Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.5
Journals
Applied Sciences
Special Issues
New Frontiers in Computational Intelligence
applsci-logo
Submit to Applied Sciences Review for Applied Sciences Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

New Frontiers in Computational Intelligence

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (30 June 2020) | Viewed by 14608

Special Issue Editor

Prof. Shie-Jue Lee

E-Mail Website
Guest Editor
National Sun Yat-sen University, Kaohsiung (NSYSU), National Sun Yat-sen University, Taiwan
Interests: artificial intelligence; machine learning; data mining; soft computing

Special Issue Information

Dear Colleagues,

Artificial Intelligence (AI), a kind of recognition science, refers to the use of machines to carry out solution processes that require intelligence. In other words, AI is the simulation of human cognitive faculties in terms of perceiving, reasoning, learning, problem solving, etc., by machines. Such technology generally involves the processing of huge amounts of information by machines followed by decision making and/or actions as well as the ability to adapt to improve performance. As a result, computing is a key component of AI and currently is an effective way of making AI achievable and useful for a variety of applications, e.g., financial, robotics, medical, transportation, and defense.

It is because of the strong relationship between computing and AI that the term “computational intelligence (CI)” has appeared in recent years. CI concerns the theory, design, and development of biologically and linguistically motivated computational paradigms. It is a fast-evolving field, and in addition to Neural Networks, Fuzzy Systems, and Evolutionary Computation, which are traditional topics, more topics, e.g., ambient intelligence, artificial life, social mining, and business intelligence, have been proposed and elaborated.

With the rapid expansion of research on computing and artificial intelligence, smart applications or products (e.g., face recognition, speech recognition, air quality forecasting, self-driving car, recommender systems, and intrusion detection systems) have been developed for practical use. For instance, AI systems are used to interact with phones and speakers through voice assistants, cars interpret and analyze their surroundings to intelligently drive themselves, and the purchase experience and the characteristics of customers are analyzed and new products are recommended to buyers. However, there are still many challenging issues to be addressed and a lot of applications to be explored in this area.

This Special Issue will present a collection of the latest research in the broad field of Information Technologies (IT) with a specific focus on computing and artificial intelligence. Papers dealing with the acquisition, processing, storage, and transmission of information related to computing and artificial intelligence are within the scope of this Special Issue. Research results from academia and industry, either theoretical or practical, are welcome. We hope to provide a forum to disseminate the valuable results to a global community of researchers.

Topics of interest include, but are not limited to the following topics:

  • Computational intelligence;
  • Neural networks theory and models;
  • Fuzzy logic and fuzzy systems;
  • Brain-/nature-inspired computing;
  • Evolutionary computation;
  • Deep learning;
  • Reinforcement learning;
  • Ambient intelligence;
  • Big data analytics, visualization, modeling;
  • Machine learning;
  • Agent-based systems and collective intelligence;
  • Expert systems;
  • Data mining, text mining, web mining;
  • AI-based applications.

Prof. Shie-Jue Lee
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • artificial intelligence
  • machine learning
  • data mining
  • big data analysis
  • intelligent agents
  • soft computing

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

20 pages, 578 KiB  
Article
Pattern Classification Based on RBF Networks with Self-Constructing Clustering and Hybrid Learning
by Zan-Rong He, Yan-Ting Lin, Chen-Yu Wu, Ying-Jie You and Shie-Jue Lee
Appl. Sci. 2020, 10(17), 5886; https://doi.org/10.3390/app10175886 - 25 Aug 2020
Cited by 3 | Viewed by 2732
Abstract
Radial basis function (RBF) networks are widely adopted to solve problems in the field of pattern classification. However, in the construction phase of such networks, there are several issues encountered, such as the determination of the number of nodes in the hidden layer, [...] Read more.
Radial basis function (RBF) networks are widely adopted to solve problems in the field of pattern classification. However, in the construction phase of such networks, there are several issues encountered, such as the determination of the number of nodes in the hidden layer, the form and initialization of the basis functions, and the learning of the parameters involved in the networks. In this paper, we present a novel approach for constructing RBF networks for pattern classification problems. An iterative self-constructing clustering algorithm is used to produce a desired number of clusters from the training data. Accordingly, the number of nodes in the hidden layer is determined. Basis functions are then formed, and their centers and deviations are initialized to be the centers and deviations of the corresponding clusters. Then, the parameters of the network are refined with a hybrid learning strategy, involving hyperbolic tangent sigmoid functions, steepest descent backpropagation, and least squares method. As a result, optimized RBF networks are obtained. With this approach, the number of nodes in the hidden layer is determined and basis functions are derived automatically, and higher classification rates can be achieved. Furthermore, the approach is applicable to construct RBF networks for solving both single-label and multi-label pattern classification problems. Full article
(This article belongs to the Special Issue New Frontiers in Computational Intelligence)
►▼ Show Figures

Figure 1

10 pages, 2899 KiB  
Article
Dynamic Modeling for Resilience Measurement: NATO Resilience Decision Support Model
by Jan Hodicky, Gökhan Özkan, Hilmi Özdemir, Petr Stodola, Jan Drozd and Wayne Buck
Appl. Sci. 2020, 10(8), 2639; https://doi.org/10.3390/app10082639 - 11 Apr 2020
Cited by 8 | Viewed by 3900
Abstract
Despite its conceptual uncertainty, resilience is mostly about the measurement of capacity. Current studies confirm the importance of resilience measurement and the necessity to support policy makers with a measurement mechanism. A holistic approach considering the measurement of different resilience domains interactively and [...] Read more.
Despite its conceptual uncertainty, resilience is mostly about the measurement of capacity. Current studies confirm the importance of resilience measurement and the necessity to support policy makers with a measurement mechanism. A holistic approach considering the measurement of different resilience domains interactively and concurrently is the critical element in this endeavor. In parallel with the rise of popularity of resilience in international organizations, NATO has initiated a project with the objective to discover whether the resilience capacity of a country can be evaluated in a dynamic way via a prototype model execution. The implemented model running both baseline (without any shock) and extraordinary scenarios (with strategic shocks), clearly demonstrates its capacity to represent quantitatively the resilience related factors of a country in the complex operational environment. Moreover, the outputs of the model substantially comply with the resilience concept existing in the literature and NATO applications. One of the main strengths of the model is its almost infinite capacity to create various scenarios and make what-if analysis limited only by the current number of endogenous parameters of the model. It allows studying the secondary and the third order effects of events introduced in scenarios. The user interfaces (input and output dashboards) of the model help decision makers modify the values of selected endogenous parameters, see and compare the time-based values of the resilience factors, and doing so to evaluate risk related to the Area of Operations. Subject matter experts have validated the model and identified the main areas of improvement. The further development brings more countries to the model and implements an aggregation mechanism for output values of both resilience capacity and risk functions. The model will form the core of the NATO Resilience expert system. Full article
(This article belongs to the Special Issue New Frontiers in Computational Intelligence)
►▼ Show Figures

Figure 1

18 pages, 1097 KiB  
Article
Leveraging User Comments for Recommendation in E-Commerce
by Pang-Ming Chu, Yu-Shun Mao, Shie-Jue Lee and Chun-Liang Hou
Appl. Sci. 2020, 10(7), 2540; https://doi.org/10.3390/app10072540 - 7 Apr 2020
Cited by 11 | Viewed by 2216
Abstract
Collaborative filtering recommender systems traditionally recommend products to users solely based on the given user-item rating matrix. Two main issues, data sparsity and scalability, have long been concerns. In our previous work, an approach was proposed to address the scalability issue by clustering [...] Read more.
Collaborative filtering recommender systems traditionally recommend products to users solely based on the given user-item rating matrix. Two main issues, data sparsity and scalability, have long been concerns. In our previous work, an approach was proposed to address the scalability issue by clustering the products using the content of the user-item rating matrix. However, it still suffers from these concerns. In this paper, we improve the approach by employing user comments to address the issues of data sparsity and scalability. Word2Vec is applied to produce item vectors, one item vector for each product, from the comments made by users on their previously bought goods. Through the user-item rating matrix, the user vectors of all the customers are produced. By clustering, products and users are partitioned into item groups and user groups, respectively. Based on these groups, recommendations to a user can be made. Experimental results show that both the inaccuracy caused by a sparse user-item rating matrix and the inefficiency due to an enormous amount of data can be much alleviated. Full article
(This article belongs to the Special Issue New Frontiers in Computational Intelligence)
►▼ Show Figures

Figure 1

25 pages, 2505 KiB  
Article
Weighted z-Distance-Based Clustering and Its Application to Time-Series Data
by Zhao-Yu Wang, Chen-Yu Wu, Yan-Ting Lin and Shie-Jue Lee
Appl. Sci. 2019, 9(24), 5469; https://doi.org/10.3390/app9245469 - 12 Dec 2019
Cited by 1 | Viewed by 2061
Abstract
Clustering is the practice of dividing given data into similar groups and is one of the most widely used methods for unsupervised learning. Lee and Ouyang proposed a self-constructing clustering (SCC) method in which the similarity threshold, instead of the number of clusters, [...] Read more.
Clustering is the practice of dividing given data into similar groups and is one of the most widely used methods for unsupervised learning. Lee and Ouyang proposed a self-constructing clustering (SCC) method in which the similarity threshold, instead of the number of clusters, is specified in advance by the user. For a given set of instances, SCC performs only one training cycle on those instances. Once an instance has been assigned to a cluster, the assignment will not be changed afterwards. The clusters produced may depend on the order in which the instances are considered, and assignment errors are more likely to occur. Also, all dimensions are equally weighted, which may not be suitable in certain applications, e.g., time-series clustering. In this paper, improvements are proposed. Two or more training cycles on the instances are performed. An instance can be re-assigned to another cluster in each cycle. In this way, the clusters produced are less likely to be affected by the feeding order of the instances. Also, each dimension of the input can be weighted differently in the clustering process. The values of the weights are adaptively learned from the data. A number of experiments with real-world benchmark datasets are conducted and the results are shown to demonstrate the effectiveness of the proposed ideas. Full article
(This article belongs to the Special Issue New Frontiers in Computational Intelligence)
►▼ Show Figures

Figure 1

28 pages, 3870 KiB  
Article
An Improved Shuffled Frog-Leaping Algorithm for Solving the Dynamic and Continuous Berth Allocation Problem (DCBAP)
by Hsien-Pin Hsu and Tai-Lin Chiang
Appl. Sci. 2019, 9(21), 4682; https://doi.org/10.3390/app9214682 - 3 Nov 2019
Cited by 13 | Viewed by 3186
Abstract
This research deals with the dynamic and continuous berth allocation problem (DCBAP) in which both arrived and incoming ships are considered and a quay is used as a continuous line to accommodate as many ships as possible at one time. The DCBAP is [...] Read more.
This research deals with the dynamic and continuous berth allocation problem (DCBAP) in which both arrived and incoming ships are considered and a quay is used as a continuous line to accommodate as many ships as possible at one time. The DCBAP is solved by a two-stage procedure. In the first stage a heuristic/metaheuristic is used to generate alternative ship placement sequences while in the second stage a specific heuristic is employed to place ships and resolve overlaps of ships for the development of a feasible solution. Different methods, including FCFS (First Come First Served), SFLA (Shuffled Frog-Leaping Algorithm), and ISFLA (Improved Shuffled Frog-Leaping Algorithm), were employed in the first stage for comparison. The experimental results show that the ISFLA outperforms the others in terms of solution quality, implying that the ISFLA has the potential to deal with the DCBAP in a container terminal. Full article
(This article belongs to the Special Issue New Frontiers in Computational Intelligence)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop