检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Berberette, Elijah Hutchins, Jack Sadovnik, Amir Department of Electrical Engineering and Computer Science University of Tennessee Knoxville United States Cyber Resilience and Intelligence Division Oak Ridge National Lab Oak Ridge United States

In recent years, large language models (LLMs) have become incredibly popular, with ChatGPT for example being used by over a billion users. While these models exhibit remarkable language understanding and logical prowess, a notable challenge surfaces in the form of"hallucinations." This phenomenon results in LLMs outputting misinformation in a confident manner, which can lead to devastating consequences with such a large user base. However, we question the appropriateness of the term"hallucination" in LLMs, proposing a psychological taxonomy based on cognitive biases and other psychological phenomena. Our approach offers a more fine-grained understanding of this phenomenon, allowing for targeted solutions. By leveraging insights from how humans internally resolve similar challenges, we aim to develop strategies to mitigate LLM hallucinations. This interdisciplinary approach seeks to move beyond conventional terminology, providing a nuanced understanding and actionable pathways for improvement in LLM reliability. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LRCB: A Comprehensive Benchmark Evaluation of Reference-free Lossless Compression Tools for Genomics Sequencing Long Reads Data

LRCB: A Comprehensive Benchmark Evaluation of Reference-free...

引用

Data Compression Conference (DCC)

作者： Hui Sun Huidong Ma Yingfeng Zheng Haonan Xie Meng Yan Cheng Zhong Xiaoguang Liu Gang Wang Nankai-Baidu Joint Lab Parallel and Distributed Software Technology Lab College of Computer Science Nankai University Tianjin China School of Electrical Engineering Guangxi University Nanning China School of Computer Electronics and Information Guangxi University Nanning China

ISBN: (数字)9798350385878

ISBN: (纸本)9798350385885

The advancement of long reads sequencing technologies has led to a significant increase in biological sequencing big data. Although several reference-free compressors are available for saving long reads data storage space, choosing the suitable one is challenging due to the shortage of thorough and systematic evaluations of their lossless compression effectiveness, both dedicated and general-purpose. In this study, we performed benchmark examinations on 30 compressors, including 11 specialized for long reads and 19 general-purpose ones, using 31 real-world datasets with differing sequencing platforms, species, and lengths. Each lossless compressor was evaluated on 13 performance measures, including compression strength, compression robustness, as well as time and peak memory required for compression and decompression. Additionally, for future long reads data compressors, we outlined investigation directions with consideration for privacy-sensitive sequences data security, hardware parallel acceleration, parameter tuning framework, and system hardware-algorithm integration design. We summarized the results as the Long Reads Compression Benchmark, available at https://***/fahaihi/LRCB.

关键词： Sequential analysis Systematics Memory management Benchmark testing Compressors Loss measurement Time measurement

来源：评论

学校读者我要写书评

暂无评论

Stochastic Sensitivity Regularized Autoencoder for Robust Feature Learning 21

Stochastic Sensitivity Regularized Autoencoder for Robust Fe...

引用

21st IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2022

作者： Zhang, Jianjun Wang, Ting Ng, Wing W. Y. Pedrycz, Witold Kwong, Sam School of Computer Science and Engineering South China University of Technology Guangzhou Guangdong China School of Medicine South China University of Technology Guangzhou First People's Hospital Department of Radiology Guangdong Guangzhou China School of Computer Science and Engineering South China University of Technology Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Guangzhou Guangdong China University of Alberta Department of Electrical and Computer Engineering EdmontonAB Canada Hong Kong City University Department of Computer Science Hong Kong Hong Kong

ISBN: (纸本)9781665490849

We present a new regularized autoencoder for robust feature learning. The regularization, implying stochastic sensitivity, is defined as the sum of entries of the absolute covariance matrix of the output perturbation at each layer of the autoencoder. The advantages of the stochastic sensitivity regularization are two-fold. Firstly, we show that the classical Frobenius norm regularization effectively enforces the network to be insensitive to input perturbation and that the Frobenius norm regularization is a special case of the proposed stochastic sensitivity regularization which enables the proposed method to train an autoencoder for robust feature learning. Secondly, we also show that the stochastic sensitivity regularization attempts to drive the network to learn a set of decorrelated feature maps which removes redundant information and thus improves generalization capabilities. These two properties enable the autoencoder to learn a set of robust and diverse feature maps. Finally, the efficacy and the robustness of the proposed regularization method are confirmed a nd quantified by comparing it against existing regularized auto encoders over a range of tasks. © 2022 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Coded Distributed Computing For Vehicular Edge Computing With Dual-Function Radar Communication

Coded Distributed Computing For Vehicular Edge Computing Wit...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Hoai Linh Nguyen Thi Hung Le Hoang Nguyen Cong Luong Tien Hoa Nguyen Sa Xiao Junjie Tan Dusit Niyato School of Electrical and Electronic Engineering Hanoi University of Science and Technology Vietnam Faculty of Computer Science PHENIKAA University Vietnam National Key Lab. of Wireless Communications University of Electronic Science and Technology of China China Kashi Institute of Electronics and Information Industry Kashi China Department of Electrical and Computer Engineering Western University London ON Canada School of Computer Science and Engineering Nanyang Technological University Singapore

In this paper, we propose a coded distributed computing (CDC)-based vehicular edge computing (VEC) framework. The framework allows a task vehicle (TV) equipped with the dual-function radar communication (DFRC) to offload its computing tasks to the nearby service vehicles (SVs) using the (m, k) maximum distance separable (MDS). The framework is thus able to address the straggler effect that is typically caused by the high mobility of the vehicles. We then formulate an optimization problem for the TV that aims to i) minimize the overall computing latency, ii) minimize the offloading cost, and iii) maximize the radar range subject to the connection duration. For this, we optimize the MDS parameters, i.e., the number of selected SVs (m) and the number of subtasks for coding (k), and the fractions of power allocated to the radar and communication functions. Under the high dynamic vehicular environment, the uncertainty of the SVs’ computing resource and networking resources, we propose a deep reinforcement learning (DRL) algorithm based on Double Deep Q-Network (DDQN) to solve the TV’s problem. To further improve the performance, we propose to incorporate a parameter norm penalty in the loss function. Simulation results show that the proposed DDQN algorithm outperforms both the DQN algorithm and the non-learning algorithm in terms of computation latency, radar range, and offloading cost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep treatment-adaptive network for causal inference

Deep treatment-adaptive network for causal inference

引用

作者： Li, Qian Wang, Zhichao Liu, Shaowu Li, Gang Xu, Guandong School of Electrical Engineering Computing and Mathematical Sciences Curtin University Perth Australia School of Electrical Engineering and Telecommunications University of New South Wales Sydney Australia Data Science and Machine Intelligence Lab School of Computer Science University of Technology Sydney Sydney Australia Centre for Cyber Security Research and Innovation Deakin University GeelongVIC3216 Australia

Causal inference is capable of estimating the treatment effect (i.e., the causal effect of treatment on the outcome) to benefit the decision making in various domains. One fundamental challenge in this research is that the treatment assignment bias in observational data. To increase the validity of observational studies on causal inference, representation-based methods as the state-of-the-art have demonstrated the superior performance of treatment effect estimation. Most representation-based methods assume all observed covariates are pre-treatment (i.e., not affected by the treatment) and learn a balanced representation from these observed covariates for estimating treatment effect. Unfortunately, this assumption is often too strict a requirement in practice, as some covariates are changed by doing an intervention on treatment (i.e., post-treatment). By contrast, the balanced representation learned from unchanged covariates thus biases the treatment effect estimation. In light of this, we propose a deep treatment-adaptive architecture (DTANet) that can address the post-treatment covariates and provide a unbiased treatment effect estimation. Generally speaking, the contributions of this work are threefold. First, our theoretical results guarantee DTANet can identify treatment effect from observations. Second, we introduce a novel regularization of orthogonality projection to ensure that the learned confounding representation is invariant and not being contaminated by the treatment, meanwhile mediate variable representation is informative and discriminative for predicting the outcome. Finally, we build on the optimal transport and learn a treatment-invariant representation for the unobserved confounders to alleviate the confounding bias. © 2022, The Author(s).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

ASFM: Augmented Social Force Model for Legged Robot Social Navigation

ASFM: Augmented Social Force Model for Legged Robot Social N...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Sebastian Ægidius Rodrigo Chacón-Quesada Andromachi Maria Delfaki Dimitrios Kanoulas Yiannis Demiris Department of Computer Science Robot Perception and Learning Lab University College London Gower Street London UK Department of Electrical and Electronic Engineering Personal Robotics Lab Imperial College London London UK Department of Computer Science AI Centre UCL and the Archimedes/Athena RC Greece

ISBN: (数字)9798350373578

ISBN: (纸本)9798350373585

Social navigation in robotics primarily involves guiding mobile robots through human-populated areas, with pedestrian comfort balanced with efficient path-finding. Although progress has been seen in this field, a solution for the seamless integration of robots into pedestrian settings remains elusive. In this paper, a social force model for legged robots is developed, utilizing visual perception for human localization. In particular, an augmented social force model is introduced, incorporating refined interpretations of repulsive forces and avoidance behaviors based on pedestrian actions, alongside a target following mechanism. Experimental evaluation on a quadruped robot, through various scenarios, including interactions with oncoming pedestrians, crowds, and obstructed paths, demonstrates that the proposed augmented model significantly improves upon previous baseline methods in terms of chosen path length, average velocity, and time-to-goal for effective and efficient social navigation. The code isopen-source, while video demonstrations can be found on the project’s webpage: https://***/ASFM/

关键词： Legged locomotion Location awareness Pedestrians Codes Navigation Force Humanoid robots Quadrupedal robots Visual perception

来源：评论

学校读者我要写书评

暂无评论

Circular LPDA Array Design for Efficient Microwave Treatment of Palm Weevil Infestation

Circular LPDA Array Design for Efficient Microwave Treatment...

引用

Microwave, Antennas & Circuits (ICMAC), International Conference on

作者： Asad Masood Muhammad Ali Zubair Mehmood Zunair Ahmad Faizan Ramzan Rifaqat Hussain Muhammad Qasim Mehmood Department of Electrical Engineering MicroNano Lab Information Technology University (ITU) Lahore Pakistan Department of Electrical Engineering Hafiz Hayat Campus University of Gujrat (UOG) Gujrat Pakistan Antenna and Electromagnetics Research Group School of Electronic Engineering and Computer Science Queen Mary University of London London UK

ISBN: (数字)9798331518424

ISBN: (纸本)9798331518431

The Red Palm Weevil (RPW) is one of the most harmful pests to palms globally. Various strategies have been used to killing this pest which includes Phyto sanitation, chemical pesticides, pheromone traps, and biological management, however the use of microwave energy for heat disinfestation appears to be a potential alternative. This article describes the method to develop a microwave antenna system that uses a circular array of Log-Periodic Dipole Antennas (LPDAs) to disinfect date palms. The simulation results are performed in FDTD solver. The proposed antenna covers a wide frequency range spanning 1.3 GHz − 3 GHz. The reflection coefficient is well below to −10 dB over the whole resonant frequency band, having a peak gain of 9.5 dBi for a single antenna. A circular LPDA antenna array is proposed to perform the thermal analysis for particular area of the palm tree to mitigate the RPW.

关键词： Electromagnetic heating Microwave integrated circuits Dipole antennas Resonant frequency Microwave theory and techniques Microwave circuits Microwave antenna arrays Thermal analysis Reflection coefficient Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs

arXiv

引用

arXiv 2024年

作者： Lai, Yao Liu, Jinxin Pan, David Z. Luo, Ping Department of Computer Science The University of Hong Kong Hong Kong Machine Intelligence Lab Westlake University Zhejiang Hangzhou China Department of Electrical & Computer Engineering The University of Texas at Austin AustinTX United States

Across a wide range of hardware scenarios, the computational efficiency and physical size of the arithmetic units significantly influence the speed and footprint of the overall hardware system. Nevertheless, the effectiveness of prior arithmetic design techniques proves inadequate, as it does not sufficiently optimize speed and area, resulting in a reduced processing rate and larger module size. To boost the arithmetic performance, in this work, we focus on the two most common and fundamental arithmetic modules: adders and multipliers. We cast the design tasks as single-player tree generation games, leveraging reinforcement learning techniques to optimize their arithmetic tree structures. Such a tree generation formulation allows us to efficiently navigate the vast search space and discover superior arithmetic designs that improve computational efficiency and hardware size within just a few hours. For adders, our approach discovers designs of 128-bit adders that achieve Pareto optimality in theoretical metrics. Compared with the state-of-the-art PrefixRL, our method decreases computational delay and hardware size by up to 26% and 30%, respectively. For multipliers, when compared to RL-MUL, our approach increases speed and reduces size by as much as 49% and 45%. Moreover, the inherent flexibility and scalability of our method enable us to deploy our designs into cutting-edge technologies, as we show that they can be seamlessly integrated into 7nm technology. We believe our work will offer valuable insights into hardware design, further accelerating speed and reducing size through the refined search space and our tree generation methodologies. See our introduction video at ***/ArithmeticTree. Codes are released at ***/laiyao1/ArithmeticTree. © 2024, CC BY-NC-SA.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

HeadSonic: Usable Bone Conduction Earphone Authentication via Head-conducted Sounds

引用

IEEE Transactions on Mobile Computing 2025年

作者： He, Zhixiang Chen, Jing He, Kun Gu, Yangyang Deng, Qiyi Zhang, Zijian Du, Ruiying Zhao, Qingchuan Wu, Cong Wuhan University School of Cyber Science and Engineering Wuhan430072 China State Key Lab of Intelligent Transportation System Beijing China Beijing Institute of Technology School of Cyberspace Science and Technology China City University of Hong Kong Department of Computer Science Hong Kong The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong

Earables (ear wearables) are rapidly emerging as a new platform encompassing a diverse of personal applications, prompting the development of authentication schemes to protect user privacy. Existing earable authentication methods are all specifically designed for air-conduction earphones, which are not suited for bone conduction earphones (BCEs) that rely on bone conduction mechanisms. In this paper, we propose HeadSonic, a usable BCE authentication system based on the unique head-conducted sounds, which can be acquired when the user wears the BCE device. Specifically, the system emits a millisecond-level sound to initiate the authentication session. The signal captured by the BCE microphone is propagated through the user’s head, which is unique in density, geometry, and bone-tissue ratio. It operates implicitly, while maintaining robustness across different behaviors. Extensive experiments involving 60 subjects demonstrate that HeadSonic achieves a commendable balanced accuracy of 96.59%, proving its efficacy and resilience against replay and synthesis attacks. Our dataset and source codes are available at https://***/r/HeadSonic1CE4. © 2025 IEEE. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Location-aware green energy availability forecasting for multiple time frames in smart buildings: The case of Estonia

引用

Measurement: Sensors 2023年 25卷

作者： Hatamian, Mehdi Panigrahi, Bivas Dehury, Chinmaya Kumar Independent researcher Tehran Iran Department of Refrigeration Air Conditioning & Energy Engineering National Chin-Yi University of Technology Taichung41170 Taiwan Mobile & Cloud Lab Institute of Computer Science University of Tartu Tartu50090 Estonia

In recent years, renewable energies (RE) have gained more attention as they provide clean and sustainable energy. Affordable and clean energy is one of the sustainable development goals (SDG-7) of the UN. Solar energy is considered to be one of the world's most abundant renewable natural resources and can certainly contribute to meeting the SDGs. The photovoltaic (PV) panel converts solar energy into electrical energy without emitting greenhouse gases. PV panels generate power based on solar radiation received at a specific location over time. As a result, PV output power is difficult to forecast. Many public/private institutes generate green energy, and balancing demand and supply is vital. This research aims to forecast PV system output power based on weather and derived features using different machine learning (ML) models. A best-fitting model is developed based on the data to accurately predict output power. Moreover, different performance metrics are used to compare and evaluate the accuracy under different ML models such as Random Forest (RF), Extreme Gradient Boosting (XGBoost), K-Nearest Neighbour (KNN), Multilayer Perceptron (MLP) and Support Vector Regression (SVR). Compared to the recent research, our results demonstrate that the obtained prediction accuracy is superior, with performance gains reaching up to 14% (R-squared) in the case of the RF model and 25% (MAPE) in the case of the SVR model. The comparison result inferred a similar performance when RF and XGBoost were applied. On the other hand, the ML models MLP, SVR, and KNN give a similar prediction pattern. © 2022 The Authors

关键词： Solar panels

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：