检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Johnson, Ruth Li, Michelle M. Noori, Ayush Queen, Owen Zitnik, Marinka Department of Biomedical Informatics Harvard Medical School BostonMA02115 United States Berkowitz Family Living Laboratory Harvard Medical School BostonMA02115 United States Bioinformatics and Integrative Genomics Program Harvard Medical School BostonMA02115 United States Harvard College CambridgeMA02138 United States Broad Institute of MIT and Harvard CambridgeMA02142 United States Harvard Data Science Initiative CambridgeMA02138 United States Kempner Institute for the Study of Natural and Artificial Intelligence Harvard University AllstonMA United States

In clinical artificial intelligence (AI), graph representation learning, mainly through graph neural networks and graph transformer architectures, stands out for its capability to capture intricate relationships and structures within clinical datasets. With diverse data-from patient records to imaging-graph AI models process data holistically by viewing modalities and entities within them as nodes interconnected by their relationships. Graph AI facilitates model transfer across clinical tasks, enabling models to generalize across patient populations without additional parameters or minimal to no re-training. However, the importance of human-centered design and model interpretability in clinical decision-making cannot be overstated. Since graph AI models capture information through localized neural transformations defined on relational datasets, they offer both an opportunity and a challenge in elucidating model rationale. Knowledge graphs can enhance interpretability by aligning model-driven insights with medical knowledge. Emerging graph AI models integrate diverse data modalities through pre-training, facilitate interactive feedback loops, and foster human-AI collaboration, paving the way to clinically meaningful predictions. © 2023, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Canopy cover estimation based on support vector regression derived from Lidar & Landsat 8 OLI 40

Canopy cover estimation based on support vector regression d...

引用

40th Asian Conference on Remote Sensing: Progress of Remote Sensing Technology for Smart Future, ACRS 2019

作者： Hudjimartsu, Sahid Tampinongkol, Felliks Rudianto, Yoga Setiawan, Yudi Prasetyo, Lilik Budi Forests2020 Programme Environmental Analysis and Spatial Modelling Laboratory Department of Forest Resource Conservation Faculty of Forestry Bogor Agricultural University Bogor West Java Indonesia Geoinformatic of Informatics Engineering Study Program Faculty of Engineering and Science Ibn Khaldun University Jalan KH Soleh Iskandar KM 2 Tanah Sereal Bogor West Jawa Indonesia

Light detection and ranging (LiDAR) provides geospatial information with massive amounts of data to use in a variety of applications. Canopy cover percentage of tree crown is one application that is estimated through LiDAR data. This study aims to estimate a canopy cover derived from LiDAR used as reference data with multispectral Landsat 8 OLI. Statistical or machine learning approaches can be used to estimate a canopy cover. In statistical inference, the form of distribution chosen by the analyst and parameter is estimated from the data. This will be a problem in the construction function for the National scale, due to many ecosystems and then will have many functions for each ecosystem. Machine learning (ML) methods, in contrast, are various kinds of algorithms that are used to learn the mapping function or classification rules inductively, directly from the training data. ML can solve problems related to big data and global method and it will be used as a methodical approach to estimate canopy cover on the National scale. In this study, we use a support vector regression (SVR) as ML method to estimate the canopy cover. The estimated percentage of canopy cover will be used as one of the parameters to classify a forest. © 2020 40th Asian Conference on Remote Sensing, ACRS 2019: "Progress of Remote Sensing Technology for Smart Future". All rights reserved.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Canvas Learning Management System Feature Analysis Using Feature-Oriented Domain Analysis (FODA)

引用

IOP Conference Series: Materials Science and Engineering 2021年第1期1077卷

作者： Galih Wasis Wicaksono Pamula Brian Nawisworo Evi Dwi Wahyuni Yus Muhammad Cholily Informatics Study Program Muhammadiyah University Malang Jalan Raya Tlogomas No. 246 Malang East Java

The impact of Covid-19 on the world of education requires the implementation of online learning. Information and computer technology can provide solutions in education through the Learning Management System (LMS). Canvas LMS is a form of LMS that can be utilized by lecturers and students in online learning during the Covid-19 pandemic. In this study, researchers analyzed the features of Canvas LMS using the Feature-Oriented Domain Analysis (FODA) method. Researchers also conducted a mapping of canvas LMS features with the National Standard of Higher Education (SN Dikti). This study showed two stages of validation by Education and LMS experts to verify the results of the analysis. At the end of the course, we recommended a new LMS feature that complies with SN Dikti for Lecturer and Student users.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving vocational education quality through life-based learning

引用

AIP Conference Proceedings 2023年第1期2531卷

作者： Yoto P. A. N. Mawangi A. N. Pramudhita Mechanical Engineering Education Study Program Mechanical Engineering Department Faculty of Engineering State University of Malang Jl. Semarang No. 5 Malang Indonesia Informatics Engineering Department State Polytechnic of Malang Jl. Sukarno-Hatta No 9 Malang Indonesia

Vocational graduates supposedly have the competencies following the purpose of vocational education: preparing medium-skilled labor in a particular area that corresponded with the industrial needs. The 21st-century learning, among others, was signified with a learning process that optimizing the brain function. In the 21st-century, businesses and industries tend to demand skilled labors in digital literacy, technology literacy, and human literacy. Thus, vocational education should be able to innovate and create to respond to the challenge and opportunity from the 21st-century implication through revitalizing the vocational education, involving learning system, education units, learners, educators, and educational staffs. A suitable learning system for the 21st-century is a life-based learning model. Life-based learning in vocational education could be performed through industrial practice, industrial class, and teaching factory activities. These three approaches aimed to bring the learning activities closer with real-life work at the workplace through field practices. With life-based learning at the real workplace, students would develop a discipline, responsible, teamwork, and work culture habits as provisions after finishing the vocational education.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimodal AI predicts clinical outcomes of drug combinations from preclinical data

arXiv

引用

arXiv 2025年

作者： Huang, Yepeng Su, Xiaorui Ullanat, Varun Liang, Ivy Clegg, Lindsay Olabode, Damilola Ho, Nicholas John, Bino Gibbs, Megan Zitnik, Marinka Department of Biomedical Informatics Harvard Medical School BostonMA United States Program in Biological and Biomedical Sciences Harvard Medical School BostonMA United States Harvard College CambridgeMA United States Clinical Pharmacology and Quantitative Pharmacology Clinical Pharmacology & Safety Sciences R&D AstraZeneca GaithersburgMD United States Clinical Pharmacology and Quantitative Pharmacology Clinical Pharmacology & Safety Sciences R&D AstraZeneca WalthamMA United States Program in Computational Biology Carnegie Mellon University PittsburghPA United States Imaging and Data Analytics Clinical Pharmacology & Safety Sciences R&D AstraZeneca WalthamMA United States Kempner Institute for the Study of Natural and Artificial Intelligence Harvard University AllstonMA United States Broad Institute of MIT and Harvard CambridgeMA United States Harvard Data Science Initiative CambridgeMA United States

Predicting clinical outcomes from preclinical data is essential for identifying safe and effective drug combinations, reducing late-stage clinical failures, and accelerating the development of precision therapies. Current models rely on structural or target-based features to identify high-efficacy, low-toxicity drug combinations. However, these approaches fail to incorporate the multimodal data necessary for accurate, clinically-relevant predictions. Here, we introduce MADRIGAL, a multimodal AI model that learns from structural, pathway, cell viability, and transcriptomic data to predict drug combination effects across 953 clinical outcomes and 21,842 compounds, including combinations of approved drugs and novel compounds in development. MADRIGAL uses a transformer bottleneck module to unify preclinical drug data modalities while handling missing data during training and inference—a major challenge in multimodal learning. It outperforms single-modality methods and state-of-the-art models in predicting adverse drug interactions. MADRIGAL performs virtual screening of anticancer drug combinations and supports polypharmacy management for type II diabetes and metabolic dysfunction-associated steatohepatitis (MASH). It identifies transporter-mediated drug interactions. MADRIGAL predicts resmetirom, the first and only FDA-approved drug for MASH, among therapies with the most favorable safety profile. It supports personalized cancer therapy by integrating genomic profiles from cancer patients. Using primary acute myeloid leukemia samples and patient-derived xenograft models, it predicts the efficacy of personalized drug combinations. Integrating MADRIGAL with a large language model allows users to describe clinical outcomes in natural language, improving safety assessment by identifying potential adverse interactions and toxicity risks. MADRIGAL provides a multimodal approach for designing combination therapies with improved predictive accuracy and clinical relevance. Copy

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Dijkstra and Bidirectional Dijkstra on Determining Evacuation Routes

引用

Journal of Physics: Conference Series 2021年第1期1803卷

作者： I G S Rahayuda N P L Santiari Program Study of Information Systems Faculty of Informatics and Computers Institute of Technology and Business STIKOM Bali Denpasar Bali Indonesia

Determination of the best path or often called the shortest path finding is a method that has many benefits and can be applied in various cases and fields of science. In previous studies, authors have developed the shortest path finding program using various algorithms, such as held-karp, iterative deepening search, bidirectional depth first search and depth limited search. In this research author implements shortest path finding on information system for determining fire disaster evacuation route using Dijkstra and bidirectional Dijkstra. The program was developed based on web using *** framework. Both algorithms were tested on several datasets and the results will be compared to find out the strengths and weaknesses. Based on the research, the algorithm was successfully developed based on the web using the *** framework and successfully tested on several datasets, it is known that 40% of the test results show that bidirectional Dijkstra is better than Dijkstra, 10% vice versa and 50% get the same results from both algorithms. From this comparison it can be concluded that the bidirectional Dijkstra algorithm is better than Dijkstra. This research succeeded in proving that the bidirectional Dijkstra algorithm can produce a better route than the standard or classic Dijkstra algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulation of model landslides observation in laboratory used by IoT

引用

AIP Conference Proceedings 2023年第1期2609卷

作者： Made Sutha Yadnya I. G. P. Wedashwara Wedarama I. Wayan Sudiarta 1Electrical Engineering Communication Laboratory Engineering Faculty University of Mataram Mataram Indonesia 2Informatics Engineering Faculty of EngineeringUniversity of Mataram Mataram Indonesia 3Physic Study Program Faculty of Mathematics and Natural Science University of Mataram Mataram Indonesia

This paper is collaboration between BMKG and the University of Mataram to mitigate land slide. For this study using light intensity sensors, air temperature sensors, voltage sensors, current sensors, humidity sensors. This research is on a laboratory scale with a soil slope of 10 degrees, dry soil with a tendency to split (clay) from brittle volcanic rocks. The initial conditions were without rain, then the soil was burdened with rain in low (drizzle), medium (25mm/h) and high (55mm/h) capacities. The second condition of the stage is given a vibration which is a model of the earthquake evenly on that stage. Soil Moisture soil, soil temperature, 3 pieces of vibration sensor switch, piezo electric vibration sensor. The initial height of the soil is 36.78 cm with a width of 79.35cm after being rained for 90 minutes, the final height is 29.93 and 60.25 cm, widening receding to the right and left sides.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Use of the Web API as a basis for obtaining the latest data on bitcoin prices at 30 exchange places

引用

IOP Conference Series: Materials Science and Engineering 2021年第1期1125卷

作者： Rizky Parlika Arista Pratama Informatics Engineering Study Program Faculty of Computer Science National Development University 'Veteran' East Java Information Systems Study Program Faculty of Computer Science Raya Rungkut Madya Road Gunung Anyar Surabaya

Bitcoin has become a commodity traded by millions of traders from all over the world. This is one of the causes of fluctuating price movements. From the data we got on coinmarketcap, Bitcoin is traded on various cryptocurrency trading exchanges. And at every exchange that has a reputation, of course, has an API service to access historical data about the price movements of all the crypto commodities they have traded from the start. By using the PHP programming language and implementation of the CURL function for JSON readings, we can pull Bitcoin movement data in real time. In this paper, Bitcoin is specifically observed because it is the forerunner and the main cryptocurrency commodity traded and is a determinant of Alternative coin price movements in general. In this paper Bitcoin price monitoring is carried out at 30 reputable exchange places through API access provided by each exchange place. Furthermore, conclusions are drawn about the various variants of how to access the API from the 30 bitcoin exchange places. The program code that is displayed directly in this paper can then be used as an initial reference if you want to develop a Cryptocurrency price movement monitoring application for Bitcoin. At the end of the paper, an example of the application of Bitcoin price monitoring will be presented using a web-based application containing charts and supporting indicators as well as a telegram bot to display price depth charts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Measuring Village Head Performance using Fuzzy TOPSIS Method 3

Measuring Village Head Performance using Fuzzy TOPSIS Method

引用

3rd International Conference on Mathematics, Sciences, Technology, Education and their Applications, ICMSTEA 2018

作者： Sahabuddin, Chuduriah Basri Muslihudin, Muhammad Latifah, Nurul Irawan, Dedi Informatics Study Program Universitas Al Asyariah Mandar West Sulawesi Indonesia Department of Information System STMIK Pringsewu Lampung Indonesia Department of Islamic Education Management STIT Pringsewu Lampung Indonesia

The village head is the leader of the village in Indonesia. The village head is the leader of the village government. The tenure of the village head is six years, and can be extended for another one term is expected to run the government with a good performance in providing services to the community. So if the government officials at the village level show good performance in organizing the government. The Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method can help decision making in determining the performance index of the village head. This research is conduct by looking for the performance of positive and negative ideal solutions. Applications with the highest V value will occupy the top size in this system. Then the criteria for determining the performance index of the head of the village are timeliness, discipline, responsibility, leadership, presence, value. The results of the decision-making system resulted in 6 alternatives suggested performance indexes of village heads, with the highest score of Sendang Agung Village. © Published under licence by IOP Publishing Ltd.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Increasing accuracy of classification physical activity based on smartphone using ensemble logistic regression with boosting method 3

Increasing accuracy of classification physical activity base...

引用

3rd International Conference on Science, ICOS 2019

作者： Lawi, A. Aziz, F. Wungo, S.L. Department of Computer Science Universitas Hasanuddin Makassar90245 Indonesia Faculty of Mathematics and Natural Sciences Universitas Pancasakti Makassar90132 Indonesia Program Study Informatics Engineering STMIK Kreatindo Monokwari98300 Indonesia

At present, the smartphone is equipped with several sensors such as Accelerometer, Gravity sensor, and Gyroscope which can be used to recognize human physical activities such as walking upstair and walking downstairs etc. Machine learning is needed to group data and get information. Statistical methods have poor performance in classifying because procedures must be met. To overcome this, an ensemble technique was used. This study proposes the application of the gradientboost ensemble method to classify walking upstair and walking downstairs. The *** system is designed for data retrieval using a smartphone. Then, the dataset will be partitioned into 70% training data and 30% test data. The results show that the performance of the ensemble boosting method produces 81.82% accuracy, 86.11% sensitivity and 77.50% specificity. © Published under licence by IOP Publishing Ltd.

关键词： Smartphones

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：