Wang, Yifan; Ishibuchi, Hisao; Pedrycz, Witold; Zhu, Jihua; Cao, Xiangyong; Wang, JunDeep fuzzy neural networks have established a fundamental connection between fuzzy systems and deep learning networks, serving as a crucial bridge between two research fields in computational intelligence. These hybrid networks have powerful learning capability stemming from deep neural networks while leveraging the advantages of fuzzy systems, such as robustness. Due to these benefits, deep fuzzy neural networks have recently been an emerging topic in computational intelligence. With the help of deep learning, fuzzy systems have achieved great performance on the classification task. Although fuzzy systems have been extensively investigated, they still struggle in terms of image classification. In this paper, we propose a convolutional fuzzy neural network that combines improved convolutional neural networks with a fuzzy-set-based fusion technique. Different from convolutional neural networks, filters are randomly generated in convolutional layers in our model. This operation not only leads to the fast learning of the model but also avoids some notorious problems of gradient descent procedures in conventional deep learning methods. Extensive experiments demonstrate that the proposed approach is competitive with state-of-the-art fuzzy models and deep learning models. Compared to classical deep models that require massive training data, the proposed approach works well on small datasets.
