Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Unlocking the Potential of AI for Advancing Scientific Research
share announcement

Unlocking the Potential of AI for Advancing Scientific Research

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

Deadline for manuscript submissions: 20 July 2024 | Viewed by 7777

Special Issue Editor

Dr. Luoyi Fu

E-Mail Website
Guest Editor
Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Interests: social networking; data mining & engineering; fundamental limits
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

AI continues to advance at an unprecedented pace and has become a transformative force in various domains, including science. After its emergence as a game-changing technology with the potential to revolutionize scientific research, AI-powered approaches are enabling breakthroughs in various scientific domains from natural language processing to computational biology. For example, large language models such as ChatGPT, fueled by massive amounts of data and deep learning algorithms, have emerged as powerful tools able to process, analyze, and generate human-like text. These models are assisting researchers in analyzing vast amounts of scientific data, optimizing experimental design, predicting properties, aiding in decision-making processes, and accelerating the pace of scientific discovery.

However, there are still challenges and limitations of AI technology, including issues related to field-specific professionalism, interpretability, ethical considerations, benchmarking, and human–AI collaboration. Addressing these challenges and developing best practices for utilizing AI technologies in scientific research is crucial for their effective and responsible use in the advancement of scientific knowledge.

We welcome original research papers, reviews, case studies, and position papers from researchers, practitioners, and interdisciplinary collaborations. Topics of interest include, but are not limited to:

  • Natural language processing for scientific text analysis, text generation, and summarization;
  • Applications of AI technology in scientific domains, such as drug discovery, climate modeling, genomics, and materials science;
  • Interpretability and explainability, including methods for understanding and validating their outputs;
  • Human–AI collaboration, including approaches for combining human expertise with AI capabilities to accelerate scientific discovery;
  • Ethical considerations and challenges, including issues of fairness, transparency, and accountability;
  • Benchmarking, evaluation, and best practices for utilizing machine learning in scientific research;
  • Future directions and opportunities for AI-powered approaches, including large language models, to advance scientific research and address current challenges.

Dr. Luoyi Fu
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
  • deep learning
  • AI for science
  • data analysis
  • natural language processing
  • simulation and modeling

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

19 pages, 683 KiB  
Article
Enhancing SPARQL Query Generation for Knowledge Base Question Answering Systems by Learning to Correct Triplets
by Jiexing Qi, Chang Su, Zhixin Guo, Lyuwen Wu, Zanwei Shen, Luoyi Fu, Xinbing Wang and Chenghu Zhou
Appl. Sci. 2024, 14(4), 1521; https://doi.org/10.3390/app14041521 - 14 Feb 2024
Viewed by 666
Abstract
Generating SPARQL queries from natural language questions is challenging in Knowledge Base Question Answering (KBQA) systems. The current state-of-the-art models heavily rely on fine-tuning pretrained models such as T5. However, these methods still encounter critical issues such as triple-flip errors (e.g., (subject, relation, [...] Read more.
Generating SPARQL queries from natural language questions is challenging in Knowledge Base Question Answering (KBQA) systems. The current state-of-the-art models heavily rely on fine-tuning pretrained models such as T5. However, these methods still encounter critical issues such as triple-flip errors (e.g., (subject, relation, object) is predicted as (object, relation, subject)). To address this limitation, we introduce TSET (Triplet Structure Enhanced T5), a model with a novel pretraining stage positioned between the initial T5 pretraining and the fine-tuning for the Text-to-SPARQL task. In this intermediary stage, we introduce a new objective called Triplet Structure Correction (TSC) to train the model on a SPARQL corpus derived from Wikidata. This objective aims to deepen the model’s understanding of the order of triplets. After this specialized pretraining, the model undergoes fine-tuning for SPARQL query generation, augmenting its query-generation capabilities. We also propose a method named “semantic transformation” to fortify the model’s grasp of SPARQL syntax and semantics without compromising the pre-trained weights of T5. Experimental results demonstrate that our proposed TSET outperforms existing methods on three well-established KBQA datasets: LC-QuAD 2.0, QALD-9 plus, and QALD-10, establishing a new state-of-the-art performance (95.0% F1 and 93.1% QM on LC-QuAD 2.0, 75.85% F1 and 61.76% QM on QALD-9 plus, 51.37% F1 and 40.05% QM on QALD-10). Full article
(This article belongs to the Special Issue Unlocking the Potential of AI for Advancing Scientific Research)
►▼ Show Figures

Figure 1

20 pages, 3791 KiB  
Article
Ensemble-Based Deep Learning Models for Enhancing IoT Intrusion Detection
by Ammar Odeh and Anas Abu Taleb
Appl. Sci. 2023, 13(21), 11985; https://doi.org/10.3390/app132111985 - 02 Nov 2023
Cited by 2 | Viewed by 1296
Abstract
Cybersecurity finds widespread applications across diverse domains, encompassing intelligent industrial systems, residential environments, personal gadgets, and automobiles. This has spurred groundbreaking advancements while concurrently posing persistent challenges in addressing security concerns tied to IoT devices. IoT intrusion detection involves using sophisticated techniques, including [...] Read more.
Cybersecurity finds widespread applications across diverse domains, encompassing intelligent industrial systems, residential environments, personal gadgets, and automobiles. This has spurred groundbreaking advancements while concurrently posing persistent challenges in addressing security concerns tied to IoT devices. IoT intrusion detection involves using sophisticated techniques, including deep learning models such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and anomaly detection algorithms, to identify unauthorized or malicious activities within IoT ecosystems. These systems continuously monitor and analyze network traffic and device behavior, seeking patterns that deviate from established norms. When anomalies are detected, security measures are triggered to thwart potential threats. IoT intrusion detection is vital for safeguarding data integrity, ensuring users’ privacy, and maintaining critical systems’ reliability and safety. As the IoT landscape evolves, effective intrusion detection mechanisms become increasingly essential to mitigate the ever-growing spectrum of cyber threats. Practical security approaches, notably deep learning-based intrusion detection, have been introduced to tackle these issues. This study utilizes deep learning models, including convolutional neural networks (CNNs), long short-term memory (LSTM), and gated recurrent units (GRUs), while introducing an ensemble deep learning architectural framework that integrates a voting policy within the model’s structure, thereby facilitating the computation and learning of hierarchical patterns. In our analysis, we compared the performance of ensemble deep learning classifiers with traditional deep learning techniques. The standout models were CNN-LSTM and CNN-GRU, achieving impressive accuracies of 99.7% and 99.6%, along with exceptional F1-scores of 0.998 and 0.997, respectively. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI for Advancing Scientific Research)
►▼ Show Figures

Figure 1

17 pages, 1529 KiB  
Article
A Qualitative Study on Artificial Intelligence and Its Impact on the Project Schedule, Cost and Risk Management Knowledge Areas as Presented in PMBOK®
by Thordur Vikingur Fridgeirsson, Helgi Thor Ingason, Haukur Ingi Jonasson and Helena Gunnarsdottir
Appl. Sci. 2023, 13(19), 11081; https://doi.org/10.3390/app131911081 - 08 Oct 2023
Cited by 2 | Viewed by 5425
Abstract
The aim of this paper is to study the main areas in which artificial intelligence (AI) will impact the field of project management in relation to cost, risk and scheduling. The research model was based on a previous study of the ten project [...] Read more.
The aim of this paper is to study the main areas in which artificial intelligence (AI) will impact the field of project management in relation to cost, risk and scheduling. The research model was based on a previous study of the ten project management knowledge areas presented in PMI’s PMBOK 6th edition, where project schedule, cost and risk management knowledge areas were identified as being the ones most likely to be affected by the development of AI. A group of graduates from a Master of Project Management program were assessed in an online questionnaire, reflecting the PMBOK’s elements of best practices and how AI will affect the project management profession in the future. Different elements of the three knowledge areas were considered to be affected more by AI than others. The schedule baseline is the element believed to be affected the most out of the project schedule management elements. For project cost management, the estimation of resource costs is believed to be affected the most. In the case of project risk management, the application of AI will have the strongest impact on the probability and impact formats. Full article
(This article belongs to the Special Issue Unlocking the Potential of AI for Advancing Scientific Research)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop