检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Peng Wang, Jianmin Li, Chunyan Wang, Zixu Liu, Yiping Sun, Siqi Lin, Jianxin Wei, Leyi Cai, Xibao Lai, Houtim Liu, Wei Wang, Longyue Liu, Yuansheng Zeng, Xiangxiang College of Information Science and Engineering Hunan University Changsha China The Interdisciplinary Graduate Program in Integrative Biotechnology Yonsei University Incheon21983 Korea Republic of School of Informatics Yunnan Normal University Kunming650500 China Department of Computer Science University of Tsukuba Tsukuba3058577 Japan Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China Shanghai AI Laboratory Shanghai200232 China Centre for Artificial Intelligence driven Drug Discovery Faculty of Applied Science Macao Polytechnic University China School of Informatics Xiamen University Xiamen China Tencent AI Lab China

While various models and computational tools have been proposed for structure and property analysis of molecules, generating molecules that conform to all desired structures and properties remains a challenge. Here, we introduce a multi-constraint molecular generation large language model, TSMMG, which, akin to a student, incorporates knowledge from various small models and tools, namely, the 'teachers'. To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers', enabling it to generate novel molecules that conform to the descriptions through various text prompts. We experimentally show that TSMMG remarkably performs in generating molecules meeting complex, natural language-described property requirements across two-, three-, and four-constraint tasks, with an average molecular validity of over 99% and success ratio of 82.58%, 68.03%, and 67.48%, respectively. The model also exhibits adaptability through zero-shot testing, creating molecules that satisfy combinations of properties that have not been encountered. It can comprehend text inputs with various language styles, extending beyond the confines of outlined prompts, as confirmed through empirical validation. Additionally, the knowledge distillation feature of TSMMG contributes to the continuous enhancement of small models, while the innovative approach to dataset construction effectively addresses the issues of data scarcity and quality, which positions TSMMG as a promising tool in the domains of drug discovery and materials science. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Study on Text Feature Selection Using Ant Colony and Grey Wolf Optimization

A Study on Text Feature Selection Using Ant Colony and Grey ...

引用

International Conference on informatics and Computing (ICIC)

作者： Joan Angelina Widians Retantyo Wardoyo Sri Hartati Doctoral Program dept. of Computer Science and Electronics Universitas Gadjah Mada Dept. of Informatics Faculty of Engineering Universitas Mulawarman Samarinda Indonesia Dept. of Computer Science and Electronics Faculty of Mathematics and Natural Sciences Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (纸本)9798350345728

Text classification (TC) is widely used for organizing digital documents. The issues in TC are numerous characteristics and high-element dimensions. Many pattern classification issues require feature selection (FS), which is pertinent. FS removes unneeded and redundant data from the dataset. The Ant Colony Optimization (ACO) and Grey Wolf Optimizer (GWO) for FS are the main topics of our thorough assessment of the literature on the Swarm Intelligence (SI) algorithm. Furthermore, it illustrates how the hybrid SI technique is used in FS across various sectors. The hybrid SI technique uses applicable data from various FS methods to find feature subsets with smaller sizes and better classification performance than those found by regular FS algorithms.

关键词： Ant colony optimization Text categorization Pattern classification Filtering algorithms Feature extraction Classification algorithms Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Genomic data processing with GenomeFlow

arXiv

引用

arXiv 2025年

作者： Park, Junseok Maury, Eduardo A. Oh, Changhoon Shin, Donghoon Denisko, Danielle Lee, Eunjung Alice Division of Genetics and Genomics Boston Children’s Hospital 3 Blackfan Circle BostonMA United States Department of Pediatrics Harvard Medical School 25 Shattuck St BostonMA United States Bioinformatics Integrative Genomics Program Harvard/MIT MD-PHD Program Harvard Medical School BostonMA United States Program in Medical and Population Genetics Broad Institute of MIT and Harvard CambridgeMA United States Graduate School of Information Yonsei University 50 Yonsei-ro Seodaemun-gu Seoul Korea Republic of Department of Human Centered Design and Engineering University of Washington SeattleWA United States Department of Biomedical Informatics Harvard Medical School BostonMA United States

Advances in genome sequencing technologies generate massive amounts of sequence data that are increasingly analyzed and shared through public repositories. On-demand infrastructure services on cloud computing platforms enable the processing of such large-scale genomic sequence data in distributed processing environments with a significant reduction in analysis time. However, parallel processing on cloud computing platforms presents many challenges to researchers, even skillful bioinformaticians. In particular, it is difficult to design a computing architecture optimized to reduce the cost of computing and disk storage as genomic data analysis pipelines often employ many heterogeneous tools with different resource requirements. To address these issues, we developed GenomeFlow, a tool for automated development of computing architecture and resource optimization on Google Cloud Platform, which allows users to process a large number of samples at minimal cost. We outline multiple use cases of GenomeFlow demonstrating its utility to significantly reduce computing time and cost associated with analyzing genomic and transcriptomic data from hundreds to tens of thousands of samples from several consortia. Here, we describe a step-by-step protocol on how to use GenomeFlow for a common genomic data processing task. We introduce this example protocol geared toward a bioinformatician with little experience in cloud computing. © 2025, CC BY.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Comparing Classification Algorithms to Analyze Twitter Sentiment on Public Opinion on Fuel Oil

Comparing Classification Algorithms to Analyze Twitter Senti...

引用

International Seminar on Intelligent Technology and Its Applications (ISITIA)

作者： Gita Widarma Rice Novita Mustakim Nesdi Evrilyan Rozanda Information Systems Department Universitas Islam Negeri Sultan Syarif Kasim Riau Graduate Program Pekanbaru Indonesia Information Systems Postgraduate Programs Universitas Negeri Padang Pekanbaru Indonesia Master of Informatics Engineering Postgraduate Programs Institut Pertanian Bogor Pekanbaru Indonesia Master of Information Systems Management Postgraduate Programs Universiti Teknologi Malaysia Pekanbaru Indonesia

Twitter is currently used as one of the applications that is often used to convey opinions or unrest by the public such as the current issue that is currently rife, namely regarding the increase in fuel oil prices (BBM) in Indonesia. With so much data scattered in a tweet that only consists of a few fragments of words, there must be valuable information or meaning that Twitter users want to convey. Text mining is a very appropriate method to do the analysis because in text mining there is a method that focuses on an opinion which will be concluded into positive and negative opinions. There are several algorithms that are most often used in data mining, namely K-Nearest Neighbor, Decision Tree, and Naive Bayes. The three algorithms used in this study were also compared with the use of feature selection Particle Swarm Optimization (PSO) which is well known for improving the performance of algorithms. There are 2165 negative opinion data and 2835 positive sentiment data. The data will be tried based on distinctive sums of data namely 1000 data, 3000 data, and 5000 data. The classic K-Nearest Neighbor algorithm obtained an accuracy result of 75.60% and made it the best when tested with 1000 data. The use of Particle Swarm Optimization (PSO) is proven to improve accuracy as when tested using 3000 data with an accuracy value of 78.21% on the K-Nearest Neighbor algorithm. In the mean time, in testing 5000 Data, the classic K-Nearest Neighbor once more gotten the most elevated exactness with a esteem of 74.02%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of Fetal Heart Rate Detection Using Envelope Extraction and Shannon Energy

Comparison of Fetal Heart Rate Detection Using Envelope Extr...

引用

2019 International Seminar on Application for Technology of Information and Communication, iSemantic 2019

作者： Setiawan, Agung W. Sujatmiko, Wahyu Biomedical Engineering Research Group School of Electrical Engineering and Informatics ITB Bandung Indonesia Graduate Program in Electrical Engineering School of Electrical Engineering and Informatics ITB Bandung Indonesia

ISBN: (纸本)9781728138329

Heart rate monitoring is widely used as a general procedure to examine fetal health condition. Fetal heart rate can be used to identified possibilities of fetal anomaly and warn the obstetrician to provide immediate intervention before any further abnormalities. The purpose of this research is to compare fetal heart rate detection result using envelope extraction and Shannon energy envelope method. There are 115 fetal phonocardiography and maternal phonocardiography that is used in this research. The dataset was obtained from Hafez Hospital, Shiraz University of Medical Science. Envelope extraction method can be used to detect fetal heart rate signal with 89.2% accuracy for all fetal phonocardiography signal while Shannon energy envelope method can be used to detect fetal heart rate signal with 88.3% accuracy for all fetal phonocardiography signal. © 2019 IEEE.

关键词： Phonocardiography

来源：评论

学校读者我要写书评

暂无评论

Airplane type identification based on mask RCNN and drone images

arXiv

引用

arXiv 2021年

作者： Alshaibani, Waleed Tawfik Abdullah Helvaci, Mustafa Shayea, Ibraheem Saad, Sawsan A. Azizan, Azizul Yakub, Fitri Institute of Informatics Satellite Communication and Remote Sensing Program Istanbul Technical University ITU Ayazaga Campus Institute of Informatics Building Sariyer Istanbul34469 Turkey Istanbul34469 Turkey Faculty of Engineering and Built Environment Universiti Sains Islam Malaysia Negeri Sembilan Bandar BaruNilai71800 Malaysia Department of Computer Engineering College of Computer Science and Engineering University of Ha'il Saudi Arabia Advance Informatics Department Razak Faculty of Technology and Informatics Universiti Teknologi Malaysia Kuala Lumpur54100 Malaysia

For dealing with traffic bottlenecks at airports, aircraft object detection is insufficient. Every airport generally has a variety of planes with various physical and technological requirements as well as diverse service requirements. Detecting the presence of new planes will not address all traffic congestion issues. Identifying the type of airplane, on the other hand, will entirely fix the problem because it will offer important information about the plane's technical specifications (i.e., the time it needs to be served and its appropriate place in the airport). Several studies have provided various contributions to address airport traffic jams;however, their ultimate goal was to determine the existence of airplane objects. This paper provides a practical approach to identify the type of airplane in airports depending on the results provided by the airplane detection process using mask region convolution neural network. The key feature employed to identify the type of airplane is the surface area calculated based on the results of airplane detection. The surface area is used to assess the estimated cabin length which is considered as an additional key feature for identifying the airplane type. The length of any detected plane may be calculated by measuring the distance between the detected plane's two furthest points. The suggested approach's performance is assessed using average accuracies and a confusion matrix. The findings show that this method is dependable. This method will greatly aid in the management of airport traffic congestion. Copyright © 2021, The Authors. All rights reserved.

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

Predicting Neurological Outcomes of Comatose Cardiac Arrest Patients Using Transformer Neural Networks with EEG Data

Predicting Neurological Outcomes of Comatose Cardiac Arrest ...

引用

Computers in Cardiology (CinC)

作者： Jefferson Dionisio Che Lin Lian-Yu Lin Wen-Chau Wu Smart Medicine and Health Informatics Program National Taiwan University (NTU) Taipei Taiwan Department of Electrical Engineering NTU Graduate Institute of Communication Engineering NTU School of Medicine NTU Center for Advanced Computing and Imaging in Biomedicine NTU Center for Biotechnology NTU Department of Internal Medicine NTU Hospital Taipei Taiwan Institute of Medical Device and Imaging NTU Department of Radiology College of Medicine NTU Graduate Institute of Clinical Medicine NTU

As part of the 2023 PhysioNet Challenge, our team FINDING_MEMO utilized Transformer to predict outcomes using patient EEG data since it excels at dealing with sequential data like EEG. We mainly used the Transformer encoder block's multi-head self-attention to generate representations from the input and leverage several hidden layers to form the final prediction. Using the latest EEG from every patient, our team achieved the challenge score of 0.42 with the hidden validation set (ranked 36th out of 73 invited teams) and obtained a result of 0.37 (ranked 29th out of 36 qualified teams). Our results show a consistent performance across varying EEG recording durations in both the validation and test set. Our team also had the second-best score when evaluated, with only 12 hours of available recordings in the test set. Such promising results showcase the models' generalizability and clinical potential in predicting outcomes for comatose patients, especially for limited available EEG recordings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Combination of Foot Switch and Low-Cost IMU for a Wearable Mouse in Human-computer Interaction

The Combination of Foot Switch and Low-Cost IMU for a Wearab...

引用

International Conference on Information Technology and Electrical engineering (ICITEE)

作者： Romy Budhi Widodo Evans Jahja Yusuf Giovanno Ma Chung Human-Machine Interaction Research Center Informatics Engineering Study Program Ma Chung University Malang Indonesia Informatics Engineering Study Program Ma Chung University Malang Indonesia

The following topics are dealt with: learning (artificial intelligence); feature extraction; mean square error methods; image classification; image segmentation; human computer interaction; invertors; diseases; Intern... 详细信息

ISBN: (数字)9781728110974

ISBN: (纸本)9781728110981

关键词： Mice Fatigue Sensors Switches Throughput Standards Foot

来源：评论

学校读者我要写书评

暂无评论

Determination location of disturbance the electricity distribution network for efficiency SOP repair of distribution networks based on Google Maps

引用

AIP Conference Proceedings 2022年第1期2499卷

作者： Yessy Asri Dwina Kuswardani Widya Nita Suliyanti M. Faiz Arnovie 1Informatics Engineering Study Program PLN Institute of Technology Jakarta Indonesia

The Electric Power Distribution Network, which in this case is also called Feeder, UP3 Manokwari has 6 (six) feeders that are used in the distribution of electricity. Feeders include Elang feeders, Kasuari feeders, Nuri feeders, Mambruk feeders, Maleo feeders, and Merpati feeders. Each feeder has a distribution transformer to distribute the electrical network to customers. Facing the feeder distribution network disruption, PLN Company UP3 Manokwari had a hard time knowing the feeder location and the faulty feeder distribution transformer location, so field officers (Yantek) had a hard time finding the location. and sub-location of each feeder disturbance. This study aims to create a system containing location and sub-location information using Google Maps as a map display. This study uses the A * (A-Star) algorithm. The A-Star algorithm uses the closest approximate distance to reach the destination and has a heuristic value. The path search process is done by first determining the nodes and assigning a graph value for each node, then calculating the graph value that brings up the latitude and longitude values. The chart values are stored in the database and then calculated using the A-Star method. The result of this system is that yantek officers can view the information directly in the form of a map showing the location points and distribution transformers of the feeder that is experiencing disturbances, the system will check the user’s position, and then the system will display the fastest route. from the officer’s location to the location of the feeder experiencing disturbances.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sources

arXiv

引用

arXiv 2023年

作者： Rajendran, Suraj Pan, Weishen Sabuncu, Mert R. Chen, Yong Zhou, Jiayu Wang, Fei Tri-Institutional Computational Biology & Medicine Program Cornell University NY United States Division of Health Informatics Department of Population Health Sciences Weill Cornell Medicine New YorkNY United States School of Electrical and Computer Engineering Cornell University IthacaNY United States Cornell Tech New YorkNY United States Department of Radiology Weill Cornell Medical School New YorkNY United States Department of Biostatistics Epidemiology and Informatics University of Pennsylvania PhiladelphiaPA United States Department of Computer Science and Engineering Michigan State University East LansingMI United States

Machine learning (ML) in healthcare presents numerous opportunities for enhancing patient care, population health, and healthcare providers' workflows. However, the real-world clinical and cost benefits remain limited due to challenges in data privacy, heterogeneous data sources, and the inability to fully leverage multiple data modalities. In this perspective paper, we introduce "patchwork learning" (PL), a novel paradigm that addresses these limitations by integrating information from disparate datasets composed of different data modalities (e.g., clinical free-text, medical images, omics) and distributed across separate and secure sites. PL allows the simultaneous utilization of complementary data sources while preserving data privacy, enabling the development of more holistic and generalizable ML models. We present the concept of patchwork learning and its current implementations in healthcare, exploring the potential opportunities and applicable data sources for addressing various healthcare challenges. PL leverages bridging modalities or overlapping feature spaces across sites to facilitate information sharing and impute missing data, thereby addressing related prediction tasks. We discuss the challenges associated with PL, many of which are shared by federated and multimodal learning, and provide recommendations for future research in this field. By offering a more comprehensive approach to healthcare data integration, patchwork learning has the potential to revolutionize the clinical applicability of ML models. This paradigm promises to strike a balance between personalization and generalizability, ultimately enhancing patient experiences, improving population health, and optimizing healthcare providers' workflows. © 2023, CC BY.

关键词： Data privacy

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：