检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Dou, Mingliang Han, Han Chen, Genlang Guo, Fei Tang, Jijun Tianjin University College of Intelligence and Computing Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China NingboTech University School of Computer and Data Engineering Ningbo China Central South University School of Computer Science and Engineering Changsha China University of South Carolina College of Engineering and Computing United States

ISBN: (纸本)9781665468190

In the treatment of many diseases, combination drug therapy has been widely used and achieved good clinical efficacy. However, drug-drug interaction (DDI) may occur between multiple drugs and pose a huge threat to the health of patients. Therefore, predicting the presence or absence of DDI among multiple drugs is an important part of pharmacovigilance. Currently, various computational methods for DDI prediction usually use biological information such as molecular structures, targets and enzymes of drugs, or construct heterogeneous networks about drugs, diseases, and genes, so as to obtain abundant information related to drugs. In addition to biological data, pharmacology texts also contain a wealth of information about drug properties, but these texts have not yet been applied to DDI predictions. In this study, we first collect six types of pharmacology texts from DrugBank that can reflect properties of drugs, and propose a novel method named BP-DDI which can combine biological information and pharmacological text to realize DDI event prediction. BP-DDI first extracts biological features (chemical substructure features and target features) from biological data, and then extracts specific types of text features from the collected pharmacology text data. Finally, the biological features are fused with different types of pharmacological text features in order to predict DDI events. Our experiments demonstrate that BP-DDI outperforms existing methods on all three types of prediction tasks. BP-DDI achieves 0.9052 on ACC, and achieves 0.9612 on AUPR. © 2022 IEEE.

关键词： Drug interactions

来源：评论

学校读者我要写书评

暂无评论

Two pairs of heteroclinic orbits coined in a new sub-quadratic Lorenz-like system

引用

The European Physical Journal B 2023年第3期96卷 1-9页

作者： Wang, Haijun Ke, Guiyao Pan, Jun Hu, Feiyu Fan, Hongdan Su, Qifang School of Electronic and Information Engineering (School of Big Data Science) Taizhou University Taizhou People’s Republic of China School of Information Zhejiang Guangsha Vocational and Technical University of Construction Dongyang People’s Republic of China School of Information Engineering GongQing Institute of Science and Technology Gongqingcheng People’s Republic of China Department of Big Data Science School of Science Zhejiang University of Science and Technology Hangzhou People’s Republic of China College of Sustainability and Tourism Ritsumeikan Asia Pacific University Jumonjibaru Beppu Japan

This paper reports a new 3D sub-quadratic Lorenz-like system and proves the existence of two pairs of heteroclinic orbits to two pairs of nontrivial equilibria and the origin, which are completely different from the existing ones to the unstable origin and a pair of stable nontrivial equilibria in the published literature. This motivates one to further explore it and dig out its other hidden dynamics: Hopf bifurcation, invariant algebraic surface, ultimate boundedness, singularly degenerate heteroclinic cycle and so on. Particularly, numerical simulation illustrates that the Lorenz-like chaotic attractors coexist with one saddle in the origin and two stable nontrivial equilibria, which are created through the broken infinitely many singularly degenerate heteroclinic cycles and explosions of normally hyperbolic stable foci $$E_{z}.$$

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Causal Inference to Explore Government Policy Impact on Computer Usage

arXiv

引用

arXiv 2025年

作者： Zhu, Mingjia Wang, Lechuan Sebot, Julien Arbab, Bijan Salimi, Babak Cloninger, Alexander University of California Computer Science and Engineering San Diego United States University of California Department of Mathematics San Diego United States Intel Corporation United States University of California Halicioğlu Data Science Institute San Diego United States

We explore the causal relationship between COVID-19 lockdown policies and changes in personal computer usage. In particular, we examine how lockdown policies affected average daily computer usage, as well as how it affected usage patterns of different groups of users. This is done through a merging of the Oxford Policy public data set, which describes the timeline of implementation of COVID policies across the world, and a collection of Intel’s data Collection & Analytics (DCA) telemetry data, which includes millions of computer usage records and updates daily. Through difference-indifference, synthetic control, and change-point detection algorithms, we identify causal links between the increase in intensity (watts) and time (hours) of computer usage and the implementation of work from home policy. We also show an interesting trend in the individual’s computer usage affected by the policy. We also conclude that computer usage behaviors are much less predictable during reduction in COVID lockdown policies than during increases in COVID lockdown policies. Copyright © 2025, The Authors. All rights reserved.

关键词： Personal computers

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory with Encoder-Decoder and Skill Optimization Algorithm based Weather Radar Echo Prediction

Long Short-Term Memory with Encoder-Decoder and Skill Optimi...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： S. Ramijaanaki V. R. Niveditha G.V.N Bhagya Sree Rajababu D R Maranan S. Kaliappan Artificial Intelligence and Data Science R.M.K College of Engineering and Technology Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai Department of Computer Science and Engineering Aditya University Surampalem Andhra Pradesh India Department of Electrical and Electronics Engineering SR University Warangal Telangana Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India Division of Research and Development Lovely Professional University Phagwara Punjab India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

This research proposes a novel implementation of Long Short-Term Memory with Encoder-Decoder and Skill Optimization Algorithm (LSTM-ED-SOA) seeking to forecast Weather Radar Echoes. It presents a model that seeks to strengthen ‘the weak’ by introducing an optimization algorithm that combines the advantages of LSTM in handling sequential data and improves the performance of the predictions over time. Temporal dependencies are appropriately modeled with the encoder-decoder structure which is coupled with a skill optimization technique that enables the model to mitigate against capricious weather conditions. Forecasting models such as EPD, TrajGRU, and ConvLSTM as well as, and PredRNN put together show weaknesses when compared to LSTM-ED-SOA. Thus, it comes out convincingly that the model performs exceptionally achieving an accuracy of 99.8%, precision of 99.6%, and an F1 score of 99.7% way ahead of the best conventional models which were achieved accuracy of 85% at the very best. These results underscore the stability and effectiveness of the LSTM-ED-SOA system, for more advanced radars, wherein, it will greatly enhance the accuracy and timeliness of weather forecasting.

关键词： Meteorological radar Accuracy Computational modeling Predictive models Prediction algorithms data models Wind forecasting Optimization Long short term memory Meteorology

来源：评论

学校读者我要写书评

暂无评论

LLM-PS: Empowering Large Language Models for Time Series Forecasting with Temporal Patterns and Semantics

arXiv

引用

arXiv 2025年

作者： Tang, Jialiang Chen, Shuo Gong, Chen Zhang, Jing Tao, Dacheng School of Computer Science and Engineering Nanjing University of Science and Technology China College of Computing and Data Science Nanyang Technological University Singapore School of Intellgence Science and Technology Nanjing University China Department of Automation Institute of Image ProceProceedingssing and Pattern Recognition Shanghai Jiao Tong University China School of Computer Science Wuhan University China

Time Series Forecasting (TSF) is critical in many real-world domains like financial planning and health monitoring. Recent studies have revealed that Large Language Models (LLMs), with their powerful in-contextual modeling capabilities, hold significant potential for TSF. However, existing LLM-based methods usually perform suboptimally because they neglect the inherent characteristics of time series data. Unlike the textual data used in LLM pre-training, the time series data is semantically sparse and comprises distinctive temporal patterns. To address this problem, we propose LLM-PS to empower the LLM for TSF by learning the fundamental Patterns and meaningful Semantics from time series data. Our LLM-PS incorporates a new multi-scale convolutional neural network adept at capturing both short-term fluctuations and long-term trends within the time series. Meanwhile, we introduce a time-to-text module for extracting valuable semantics across continuous time intervals rather than isolated time points. By integrating these patterns and semantics, LLM-PS effectively models temporal dependencies, enabling a deep comprehension of time series and delivering accurate forecasts. Intensive experimental results demonstrate that LLM-PS achieves state-of-the-art performance in both short- and long-term forecasting tasks, as well as in few- and zero-shot settings. © 2025, CC BY.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Enhancement of IoT based Flood Detection and Prevention using Arduino UNO with WiFi Module

Enhancement of IoT based Flood Detection and Prevention usin...

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： R. M. Dilip Charaan J. Shobana P. Krishnamoorthy B. Anni Princy R. J. Abinaya K. Murugesan Department of Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Tamil Nadu India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of Computer Science and Engineering Siddharth Institute of Engineering & Technology Tamil Nadu India Department of Computer and Communication Engineering Panimalar Engineering College Tamil Nadu India Department of Electronics and Communication Engineering Karpagam Academy of Higher Education Tamil Nadu India Department of Electronics and Communication Engineering Loyola Institute of Technology Tamil Nadu India

The overflow of water from a lake or river usually causes flooding. Sometimes, a dam breach might result in the unexpected release of vast quantities of water. Some of the water seeps into the ground, flooding the region. In a station, rivers are involving the riverbanks. Along with a lack of goods and houses, businesses, and offices, street infrastructure floods contain bacteria, sewage from waste sites, and chemical spills, which later cause a number of diseases. The rate of change in river stage in real time, which can assist signal the gravity and immediacy of this hazard, is a crucial piece of information for flood predictions. Understanding the type of storm that produced the moisture, including its duration, strength, and actual extent, is important for determining the possible severity of the flood. In this system, an Arduino Uno is connected to four separate sensors: a humidity sensor, a flow sensor, a float sensor, and an ultrasonic sensor. The float sensor detects when the water is full. With the aid of IOT, these sensor combinations are utilised to predict floods, alert the appropriate authorities, and sound an immediate alarm in adjacent communities to rapidly relay information about potential floods. These sensors provide data via the IOT’s WiFi module. When flooding conditions are detected, the system warns the nearby villages and places and estimates how long it would take for help to reach at a particular location. The technology also determines when it might be considered a flood and gives them a window of time to leave in case it does.

关键词： Dams Storms Sensor systems Real-time systems Sensors Rivers Floods

来源：评论

学校读者我要写书评

暂无评论

TRACKING OBJECTS AND ACTIVITIES WITH ATTENTION FOR TEMPORAL SENTENCE GROUNDING

arXiv

引用

arXiv 2023年

作者： Xiong, Zeyu Liu, Daizong Zhou, Pan Zhu, Jiahao Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China Wangxuan Institute of Computer Technology Peking University China

Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video. Most existing methods extract frame-grained features or object-grained features by 3D ConvNet or detection network under a conventional TSG framework, failing to capture the subtle differences between frames or to model the spatio-temporal behavior of core persons/objects. In this paper, we introduce a new perspective to address the TSG task by tracking pivotal objects and activities to learn more fine-grained spatio-temporal behaviors. Specifically, we propose a novel Temporal Sentence Tracking Network (TSTNet), which contains (A) a Cross-modal Targets Generator to generate multi-modal templates and search space, filtering objects and activities, and (B) a Temporal Sentence Tracker to track multi-modal targets for modeling the targets' behavior and to predict query-related segment. Extensive experiments and comparisons with state-of-the-arts are conducted on challenging benchmarks: Charades-STA and TACoS. And our TSTNet achieves the leading performance with a considerable real-time speed. Copyright © 2023, The Authors. All rights reserved.

关键词： Arts computing

来源：评论

学校读者我要写书评

暂无评论

Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentation 39

Gradient Alignment Improves Test-Time Adaptation for Medical...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Ziyang Ye, Yiwen Pan, Yongsheng Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China Research & Development Institute Northwestern Polytechnical University in Shenzhen Shenzhen China Ningbo Institute Northwestern Polytechnical University Ningbo China

ISBN: (纸本)157735897X

Although recent years have witnessed significant advancements in medical image segmentation, the pervasive issue of domain shift among medical images from diverse centres hinders the effective deployment of pre-trained models. Many Test-time Adaptation (TTA) methods have been proposed to address this issue by fine-tuning pre-trained models with test data during inference. These methods, however, often suffer from less-satisfactory optimization due to suboptimal optimization direction (dictated by the gradient) and fixed step-size (predicated on the learning rate). In this paper, we propose the Gradient alignment-based Test-time adaptation (GraTa) method to improve both the gradient direction and learning rate in the optimization procedure. Unlike conventional TTA methods, which primarily optimize the pseudo gradient derived from a self-supervised objective, our method incorporates an auxiliary gradient with the pseudo one to facilitate gradient alignment. Such gradient alignment enables the model to excavate the similarities between different gradients and correct the gradient direction to approximate the empirical gradient related to the current segmentation task. Additionally, we design a dynamic learning rate based on the cosine similarity between the pseudo and auxiliary gradients, thereby empowering the adaptive fine-tuning of pre-trained models on diverse test data. Extensive experiments establish the effectiveness of the proposed gradient alignment and dynamic learning rate and substantiate the superiority of our GraTa method over other state-of-the-art TTA methods on a benchmark medical image segmentation task. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Accident detection using automotive smart black- box based

引用

Measurement: Sensors 2023年 27卷

作者： Josephinshermila, P. Sharon priya, S. Malarvizhi, K. hegde, Ramakrishna Gokul Pran, S. Veerasamy, B. Department of artificial intelligence and data science R.M.K.College of Engineering and Technology Tamil Nadu Chennai India Department of Computer Science Engineering B.S.Abdur Rahman Crescent Institute of Science and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering JCT College of Engineering and Technology Pichanur Tamil Nadu Coimbatore India Department of Computer Science and Engineering Vidyavardhaka College of Engineering Mysore India Department of Computer Science Engineering Sreevidyanikethan Engineering College Tirupathi India Department of Electronics and Communication Engineering Hindusthan College of Engineering and Technology Tamil Nadu Coimbatore641050 India

Autonomous vehicles want reliable and strong sensor suites and alert systems. This paper discusses the composition and performance of a sophisticated monitoring and alert system for automobile vehicle parameters. The number of automobiles has also grown quickly to meet the enormous population. Additionally, this resulted in an increase in accidents. The accident prevention strategies now in use are all static and dated. Additionally, there is no reliable accident detection system. Automobile vehicle parameters are continuously monitored by a micro-controller which stores the data logs containing vehicle parameter data into a sheltered digital memory card and in the cloud storage. The system doesn't solely record the vehicle parameters data of the automobile periodically, but also actively monitors for any sudden vehicle accident detection. The sensor may facilitate folks to analyze the accident quickly and lawfully when a collision happens to alert the emergency services to that location. The system will update the information whenever an abnormal system event happens. A black box in a vehicle gather driving information about the vehicle before, during and after a crash. The data gathered includes, speed, acceleration, braking, steering and air-bag deployment. The Automotive black box system can aid with vehicle safety, increase collision victim care, assist insurance corporations with vehicle crash investigations, and improve road conditions to reduce death rates. According to experimental findings, the proposed technique achieves 29.3103%, 22.70 %, 18.103% and 11.206 % higher accuracy compared to RFID, SVM,CNN and RNN Methods. © 2023 The Authors

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A New Federated Learning Framework Against Gradient Inversion Attacks

arXiv

引用

arXiv 2024年

作者： Guo, Pengxin Zeng, Shuang Chen, Wenhao Zhang, Xiaodan Ren, Weihong Zhou, Yuyin Qu, Liangqiong School of Computing and Data Science The University of Hong Kong Hong Kong Department of Mathematics The University of Hong Kong Hong Kong College of Computer Science Beijing University of Technology China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering UC Santa Cruz United States

Federated Learning (FL) aims to protect data privacy by enabling clients to collectively train machine learning models without sharing their raw data. However, recent studies demonstrate that information exchanged during FL is subject to Gradient Inversion Attacks (GIA) and, consequently, a variety of privacy-preserving methods have been integrated into FL to thwart such attacks, such as Secure Multi-party Computing (SMC), Homomorphic Encryption (HE), and Differential Privacy (DP). Despite their ability to protect data privacy, these approaches inherently involve substantial privacy-utility trade-offs. By revisiting the key to privacy exposure in FL under GIA, which lies in the frequent sharing of model gradients that contain private data, we take a new perspective by designing a novel privacy preserve FL framework that effectively "breaks the direct connection" between the shared parameters and the local private data to defend against GIA. Specifically, we propose a Hypernetwork Federated Learning (HyperFL) framework that utilizes hypernetworks to generate the parameters of the local model and only the hypernetwork parameters are uploaded to the server for aggregation. Theoretical analyses demonstrate the convergence rate of the proposed HyperFL, while extensive experimental results show the privacy-preserving capability and comparable performance of HyperFL. Code is available at https://***/Pengxin-Guo/HyperFL. © 2024, CC BY.

关键词： Federated learning

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：