Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.6
Journals
Electronics
Special Issues
Data-Driven Processing from Complex Systems Perspective
share announcement

Data-Driven Processing from Complex Systems Perspective

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (30 April 2023) | Viewed by 15042

Special Issue Editors

Prof. Dr. Yeliz Karaca

E-Mail Website
Guest Editor
University of Massachusetts Medical School, Worcester, MA 01655, USA
Interests: mathematical neuroscience; applied mathematics; complex systems; fractals; fractional calculus; entropy; wavelet; computational complexity; advanced AI applications; stochastic processes and analyses; computational methods; multi-fractional methods; mathematical biology; clinical and medical applications; advanced data analysis
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Yudong Zhang

grade E-Mail Website
Guest Editor
Informatics Building School of Informatics, University of Leicester, Leicester LE1 7RH, UK
Interests: explainable deep learning; medical image analysis; pattern recognition and medical sensors; artificial intelligence; intelligent computing
Special Issues, Collections and Topics in MDPI journals
Dr. Khan Muhammad

E-Mail Website
Guest Editor
Department of Applied AI, Sungkyunkwan University, Seoul 03063, Korea
Interests: action recognition; activity recognition; anomaly recognition; computer vision; video analytics; deep learning; video summarization
Special Issues, Collections and Topics in MDPI journals
Dr. Shuihua Wang

E-Mail Website
Guest Editor
Department of Mathematics, University of Leicester, University Road, Leicester LE1 7RH, UK
Interests: deep learning; unsupervised learning; biomedical image analysis; pattern recognition; transfer learning; data analysis
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Complex networked systems with interacting elements characterized by non-linearity, high dimensionality, and heterogeneity in the interconnected universe of today require a solid understanding and control of their structure and dynamics, which has become a grand challenge for various fields of science. Complex systems and their conceptual knowledge along with the related approaches and methodologies are geared toward a viable model regarding how different data entities and streams have an impact on and interact with one another for the generation of features and trends on a multitude of spatiotemporal scales. Computational predictive analytics in highly complex and diverse fields have been and are currently developed for the characterization and quantification of concurrently and mutually interacting facets of different scenarios regarding real-world, universal, and natural phenomena. 

New computational methods with complex data and the related advancements in computations aim at a more profound and versatile understanding of the substantial masses of data and have enabled an improvement of predictions by transferring the results based on data analytics into the benefits at large, which underpins the utility and interdisciplinary approach of the domain.  Accordingly, data-driven and multifarious methods are required for the optimal prediction solutions and critical decision-making processes, whereby Artificial Intelligence (AI), fractional calculus, and multifractal methods have the capability of learning and modeling the system’s complex behavior, establishing the governing methods from the experimental data. Science pertaining to complex systems relies on data-driven approaches that obtain rigorous principles that generate accurate predictions and reliable laws, enabling the parametrization of models given the available and viable quantification and optimization.

This Special Issue, considering the fact that driven models bring a novel ingredient in the overall modeling of complex systems, focuses on recent advancements, applications, and contributions in Artificial Intelligence (AI) applications, machine learning methods, data analysis, big data analytics, computational predictive analytics, computational complexity, spatiotemporal scales, fractals and multifractional methods, fractional calculus, dynamical processes as per fixed, variable, and distributed systems, nonlinear dynamics and non-equilibrium processes, stochastic processes, fractional order integrodifferentiation, hierarchical nonlinear principal component analyses by machine learning, and related concepts.  With this endeavor,  we aim at contributing to the research areas of diverse fields on nonlinear integrated systems in complex natural phenomena,  complex signal and image processing, recurrent neural networks, differential/integral equations, multiresolution analysis, entropy, wavelets as a reflection of the versatile dimensions of the theoretical and applied areas concerned with mathematics, information science, computer science, physics, biology, medicine, genetics, neuroscience, chemistry, engineering, and social sciences , in addition to the extensive line of other applied sciences.

Potential topics of the special issue include but are not limited to:

  • Advanced data analysis and/or data visualization in complex models;
  • Big data analysis within multifractal analysis or fractional calculus methods in complex systems;
  • Advanced topics in fractional calculus and complex systems;
  • Quantization optimization algorithms for complex systems;
  • AI approaches in complex systems for real-world, universal, and natural phenomena;
  • Data-driven stochastic differential equations;
  • Machine learning applications in complex data;
  • Optimization by deep neural networks;
  • Medical algorithmic applications;
  • AI applications in signal processing;
  • Advanced AI and embedded vision for complex surveillance environments;
  • Advanced computational imaging;
  • Fractional dynamical models in complex systems;
  • Fractal dynamics and kinetics of complex systems;
  • Discrete, stochastic, and hybrid dynamics;
  • Multifractal systems in real-world, universal, and natural phenomena.

Dr. Yeliz Karaca
Prof. Dr. Yudong Zhang
Dr. Khan Muhammad
Dr. Shuihua Wang
Guest Editors

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. Electronics 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.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

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

17 pages, 4887 KiB  
Article
Recommender System Metaheuristic for Optimizing Decision-Making Computation
by Victor Bajenaru, Steven Lavoie, Brett Benyo, Christopher Riker, Mitchell Colby and James Vaccaro
Electronics 2023, 12(12), 2661; https://doi.org/10.3390/electronics12122661 - 14 Jun 2023
Viewed by 1400
Abstract
We implement a novel recommender system (RS) metaheuristic framework within a nonlinear NP-hard decision-making problem, for reducing the solution search space before high-burden computational steps are performed. Our RS-based metaheuristic supports consideration of comprehensive evaluation criteria, including estimations of the potential solution set’s [...] Read more.
We implement a novel recommender system (RS) metaheuristic framework within a nonlinear NP-hard decision-making problem, for reducing the solution search space before high-burden computational steps are performed. Our RS-based metaheuristic supports consideration of comprehensive evaluation criteria, including estimations of the potential solution set’s optimality, diversity, and feedback/preference of the end-user, while also being fully compatible with additional established RS evaluation metrics. Compared to prior Operations Research metaheuristics, our RS-based metaheuristic allows for (1) achieving near-optimal solution scores through comprehensive deep learning training, (2) fast metaheuristic parameter inference during solution instantiation trials, and (3) the ability to reuse this trained RS module for traditional RS ranking of final solution options for the end-user. When implementing this RS metaheuristic within an experimental high-dimensionality simulation environment, we see an average 91.7% reduction in computation time against a baseline approach, and solution scores within 9.1% of theoretical optimal scores. A simplified RS metaheuristic technique was also developed in a more realistic decision-making environment dealing with multidomain command and control scenarios, where a significant computation time reduction of 87.5% is also achieved compared with a baseline approach, while maintaining solution scores within 9.5% of theoretical optimal scores. Full article
(This article belongs to the Special Issue Data-Driven Processing from Complex Systems Perspective)
►▼ Show Figures

Figure 1

21 pages, 1594 KiB  
Article
A Novel Tightly Coupled Information System for Research Data Management
by Kennedy Senagi and Henri E. Z. Tonnang
Electronics 2022, 11(19), 3196; https://doi.org/10.3390/electronics11193196 - 5 Oct 2022
Cited by 1 | Viewed by 2285
Abstract
Most research projects are data driven. However, many organizations lack proper information systems (IS) for managing data, that is, planning, collecting, analyzing, storing, archiving, and sharing for use and re-use. Many research institutions have disparate and fragmented data that make it difficult to [...] Read more.
Most research projects are data driven. However, many organizations lack proper information systems (IS) for managing data, that is, planning, collecting, analyzing, storing, archiving, and sharing for use and re-use. Many research institutions have disparate and fragmented data that make it difficult to uphold the FAIR (findable, accessible, interoperable, and reusable) data management principles. At the same time, there is minimal practice of open and reproducible science. To solve these challenges, we designed and implemented an IS architecture for research data management. Through it, we have a centralized platform for research data management. The IS has several software components that are configured and unified to communicate and share data. The software components are, namely, common ontology, data management plan, data collectors, and the data warehouse. Results show that the IS components have gained global traction, 56.3% of the total web hits came from news users, and 259 projects had metadata (and 17 of those also had data resources). Moreover, the IS aligned the institution’s scientific data resources to universal standards such as the FAIR principles of data management and at the same time showcased open data, open science, and reproducible science. Ultimately, the architecture can be adopted by other organizations to manage research data. Full article
(This article belongs to the Special Issue Data-Driven Processing from Complex Systems Perspective)
►▼ Show Figures

Figure 1

13 pages, 2287 KiB  
Article
ROENet: A ResNet-Based Output Ensemble for Malaria Parasite Classification
by Ziquan Zhu, Shuihua Wang and Yudong Zhang
Electronics 2022, 11(13), 2040; https://doi.org/10.3390/electronics11132040 - 29 Jun 2022
Cited by 24 | Viewed by 2359
Abstract
(1) Background: People may be infected with an insect-borne disease (malaria) through the blood input of malaria-infected people or the bite of Anopheles mosquitoes. Doctors need a lot of time and energy to diagnose malaria, and sometimes the results are not ideal. Many [...] Read more.
(1) Background: People may be infected with an insect-borne disease (malaria) through the blood input of malaria-infected people or the bite of Anopheles mosquitoes. Doctors need a lot of time and energy to diagnose malaria, and sometimes the results are not ideal. Many researchers use CNN to classify malaria images. However, we believe that the classification performance of malaria parasites can be improved. (2) Methods: In this paper, we propose a novel method (ROENet) to automatically classify malaria parasite on the blood smear. The backbone of ROENet is the pre-trained ResNet-18. We use randomized neural networks (RNNs) as the classifier in our proposed model. Three RNNs are used in ROENet, which are random vector functional link (RVFL), Schmidt neural network (SNN), and extreme learning machine (ELM). To improve the performance of ROENet, the results of ROENet are the ensemble outputs from three RNNs. (3) Results: We evaluate the proposed ROENet by five-fold cross-validation. The specificity, F1 score, sensitivity, and accuracy are 96.68 ± 3.81%, 95.69 ± 2.65%, 94.79 ± 3.71%, and 95.73 ± 2.63%, respectively. (4) Conclusions: The proposed ROENet is compared with other state-of-the-art methods and provides the best results of these methods. Full article
(This article belongs to the Special Issue Data-Driven Processing from Complex Systems Perspective)
►▼ Show Figures

Figure 1

14 pages, 3068 KiB  
Article
A Hybrid Framework for Lung Cancer Classification
by Zeyu Ren, Yudong Zhang and Shuihua Wang
Electronics 2022, 11(10), 1614; https://doi.org/10.3390/electronics11101614 - 18 May 2022
Cited by 41 | Viewed by 3983
Abstract
Cancer is the second leading cause of death worldwide, and the death rate of lung cancer is much higher than other types of cancers. In recent years, numerous novel computer-aided diagnostic techniques with deep learning have been designed to detect lung cancer in [...] Read more.
Cancer is the second leading cause of death worldwide, and the death rate of lung cancer is much higher than other types of cancers. In recent years, numerous novel computer-aided diagnostic techniques with deep learning have been designed to detect lung cancer in early stages. However, deep learning models are easy to overfit, and the overfitting problem always causes lower performance. To solve this problem of lung cancer classification tasks, we proposed a hybrid framework called LCGANT. Specifically, our framework contains two main parts. The first part is a lung cancer deep convolutional GAN (LCGAN) to generate synthetic lung cancer images. The second part is a regularization enhanced transfer learning model called VGG-DF to classify lung cancer images into three classes. Our framework achieves a result of 99.84%±0.156% (accuracy), 99.84%±0.153% (precision), 99.84%±0.156% (sensitivity), and 99.84%±0.156% (F1-score). The result reaches the highest performance of the dataset for the lung cancer classification task. The proposed framework resolves the overfitting problem for lung cancer classification tasks, and it achieves better performance than other state-of-the-art methods. Full article
(This article belongs to the Special Issue Data-Driven Processing from Complex Systems Perspective)
►▼ Show Figures

Graphical abstract

17 pages, 1280 KiB  
Article
Modeling of the Crystallization Conditions for Organic Synthesis Product Purification Using Deep Learning
by Mantas Vaškevičius, Jurgita Kapočiūtė-Dzikienė and Liudas Šlepikas
Electronics 2022, 11(9), 1360; https://doi.org/10.3390/electronics11091360 - 24 Apr 2022
Cited by 3 | Viewed by 3198
Abstract
Crystallization is an important purification technique for solid products in a chemical laboratory. However, the correct selection of a solvent is important for the success of the procedure. In order to accelerate the solvent or solvent mixture search process, we offer an in [...] Read more.
Crystallization is an important purification technique for solid products in a chemical laboratory. However, the correct selection of a solvent is important for the success of the procedure. In order to accelerate the solvent or solvent mixture search process, we offer an in silico alternative, i.e., a never previously demonstrated approach that can model the reaction mixture crystallization conditions which are invariant to the reaction type. The offered deep learning-based method is trained to directly predict the solvent labels used in the crystallization steps of the synthetic procedure. Our solvent label prediction task is a multi-label multi-class classification task during which the method must correctly choose one or several solvents from 13 possible examples. During the experimental investigation, we tested two multi-label classifiers (i.e., Feed-Forward and Long Short-Term Memory neural networks) applied on top of vectors. For the vectorization, we used two methods (i.e., extended-connectivity fingerprints and autoencoders) with various parameters. Our optimized technique was able to reach the accuracy of 0.870 ± 0.004 (which is 0.693 above the baseline) on the testing dataset. This allows us to assume that the proposed approach can help to accelerate manual R&D processes in chemical laboratories. Full article
(This article belongs to the Special Issue Data-Driven Processing from Complex Systems Perspective)
►▼ 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