检索结果-内蒙古大学图书馆

IEEE International Conference on Consumer Electronics (ICCE)

作者： Andy Desman Kahlil Muchtar Maulisa Oktiana Maya Fitria Yuwaldi Away Fardian Fardian Hammam Riza Dept. of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia Dept. of Electrical and Computer Engineering Department of Informatics Universitas Syiah Kuala The Master Program in Artificial Intelligence Universitas Syiah Kuala (USK) Banda Aceh Indonesia Department of Informatics BRIN (National Research and Innovation Agency) Indonesia The Master Program in Artificial Intelligence Universitas Syiah Kuala Banda Aceh Indonesia

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The WHO predicts that by 2030 road accidents will be the 5th leading cause of death. Globally, road accidents account for 1.25 million casualties each year, and road defects cause 34% of these casualties. The road survey process in many countries have several challenges, one of which is detection using cameras that do not have a recognition system. In this study, a model with YOLOS architecture based on Vision Transformer trained on the RDD2022 dataset successfully recognizes road damage well, as indicated by the number of objects detected, bounding box on accurate objects, and the ability to recognize objects with inconsistent shadow and light inference. This research uses assessment parameters such as Average Precision (AP) and Average Recall (AR) to determine the overall performance of the model. The model achieves the highest AP value at Intersection of Union (IoU) 0.5, 0.75, and 0.5-0.95, worth 62.1%, 37.1%, and 36.2% respectively, and the highest AR value in Large, Medium, and Small Areas, worth 42.1%, 60.3%, and 75.4% respectively. The supplementary material can be found through this link: https://***/watch?v=LzkI2e_IORE.

关键词： YOLO Surveys computer vision Road accidents Roads Manuals Transformers Cameras Cleaning Tuning

来源：评论

学校读者我要写书评

暂无评论

GraphT5: Unified Molecular Graph-Language Modeling via Multi-Modal Cross-Token Attention

arXiv

引用

arXiv 2025年

作者： Kim, Sangyeup Kim, Nayeon Piao, Yinhua Kim, Sun Computer Science and Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of AIGENDRUG Co. Ltd Korea Republic of

Molecular language modeling tasks such as molecule captioning have been recognized for their potential to further understand molecular properties that can aid drug discovery or material synthesis based on chemical reactions. Unlike the common use of molecule graphs in predicting molecular properties, most methods in molecular language modeling rely heavily on SMILES sequences. This preference is because the task involves generating a sequence of multiple tokens using transformer-based models. Therefore, a main challenge is determining how to integrate graph data, which contains structural and spatial information about molecules, with text data. In addition, simply using both 1D SMILES text and 2D graph as inputs without addressing how they align and represent the molecule structure in different modalities makes it challenging to fully utilize structural knowledge about molecules. To this end, we propose GraphT5, a multi-modal framework that integrates 1D SMILES text and 2D graph representations of molecules for molecular language modeling. Specifically, we introduce a novel cross-token attention module in GraphT5 to bridge the gap arising from the fundamental differences between the two modalities of molecule representations. Cross-token attention exploits implicit information between SMILES and graphs of molecules, resulting from their interactions at a fine-grained token level that benefits molecular language modeling. Extensive experiments including molecule captioning, IUPAC name prediction tasks, and case studies show that our GraphT5 outperforms the latest baseline approaches, which validates the effectiveness of our GraphT5 in sufficiently utilizing 1D SMILES text and 2D graph representations. © 2025, CC BY-NC-ND.

关键词： Unified Modeling Language

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Air Box Application for Indoor Environment Classification and LSTM Microclimate Prediction 6

Low-Cost Air Box Application for Indoor Environment Classifi...

引用

6th International Conference on Control and Robotics, ICCR 2024

作者： Hsun-Jui, Hu Yu-Hsien, Chiu Pei-Ching, Yang Chang Jung Christian University Master Degree Program in Information and Design Tainan Taiwan Kaohsiung Medical University Department of Healthcare Administration and Medical Informatics Kaohsiung Taiwan Artificial Intelligence Research Center Chang Jung Christian University Tainan Taiwan Chang Jung Christian University Department of Computer Science and Information Engineering Tainan Taiwan

ISBN: (纸本)9798331518158

Air pollution is a significant issue because it burdens human health and the environment. Particulate matter with a diameter of 2.5 micrometers or smaller (PM2.5) can penetrate the lungs and enter the bloodstream, seriously affecting the cardiovascular system, causing strokes, and impacting the respiratory system. Modern individuals spend 70% to 90% of their time indoors, making indoor air quality even more important than outdoor air quality. To estimate and predict indoor air quality, this study utilizes low-cost, self-assembled air boxes based on the Internet of Things to collect various air quality data. The collected data is then used in an indoor air quality forecasting system that combines Long Short-Term Memory (LSTM) and K-means clustering methods to compare the overall performance of the algorithms. The experimental results are analyzed and statistically described based on each model method prediction accuracy and clustering results. These methods are integrated to develop an indoor air quality forecasting system to help indoor populations prevent issues in advance or optimize energy usage. © 2024 IEEE.

关键词： Indoor air pollution

来源：评论

学校读者我要写书评

暂无评论

A Low Complexity ML-Based Methods for Malware Classification

引用

computers, Materials & Continua 2024年第9期80卷 4833-4857页

作者： Mahmoud E.Farfoura Ahmad Alkhatib Deema Mohammed Alsekait Mohammad Alshinwan Sahar A.El-Rahman Didi Rosiyadi Diaa Salama Abd Elminaam Cybersecurity Department Al-Zaytoonah University of JordanAmman11733Jordan Department of Computer Science and Information Technology Applied CollegePrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Faculty of Information Technology Applied Science Private UniversityAmman11931Jordan Computer Systems Program-Electrical Engineering Department Faculty of Engineering-ShoubraBenha UniversityCairo11629Egypt Research Center for Artificial Intelligence and Cybersecurity Electronics and Informatics OrganizationNational Research and Innovation Agency(BRIN)KST Samaun SamadikunBandung40135Republic of Indonesia Jadara Research Center Jadara UniversityIrbid21110Jordan MEU Research Unit Middle East UniversityAmman11831Jordan

The article describes a new method for malware classification,based on a Machine Learning(ML)model architecture specifically designed for malware detection,enabling real-time and accurate malware *** an innovative feature dimensionality reduction technique called the Interpolation-based Feature Dimensionality Reduction Technique(IFDRT),the authors have significantly reduced the feature space while retaining critical information necessary for malware *** technique optimizes the model’s performance and reduces computational *** proposed method is demonstrated by applying it to the BODMAS malware dataset,which contains 57,293 malware samples and 77,142 benign samples,each with a 2381-feature *** the IFDRT method,the dataset is transformed,reducing the number of features while maintaining essential data for accurate *** evaluation results show outstanding performance,with an F1 score of 0.984 and a high accuracy of 98.5%using only two reduced *** demonstrates the method’s ability to classify malware samples accurately while minimizing processing *** method allows for improving computational efficiency by reducing the feature space,which decreases the memory and time requirements for training and *** new method’s effectiveness is confirmed by the calculations,which indicate significant improvements in malware classification accuracy and *** research results enhance existing malware detection techniques and can be applied in various cybersecurity applications,including real-timemalware detection on resource-constrained *** and scientific contribution lie in the development of the IFDRT method,which provides a robust and efficient solution for feature reduction in ML-based malware classification,paving the way for more effective and scalable cybersecurity measures.

关键词： Malware detection ML-based models dimensionality reduction feature engineering

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Detection: A PySpark-Driven Approach with VGG 16 Feature Extraction and MLP Classification

Diabetic Retinopathy Detection: A PySpark-Driven Approach wi...

引用

Novel Intelligent and Leading Emerging Sciences Conference (NILES)

作者： Toka Nabil Sama Ayman Samaa Ahmed Mawada Nagy Muhammad Megahed Abdulmoniem Elsaeed Monier Ashraf Khaled M. Fouad Ibrahim Abdelbaky School of Infromation Technology and Computer Science Nile University Giza Egypt CS program School of Information Technology and Computer Science (ITCS) Nile University Giza Egypt Faculty of Computer Science and Engineering New Mansoura University Artificial Intelligence Department Faculty of Computers and Artificial Intelligence Benha University Banha Egypt

ISBN: (数字)9798350378511

ISBN: (纸本)9798350378528

The current study used cutting-edge techniques to experimentally test the early diagnosis of diabetes via retinal scans. The goal was to enable effective disease prediction and management by facilitating quick and precise medical diagnostics. Three processes were involved in the development of a Diabetic Retinopathy (DR) diagnosis tool: feature extraction, feature reduction, and image classification. The research employed Apache Spark, a distributed computing framework, to manage large datasets and enhance the performance of the multilayer perceptron (MLP) model via hyperparameter tuning and cross validation. Utilizing resources more effectively and achieving faster training times were made possible by Apache Spark. To support data-driven decision-making, the study also emphasized the significance of distributed platforms for analyzing large amounts of real-time diabetic data. To produce discriminative features for classification, the VGG16 architecture was employed for feature extraction. In the last epoch, the MLP model performed remarkably well, with an accuracy of 97%. The study also underlined the value of distributed platforms for data-driven decision-making by analyzing substantial volumes of real-time diabetes data.

关键词： Diabetic retinopathy Computational modeling Distributed databases Cluster computing Machine learning Multilayer perceptrons Feature extraction Retina Real-time systems Medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

Improving Out-of-Distribution Generalization in Graphs via Hierarchical Semantic Environments

Improving Out-of-Distribution Generalization in Graphs via H...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yinhua Piao Sangseon Lee Yijingxiu Lu Sun Kim Department of Computer Science and Engineering Seoul National University Institute of Computer Technology Seoul National University AIGENDRUG Co. Ltd. Interdisciplinary Program in Artificial Intelligence Seoul National University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Out-of-distribution (OOD) generalization in the graph domain is challenging due to complex distribution shifts and a lack of environmental contexts. Recent methods attempt to enhance graph OOD generalization by generating flat environments. However, such flat environments come with inherent limitations to capture more complex data distributions. Considering the DrugOOD dataset, which contains diverse training environments (e.g., scaffold, size, etc.), flat contexts cannot sufficiently address its high heterogeneity. Thus, a new challenge is posed to generate more seman-tically enriched environments to enhance graph invariant learning for handling distribution shifts. In this paper, we propose a novel approach to generate hierarchical seman-tic environments for each graph. Firstly, given an input graph, we explicitly extract variant subgraphs from the in-put graph to generate proxy predictions on local environ-ments. Then, stochastic attention mechanisms are employed to re-extract the subgraphs for regenerating global environ-ments in a hierarchical manner. In addition, we introduce a new learning objective that guides our model to learn the diversity of environments within the same hierarchy while maintaining consistency across different hierarchies. This approach enables our model to consider the relationships between environments and facilitates robust graph invariant learning. Extensive experiments on real-world graph data have demonstrated the effectiveness of our framework. Par-ticularly, in the challenging dataset DrugOOD, our method achieves up to 1.29% and 2.83% improvement over the best baselines on IC50 and EC50 prediction tasks, respectively.

关键词： Training computer vision Attention mechanisms Computational modeling Semantics Stochastic processes Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Momentum-Based Distributed Economic Dispatch of Smart Grids in Time-Varying Directed Networks

引用

IEEE Transactions on Network Science and engineering 2025年

作者： Zhang, Keke Lu, Qingguo Zhou, Qixing Li, Huaqing Xia, Dawen Huang, Tingwen Chongqing University College of Computer Science China Southwest University College of Electronic and Information Engineering China Kaili University College of Microelectronics and Artificial Intelligence College of Big Data Engineering China Texas A&M University at Qatar Science Program Doha23874 Qatar

In this paper, we investigate the economic dispatch problem of smart grids in time-varying directed networks. The EDP essentially revolves around optimizing the distribution of generation power amongst multiple generators, with the aim of fulfilling load demands at the lowest possible total generation cost, while strictly conforming to the constraints imposed by the local generation capacity. For a faster resolution of the EDP, we propose an efficient distributed accelerated economic dispatch algorithm that incorporates a unified momentum acceleration strategy into the push-pull deviation tracking approach. The involved acceleration strategy under specific momentum parameters includes two well-known acceleration strategies, i.e., the heavy-ball and Nesterov acceleration strategies, which is more flexible and provides additional improvements in convergence. We present rigorously theoretical proof of linear convergence to the optimal dispatch with explicit bounds for step size and momentum parameters. Finally, to verify the effectiveness of our algorithm and the correctness of the theoretical analysis, we conduct simulations of diverse EDP studies in smart grids. © 2013 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment

arXiv

引用

arXiv 2024年

作者： Yu, Sangwon Song, Jongyoon Hwang, Bongkyu Kang, Hoyoung Cho, Sooah Choi, Junhwa Joe, Seongho Lee, Taehee Gwon, Youngjune L. Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Samsung SDS Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

A binary decision task, like yes-no questions or answer verification, reflects a significant real-world scenario such as where users look for confirmation about the correctness of their decisions on specific issues. In this work, we observe that language models exhibit a negative bias in the binary decisions of complex reasoning tasks. Based on our observations and the rationale about attention-based model dynamics, we propose a negative attention score (NAS) to systematically and quantitatively formulate negative bias. Based on NAS, we identify attention heads that attend to negative tokens provided in the instructions as answer candidate of binary decisions, regardless of the question in the prompt, and validate their association with the negative bias. Additionally, we propose the negative attention score alignment (NASA) method, which is a parameter-efficient fine-tuning technique to address the extracted negatively biased attention heads. Experimental results from various domains of reasoning tasks and large model search space demonstrate that NASA significantly reduces the gap between precision and recall caused by negative bias while preserving their generalization abilities. Our codes are available at https://***/ysw1021/NASA. Copyright © 2024, The Authors. All rights reserved.

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

PHORTEX: Physically-Informed Operational Robotic Trajectories for Scientific Expeditions

Field Robotics

引用

Field Robotics 2025年 4卷 138-181页

作者： Victoria L. Preston Genevieve E. Flaspohler John W. Fisher Anna P. M. Michel Nicholas Roy Applied Ocean Physics and Engineering Massachusetts Institute of Technology and Woods Hole Oceanographic Institution Joint Program Cambridge MA 02139 Electrical Engineering and Computer Science Massachusetts Institute of Technology and Woods Hole Oceanographic Institution Joint Program Cambridge MA 02139 Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA 02139 Applied Ocean Physics and Engineering Woods Hole Oceanographic Institution Woods Hole MA 02543

Mobile robots are increasingly used to collect valuable in situ samples during scientific expeditions. However, many phenomena of scientific interest—deep-sea hydrothermal plumes, algal blooms, warm-core eddies, and lava flows—are spatiotemporal distributions that evolve on spatial and temporal scales that complicate sample collection. Here, we consider the problem of charting the space-time dynamics of deep-sea hydrothermal plumes with the state-of-the-art autonomous underwater vehicle (AUV) Sentry. In the hydrothermal plume charting problem, the plume state is driven by complicated and unobserved dynamics in the deep sea. To effectively sample the moving plume, an autonomy system must infer plume dynamics from sparse, point observations, while respecting operational constraints of AUV Sentry that restrict the set of possible trajectories to nonadaptive, uniform-coverage patterns. We frame the plume charting problem as a sequential decision-making problem and formulate a mission planner PHORTEX (PHysically-informed Operational Robotic Trajectories for Expeditions) that strategically designs full mission trajectories for Sentry, where each mission plan is informed by the observations of the last. PHORTEX is composed of a trajectory optimizer, which maximizes expected samples collected within a moving plume, and PHUMES (PHysically-informed Uncertainty Models for Environment Spatiotemporality), a modeling framework that leverages an embedded simulator of idealized plume physics as an inductive bias to enable dynamics learning from extreme partial observations and a few Sentry deployments. In both simulation and in field trials at a hydrothermal site in the Gulf of California, we demonstrate that Sentry using PHORTEX learns to track a moving hydrothermal plume and gather samples that significantly improve upon baseline spatial and temporal diversity for use in downstream science tasks.

关键词： Trajectory Sensors Oceans Vehicle dynamics Robot sensing systems Adaptation models Spatiotemporal phenomena Decision making Marine robots Environmental monitoring Mobile robots

来源：评论

学校读者我要写书评

暂无评论

DDD: A PERCEPTUALLY SUPERIOR LOW-RESPONSE-TIME DNN-BASED DECLIPPER

arXiv

引用

arXiv 2024年

作者： Yi, Jayeon Koo, Junghyun Lee, Kyogu Dept. of Electrical Engineering and Computer Science University of Michigan United States Dept. of Intelligence and Information Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Artificial Intelligence Institute Seoul National University Korea Republic of

Clipping is a common nonlinear distortion that occurs whenever the input or output of an audio system exceeds the supported range. This phenomenon undermines not only the perception of speech quality but also downstream processes utilizing the disrupted signal. Therefore, a real-time-capable, robust, and low-response-time method for speech declipping (SD) is desired. In this work, we introduce DDD (Demucs-Discriminator-Declipper), a real-time-capable speech-declipping deep neural network (DNN) that requires less response time by design. We first observe that a previously untested real-time-capable DNN model, Demucs, exhibits a reasonable declipping performance. Then we utilize adversarial learning objectives to increase the perceptual quality of output speech without additional inference overhead. Subjective evaluations on harshly clipped speech shows that DDD outperforms the baselines by a wide margin in terms of speech quality. We perform detailed waveform and spectral analyses to gain an insight into the output behavior of DDD in comparison to the baselines. Finally, our streaming simulations also show that DDD is capable of sub-decisecond mean response times, outperforming the state-of-the-art DNN approach by a factor of six. © 2024, CC BY-NC-SA.

关键词： Deep neural networks

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：