检索结果-内蒙古大学图书馆

Fine-tuning a pre-trained Transformers-based model for gene name entity recognition in biomedical text using a customized dataset: case of Desulfovibrio vulgaris Hildenborough

Fine-tuning a pre-trained Transformers-based model for gene ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Alain Bertrand Bomgni Dialo Abdala Bichar Dip Shrestha Gurung Marcellin Julius Nkenlifack Venkataramana Gadhamshetty Z. Etienne Gnimpieba Dept. of Biomedical Engineering University of South Dakota Vermillion SD USA Dept. of Computer Science University of Dschang Dschang Cameroon Dept. of Civil and Environmental Engineering South Dakota School of Mines and Technology Rapid City SD USA

Gene Name Entity Recognition (NER) plays a crucial role in the realm of biomedical text mining by focusing on the identification and extraction of gene references from scientific literature. Recent advancements in the field-particularly the emergence of pre-trained transformer-based language models like BioBERT-have shown significant promise in the domain of biomedical NER. However, these models are often trained on existing, publicly available datasets, which may not fully capture the nuances of the domain or adequately cover less-studied genes. This study places its primary emphasis on fine-tuning BioBERT specifically for gene NER tasks. To address the limitations associated with current publicly available datasets, we have meticulously crafted a custom dataset. This dataset is thoughtfully constructed through the systematic collection and detailed annotation of a diverse range of biomedical literature from specialized sources. It intentionally includes genes that have been extensively researched, as well as those that have received limited attention in existing corpora. The fine-tuning process involves initializing the BioBERT model with pre-trained weights and then training it on our custom dataset using a sequence tagging approach. To enhance the model’s performance, we systematically explore various techniques, including data augmentation, entity-level features, and attention mechanisms. Additionally, we conduct rigorous hyperparameter optimization to maximize the model’s accuracy, precision, and recall in gene mention recognition. We thoroughly evaluate the performance of the fine-tuned BioBERT model through a comprehensive set of cross-validation experiments. The results highlight the effectiveness of our tailored dataset in enhancing BioBERT’s performance in gene NER. The fine-tuned model achieves impressive F1 scores, precision, and recall, specifically 0.96, 0.95, and 0.98, surpassing previous models when it comes to recognizing the dvu (Desulfovibrio vul

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using textile capacitive sensors to train synchronized movement of hands

Using textile capacitive sensors to train synchronized movem...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Chang-Ming Yang Shu-Cing Wu Shih-Hung Chen Ze-We Wu Kuo-Cheng Liao Chi-Chun Chen Ming Young Biomedical Corp. Miaoli Taiwan Program Prospective Technology of Electrical Engineering and Computer Science National Chin-Yi University of Technology Taichung Taiwan Dept. of Computer Science and Information Engineering National Chin-Yi University of Technology Taichung Taiwan Dept. of Electronic Engineering National Chin-Yi University of Technology Taichung Taiwan

This study introduced a capacitive sensing interactive game platform aimed at promoting emotional stability, which we have named the “Sunrise and Sunset” game. This game primarily consists of two pieces of regular textile fabric enveloping conductive silver fabric. A microcontroller was employed to extract the sensed capacitive values, and a game named “Sunrise and Sunset” is designed to complement the slow raising and lowering of both hands. The development of this gaming platform has the potential to offer a novel method of emotional management, particularly in high-stress living environments. It can serve as an effective relaxation tool, aiding individuals in emotional balance, anxiety reduction, and stress alleviation. Simultaneously, this platform can contribute to the promotion of mental well-being, providing an engaging and beneficial means for people to manage their emotions and moods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Physically Unclonable Function Using Time-to-Digital Converter with Linearity Self-Calibration and its FPGA Implementation

A Physically Unclonable Function Using Time-to-Digital Conve...

引用

International Test Conference in Asia (ITC-Asia)

作者： Kentaroh Katoh Shuhei Yamamoto Zheming Zhao Yujie Zhao Shogo Katayama Anna Kuwana Takayuki Nakatani Kazumi Hatayama Haruo Kobayashi Keno Sato Takashi Ishida Toshiyuki Okamoto Tamotsu Ichikawa Dept. of Electronics Engineering and Computer Science Faculty of Engineering Fukuoka University Fukuoka Japan Faculty of Science of technology Division of Electronics and Informatics Gunma University ROHM Semiconductor Yokohama Japan

This paper presents a physically unclonable function (PUF) using flash time-to-digital converter (TDC) with linearity self-calibration. The proposed PUF utilizes that the variation of delay of delay elements of TDC is unique to the device and unclonable. The proposed PUF is constructed using the flash TDC with linearity self-calibration using histogram method. With the linearity self-calibration operation, variation of delay elements is estimated. The response output of the PUF is calculated using the estimated variation and the challenge inputs. The proposed PUF is a simple digital circuit consisting of basic digital elements. It is easy to design and implement to both SoC and FPGA. It can be used as not only strong PUF but also as a TDC with fine linearity. The experimental results with Artix7 FPGA show that the intra-chip variation is 8.9 % and the inter-chip variation is 46.9 %. The probability of the correct identification is 99.8 %. Extra resources to construct the proposed PUF are 33.7 % of the resources of the TDC with linearity self-calibration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PatchBMI-Net: Lightweight Facial Patch-based Ensemble for BMI Prediction

arXiv

引用

arXiv 2023年

作者： Aarotale, Parshuram N. Hill, Twyla Rattani, Ajita Dept. of Biomedical Engineering Wichita State University Kansas United States Dept. of Sociology Wichita State University Kansas United States Dept. of Computer Science and Engineering Uni. of North Texas DentonTX United States

Due to an alarming trend related to obesity affecting 93.3 million adults in the United States alone, body mass index (BMI) and body weight have drawn significant interest in various health monitoring applications. Consequently, several studies have proposed self-diagnostic facial image-based BMI prediction methods for healthy weight monitoring. These methods have mostly used convolutional neural network (CNN) based regression baselines, such as VGG19, ResNet50, and EfficientNetB0, for BMI prediction from facial images. However, the high computational requirement of these heavy-weight CNN models limits their deployment to resource-constrained mobile devices, thus deterring weight monitoring using smartphones. This paper aims to develop a lightweight facial patch-based ensemble (PatchBMI-Net) for BMI prediction to facilitate the deployment and weight monitoring using smartphones. Extensive experiments on BMI-annotated facial image datasets suggest that our proposed PatchBMI-Net model can obtain Mean Absolute Error (MAE) in the range [3.58, 6.51] with a size of about 3.3 million parameters. On cross-comparison with heavyweight models, such as ResNet-50 and Xception, trained for BMI prediction from facial images, our proposed PatchBMI-Net obtains equivalent MAE along with the model size reduction of about 5.4× and the average inference time reduction of about 3× when deployed on Apple-14 smartphone. Thus, demonstrating performance efficiency as well as low latency for on-device deployment and weight monitoring using smartphone applications. © 2023, CC BY-NC-ND.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Correlation Network Analysis of ASEAN Foreign Direct Investment

Correlation Network Analysis of ASEAN Foreign Direct Investm...

引用

2023 IEEE International Conference on Computing, ICOCO 2023

作者： Mansor, Mahayaudin M. Ibrahim, Nurain Yeo, Ivan Abu Bakar, Mohd Aftar Kaur, Sukhminder Razak, Fatimah Abdul School of Mathematical Sciences College of Computing Informatics & Mathematics Universiti Teknologi Mara Shah Alam Malaysia Universiti Tunku Abdul Rahman Lee Kong Chian Faculty of Eng. & Science Dept. of Mathematical & Acturial Sciences Malaysia Universiti Kebangsaan Malaysia Faculty of Science & Technology Department of Mathematical Sciences Bangi Malaysia School of Computer Science Taylor's University Faculty of Innovation & Technology Subang Jaya Malaysia

ISBN: (纸本)9798350302684

Although ASEAN aims to promote regional economic and security cooperation, among others, the empirical evidence in this study evinces that the impact of ASEAN on the economic integration between ASEAN countries remains limited. The economic integration is investigated based on the association of foreign direct investments (FDI) between Brunei, Cambodia, Indonesia, Laos, Malaysia, Myanmar, Philippines, Singapore, Thailand, and Vietnam. The longest common period of the FDI series is 29 years beginning in 1993. We examine the yearly FDI performances using a time series plot and descriptive statistics including the coefficient of variance for performance consistency. The association, strength, and effect of ASEAN economic integration are measured and illustrated by using Pearson's correlation matrix-circle plot. There are 45 unique associations representing the economic integration between ASEAN countries that unfortunately exist only in moderate strength, at most. The highest association of 0.62 is between Cambodia and Laos, and there is negligible association between Philippines-Vietnam and Indonesia-Philippines. It is also noted that almost 60% of the associations are positively correlated to one another. For the second objective, the correlations are clustered and visualized using network plots. The correlation- based network plot reveals two subgroups linking Indonesia- Cambodia-Singapore-Laos and Malaysian-Vietnam-Brunei closer together, while Thailand, Myanmar, and the Philippines are isolated from the subgroups. The most long-lasting interconnections between economies are found in the subgroup centered on Cambodia. In addition, there are only 14 weak- medium integrated links when clustering the correlation values above magnitude 0.3. The results suggest that the vast economic cooperation opportunities have not been fully explored among the ASEAN countries. Therefore, strategies may be necessary, such as adding packages and quotas to attract FDI from individual i

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Ensemble Distillation of Divergent Opinions for Robust Pathological Image Classification

Ensemble Distillation of Divergent Opinions for Robust Patho...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Kazuki Uehara Wataru Uegami Hirokazu Nosato Masahiro Murakawa Junya Fukuoka Hidenori Sakanashi Faculty of Global and Regional Studies University of the Ryukyus Okinawa Japan National Institute of Advanced Industrial Science and Technology (AIST) Ibaraki Japan Dept. of Pathology Informatics Nagasaki University Graduate School of Biomedical Sciences Nagasaki Japan Dept. of Pathology Kameda Medical Center Chiba Japan

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

The construction of highly accurate deep neural networks (DNNs) requires consistent labeled data. However, there are numerous cases wherein the ground truth is not uniquely determined, even for the same data, owing to different interpretations depending on observers’ decision criteria. Studies on the definition of labels and the building of a DNN model under such circumstances are scarce. Thus, this study addresses this issue in the field of pathological image diagnosis, where opinions occasionally vary, even among medical experts. We propose a method for constructing DNN models that are more robust to inter-observer variability by exploiting the knowledge about the relationships among the data learned by multiple DNN models. Comparison experiments were conducted using multiple pathology datasets of independently labeled images by different pathologists for the same set of images. The proposed method exhibited good generalization capability and outperformed the classification accuracy of baseline models specific to certain decision criteria.

关键词： Pathology Accuracy Buildings Artificial neural networks Data models Medical diagnostic imaging Image classification

来源：评论

学校读者我要写书评

暂无评论

Mastering Reference Architectures with Modeling Assistants

Mastering Reference Architectures with Modeling Assistants

引用

Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C)

作者： Amleto Di Salle Ludovico Iovino Leonardo Mariani Dept. of Human Sciences European University of Rome Rome Italy Computer Science area Gran Sasso Science Institute L'Aquila Italy Dept. of Informatics Systems and Communication Università degli Studi di Milano-Bicocca Milan Italy

Reference architectures (RA) can significantly simplify and speed up the design and evolution of software systems in virtually any domain. Rather than starting from scratch or trying to reuse models not meant for reuse, software architects can exploit RAs to initiate their designs from rigorously-defined architectural models specifically defined to support reuse. RAs can guarantee the satisfaction of key functional and non-functional requirements, including those related to technical and societal challenges, such as security and sustainability, significantly reducing the design effort and improving the design quality. The growing popularity of RAs is confirmed by the many providers, including Amazon AWS, Microsoft Azure, IBM, and Salesforce, that offer RAs for application deployment on their infrastructures. Unfortunately, RAs are expensive to define since they must comprehensively synthesize the design knowledge of specific application domains (e.g., e-commerce, automotive, etc.) and technical contexts (e.g., cloud systems, mobile apps, IoT, etc.). This challenge limits the availability of RAs to a few domains and contexts, hindering their adoption. We envision the opportunity to facilitate RA-based design by introducing a novel combination of mining in-the-wild and continuous knowledge refinement through a framework named ASSISTRA. Mining in-the-wild consists of bots crawling architectural models at scale (e.g., from public repos) and analyzing them continuously to automatically synthesize RAs and extract RAs-related practices that shall feed knowledge bases. Continuous knowledge refinement consists of a population of recommender systems that, while interactively supporting the architects in their activity using the shared knowledge bases, shall continuously refine the mined content in the knowledge base (e.g., based on architects accepting, modifying, or rejecting suggestions). This process shall generate high-quality recommendations, drastically simplifying the

关键词：

来源：评论

学校读者我要写书评

暂无评论

NLPADADE: Leveraging Natural Language Processing for Automated Detection of Adverse Drug Effects

NLPADADE: Leveraging Natural Language Processing for Automat...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Alain Bertrand Bomgni Claude Epiphanie Mbotchack Ngale Shiva Aryal Marcellin Julius Nkenlifack Venkataramana Gadhamshetty Z. Etienne Gnimpieba Dept. of Biomedical Engineering University of South Dakota Vermillion SD USA Dept. of Computer Science University of Dschang Dschang Cameroon Dept. of Civil and Environmental Engineering South Dakota School of Mines and Technology Rapid City SD USA

Pharmacovigilance is a systematic and scientifically rigorous discipline that assumes responsibility for the safety of pharmaceuticals, with its primary objective being the mitigation of risks while optimizing the benefits associated with medication usage. This mission-critical undertaking plays an indispensable role in preserving public health. At its core, pharmacovigilance entails the methodical collection and proficient management of data pertaining to medication safety. Additionally, these activities encompass the vigilant scrutiny of data to detect emerging "signals" indicative of new or evolving safety concerns. The expert evaluation of this data facilitates well-informed decision-making regarding matters of drug safety. Furthermore, proactive risk management strategies are deployed to effectively mitigate potential associated risks. In the pursuit of proactive health protection, regulatory actions are swiftly executed. Concurrently, the World Health Organization (WHO) underscores the global importance of establishing a robust pharmacovigilance framework. It advocates for the establishment of a comprehensive pharmacovigilance system, defined as encompassing "the science and activities related to the detection, assessment, understanding, and prevention of adverse effects or any other problem related to drugs or any other healthcare product." In this dynamic landscape, a pivotal question arises: "How can the automated identification and extraction of references to diseases, medications, and adverse effects from clinical notes and biomedical literature be achieved?" Central to this discourse are adverse drug effects (ADEs), which present a formidable public health challenge, manifesting as a significant source of patient morbidity and mortality. To expedite the utilization of real-world data (RWD) for the enhancement of pharmacovigilance practices, our focus has gravitated towards the development of a high-performance natural language processing (NLP) model. Thi

关键词：

来源：评论

学校读者我要写书评

暂无评论

Just the Right Amount of Exercise: Aerobic Exercise and Memory

Just the Right Amount of Exercise: Aerobic Exercise and Memo...

引用

Adjunct Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable computers

作者： Andrew Vargo Kentaro Ohara Takumi Nakai Koichi Kise Graduate School of Informatics Osaka Metropolitan University Japan Osaka Prefecture University Japan Dept. of Computer Science and Intelligent Systems Osaka Prefecture University Japan

ISBN: (纸本)9781450394239

A popular perception is that aerobic exercises are effective for improving performance on memory tasks. However, previous studies have not yet explored the effectiveness of aerobic exercise for individuals. We investigate the effects of aerobic exercise on English vocabulary learning by managing the conditions under which aerobic exercise is effective for individuals. We use a heart-rate sensor to control the amount of exertion a participant made on a treadmill while learning the vocabulary words. The results show this method can improve memory retention. This indicates that close monitoring of individual aerobic exertion through physiological sensing can make improved learning with exercise a reality.

关键词： physiological sensing ubiquitous sensing augmented learning

来源：评论

学校读者我要写书评

暂无评论

Heart Failure: Machine Learning Prediction Within a 5-Year Framework

Heart Failure: Machine Learning Prediction Within a 5-Year F...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Konstantina-Helen Tsarapatsani Vasilios D. Tsakanikas Antonis Sakellarios Hans J. Trampisch Efterpi Karapintzou Henrik Rudolf George K. Matsopoulos Dimitrios I. Fotiadis Biomedical Research Institute Foundation for Research and Technology-Hellas Ioannina Greece Department of Medical Informatics Biometry and Epidemiology Ruhr University Bochum Bochum Germany Dept. of Materials Science and Engineering Unit of Medical Technology and Intelligent Information Systems University of Ioannina Greece Institute for Biostatistics and Informatics in Medicine and Ageing Research University Medical Center Rostock Germany School of Electrical and Computer Engineering National Technical University of Athens Athens Greeece Dept. of Materials Science and Engineering Unit of Medical Technology and Intelligent Information Systems University of Ioannina and Biomedical Research Institute-FORTH Ioannina Greece

ISBN: (数字)9798331518622

ISBN: (纸本)9798331518639

Heart failure (HF) is a complex syndrome that is affected by many factors and causes. It is crucial to early recognize the disease subtypes and the unidentified clinical pathways that give rise to it. Machine learning (ML) is the tool that assist to deal with these challenges and improve the prediction of HF. In this work, the HF risk prediction was implemented by employed ML classifiers, such as Random Forest (RF), Extreme Grading Boosting (XGBoost) and Light Gradient-Boosting Machine (LGBM). We utilized the data from the German epidemiological trial on ankle brachial index - getABI cohort, which includes 6,454 patients. The performance of classifiers was estimated by Accuracy (ACC), Sensitivity, Specificity and the area under the receiver operating characteristic curve (AUC) in mean values for each ML classifier. The results were also interpreted using the Explainable artificial intelligence (XAI) approach, the Shapley Additive exPlanations (SHAP) values. Our work reveals that LGBM classifier predict the HF risk within 5 years follow-up in general population with 68 % accuracy. Moreover, the N-terminal pro-B-type natriuretic peptide (NT-proBNP) was identified as the most important feature for HF risk prediction.

关键词： Accuracy Sensitivity Explainable AI Biological system modeling Peptides Receivers Predictive models Indexes Cardiovascular diseases Random forests

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：