检索结果-内蒙古大学图书馆

An evaluation of platforms for processing camera-trap data using artificial intelligence

METHODS IN ECOLOGY AND EVOLUTION 2023年第2期14卷 459-477页

作者： Velez, Juliana McShea, William Shamon, Hila Castiblanco-Camacho, Paula J. Tabak, Michael A. Chalmers, Carl Fergus, Paul Fieberg, John Univ Minnesota Dept Fisheries Wildlife & Conservat Biol St Paul MN 55108 USA Smithsonians Natl Zoo & Conservat Biol Inst Conservat Ecol Ctr Front Royal VA 22630 USA Univ Los Andes Dept Ciencias Biol Bogots Colombia Quantitat Sci Consulting LLC Toronto ON Canada Liverpool John Moores Univ Sch Comp Sci & Math Liverpool Merseyside England

Camera traps have quickly transformed the way in which many ecologists study the distribution of wildlife species, their activity patterns and interactions among members of the same ecological community. Although they provide a cost-effective method for monitoring multiple species over large spatial and temporal scales, the time required to process the data can limit the efficiency of camera-trap surveys. Thus, there has been considerable attention given to the use of artificial intelligence (AI), specifically deep learning, to help process camera-trap data. Using deep learning for these applications involves training algorithms, such as convolutional neural networks (CNNs), to use particular features in the camera-trap images to automatically detect objects (e.g. animals, humans, vehicles) and to classify species. To help overcome the technical challenges associated with training CNNs, several research communities have recently developed platforms that incorporate deep learning in easy-to-use interfaces. We review key characteristics of four AI platforms-Conservation AI, MegaDetector, MLWIC2: Machine Learning for Wildlife image Classification and Wildlife Insights-and two auxiliary platforms-Camelot and Timelapse-that incorporate AI output for processing camera-trap data. We compare their software and programming requirements, AI features, data management tools and output format. We also provide R code and data from our own work to demonstrate how users can evaluate model performance. We found that species classifications from Conservation AI, MLWIC2 and Wildlife Insights generally had low to moderate recall. Yet, the precision for some species and higher taxonomic groups was high, and MegaDetector and MLWIC2 had high precision and recall when classifying images as either 'blank' or 'animal'. These results suggest that most users will need to review AI predictions, but that AI platforms can improve efficiency of camera-trap-data processing by allowing users to filt

关键词： artificial intelligence camera traps computer vision data processing deep learning image classification remote sensing review

来源：评论

学校读者我要写书评

暂无评论

You Only Get One-Shot: Eavesdropping Input images to neural Network by Spying SoC-FPGA Internal Bus 23

You Only Get One-Shot: Eavesdropping Input Images to Neural ...

引用

18th International Conference on Availability, Reliability and Security (ARES)

作者： Thu, May Myat Real, Maria Mendez Pelcat, Maxime Besnier, Philippe Nantes Univ Univ Rennes CNRS INSA RennesIETRUMR 6164 F-35000 Rennes France

ISBN: (纸本)9798400707728

Deep learning is currently integrated into edge devices with strong energy consumption and real-time constraints. To fulfill such requirements, high hardware performances can be provided by hardware acceleration of heterogeneous integrated circuits (IC) such as System-on-Chip (SoC)-field programmable gate arrays (FPGAs). With the rising popularity of hardware accelerators for artificial intelligence (AI), more and more neural networks are employed in a variety of domains, involving computer vision applications. Autonomous driving, defence and medical domains are well-known examples from which the latter two in particular require processing sensitive and private data. Security issues of such systems should be addressed to prevent the breach of privacy and unauthorised exploitation of systems. In this paper, we demonstrate a confidentiality vulnerability in a SoC-based FPGA binarized neural network (BNN) accelerator implemented with a recent mainstream framework, FINN, and successfully extract the secret BNN input image by using an electromagnetic (EM) side-channel attack. Experiments demonstrate that with the help of a near-field magnetic probe, an attacker can, with only one inference, directly retrieve sensitive information from EM emanations produced by the internal bus of the SoC-FPGA. Our attack reconstructs SoC-FPGA internal images and recognizes a handwritten digit image with an average accuracy of 89% using a non-retrained MNIST classifier. Such vulnerability jeopardizes the confidentiality of SoC-FPGA embedded AI systems by exploiting side-channels that withstand the protection of chip I/Os through cryptographic methods.

关键词： Electromagnetic Side-Channel Near field neural Network image processing System-on-Chip Field Programmable Gate Array On-chip Communication Bus

来源：评论

学校读者我要写书评

暂无评论

Research and experiment on pepper recognition based on improved convolutional neural network algorithm

引用

Discover artificial Intelligence 2025年第1期5卷 1-13页

作者： Zhang, Liyong Qiao, Zhanquan Zhang, Shougang Wang, Guanbo Yu, Feipeng Fan, Ruili Tang, Juan Wang, Wenxiang Wang, Jing Xia, Taotao Jiang, Yehu Wei, Fangkun Niu, Yutian Anhui Science and Technology University Chuzhou233100 China JJiangsu Zhonggong High-end Equipment Research Institute Co. Ltd. Taizhou225300 China China Academy of Machinery Zhengzhou Research Institute of Mechanical Engineering Co. Ltd. Zhengzhou450000 China Anhui Zhongxin S & T Co. Ltd. Chuzhou233100 China Anhui VSEE Optoelectronic Technology Co. Ltd. Hefei231200 China

Pepper is a common vegetable, with a wide range of applications and market demand. Pepper recognition is an important task when harvesting peppers by a robot. Due to the fact that chili peppers are usually planted very densely, the fruits often grow in clusters. As a result, identifying and locating peppers that are obscured by other peppers, branches, and leaves becomes a challenging task. In this task, the robot needs to overcome visual obstacles in order to accurately detect and locate the target pepper. This paper proposes a pepper recognition method based on the improved You Only Look Once version 3 (YOLOv3) convolutional neural network. By adding Res2Net backbone into the feature extraction network of YOLOv3, the extraction performance is improved, and the accuracy and efficiency of pepper identification are also improved. In this study, large-scale pepper image data sets were used for training and testing, and the generalizability and robustness of the model were improved through data enhancement and transfer learning techniques. For the test samples, the recognition rate of the traditional Backpropagation neural Network (BPNN) algorithm is 66.25%, while the recognition rate of the improved YOLOv3 convolutional network for the same test samples is 91.25%. The experimental results show that this method has good performance in the pepper recognition task, with high accuracy and fast processing speed. © The Author(s) 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

6.9 A 0.35V 0.367TOPS/W image Sensor with 3-Layer Optical-Electronic Hybrid Convolutional neural Network

6.9 A 0.35V 0.367TOPS/W Image Sensor with 3-Layer Optical-El...

引用

2024 IEEE International Solid-State Circuits Conference, ISSCC 2024

作者： Wang, Xuecheng Huang, Zheng Liu, Tianyi Shi, Wanxin Chen, Hongwei Zhang, Milin Tsinghua University Beijing China

ISBN: (纸本)9798350306200

Traditional computer-vision technology that relies on image sensors coupled with cloud processing or on-chip artificial Intelligence (AI) processors have encountered significant challenges in terms of power consumption, delays arising from data transmission, and/or memory access. In-sensor and near-sensor computing have been reported to solve this issue by applying pixel or array level feature extraction [2-6]. In [2, 4], capacitors are utilized for analog-domain Haar filtering to reduce the processing power consumption, but sacrificing the Fill Factor (FF) due to the use of the capacitor array [2], or complicated pixel-level logic [4]. An image sensor in introduced in [3] with Hog feature-based object detection, achieving both low power and high accuracy for the detection of up to three object classes. However, it does not work on more complex tasks. Convolutional neural networks (CNNs) [5, 6] offer enhanced accuracy in practical applications, but increase the power consumption and circuit complexity. Optical-domain processing [7] is capable of parallel information processing through an optical architecture based on free space. However, in [7] this is based on diffraction and requires coherent light as input, which constrains the practicality for edge computing. This paper presents a Pulse Width Modulation (PWM) pixel-based image sensor array that integrates an optical-electronic hybrid 3-layer convolutional processing unit. The first layer of the convolution is performed in the optical domain without introducing extra power consumption. The integration of optical convolution with electrical convolution offers the potential to leverage the energy-efficient advantages of optical convolution, while simultaneously providing the essential programmability needed to address multiple use-cases through reprogramming within a single device. A dual-mode processing Element (PE) is proposed enables both acquisition mode and calculation mode. The integration of a sum/differenti

关键词：

来源：评论

学校读者我要写书评

暂无评论

Near-Sensor Edge Computing System Enabled by a CMOS Compatible Photonic Integrated Circuit Platform Using Bilayer AlN/Si Waveguides

引用

NANO-MICRO LETTERS 2025年第1期17卷 1-20页

作者： Ren, Zhihao Zhang, Zixuan Zhuge, Yangyang Xiao, Zian Xu, Siyu Zhou, Jingkai Lee, Chengkuo Natl Univ Singapore Dept Elect & Comp Engn Singapore 117583 Singapore Natl Univ Singapore Ctr Intelligent Sensors & MEMS Singapore 117608 Singapore Natl Ctr Adv Integrated Photon NCAIP Singapore 639798 Singapore Natl Univ Singapore NUS Grad Sch Integrat Sci & Engn Programme ISEP 21 Lower Kent Ridge Rd Singapore 119077 Singapore

The rise of large-scale artificial intelligence (AI) models, such as ChatGPT, DeepSeek, and autonomous vehicle systems, has significantly advanced the boundaries of AI, enabling highly complex tasks in natural language processing, image recognition, and real-time decision-making. However, these models demand immense computational power and are often centralized, relying on cloud-based architectures with inherent limitations in latency, privacy, and energy efficiency. To address these challenges and bring AI closer to real-world applications, such as wearable health monitoring, robotics, and immersive virtual environments, innovative hardware solutions are urgently needed. This work introduces a near-sensor edge computing (NSEC) system, built on a bilayer AlN/Si waveguide platform, to provide real-time, energy-efficient AI capabilities at the edge. Leveraging the electro-optic properties of AlN microring resonators for photonic feature extraction, coupled with Si-based thermo-optic Mach-Zehnder interferometers for neural network computations, the system represents a transformative approach to AI hardware design. Demonstrated through multimodal gesture and gait analysis, the NSEC system achieves high classification accuracies of 96.77% for gestures and 98.31% for gaits, ultra-low latency (< 10 ns), and minimal energy consumption (< 0.34 pJ). This groundbreaking system bridges the gap between AI models and real-world applications, enabling efficient, privacy-preserving AI solutions for healthcare, robotics, and next-generation human-machine interfaces, marking a pivotal advancement in edge computing and AI deployment.

关键词： Photonic integrated circuits Edge computing Aluminum nitride neural networks Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

EG-SpikeFormer: Eye-Gaze Guided Transformer on Spiking neural networks for Medical image Analysis 22

EG-SpikeFormer: Eye-Gaze Guided Transformer on Spiking Neura...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Pan, Yi Jiang, Hanqi Chen, Junhao Li, Yiwei Zhao, Huaqin Zhou, Yifan Shu, Peng Wu, Zihao Liu, Zhengliang Zhu, Dajiang Li, Xiang Abate, Yohannes Liu, Tianming School of Computing University of Georgia Athens GA United States University of Texas at Arlington Department of Computer Science and Engineering TX United States Massachusetts General Hospital Harvard Medical School Department of Radiology MA United States University of Georgia Department of Physics and Astronomy Athens GA United States

ISBN: (纸本)9798331520526

Neuromorphic computing has emerged as a promising energy-efficient alternative to traditional artificial neural networks (ANNs), predominantly utilizing spiking neural networks (SNNs) implemented on neuromorphic hardware. SNNs are more energy-efficient and excel at processing spatio-temporal data than ANNs. Significant advancements have been made in SNN-based convolutional neural networks (CNNs) and Transformer architectures. However, neuromorphic computing for the medical imaging domain remains underexplored. In this study, we introduce EG-SpikeFormer, an SNN architecture tailored for clinical tasks that incorporates eye-gaze data to guide the model's attention to the diagnostically relevant regions in medical images. Our developed approach effectively addresses shortcut learning issues commonly observed in conventional models, especially in scenarios with limited clinical data and high demands for model reliability, generalizability, and transparency. Our EG-SpikeFormer not only demonstrates superior energy efficiency and performance in medical image prediction tasks but also enhances clinical relevance through multi-modal information alignment. By incorporating eye-gaze data, the model improves interpretability and generalization, opening new directions for applying neuromorphic computing in medical image analysis. © 2025 IEEE.

关键词： eye-gaze healthcare applications medical image analysis Neuromorphic computing spiking neural networks

来源：评论

学校读者我要写书评

暂无评论

Low-rank discrete multi-view spectral clustering

引用

neural networks 2023年第1期166卷 137-147页

作者： Yun, Yu Li, Jing Gao, Quanxue Yang, Ming Gao, Xinbo Xidian Univ Sch Telecommun Engn Xian 710071 Shaanxi Peoples R China Harbin Engn Univ Coll Math Sci Harbin 150001 Heilongjiang Peoples R China Chongqing Univ Posts & Telecommun Chongqing Key Lab Image Cognit Chongqing 400065 Peoples R China

Spectral clustering has attracted intensive attention in multimedia applications due to its good performance on arbitrary shaped clusters and well-defined mathematical framework. However, most existing multi-view spectral clustering methods still have the following demerits: (1) They ignore useful complementary information embedded in indicator matrices of different views. (2) The conventional post-processing methods based on the relax and discrete strategy inevitably result in the sub-optimal discrete solution. To tackle the aforementioned drawbacks, we propose a low-rank discrete multi-view spectral clustering model. Drawing inspiration from the fact that the difference between indicator matrices of different views provides useful complementary information for clustering, our model exploits the complementary information embedded in indicator matrices with tensor Schatten p-norm constraint. Further, we integrate low-rank tensor learning and discrete label recovering into a uniform framework, which avoids the uncertainty of the relaxed and discrete strategy. Extensive experiments on benchmark datasets have demonstrated the effectiveness and superiority of the proposed method. & COPY;2023 Elsevier Ltd. All rights reserved.

关键词： Discrete label learning Spectral clustering Low-rank

来源：评论

学校读者我要写书评

暂无评论

SPECIAL ISSUE ON Al AND MACHINE LEARNING BASED TECHNOLOGIES FOR MICROWAVES

引用

IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES 2022年第11期70卷 4595-4596页

作者： Zhang, Qi-Jun Carleton Univ Dept Elect Ottawa ON K1S 5B6 Canada

artificial intelligence (AI) and machine learning have experienced phenomenal success in the past decade in signal processing, image and speech recognition, robotics, autonomous systems, and more. This success is also coupled with the expanding applications of AI and machine learning in broad areas of science and engineering. The microwave community is among the earliest in exploring machine learning and artificial neural networks (ANN) for wireless and wireline electronic device, and circuit and system designs. Early works that appeared in the IEEE MTT-S International Microwave Symposium (IMS) are, for example, ANN for microstrip design (1993), ANN for microwave circuit analysis and optimization (1994), ANN for via interconnect (1996), and ANN for microwave computer-aided design (1996). The first time that IMS hosted a workshop on this topic (applications of ANN for Microwave Design) was in IMS 1997, where the workshop was organized by Profs. K. C. Gupta and Michel Nakhla, and the invited speakers included R. L. Mahajan, K. C. Gupta, M. S. Nakhla, G. L. Creech, and Q. J. Zhang. Over the subsequent years, many researchers from around the world have contributed to the continuing development of ANN/machine learning techniques for microwave design. Several factors drove the development, one being the learning and generalization ability of ANN to learn computationally expensive microwave modeling/design problems offline, and to provide fast solutions to the problems during online design tasks. Another driving factor is the ability of ANN to learn microwave relationships directly from data even if analytical formulas for the targeted relationship are not available. From this angle, various ANN-based inverse modeling methods are developed, providing direct solutions to microwave design problems which otherwise would require expensive iterative process to solve. Further integrations between the microwave and machine learning disciplines led to knowledge-based approaches fo

关键词： Special issues and sections Microwave theory and techniques Machine learning Optimization artificial neural networks Microwave imaging Microwave circuits Microwave filters

来源：评论

学校读者我要写书评

暂无评论

NeuroNet: A Deep Learning Framework for Stroke Analysis 2

NeuroNet: A Deep Learning Framework for Stroke Analysis

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Prasad, Arpana Asha, V. Tressa, Neethu Sharma, Divya Deepthi, V. Divyashree, S. New Horizon College of Engineering Master of Computer Applications Bengaluru India

ISBN: (纸本)9798350327533

The revolutionary potential of a deep learning framework for stroke analysis and prediction in the healthcare industry is examined in this paper. The suggested framework uses large datasets, such as patient records, medical images, and pertinent health information, to create histicated neural networks in order to address the critical need for early detection and intervention in stroke cases. Important areas like stroke type classification, natural language processing, image analysis, treatment optimization, outcome prediction, telemedicine, and explainable artificial intelligence are highlighted in the thorough review of related work. The steps involved in data collection, preprocessing, model selection, and result interpretation are all carefully laid out in the methodology. A thorough evaluation of machine learning models, such as Random Forest, SVM, XGBoost, and Logistic Regression, is carried out;Random Forest continuously performs well. The results highlight how difficult it is to predict strokes and how crucial it is to choose models carefully. With the ultimate goal of improving stroke diagnosis, treatment, and prevention for improved patient care through ongoing research and technological advancements, ethical considerations and adherence to healthcare regulations in AI applications are emphasized. © 2024 IEEE.

关键词： and Data Analysis artificial Intelligence Risk Prediction Stroke

来源：评论

学校读者我要写书评

暂无评论

Demystifying Deep Learning: An Introduction to the Mathematics of neural networks

引用

2024年

作者： Douglas J. Santry

ISBN: (数字)9781394205622;9781394205615

ISBN: (纸本)9781394205608

DEMYSTIFYING DEEP LEARNING Discover how to train Deep Learning models by learning how to build real Deep Learning software libraries and verification software! The study of Deep Learning and artificial neural networks (ANN) is a significant subfield of artificial intelligence (AI) that can be found within numerous fields: medicine, law, financial services, and science, for example. Just as the robot revolution threatened blue-collar jobs in the 1970s, so now the AI revolution promises a new era of productivity for white collar jobs. Important tasks have begun being taken over by ANNs, from disease detection and prevention, to reading and supporting legal contracts, to understanding experimental data, model protein folding, and hurricane modeling. AI is everywhere—on the news, in think tanks, and occupies government policy makers all over the world —and ANNs often provide the backbone for AI. Relying on an informal and succinct approach, Demystifying Deep Learning is a useful tool to learn the necessary steps to implement ANN algorithms by using both a software library applying neural network training and verification software. The volume offers explanations of how real ANNs work, and includes 6 practical examples that demonstrate in real code how to build ANNs and the datasets they need in their implementation, available in open-source to ensure practical usage. This approachable book follows ANN techniques that are used every day as they adapt to natural language processing, image recognition, problem solving, and generative applications. This volume is an important introduction to the field, equipping the reader for more advanced study. Demystifying Deep Learning readers will also find:

A volume that emphasizes the importance of classification
Discussion of why ANN libraries, such as Tensor Flow and Pytorch, are written in C++ rather than Python
Each chapter concludes with a “Projects” page to promote students experimenting with real cod

关键词：

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：