Nothing Special   »   [go: up one dir, main page]
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
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
Defining, Engineering, and Governing Green Artificial Intelligence
share announcement

Defining, Engineering, and Governing Green Artificial Intelligence

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: closed (30 April 2023) | Viewed by 13626

Special Issue Editors

Prof. Dr. Rashid Mehmood

E-Mail Website
Guest Editor
High Performance Computing Center, King Abdulaziz University, Jeddah 21589, Saudi Arabia
Interests: high-performance computing (HPC); big data; AI and IoT with applications in smart cities, healthcare, transportation, logistics, and toxicology
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Tan Yigitcanlar

grade E-Mail Website
Guest Editor
School of Architecture and Built Environment, Queensland University of Technology, Brisbane, Australia
Interests: smart technologies, communities, cities and urbanism; knowledge-based development of cities and innovation districts; sustainable and resilient cities; communities and urban ecosystems
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Juan M. Corchado

E-Mail Website
Guest Editor
BISITE Research Group, Edificio Multiusos I+D+I, University of Salamanca, 37007 Salamanca, Spain
Interests: artificial Intelligence; machine learning; edge computing; distributed computing; Blockchain; consensus model; smart cities; smart grid
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Smartness is the latest trend and data-driven AI is at the heart of it. Artificial intelligence (AI) continues to amaze us with its exponential growth, manifesting itself in many disruptive technologies and smart applications that have appeared in quick succession. However, its risks and negative impacts on our lives and planet also continue to grow exponentially. Individuals, societies, and nations are struggling to deal with the challenges and issues brought by rapid AI developments. For instance, AI with its data-driven nature requires incredibly large amounts of energy and this has endangered the survivability of our planet. Solutions and tools to reduce AI energy requirements have begun to appear such as model compression, pruning, TinyML, TensorFlow Lite, etc., however, these solutions are mainly driven by technology needs rather than by the intent to reduce energy usage. The tendency is to go with bigger and bigger data and larger and larger AI models to develop the ultimate (e.g., strong, general, or super) artificial intelligence.

A fundamental shift is needed in the way the AI engineers, developers, users, and others think about and utilize AI.

The term ‘green’ for scientists and engineers typically means something that uses less energy and fewer computational resources. Environmentalists associate ‘green’ with sustainable development. Green AI has been defined as “AI research that is more environmentally friendly and inclusive”. Green AI has also been defined as an approach “that moves away from short-term efficiency solutions to focus on a long-term ethical, responsible, and sustainable AI practice that will help build sustainable urban futures for all through smart city transformation”. Many more efforts are needed to define and engineer green AI.

To this end, this Special Issue calls for defining, engineering, and governing green AI, incorporating parameters for ‘greening’ AI, including, but not limited to, equity, resilience, inclusivity, security, privacy, safety, ethics, morality, trust, legislation, regulation, compliance, AI explainability, responsibility, and sustainability (social, environmental, and economic). To elaborate, since AI is so ingrained into every aspect of our lives, there is a need to understand and infuse in AI algorithms characteristics such as equity, resilience, security, safety, and ethics so that the AI-driven systems around us make “green” decisions to sustain our societies, economies, and environment.     

The SI specifically calls for contributions from scientists and engineers that can help in developing policies, frameworks, ethics, regulations, instruments, and infrastructure for the development of green AI. The contributions can focus on hardware, software, middleware, firmware, theory, knowledge, policy, etc. Contributions from academics and practitioners in social sciences, law, and other disciplines are also welcome.

The submissions can be research papers, case reports, viewpoints, or literature reviews.

The topics include but are not limited to the following.

  • Green Smartness
  • Green Infrastructure
  • Green AI in Natural Language Processing and Generation (NLP/NLG)
  • Green AI for Smart Cities and Societies
  • Green AI for preventive and Personalized Healthcare
  • Green AI for Transportation
  • Green AI for Supply Chain Management
  • Green AI for Smart Manufacturing
  • Green AI for Precision Agriculture
  • Green AI for Tourism
  • Green AI for Robotics
  • Green AI for Collaborative Robotics
  • Big Data and Datasets for Green AI
  • Green AI for Triple Bottom Line (TBL)
  • Green AI Policies, Frameworks, Ethics, Regulations, Instruments, and Mechanisms
  • Green AI for Edge, Fog, and Cloud Computing

Prof. Dr. Rashid Mehmood
Prof. Dr. Tan Yigitcanlar
Prof. Dr. Juan M. Corchado
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.

Keywords

  • green deep learning networks
  • green NLP
  • green computer vision
  • green healthcare
  • green big data
  • green edge computing
  • green fog computing

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 (3 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

Jump to: Review

14 pages, 9647 KiB  
Article
An Aero-Engine Damage Detection Method with Low-Energy Consumption Based on Multi-Layer Contrastive Learning
by Xing Huang, Lei Li, Jingsheng Zhang, Dengfeng Yin, Xinjian Hu and Peibing Du
Electronics 2022, 11(13), 2093; https://doi.org/10.3390/electronics11132093 - 4 Jul 2022
Viewed by 1869
Abstract
The health of aero-engines is pivotal to the safe operation of aircraft. With increasing service time, the internal components of the engine will be damaged by threats from different sources, so it is necessary to regularly detect the damage inside the engine. At [...] Read more.
The health of aero-engines is pivotal to the safe operation of aircraft. With increasing service time, the internal components of the engine will be damaged by threats from different sources, so it is necessary to regularly detect the damage inside the engine. At present, most of the detection methods of major airlines rely on the internal images of the engine obtained by manual use of a borescope to detect damage or traditional machine learning methods, which consume high levels of human and computational resources but have low efficiency. Artificial intelligence in various fields can achieve better performance than traditional methods, but to achieve the industrialization standard of Green AI, we need further research. Accordingly, we introduce a multi-layer contrastive learning method to a lightweight target detection model design, which is applied to real aero-engine borescope images of complex components to accomplish real-time damage detection. We intensively conduct comparative experiments to evaluate the effectiveness of our method. The verification results demonstrate that the method can help our model perform excellently compared with other available baseline models. Full article
(This article belongs to the Special Issue Defining, Engineering, and Governing Green Artificial Intelligence)
►▼ Show Figures

Figure 1

Figure 1
<p>The structure of the YOLOX target detection model.</p> Full article ">Figure 2
<p>The encoder uses five cascaded CSP modules to downsample the features and then uses an SPP module to increase the receptive field of the network. The feature map is subjected to three maximum pooling of different sizes through this module. The feature pyramid fuses the output features of the backbone network, aggregates the information of different layers, and then outputs the anchor sample (sample image to be trained) features through linear transformation. The anchor sample features are compared with the positive and negative samples found in the dictionary, and the feature extraction network is updated to complete the pre-training.</p> Full article ">Figure 3
<p>Positive and negative sample construction method in the multi-layer.</p> Full article ">Figure 4
<p>Partial damage.</p> Full article ">Figure 5
<p>The damaged area of the eddy current device is relatively large, the larger part is less than 50,000, and the larger part is more evenly distributed. Most of the damaged areas of the large elbow pipe dataset are less than 10,000, and all of them are below 20,000. Most of the damaged areas of the blade datasets are less than 10,000, but the distribution is smoother than that of the large elbow pipe.</p> Full article ">Figure 6
<p>An example of the image after Mosaic and MixUp image augmentation.</p> Full article ">Figure 7
<p>Comparison of experimental results between the multi-layer MoCo method and the MoCo method for the swirler dataset.</p> Full article ">Figure 8
<p>Comparison of experimental results between the multi-layer MoCo method and the MoCo method for the large elbow pipe dataset.</p> Full article ">Figure 9
<p>Comparison of experimental results between the multi-layer MoCo method and the MoCo method for the air compressor/turbine blades dataset.</p> Full article ">Figure 10
<p>Visual comparison example between the multi-layer MoCo method and the MoCo method for the swirler, large elbow pipe, and air compressor/turbine blades. Our detection method is able to detect the damaged areas ignored by the other.</p> Full article ">
18 pages, 29309 KiB  
Article
Explainable Computational Intelligence Model for Antepartum Fetal Monitoring to Predict the Risk of IUGR
by Nida Aslam, Irfan Ullah Khan, Reem Fadel Aljishi, Zahra Maher Alnamer, Zahra Majed Alzawad, Fatima Abdulmohsen Almomen and Fatima Abbas Alramadan
Electronics 2022, 11(4), 593; https://doi.org/10.3390/electronics11040593 - 15 Feb 2022
Cited by 12 | Viewed by 4071
Abstract
Intrauterine Growth Restriction (IUGR) is a restriction of the fetus that involves the abnormal growth rate of the fetus, and it has a huge impact on the new-born’s health. Machine learning (ML) algorithms can help in early prediction and discrimination of the abnormality [...] Read more.
Intrauterine Growth Restriction (IUGR) is a restriction of the fetus that involves the abnormal growth rate of the fetus, and it has a huge impact on the new-born’s health. Machine learning (ML) algorithms can help in early prediction and discrimination of the abnormality of the fetus’ health to assist in reducing the risk during the antepartum period. Therefore, in this study, Random Forest (RF), Support Vector Machine (SVM), K Nearest Neighbor (KNN) and Gradient Boosting (GB) was utilized to discriminate whether a fetus was healthy or suffering from IUGR based on the fetal heart rate (FHR). The Recursive Feature Elimination (RFE) method was used to select the significant feature for the classification of fetus. Furthermore, the study Explainable Artificial Intelligence (EAI) was implemented using LIME and SHAP to generate the explanation and to add comprehensibility in the proposed models. The experimental results indicate that RF achieved the highest accuracy (0.97) and F1-score (0.98) with the reduced set of features. However, the SVM outperformed it in terms of Positive Predictive Value (PPV) and specificity (SP). The performance of the model was further validated using another dataset and found that it outperformed the baseline studies for both the datasets. The proposed model can aid doctors in monitoring fetal health and enhancing the prediction process. Full article
(This article belongs to the Special Issue Defining, Engineering, and Governing Green Artificial Intelligence)
►▼ Show Figures

Figure 1

Figure 1
<p>Attribute’s correlation heatmap for dataset I.</p> Full article ">Figure 2
<p>Selected attribute’s correlation heatmap for dataset II.</p> Full article ">Figure 3
<p>SVM Rank Test Score with different values of C and Gamma.</p> Full article ">Figure 4
<p>Rank Test Score—RF with optimization values.</p> Full article ">Figure 5
<p>Different value of K and the accuracy of the algorithm.</p> Full article ">Figure 6
<p>Recursive Feature Elimination for Support Vector Machine.</p> Full article ">Figure 7
<p>Recursive Feature Elimination for Random Forest.</p> Full article ">Figure 8
<p>Recursive Feature Elimination for K Nearest Neighbor.</p> Full article ">Figure 9
<p>Recursive Feature Elimination for Gradient Boosting.</p> Full article ">Figure 10
<p>Confusion matrix for classifiers using all features in the dataset.</p> Full article ">Figure 11
<p>Confusion matrix for classifiers using selected features in the dataset.</p> Full article ">Figure 12
<p>Global feature importance mean ([SHAP value]).</p> Full article ">Figure 13
<p>LIME for explaining the prediction for individual sample.</p> Full article ">Figure 14
<p>Induced Decision Tree representation for the IUGR prediction Dataset I.</p> Full article ">

Review

Jump to: Research

44 pages, 1352 KiB  
Review
Data Locality in High Performance Computing, Big Data, and Converged Systems: An Analysis of the Cutting Edge and a Future System Architecture
by Sardar Usman, Rashid Mehmood, Iyad Katib and Aiiad Albeshri
Electronics 2023, 12(1), 53; https://doi.org/10.3390/electronics12010053 - 23 Dec 2022
Cited by 9 | Viewed by 5934
Abstract
Big data has revolutionized science and technology leading to the transformation of our societies. High-performance computing (HPC) provides the necessary computational power for big data analysis using artificial intelligence and methods. Traditionally, HPC and big data had focused on different problem domains and [...] Read more.
Big data has revolutionized science and technology leading to the transformation of our societies. High-performance computing (HPC) provides the necessary computational power for big data analysis using artificial intelligence and methods. Traditionally, HPC and big data had focused on different problem domains and had grown into two different ecosystems. Efforts have been underway for the last few years on bringing the best of both paradigms into HPC and big converged architectures. Designing HPC and big data converged systems is a hard task requiring careful placement of data, analytics, and other computational tasks such that the desired performance is achieved with the least amount of resources. Energy efficiency has become the biggest hurdle in the realization of HPC, big data, and converged systems capable of delivering exascale and beyond performance. Data locality is a key parameter of HPDA system design as moving even a byte costs heavily both in time and energy with an increase in the size of the system. Performance in terms of time and energy are the most important factors for users, particularly energy, due to it being the major hurdle in high-performance system design and the increasing focus on green energy systems due to environmental sustainability. Data locality is a broad term that encapsulates different aspects including bringing computations to data, minimizing data movement by efficient exploitation of cache hierarchies, reducing intra- and inter-node communications, locality-aware process and thread mapping, and in situ and transit data analysis. This paper provides an extensive review of cutting-edge research on data locality in HPC, big data, and converged systems. We review the literature on data locality in HPC, big data, and converged environments and discuss challenges, opportunities, and future directions. Subsequently, using the knowledge gained from this extensive review, we propose a system architecture for future HPC and big data converged systems. To the best of our knowledge, there is no such review on data locality in converged HPC and big data systems. Full article
(This article belongs to the Special Issue Defining, Engineering, and Governing Green Artificial Intelligence)
►▼ Show Figures

Figure 1

Figure 1
<p>Design patterns and AI-based Architecture for Converged HPC and Big Data Environments.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop