Article
Materials Science, Multidisciplinary
Daekeun Kim, Dayoon Kang, Donghwan Kim, Jinah Jang
Summary: Engineered tissues and organs that mimic actual organs have great potential in advancing medicine and pharmacology, but current tissue-engineering techniques face challenges in creating clinically relevant constructs. Three-dimensional bioprinting technology is expected to enable the creation of large-scale functional organs for various applications. This article discusses key considerations and recent advances in volumetric bioprinting, addressing the donor organ shortage and lack of reliable in vitro models.
Article
Computer Science, Information Systems
Sahraoui Dhelim, Nyothiri Aung, Mohand Tahar Kechadi, Huansheng Ning, Liming Chen, Abderrahmane Lakas
Summary: Trust Management System (TMS) is crucial in IoT networks to ensure network security, data integrity, and promote legitimate devices while punishing malicious activities. Trust scores assigned by TMSs reflect devices' reputations, which help predict future behaviors and assess reliability in IoT networks. This article proposes Trust2Vec, a TMS for large-scale IoT systems that leverages a random-walk network exploration algorithm and network embeddings community detection algorithm to manage trust relationships and mitigate large-scale trust attacks by malicious devices.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Xingsi Xue, Jie Zhang
Summary: A biomedical ontology helps to address data heterogeneity in different databases, but may introduce heterogeneity issue among ontologies. A framework is proposed to partition and match large-scale biomedical ontologies, with algorithms and techniques ensuring efficiency and quality of alignment. Experimental results show significant improvement over existing techniques in aligning biomedical ontologies.
APPLIED SOFT COMPUTING
(2021)
Article
Multidisciplinary Sciences
Salvatore Giancani, Riccardo Albertoni, Chiara Eva Catalano
Summary: This paper proposes a new evaluation methodology to test the coverage of embeddings against a targeted domain of interest in the biomedical context. It defines measures to assess the terminology, similarity, and analogy coverage, which are core aspects of the embeddings. The methodology and measures proposed can be applied to any application domain.
Article
Multidisciplinary Sciences
Joshua L. Schoenbachler, Jacob J. Hughey
Summary: pmparser and PMDB allow for large-scale, reproducible, and transparent analyses of biomedical literature.
Article
Computer Science, Artificial Intelligence
Likeng Liang, Tianyong Hao, Choujun Zhan, Hong Qiu, Fu Lee Wang, Jun Yan, Heng Weng, Yingying Qu
Summary: This article introduces a fast method for medical concept normalization, which uses a variant of transformer encoder and incorporates a pre-trained model called SISA to improve efficiency and performance. Experimental results show that this method is highly efficient in both training and inference, and is thousands of times faster than the state-of-the-art method in inference.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Adrian Ball, Katherine L. Silversides, Anna Chlingaryan, Arman Melkumyan
Summary: This paper presents a method for automatically estimating surfaces in local regions from exploration and production blast hole data, which captures boundary variations and is deemed geologically sound by experts in the field.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Yabing Wang, Guimin Huang, Jun Li, Hui Li, Ya Zhou, Hua Jiang
Summary: This paper introduces the concept of sentiment concept and achieves accurate embedding of sentiment information for words by constructing a multi-semantics sentiment intensity lexicon. It provides more accurate semantics and sentiment representation for words by combining two refined word embeddings methods.
Article
Health Care Sciences & Services
Laila Rasmy, Yang Xiang, Ziqian Xie, Cui Tao, Degui Zhi
Summary: Med-BERT, a contextualized embedding model pretrained on a structured EHR dataset, significantly improves prediction accuracy and performance on small training sets, showing promising results for disease prediction studies with limited local training data.
NPJ DIGITAL MEDICINE
(2021)
Article
Biochemical Research Methods
Mario Saenger, Ulf Leser
Summary: Automatic extraction of relationships between molecular entities has important applications in biomedicine, with existing methods focusing on single articles or sentences. Experts rely on complete literature to make reliable decisions, posing an open research question on how to do this effectively in an automatic manner. Recent approaches using representation learning techniques create comprehensive models by considering all publications mentioning specific entities, outperforming traditional methods by capturing semantic information of entities under study.
Article
Computer Science, Software Engineering
Xue Bin Peng, Yunrong Guo, Lina Halper, Sergey Levine, Sanja Fidler
Summary: The study presents a large-scale data-driven framework for learning versatile and reusable skill embeddings for physically simulated characters. The models can be trained using unstructured motion clips without any task-specific annotation or segmentation, and can learn a rich and versatile repertoire of skills. The system allows users to specify tasks through simple reward functions, and the skill embedding enables the character to automatically synthesize complex and naturalistic strategies to achieve the task objectives.
ACM TRANSACTIONS ON GRAPHICS
(2022)
Article
Computer Science, Artificial Intelligence
Elif Selen Baburoglu, Alptekin Durmusoglu, Turkay Dereli
Summary: This study focuses on addressing concept drift during online learning through a large-scale comparison of drift detectors and classifiers to determine the most efficient matched pairs for improving model accuracy. The results indicate that the most effective pairs primarily include the HDDMA, RDDM, WSTD, and FHDDM detectors, which vary depending on the dataset type and size.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Yubo Dou, Liting Jing, Xionghui Cai, Chunfu Lu, Ting Lv, Shaofei Jiang
Summary: Concept evaluation plays a crucial role in mechatronic product development and its results significantly impact subsequent design and manufacturing processes. This research proposes an approach for concept evaluation based on incomplete information, with a focus on large-scale criteria and decision makers' risk attitudes. The approach utilizes criteria clustering, uncertainty modeling, and evidence theory to fuse incomplete evaluation information and select the optimal concept. The effectiveness of the approach is verified through an engineering case study involving a pipe inspection robot, demonstrating its reliability and robustness in large-scale criteria concept evaluation.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Anastasios Nentidis, Thomas Chatzopoulos, Anastasia Krithara, Grigorios Tsoumakas, Georgios Paliouras
Summary: This study proposes a new method for the automated refinement of subject annotations in biomedical literature. With weak supervision based on concept occurrence in the abstract, enhanced by dictionary-based heuristics, the method tackles the challenges of the task. The evaluation in a large-scale retrospective scenario shows the effectiveness of the proposed method.
JOURNAL OF BIOMEDICAL INFORMATICS
(2023)
Article
Computer Science, Information Systems
Mingwen Shao, Gaozhi Zhang, Wangmeng Zuo, Deyu Meng
Summary: This paper investigates the impact of adversarial examples on biomedical image segmentation models, proposing a multi-scale gradient-based attack method. Experimental results demonstrate that the predicted masks generated by this method have high intersection over union and pixel accuracy with the target masks, while reducing the distances between adversarial and clean examples compared to the state-of-the-art method.
INFORMATION SCIENCES
(2021)