检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2024年第1期25卷 2557-2625页

作者： Chanwoo Park Ernest K. Ryu Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Massachusetts Department of Mathematical Sciences Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea

In this work, we present a novel algorithm design methodology that finds the optimal algorithm as a function of inequalities. Specifically, we restrict convergence analyses of algorithms to use a prespecified subset of inequalities, rather than utilizing all true inequalities, and find the optimal algorithm subject to this restriction. This methodology allows us to design algorithms with certain desired characteristics. As concrete demonstrations of this methodology, we find new state-of-the-art accelerated first-order gradient methods using randomized coordinate updates and backtracking line searches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human intracortical responses to varying electrical stimulation conditions are separable in low-dimensional subspaces

Human intracortical responses to varying electrical stimulat...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Sun, Samantha Levinson, Lila H. Paschall, Courtnie J. Herron, Jeffrey Weaver, Kurt Hauptman, Jason Ko, Andrew Ojemann, Jeffrey Rao, Rajesh P. N. University of Washington Paul G. Allen School of Computer Science & Engineering Department of Bioengineering SeattleWA98195 United States University of Washington Graduate Program in Neuroscience Paul G. Allen School of Computer Science & Engineering SeattleWA98195 United States University of Washington Paul G. Allen School of Computer Science & Engineering Department of Neurological Surgery SeattleWA98195 United States University of Washington Paul G. Allen School of Computer Science & Engineering Department of Radiology SeattleWA98195 United States

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Electrical stimulation is a powerful tool for targeted neurorehabilitation, and recent work in adaptive stimulation where stimulation can be adjusted in real-time has shown promise in improving stimulation outcomes and reducing stimulation-induced side effects. Mapping the relationship between electrical stimulation input and neural activity response can help reveal their interactions and can give us tools to iterate and improve on our stimulation protocols. Here, we introduce methods for identifying low-dimensional subspaces of human intracortical responses to electrical stimulation in invasive electroencephalography. In epilepsy patients (n=4) undergoing clinical monitoring, we applied a stimulation protocol of varying amplitude and frequency in 5-second intervals to capture a range of responses to different stimulation conditions. We characterized these responses using time-frequency spectral power, applied baseline subtraction and outlier removal procedures, and performed principal component analysis across frequencies. We identified that intracortical responses to different stimulation conditions can be represented in a 3-dimensional subspace, accounting for more than 95% of the variance. Using support vector machine classification, we demonstrated separability of intracortical responses in different stimulation conditions across subjects, where this separability was contingent on applying baseline subtraction and outlier removal. Our results represent a first step towards building a predictive model of neural response from stimulation input, an important prerequisite for adaptive closed-loop stimulation for targeted neurorehabilitation. © 2022 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

AV Navigation in 3D Urban Environments with Curriculum-based Deep Reinforcement Learning

AV Navigation in 3D Urban Environments with Curriculum-based...

引用

2023 International Conference on Unmanned Aircraft Systems, ICUAS 2023

作者： Braathen De Carvalho, Kevin De Oliveira, Iure Rosa L. Brandao, Alexandre S. Universidade Federal de Viçosa Nucleus of Specialization in Robotics Department of Electrical Engineering Graduate Program in Computer Science MG Viçosa36570-900 Brazil Federal University of Viçosa Department of Electrical Engineering MG Viçosa Brazil

ISBN: (纸本)9798350310375

Unmanned Aerial Vehicles (UAVs) are widely used in various applications, from inspection and surveillance to transportation and delivery. Navigating UAVs in complex 3D environments is a challenging task that requires robust and efficient decision-making algorithms. This paper presents a novel approach to UAV navigation in 3D environments using a Curriculum-based Deep Reinforcement Learning (DRL) approach. The proposed method utilizes a deep neural network to model the UAV's decision-making process and to learn a mapping from the state space to the action space. The learning process is guided by a reinforcement signal that reflects the performance of the UAV in terms of reaching its target while avoiding obstacles and with energy efficiency. Simulation results show that the proposed method has a positive trade off when compared to the baseline algorithm. The proposed method was able to perform well in environments with a state space size of 22 millions, allowing the usage in big environments or in maps with high resolution. The results demonstrate the potential of DRL for enabling UAVs to operate effectively in complex environments. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Event Argument Extraction with Two-Dimensional Enhanced Fusion Mechanism

引用

computer engineering and Applications 2025年第10期61卷 111-119页

作者： Wang, Luxiang Chen, Yanping Huang, Hui Huang, Ruizhang Qin, Yongbin Engineering Research Center of Ministry of Education for Text Computing and Cognitive Intelligence School of Computer Science and Technology Guizhou University Guiyang550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang550025 China

Addressing the lack of interaction between trigger and arguments, and the lack of interaction within channels in existing studies of event argument extraction, this paper proposes a two-dimensional enhanced fusion mechanism for event argument extraction (W2-ARG) that incorporates a 2D enhanced fusion method. It inserts identifiers on both sides of a trigger word in a sentence, which encodes information about the event type. In the learning process, it is effective to enhance the interaction between trigger and argument, and encode the trigger separately to highlight its information in the sentence. The event argument extraction is implemented as a two-dimensional representation of label prediction. It has the advantage to capture semantic interactions of words at different distances through dilated convolution. Subsequently, a channel attention module is applied to enhance the interactions within the channel to strengthen the information transfer within the channel. Finally, the Laplace operator is utilized to highlight the positional features of event arguments in the semantic space to improve the performance. The proposed model is experimented on the ACE05-EN and ERE-EN datasets. Experimental results show clear performance improvement of the proposed model compared with other event argument extraction methods. © 2025 Journal of computer engineering and Applications Beijing Co., Ltd.;science Press. All rights reserved.

关键词： BERT channel attention event argument extraction Laplace operator sentence planarization representation

来源：评论

学校读者我要写书评

暂无评论

NFT-Based Hydroponic Automated Control Using Adaptive Network-Based Fuzzy Inference System 2

NFT-Based Hydroponic Automated Control Using Adaptive Networ...

引用

2nd International Conference on Robotics, Automation and Artificial Intelligence, RAAI 2022

作者： Surantha, Nico Vincentdo, Vito Bina Nusantara University Binus Graduate Program - Computer Science Jakarta11480 Indonesia Tokyo City University Faculty of Scienc and Engineering Department of Electrical Electronics and Communication Engineering Japan

ISBN: (纸本)9781665459440

The rapid population growth and industrial development in developing countries harm the agricultural sector because many agricultural lands are converted into residential or industrial areas. Applying modern agriculture technologies such as hydroponic could help to overcome the problem. However, hydroponics requires special attention in adjusting the pH and nutrient levels to maximize plant growth, so an automated system is needed to manage the process. In this research, a smart hydroponic system is proposed by applying Adaptive Networkbased Fuzzy Inference System (ANFIS) and Internet-of-Things. The IoT system consists of sensor, actuator, and data processing layer is designed to monitor and control the condition of pH and nutrition of the observed plants. Then, the ANFIS algorithm is designed to control the level of pH and nutrition. The experiment results show that the system can automatically adjust the pH and nutrient levels to the expected range for growing plants, and the fuzzy controller made using ANFIS are more accurate and stable than the fuzzy controller made using Sugeno. This study shows that ANFIS has excellent performance when controlling multiple actuators, as long as the data set has great granularity and well defined. © 2022 IEEE.

关键词： Hydroponics

来源：评论

学校读者我要写书评

暂无评论

An autonomous robotic system for collecting garbage over small water bodies 6

An autonomous robotic system for collecting garbage over sma...

引用

6th International Conference on Automation, Control and Robotics engineering, CACRE 2021

作者： Hasany, Syed Nouman Zaidi, Saniya Shah Sohail, Syed Ahmad Farhan, Muhammad Electrical Engineering Program Habib University Karachi Pakistan Computer Science Program Habib University Karachi Pakistan Electrical and Computer Engineering Program Habib University Karachi Pakistan

ISBN: (纸本)9781665435765

Water pollution is a grave problem requiring utmost attention as it directly affects marine lives. In freshwater ecosystem, for example, lakes and ponds, a major chunk of water garbage is plastic floating on the surface of water which is labor intensive to collect manually. In this paper, we present a novel autonomous robotic system capable of navigating small water bodies and is equipped with computer vision that helps it to detect the garbage. The detection is followed by focusing on an area of interest to determine whether the garbage lies in the scope of robot for collection. Additionally, if WiFi communication is available, the robot has the provision of tracking the detected garbage to determine its path. The design of garbage collection unit of the robot ensures the garbage does not move outward once collected. The robot is tested in two different pools and with plastic bottles as main type of garbage. The results manifest the high degree of control of its locomotion as well as of detection and collection of the bottles. The deep neural network based detector onboard the robot can be retrained after self-collection of appropriate data to detect other types of garbage as well. © 2021 IEEE.

关键词： Plastic bottles

来源：评论

学校读者我要写书评

暂无评论

3D-to-2D-to-3D Conscious Learning

3D-to-2D-to-3D Conscious Learning

引用

2022 IEEE International Conference on Consumer Electronics, ICCE 2022

作者： Weng, Juyang Department of Computer Science and Engineering Michigan State University East LansingMI48824 United States Cognitive Science Program Michigan State University East LansingMI48824 United States Neuroscience Program Michigan State University East LansingMI48824 United States Brain-Mind Institute OkemosMI48864 United States GENISAMA OkemosMI48864 United States

ISBN: (纸本)9781665441544

This is a theoretical paper on conscious learning for thoughts and creativity through general-purpose and autonomous imitation of demonstrations. This conscious learning is end-to-end (3D-to-2D-to-3D) and free from annotations of 2D images and 2D motor images (e.g., a bounding box to be attended to). The conscious learning algorithm directly takes that of the Developmental Networks that has been previously published extensively with rich experimental results. Apparently, humans and animals do this type of fully automated learning daily, but it is unclear a robot can do the same. Recently, [1], [2] presented a theory of conscious learning rooted in emergent universal Turing machines. It appeared to be the first algorithmic level theory of holistic consciousness, other than many papers in the literature about piecemeal consciousness. However, [1], [2] proved only conscious learning in motor-imposed training mode, namely 3D-to-2D taught by 2D motor impositions, free from 2D annotations. This paper fills the challenging gap in [1], [2] so the conscious learning is 3D-to-2D-to-3D (end-to-end) without motor-impositions or computing 'inverse kinematics'. This is a major departure from traditional AI-handcrafting symbolic labels that tend to be brittle (e.g., for driverless cars) and then 'spoon-feeding' pre-collected 'big data'. Autonomous imitations drastically reduce the teaching complexity compared to pre-collected 'big data', especially because no annotations of training data are needed. Furthermore, conscious learning allows creativity beyond what is taught. This work is directly related to consumer electronics because it requires large-scale on-the-fly brainoid chips in future wearable robots/devices for consumers. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

A Multi-phase Deep Learning Approach for Predicting HCC Response to TACE using Complete Computed Tomography

A Multi-phase Deep Learning Approach for Predicting HCC Resp...

引用

2023 IEEE EMBS Special Topic Conference on Data science and engineering in Healthcare, Medicine and Biology, IEEECONF 2023

作者： Chang, Shun Cheng Liu, Chien Fu Misztal, Marta Hsieh, Yi Hsien Lin, Che Taiwan School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Department of Electrical Engineering Ntu Taiwan Center for Computational and Systems Biology Center for Biotechnology Ntu Taiwan Smart Medicine and Health Informatics Program Ntu Taiwan

ISBN: (纸本)9798350383386

In this research study, we compare the predictive performance of two advanced deep learning-based models in order to provide a solution to TACE (Transarterial Chemoembolization) response prediction in HCC (Hepatocellular Carcinoma) patients. Using entire abdominal CT scans enabled a broader perspective available for the model, eliminating the need for segmentation during the preprocessing. Making use of both single-phase and multi-phase CT imaging, we have used DenseNet121 and have obtained an accuracy of 80% for the multi-phase *** Relevance: The ability to predict the effectiveness of TACE treatment prior to its administration makes it possible to provide a better decision-making aid for physicians and patients. © 2023 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cancer Gene Prediction through Aligned Fusion of Multiple PPI Networks Using Graph Transformer Models

Enhancing Cancer Gene Prediction through Aligned Fusion of M...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zebei Han Gufeng Yu Yang Yang Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China

Despite the considerable progress that has been made in cancer research, identifying cancer genes remains a significant challenge due to the intricate nature of the disease. Given the importance of incorporating gene interaction relationships in identifying potential cancer genes, Graph Neural Networks (GNNs) have garnered increasing attention for their ability to model gene associations effectively. Particularly, recent studies have demonstrated the superiority of GNNs in deciphering the knowledge embedded in Protein-Protein Interaction (PPI) networks for cancer gene prediction. However, these studies primarily focused on a single PPI network, overlooking the valuable insights encapsulated within other PPI networks. Additionally, previous endeavors often centered around pan-cancer datasets, neglecting the importance of predicting specific cancer genes. To address these limitations, we present a novel method called MPIT, which employs Graph Transformer Networks (GTNs) to identify specific cancer driver genes. MPIT effectively integrates data from diverse PPI and multi-omics data via the alignment and fusion of gene representations learned from different PPI networks. We collect three distinct cancer cell line datasets to assess the model performance. Our experimental findings demonstrate the superiority of MPIT over the existing methods, achieving the state-of-the-art performance across all three datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RBP-Former: Joint Prediction of RNA-protein Binding Sites on Full-length RNA Transcripts for Multiple RBPs

RBP-Former: Joint Prediction of RNA-protein Binding Sites on...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Yichong Liu, Xiaojian Cheng, Fan Pan, Xiaoyong Yang, Yang Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai200240 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai200240 China

ISBN: (纸本)9798350386226

RNA-binding proteins (RBPs) are essential for gene expression, and the complex RNA-protein interaction mechanisms require analysis of global RNA information. Therefore, accurate prediction of RBP binding sites on full-length RNA transcripts is crucial for understanding these mechanisms and their roles in diseases. While machine learning methods can predict RBP binding to RNA fragments, extending this to full-length transcripts presents challenges due to sequence length and data imbalance. In this paper, we introduce RBP-Former, a binding site joint prediction model designed specifically for full-length RNA transcripts that can be used for multiple RBPs. This model processes information at both coarse and fine-grained levels to fully exploit sequence data and its interactions with multiple RBPs. We develop multi-level imbalance learning strategies, achieving favorable results on imbalanced data. Our method outperforms existing methods in predicting binding sites on full-length RNA transcripts for multiple RBPs, demonstrating its effectiveness in handling imbalanced label and sample distributions. © 2024 IEEE.

关键词： Binding sites

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：