Review
Biochemical Research Methods
Jie Huang, Jiazhou Chen, Bin Zhang, Lei Zhu, Hongmin Cai
Summary: Accurately identifying the interactions between genomic factors and the response of cancer drugs is crucial in drug discovery, drug repositioning, and cancer treatment. Studies have shown that interactions between genes and drugs are 'many-genes-to-many drugs' interactions, requiring improved strategies to identify common modules among pharmacogenomics data. This paper evaluates state-of-the-art common module identification techniques from a machine learning perspective, highlighting the importance of understanding complex biological regulatory mechanisms in cancer drug interactions.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Remote Sensing
Jiaqi Yang, Jun Xu, Yunshuo Lv, Chenghu Zhou, Yunqiang Zhu, Weiming Cheng
Summary: In this study, a semantic segmentation model was used to classify elementary landform types, and digital terrain mapping using AW3D30 DEM data was crucial in studying landforms. A semantic segmentation model with an FCN-ResNet architecture was built to extract features using a residual network (ResNet) and achieve pixel-level segmentation of the DEM. Results showed that increasing terrain factors had no significant impact on the model, and semantic information could be learned solely from DEM data. The model demonstrated strong feature extraction capability and tolerance to noise and error, and deep learning methods showed great potential in landform classification for geomorphological research.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2023)
Review
Psychology, Multidisciplinary
Jeffrey C. Zemla
Summary: The semantic fluency task is commonly used to measure one's ability to retrieve semantic concepts. The ordering of responses can provide insights into how individuals or groups organize semantic concepts within a category. However, there are still many unresolved questions surrounding the validity and reliability of this approach.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Biochemistry & Molecular Biology
Taukir Alam, Wei-Chung Shia, Fang-Rong Hsu, Taimoor Hassan
Summary: This research analyzes and evaluates breast cancer detection and diagnosis using segmentation models. The Unet3+ model is found to have optimal performance, with an average accuracy of 82.53% and an average intersection over union (IU) of 52.57%. The application of these models shows remarkable results and has the potential to improve patient outcomes.
Article
Environmental Sciences
Weicheng Xu, Weiguang Yang, Pengchao Chen, Yilong Zhan, Lei Zhang, Yubin Lan
Summary: This study uses time-series UAV multispectral and RGB remote sensing images combined with machine learning to model four main quality indicators of cotton fibers. A deep learning algorithm is used to identify and extract cotton boll pixels in remote sensing images and improve the accuracy of quantitative extraction of spectral features. The prediction model can well predict the average length, uniformity index, and micronaire value of the upper half.
Article
Psychology, Multidisciplinary
Catarina Vales, Christine Wu, Jennifer Torrance, Heather Shannon, Sarah L. States, Anna Fisher
Summary: Remote data collection procedures can address limitations of in-person data collection and recruit more diverse samples. Successfully replicating experimental effects with children participants remotely is important for integrating results across studies.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Hajer Ayadi, Mouna Torjmen-Khemakhem, Jimmy X. Huang
Summary: Text-Based Medical Image Retrieval (TBMIR) is successful in retrieving medical images with brief textual descriptions. A Bayesian Network thesaurus using medical terms has been proposed to improve the retrieval performance, however, it is not efficient due to co-occurrence measure issues. This paper presents a new efficient association Rule Based Bayesian Network (R2BN) model combining medically-dependent features (MDF) and a probabilistic model for image relevance prediction, demonstrating significantly enhanced retrieval accuracy.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2023)
Article
Multidisciplinary Sciences
Craig Mayer, Vojtech Huser
Summary: There are many initiatives trying to standardize data collection in human clinical studies using common data elements (CDEs). Analyzing the All of Us (AoU) program as an example, it adopted the OMOP Common Data Model to standardize research and real-world data. AoU included CDEs from terminologies such as LOINC and SNOMED CT to standardize specific data elements and values. The inclusion of CDEs in large studies like AoU is important for facilitating the use of existing tools and improving the ease of understanding and analyzing the collected data.
Article
Environmental Studies
Tao Zhang, Yibo Yan, Qi Chen, Ze Liu
Summary: Given the accelerating speed and scale of urbanization in China, this study proposes a method for evaluating the spatial relationship among facilities around bus terminals. The validity and applicability of the methods are verified using samples, and strategic suggestions are offered for the composite development of bus terminals in Zhengzhou.
Article
Construction & Building Technology
Xinxing Yuan, Alan Smith, Rodrigo Sarlo, Christopher D. Lippitt, Fernando Moreu
Summary: This study introduced an algorithm that automatically identifies rebar positions using LiDAR, resulting in an automatic Rebar Layout Quality Index (RLQI). By comparing real rebar mat data with design drawings, the quality of structural construction was evaluated and quantified with a new flexural relative moment strength index.
AUTOMATION IN CONSTRUCTION
(2021)
Article
Business
Imene Belboula, Claire-Lise Ackermann
Summary: Consumers' responses to design features involve both conscious and non-conscious information processing. The study suggests using a combination of explicit and implicit measures to assess consumer understanding of service brand meaning conveyed by physical elements. Results show that mastery of design language, captured by design acumen and involvement in the product category, enhances implicit understanding of brand meaning conveyed by a service brand's physical elements.
JOURNAL OF RETAILING AND CONSUMER SERVICES
(2021)
Article
Clinical Neurology
Jacson Gabriel Feiten, Bruno Paz Mosqueiro, Mariana Uequed, Ives Cavalcante Passos, Marcelo P. Fleck, Marco Antonio Caldieraro
Summary: This study suggests that self-rated scales may perform better in assessing the association between guilt and other symptoms in MDD. Different communities of symptoms and connection structures in the networks indicate that insomnia may be an independent symptom requiring specific interventions. Some similar items are strongly connected and could be collapsed.
JOURNAL OF AFFECTIVE DISORDERS
(2021)
Article
Chemistry, Analytical
Justin A. Mahlberg, Howell Li, Bjoern Zachrisson, Dustin K. Leslie, Darcy M. Bullock
Summary: This paper examines the use of on-board sensors in connected vehicles to obtain crowdsource estimates of road quality, and presents a case study that demonstrates the viability of connected vehicle roughness data as a tool for network level monitoring of pavement quality.
Article
Engineering, Electrical & Electronic
Pablo Rodriguez-Pajaron, Araceli Hernandez Bayo, Jovica Milanovic
Summary: This paper introduces a methodology for forecasting voltage total harmonic distortion (THD) at low voltage busbars of residential distribution feeders based on data from smart meters. The methodology provides relevant power quality indices using existing monitoring infrastructure for demand response operation. Different algorithms for voltage THD forecasting are implemented and their performance is tested and compared.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2022)
Article
Computer Science, Theory & Methods
Farman Ali, Shaker El-Sappagh, S. M. Riazul Islam, Amjad Ali, Muhammad Attique, Muhammad Imran, Kyung-Sup Kwak
Summary: Wearable sensors and social networking platforms are crucial for healthcare monitoring, generating large volumes of unstructured data. A novel healthcare monitoring framework based on the cloud environment and a big data analytics engine is proposed to efficiently store and analyze healthcare data, improving classification accuracy. Data mining techniques, ontologies, and Bi-LSTM are utilized for efficient preprocessing and classification of healthcare data, leading to accurate health condition classification and drug side effect predictions.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)