检索结果-内蒙古大学图书馆

36th International Florida Artificial Intelligence research Society Conference, FLAIRS-36 2023

作者： Licato, John Fields, Logan Hollis, Brayden Lab Department of Computer Science and Engineering University of South Florida United States Information Directorate Air Force Research Lab United States

Large pre-trained language models (LMs) such as GPT-3 Codex are able to generate code remarkably well given prompts of natural language text. But if we want to use such LMs to generate code compatible with a specific API or library (e.g., an API which provides the environments in which certain rules, laws, or orders are to be carried out), the amount of computational and data resources required to fine-tune such models can be cost prohibitive to most organizations. Given these practical limitations, is it possible to utilize these massive codegeneration LMs to write code compatible with a given API? We develop an algorithm that selects code examples using a smaller LM trained to predict which features of an API are likely to be used in the resulting code, which is a simpler problem than actually generating the code. The selected examples are then used to build a prompt for the larger LM, which in turn generates the final code. We demonstrate our results on a benchmark dataset derived from the collectible card game "Magic: the Gathering," and obtain state-of-the-art results. © 2023 by the authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

The Truncated Cone Effect in AFM Nanoindentation on Soft Materials

引用

Micro and Nanosystems 2023年第2期15卷 153-158页

作者： Kontomaris, Stylianos-Vasileios Malamou, Anna Department of Research and Development BioNanoTec LTD Nicosia Cyprus Faculty of Engineering and Architecture Metropolitan College Athens Greece Radar Systems and Remote Sensing Lab of the School of Electrical & Computer Engineering of National Technical University of Athens Athens Greece

Background: Atomic Force Microscopy (AFM) nanoindentation is the principal method for the characterization of soft materials at the nanoscale. In most cases, pyramidal tips are used and approximated to perfect cones. However, the extended use of the AFM tip may alter its sharp-ness. Objective: In many cases, a truncated cone shape is appropriate for tip modeling. In this technical note, the equation that relates the force with the indentation depth when indenting an elastic half-space using a truncated cone is derived. Methods: The nanoindentation equation for a truncated cone tip is derived using the fundamental differential equation that relates the sample’s contact stiffness with Young’s modulus. Results: When fitting Sneddon’s equation (which is valid for a perfect cone) on data obtained using a truncated cone-shaped AFM tip, the results show a ‘pseudo-softening’ behavior. Conclusion: The AFM tip's sharpness in nanoindentation experiments is a crucial parameter for obtaining the correct mechanical patterns of unknown samples. © 2023 Bentham Science Publishers.

关键词： Biological materials

来源：评论

学校读者我要写书评

暂无评论

Reducing the Computational Cost of Transformers for Person Re-identification

Reducing the Computational Cost of Transformers for Person R...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Wang, Wen Lin, Zheyuan Ji, Shanshan Li, Te Gu, Jason Wan, Minhong Zhang, Chunlong Research Center for Intelligent Robotics Zhejiang Lab Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China Dalhousie University Department of Electrical and Computer Engineering Canada

ISBN: (纸本)9798350325706

Transformer-based visual technologies have witnessed remarkable progress in recent years, and person re-identification (ReID) is one of the active research areas that adopts transformers to improve the performance. However, a major challenge of applying transformers to ReID is the high computational cost, which hinders the real-time deployment of such methods. To address this issue, this paper proposes two simple yet effective techniques to reduce the computation of transformers for ReID. The first technique is to eliminate the invalid patches that do not contain any person information, thereby reducing the number of tokens fed into the transformer. Considering that computational complexity is quadratic with respect to input tokens, the second technique partitions the image into multiple windows, applies separate transformers to each window, and merges class tokens from each window, which can reduce the complexity of the self-attention mechanism. By combining these two techniques, our proposed method reduces the SOTA baseline model by 12.2% FLOPs, while slightly improving the rank-1 accuracy and only sacrificing 1.1% mAP on DukeMTMC-ReID dataset. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A survey on hyperspectral image restoration: from the view of low-rank tensor approximation

引用

Science China(Information Sciences) 2023年第4期66卷 33-63页

作者： Na LIU Wei LI Yinjian WANG Ran TAO Qian DU Jocelyn CHANUSSOT School of Information and Electronics and Beijing Key Laboratory of Fractional Signals and Systems Beijing Institute of Technology Department of Electrical and Computer Engineering Mississippi State University GIPSA-Lab University of Grenoble Alpes Aerospace Information Research Institute Chinese Academy of Sciences

The ability to capture fine spectral discriminative information enables hyperspectral images(HSIs) to observe, detect and identify objects with subtle spectral discrepancy. However, the captured HSIs may not represent the true distribution of ground objects and the received reflectance at imaging instruments may be degraded, owing to environmental disturbances, atmospheric effects, and sensors' hardware limitations. These degradations include but are not limited to complex noise, heavy stripes, deadlines,cloud/shadow occlusion, blurring and spatial-resolution degradation, etc. These degradations dramatically reduce the quality and usefulness of HSIs. Low-rank tensor approximation(LRTA) is such an emerging technique, having gained much attention in the HSI restoration community, with an ever-growing theoretical foundation and pivotal technological innovation. Compared to low-rank matrix approximation(LRMA),LRTA characterizes more complex intrinsic structures of high-order data and owns more efficient learning abilities, being established to address convex and non-convex inverse optimization problems induced by HSI restoration. This survey mainly attempts to present a sophisticated, cutting-edge, and comprehensive technical survey of LRTA toward HSI restoration, specifically focusing on the following six topics: denoising, fusion,destriping, inpainting, deblurring, and super-resolution. For each topic, state-of-the-art restoration methods are introduced, with quantitative and visual performance assessments. Open issues and challenges are also presented, including model formulation, algorithm design, prior exploration, and application concerning the interpretation requirements.

关键词： hyperspectral image image restoration low-rank tensor approximation multisource fusion remote sensing

来源：评论

学校读者我要写书评

暂无评论

Design of a LiFi System for Short-Distance Communications 14

Design of a LiFi System for Short-Distance Communications

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Devrani, Ashutaosh Darshan, Divya Vidyarthi, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Electronics & Communication Engineering Dehradun India Department of Electronics & Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350335095

LiFi technology introduces Visible Light communication that uses light as a source to deliver high data speed, which is much greater than that of Wi-Fi. The research paper proposes a communication system that utilizes Light-Fidelity (Li-Fi) technology for short-range wireless communication. The article begins with an introduction to Li-Fi technology and its advantages over traditional wireless communication systems. The paper also highlights the limitations of Li-Fi, including its short range. The authors then present their proposed approach, which includes a transmitter section, a receiver section, and two modes of operation (text and audio). Additionally, the system consists of two applications to demonstrate its functionality: an SOS application and a device on/off application. The paper concludes with a detailed explanation of how the proposed system works and its potential applications in various fields. © 2023 IEEE.

关键词： Visible light communication

来源：评论

学校读者我要写书评

暂无评论

Single Ultra-Wideband Anchor Based Blind Spot Pedestrian Localization in a Moving Vehicle

Single Ultra-Wideband Anchor Based Blind Spot Pedestrian Loc...

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Jee, Ohgeun Choi, JungHun Ham, Doyoung Kim, Check Kim, Seong-Cheol Seoul National University Department of Electrical and Computer Engineering Seoul Korea Republic of EP Acoustics & Vibration Research Lab Hyundai Motor Company Hwaseong Korea Republic of

ISBN: (纸本)9798331510756

Detecting pedestrians in blind spots is a critical component of ensuring vehicle safety, especially in urban environments. This paper presents a pedestrian localization system utilizing a single ultra-wideband (UWB) anchor installed in a moving vehicle. The proposed system leverages UWB's robust ranging capabilities to estimate the position of a pedestrian carrying a UWB-enabled smartphone, even in Non-Line-of-Sight conditions. The focus is on analyzing the UWB ranging protocol performance when the anchor is in motion and how the position of pedestrians can be estimated in both two-ranging and three-ranging point scenarios. Experiments are conducted at various vehicle speeds and demonstrated the effectiveness of the approach. © 2025 IEEE.

关键词： Ultra-wideband (UWB)

来源：评论

学校读者我要写书评

暂无评论

Thermometer: Towards Universal Calibration for Large Language Models 41

Thermometer: Towards Universal Calibration for Large Languag...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Shen, Maohao Das, Subhro Greenewald, Kristjan Sattigeri, Prasanna Wornell, Gregory Ghosh, Soumya Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge United States MIT-IBM Watson AI Lab IBM Research United States

We consider the issue of calibration in large language models (LLM). Recent studies have found that common interventions such as instruction tuning often result in poorly calibrated LLMs. Although calibration is well-explored in traditional applications, calibrating LLMs is uniquely challenging. These challenges stem as much from the severe computational requirements of LLMs as from their versatility, which allows them to be applied to diverse tasks. Addressing these challenges, we propose THERMOMETER, a calibration approach tailored to LLMs. THERMOMETER learns an auxiliary model, given data from multiple tasks, for calibrating a LLM. It is computationally efficient, preserves the accuracy of the LLM, and produces better-calibrated responses for new tasks. Extensive empirical evaluations across various benchmarks demonstrate the effectiveness of the proposed method. Copyright 2024 by the author(s)

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Integrated Analysis of Remote Sensing Imagery for Geological Characterization of Volcanic Terrain: A Focus on Lithology, Geomorphology, and Structure 15

Integrated Analysis of Remote Sensing Imagery for Geological...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Nath, Somalin Shekhar, Sushant Gusain, Raj Vidyarthi, Anurag Prakash, Rishi Gowri, R. Indian Institute of Technology National Centre for Geodesy Kanpur India Propagation Research Lab Department of Electronics & Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350370249

This study employs advanced radar imaging techniques to conduct a comprehensive analysis of a volcanic terrain, unraveling its geological intricacies through the lenses of lithology, geomorphology, and structural features. The research harnesses the power of synthetic aperture radar (SAR) data to provide unprecedented insights into the Earth's surface, facilitating a holistic understanding of the volcanic landscape. The investigation begins with the utilization of radar backscatter data to discern lithological variations within the volcanic terrain. By correlating radar signatures with known lithological compositions, the study aims to delineate distinct geomorphological units and unveil the spatial distribution of volcanic materials. Additionally, the analysis extends to geomorphological features, employing radar imagery to delineate landforms associated with volcanic activity such as lava flows, calderas, and volcanic cones. Furthermore, the study delves into the structural characteristics of the volcanic terrain, employing radar interferometry techniques to detect and quantify ground deformation associated with identification of fault lines, fractures, and other structural anomalies that contribute to the overall geological context. The integration of these diverse datasets results in a multidimensional understanding of the volcanic landscape, offering valuable insights for geological mapping, hazard assessment, and resource management. The findings of this research contribute to advancing the field of remote sensing and geological exploration, highlighting the efficacy of radar imagery in unraveling the geological complexity of volcanic terrains. Such knowledge is crucial for informed decision-making in areas prone to volcanic activity, ultimately enhancing our ability to mitigate geological risks and promote sustainable development in volcanic regions. © 2024 IEEE.

关键词： Geomorphology Synthetic Aperture Radar Tectonic Structures Volcanic Terrain

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Malware Detection and Classification in Encrypted TLS Traffic 1

引用

Second International Conference on Security, Privacy and Data Analytics, ISPDA 2022

作者： Kashyap, Himanshu Pais, Alwyn Roshan Kondaiah, Cheemaladinne Information Security Research Lab Department of Computer Science and Engineering National Institute of Technology Karnataka Karnataka Surathkal575025 India

ISBN: (数字)9789819935697

ISBN: (纸本)9789819935680

Malware has become a significant threat to Internet users in the modern digital era. Malware spreads quickly and poses a significant threat to cyber security. As a result, network security measures play an important role in countering these cyber threats. Existing malware detection techniques are unable to detect them effectively. A novel Ensemble Machine Learning (ML)-based malware detection technique from Transport Layer Security (TLS)-encrypted traffic without decryption is proposed in this paper. The features are extracted from TLS traffic. Based on the extracted features, malware detection is performed using Ensemble ML algorithms. The benign and malware file datasets are created using features extracted from TLS traffic. According to the experimental results, the 65 new extracted features perform well in detecting malware from encrypted traffic. The proposed method achieves an accuracy of 99.85% for random forest and 97.43% for multiclass classification for identifying malware families. The ensemble model achieved an accuracy of 99.74% for binary classification and 97.45% for multiclass classification. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Sound of Reason: Using AI to build a Digital Twin after the Kanon of Pythagoras in school settings 10

Sound of Reason: Using AI to build a Digital Twin after the ...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Anthis, Zach Basiakoulis, Alexandros Efstathiou, Kyriakos Efstathiou, Marianna Department of Communication Culture and Media London United Kingdom Aristotle University of Thessaloniki Laboratory for Machine Tools and Manufacturing Engineering Department of Mechanical Engineering Thessaloniki Greece Cyprus University of Technology Digital Heritage Research Lab Department of Electrical Engineering Computer Engineering and Informatics Limassol Cyprus

ISBN: (纸本)9798331520861

This paper presents ongoing work on kanON, an AI-driven EdTech tool designed to foster interactive learning and support Digital Cultural Heritage (DCH) preservation. kanON facilitates the digital reconstruction of the infamous Pythagorean monochord, by allowing users to seamlessly manipulate parameters such as origin (location and epoch), materials, and shape/dimensions. Through the integration of Machine Learning (ML) algorithms, the tool predicts missing archaeological data and generates real-time 3D renderings based on user input, accompanied by corresponding confidence metrics. A mixed-methods (pilot) study was conducted in classroom environments to evaluate its educational impact via quantitative Likert scale assessments and qualitative content analysis of educator feedback. Preliminary results demonstrate high levels of student engagement and reflect positive educator responses, highlighting its potential to enhance the in-class accessibility and understanding of complex historical concepts, as well as to enable the preservation and exploration of cultural artifacts through digital means. Future work will focus on refining kanON and expanding its applicability within both educational and DCH contexts, by introducing the capability of outputting a fully operational digital twin, that integrates mixed reality functionalities. The idea is to enable users to later engage with their (personalized) model dynamically (e.g., readjusting string length and tension), thus allowing them to produce different soundscapes in real-time. This advancement aims to deepen the pedagogical impact by merging tactile interaction with visual and auditory feedback, further enhancing the educational experience via immersive, experiential learning. © 2024 IEEE.

关键词： Adversarial machine 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：