检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Takács, Kristóf Elek, Renáta Nagyné Haidegger, Tamás Antal Bejczy Center for Intelligent Robotics Obuda Universtiy Budapest Hungary Doctoral School of Applied Informatics and Applied Mathematics Obuda University Hungary John von Neumann Faculty of Informatics Obuda University Budapest Hungary Obuda University Budapest Hungary Austrian Center for Medical Innovation and Technology Wiener Neustadt Austria

image processing techniques have huge impact on most fields of robotics and industrial automation. Real time methods are usually employed in complex automation tasks, assisting with decision making or directly guiding robots and machinery, while post-processing is usually used for retrospective assessment of systems and processes. While artificial intelligence based image processing algorithms (usually neural networks) are more common nowadays,"classical" methods can also be used effectively even in modern applications. This paper focuses on optical flow based image processing, proving its efficiency by presenting optical flow based solutions for modern challenges in different fields of robotics such as robotic surgery and food industry automation. The main subject of the paper is a smart robotic gripper designed for automated robot cells in the meat industry, that is capable of slip detection and secure gripping of soft, slippery tissues with the help of the implemented optical flow based algorithm. © 2023, CC BY-SA.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Exploring Parallelism in ZynqNet AI Engine to Accelerate image Classification in Aerospace

Exploring Parallelism in ZynqNet AI Engine to Accelerate Ima...

引用

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Eduardo Marañon Aguilar Fabio Benevenuti Fernanda Lima Kastensmidt Federal University of Rio Grande do Sul (UFRGS) Institute of Informatics Microelectronics Graduate Program (PGMICRO) Porto Alegre Brazil

ISBN: (数字)9798331522124

ISBN: (纸本)9798331522131

This research investigates various configurations of the Zynqnet AI Engine to accelerate image classification tasks using the SAT-6 dataset and a 4-layer CNN. The C++ code for the hardware accelerator was translated into RTL using Vivado HLS and integrated with the Zynq processing System on a ZedBoard Zynq-7000 ARM/FPGA SoC. The AI engine was configured to work with 32 -bit floating point, 8bit fixed point and 8 -bit integer type operations, with different processing elements for parallelizing CNN tasks. Given a 64-bit data memory bus in communication with the accelerator and an 8-bit integer quantization, the variation in the number of processing elements does not result in a significant performance improvement. To address this, 8 values were grouped for reading and writing in 64-bit parallel mode, and different communication architectures were designed to improve data transfer between the accelerator and DDR memory, with optional enablement of L1D and L2 cache. The research analyzes CNN computation performance and FPGA resource usage (LUTs, FFs, BRAMs, DSPs) across configurations, providing insights into the trade-offs in FPGA-based CNN implementations, aiding the development of efficient, high-performance hardware accelerators for Deep Learning applications.

关键词： Quantization (signal) Writing Table lookup System-on-chip Convolutional neural networks artificial intelligence Hardware acceleration Engines Field programmable gate arrays image classification

来源：评论

学校读者我要写书评

暂无评论

An Improved Hybrid Deep Learning Strategy to Predict Digital image Forgery using artificial Intelligence Principle

An Improved Hybrid Deep Learning Strategy to Predict Digital...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： L Hubert Mary Anita Titus M. Priscilla K. Sailaja A. B. Hajira Be Department of ECE Jeppiaar Institute of Technology Chennai Department of Electronics and Communication Engineering Jeppiaar University Chennai Department of ECE S.A. Engineering College Chennai Department of Computer Applications School of Computing Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupati Department of Computer Applications Karpaga Vinayaga College of Engineering and Technology Chennai

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Several modern-day application domains rely heavily on digital images. The practice of manipulating a digital image in such a way as to conceal important or useful details is known as image faking. The new researchers will benefit from this study’s information on picture fraud and how to identify it. An image or picture that is digitally represented is called a digital image. A two-dimensional image is represented numerically, typically in binary form. One of the most important ways to disseminate information on the Internet, digital images are employed in practically every industry. National security and commercial secrets make up the vast majority of digital photographs. Scientists and technologists now face the pressing problem of how to ensure the integrity of images due to the proliferation of the Internet and other forms of simple multimedia sharing. image processing may be defined as a method for improving or extracting useful information from digital images by converting them to a digital format and then doing various operations on them. Many different types of researchers are interested in image processing. In order to create a featured picture that can be used to train a pre-trained model, the difference between the original and compressed versions of the image must be calculated. Training the pre-trained model involves removing the classifier and replacing it with a newly-tuned one. Eight distinct pre-trained models optimized for binary classification are compared. Applying the suggested strategy with the modified pre-trained models outperforms current state-of-the-art approaches, according to the experimental results. For the purpose of easily identifying forgery images, this paper presented a new AI-assisted approach called AIIFI. To assess the efficacy of the proposed scheme, it was cross-validated with an existing learning model called Convolution neural Network (CNN).

关键词： Deep learning Training Digital images neural networks Pressing Predictive models Forgery

来源：评论

学校读者我要写书评

暂无评论

Mapping EEG Signals to Visual Stimuli: A Deep Learning Approach to Match vs Mismatch Classification

Mapping EEG Signals to Visual Stimuli: A Deep Learning Appro...

引用

IEEE International Conference on Signal processing, Communications and Computing (ICSPCC)

作者： Yiqian Yang Zhengqiao Zhao Qian Wang Yan Yang Jingdong Chen Center of Intelligent Acoustics and Immersive Communications Shaanxi Provincial Key Laboratory of Artificial Intelligence School of Marine Science and Technology Northwestern Polytechnical University Xi'an Shaanxi China Hong Kong University of Science and Technology North Electro-Optic Science & Technology Defense Co. Ltd

ISBN: (数字)9798350366556

ISBN: (纸本)9798350366563

Existing approaches to modeling associations between visual stimuli and brain responses are facing difficulties in handling between-subject variance and model generalization. Inspired by the recent progress in modeling speech-brain response, we propose a “match-vs-mismatch” deep learning model in this study to classify whether a video clip elicits neural responses in recorded EEG signals. Our model employs dilated convolutional neural networks and gated recurrent units to extract features from both EEG and video signals, enabling the learning of associations between visual content and corresponding neural recordings. We demonstrate that our proposed model achieves the highest accuracy on unseen subjects compared to other baseline models. Additionally, we assess inter-subject noise using a subject-level silhouette score in the embedding space, revealing that our model effectively mitigates inter-subject noise and significantly reduces the silhouette score. Furthermore, we investigate Grad-CAM activation scores, revealing that brain regions linked to language processing contribute most to model predictions, followed by regions associated with visual processing. These findings hold promise for advancing neural recording-based video reconstruction and related applications.

关键词： Deep learning Visualization Accuracy Noise Predictive models Brain modeling Feature extraction Electroencephalography Vectors image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Learning to Anticipate Egocentric Actions by Imagination

引用

IEEE TRANSACTIONS ON image processing 2021年 30卷 1143-1152页

作者： Wu, Yu Zhu, Linchao Wang, Xiaohan Yang, Yi Wu, Fei Univ Technol Sydney Australian Artificial Intelligence Inst Ultimo NSW 2007 Australia Zhejiang Univ Coll Comp Sci & Technol Hangzhou 310027 Peoples R China

Anticipating actions before they are executed is crucial for a wide range of practical applications, including autonomous driving and robotics. In this paper, we study the egocentric action anticipation task, which predicts future action seconds before it is performed for egocentric videos. Previous approaches focus on summarizing the observed content and directly predicting future action based on past observations. We believe it would benefit the action anticipation if we could mine some cues to compensate for the missing information of the unobserved frames. We then propose to decompose the action anticipation into a series of future feature predictions. We imagine how the visual feature changes in the near future and then predicts future action labels based on these imagined representations. Differently, our ImagineRNN is optimized in a contrastive learning way instead of feature regression. We utilize a proxy task to train the ImagineRNN, i.e., selecting the correct future states from distractors. We further improve ImagineRNN by residual anticipation, i.e., changing its target to predicting the feature difference of adjacent frames instead of the frame content. This promotes the network to focus on our target, i.e., the future action, as the difference between adjacent frame features is more important for forecasting the future. Extensive experiments on two large-scale egocentric action datasets validate the effectiveness of our method. Our method significantly outperforms previous methods on both the seen test set and the unseen test set of the EPIC Kitchens Action Anticipation Challenge.

关键词： Task analysis Uncertainty Predictive models Visualization Recurrent neural networks image segmentation image recognition Action anticipation action prediction egocentric videos

来源：评论

学校读者我要写书评

暂无评论

SSR: A Skeleton-based Synthesis Flow for Hybrid processing-in-RRAM Modes 40

SSR: A Skeleton-based Synthesis Flow for Hybrid Processing-i...

引用

40th IEEE/ACM International Conference on Computer Aided Design (ICCAD)

作者： Wang, Feng Sun, Guangyu Luo, Guojie Peking Univ Ctr Energy Efficient Comp & Applicat Beijing Peoples R China Peking Univ Adv Inst Informat Technol Hangzhou Peoples R China

ISBN: (纸本)9781665445078

Recently, the emerging resistive random access memory (RRAM) shows its potential to construct a processing-in-memory (PIM) architecture. It supports a variety of computation modes, including the digital mode and the analog mode. Both modes can perform parallel computation inside an RRAM crossbar. However, the lack of automatic synthesis flow limits their application scenarios. Although previous works implement several large-scale applications, e.g., image processing algorithms and neural networks, using these two modes, most of their implementations are designed manually or semi-manually. In our view, the lack of a specific application representation is a limiting factor for developing a synthesis flow. Therefore, in this work, we propose the skeleton as an application representation. Users can model applications and their potential parallelism in RRAM with nested skeletons and primitive operations. Then, we propose SSR, a skeleton-based flow that can automatically synthesize large-scale applications to RRAM crossbars. For an application represented in skeletons, SSR first partitions it into the digital part and the potential analog part. After that, SSR optimizes primitive operations and allocates bounding boxes to skeletons for both parts under the guide of pre-synthesis results. Finally, SSR maps bounding boxes of skeletons onto crossbars to enable pipelined computation. Experimental evaluations on several popular applications show that SSR improves throughput, latency, and area multiple times over previous works.

关键词： Limiting Design automation image processing Resistive RAM neural networks Computer architecture Parallel processing

来源：评论

学校读者我要写书评

暂无评论

Learning Local Neighboring Structure for Robust 3D Shape Representation 35

Learning Local Neighboring Structure for Robust 3D Shape Rep...

引用

35th AAAI Conference on artificial Intelligence / 33rd Conference on Innovative applications of artificial Intelligence / 11th Symposium on Educational Advances in artificial Intelligence

作者： Gao, Zhongpai Yan, Junchi Zhai, Guangtao Zhang, Juyong Yang, Yiyan Yang, Xiaokang Shanghai Jiao Tong Univ AI Inst MoE Key Lab Artificial Intelligence Shanghai Peoples R China Shanghai Jiao Tong Univ Inst Image Commun & Network Engn Shanghai Peoples R China Univ Sci & Technol China Sch Math Sci Hefei Peoples R China

ISBN: (纸本)9781577358664

Mesh is a powerful data structure for 3D shapes. Representation learning for 3D meshes is important in many computer vision and graphics applications. The recent success of convolutional neural networks (CNNs) for structured data (e.g., images) suggests the value of adapting insight from CNN for 3D shapes. However, 3D shape data are irregular since each node's neighbors are unordered. Various graph neural networks for 3D shapes have been developed with isotropic filters or predefined local coordinate systems to overcome the node inconsistency on graphs. However, isotropic filters or predefined local coordinate systems limit the representation power. In this paper, we propose a local structure-aware anisotropic convolutional operation (LSA-Conv) that learns adaptive weighting matrices for each node according to the local neighboring structure and performs shared anisotropic filters. In fact, the learnable weighting matrix is similar to the attention matrix in the random synthesizer - a new Transformer model for natural language processing (NLP). Comprehensive experiments demonstrate that our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

artificial intelligence in lung cancer screening: Detection, classification, prediction, and prognosis

引用

CANCER MEDICINE 2024年第7期13卷 e7140页

作者： Wu, Quanyang Huang, Yao Wang, Sicong Qi, Linlin Zhang, Zewei Hou, Donghui Li, Hongjia Zhao, Shijun Canc Hosp Chinese Acad Med Sci & Peking Union Med Coll Dept Diagnost Radiol Natl Canc Ctr Dept Diagnost RadiolNatl Canc Ctr Beijing Peoples R China Magnet Resonance Imaging Res Gen Elect Healthcare China Beijing Peoples R China Canc Hosp Chinese Acad Med Sci & Peking Union Med Coll PET CT Ctr Natl Canc Ctr PET CT CtrNatl Canc Ctr Beijing Peoples R China

BackgroundThe exceptional capabilities of artificial intelligence (AI) in extracting image information and processing complex models have led to its recognition across various medical fields. With the continuous evolution of AI technologies based on deep learning, particularly the advent of convolutional neural networks (CNNs), AI presents an expanded horizon of applications in lung cancer screening, including lung segmentation, nodule detection, false-positive reduction, nodule classification, and *** review initially analyzes the current status of AI technologies. It then explores the applications of AI in lung cancer screening, including lung segmentation, nodule detection, and classification, and assesses the potential of AI in enhancing the sensitivity of nodule detection and reducing false-positive rates. Finally, it addresses the challenges and future directions of AI in lung cancer *** holds substantial prospects in lung cancer screening. It demonstrates significant potential in improving nodule detection sensitivity, reducing false-positive rates, and classifying nodules, while also showing value in predicting nodule growth and pathological/genetic *** offers a promising supportive approach to lung cancer screening, presenting considerable potential in enhancing nodule detection sensitivity, reducing false-positive rates, and classifying nodules. However, the universality and interpretability of AI results need further enhancement. Future research should focus on the large-scale validation of new deep learning-based algorithms and multi-center studies to improve the efficacy of AI in lung cancer screening.

关键词： artificial intelligence computed tomography convolutional neural network deep learning lung cancer

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient All-Spin BNN Using Voltage-Controlled Spin-Orbit Torque Device for Digit Recognition

引用

IEEE TRANSACTIONS ON ELECTRON DEVICES 2021年第1期68卷 385-392页

作者： Shreya, Sonal Verma, Gaurav Piramanayagam, S. N. Kaushik, Brajesh Kumar Indian Inst Technol Roorkee Elect & Commun Engn Dept Roorkee 247667 Uttar Pradesh India Nanyang Technol Univ Sch Phys & Math Sci Singapore 639798 Singapore

artificial intelligence has been demonstrated for numerous applications including image recognition and processing, internet-of-things (IoT), and speech recognition. Recent neural network (NN) architectures escalating to perform these functionalities require deep-learning and deep NN (DNN) implementation. However, the present algorithm and circuit of DNN suffer from area and energy-efficiency. The usage of an energy-efficient and cost-effective binary NN (BNN) can mitigate the performance bottleneck. The basic component of BNN (the XNOR and accumulate module) is capable of replacing the conventional multiply-and-accumulate (MAC) operation. Among various emerging nonvolatile memories (NVMs), spintronics-based devices are attracting attention for the implementation of the aforementioned architectures. Multilevel voltage-controlled spin-orbit torque -based magnetic memory (MV-SOTM) spin device as synapse and voltage-controlled SOTM (V-SOTM) device as spin-neuron are capable of producing an all-spin NN. This article presents advanced XNOR operation using a computing-in-memory (CiM) mechanism wherein both V-SOTM and MV-SOTM (using series and parallel configuration) based synapses are compared. The MV-SOTM design dissipates 35.51% lesser energy as compared to the 1-bit V-SOTM. Further, the 8-bit synaptic crossbar array is implemented using both the devices with two output spin-neurons. These series and parallel MV-SOTM-based synaptic arrays consume 42.22% and 45.12% lesser power, respectively, as compared to 1-bit V-SOTM based synaptic array. Furthermore, the all-spin BNN design demonstrates a handwritten digit recognition application.

关键词： artificial neural networks Neurons Computer architecture Synapses Torque Nonvolatile memory Performance evaluation Binary neural network (BNN) computing-in-memory (CiM) magnetic memory neuromorphic computing voltage-controlled spin-orbit torque (SOT)

来源：评论

学校读者我要写书评

暂无评论

Detection of Corn Leaf Infection Using CNN with Various Optimizers

Detection of Corn Leaf Infection Using CNN with Various Opti...

引用

artificial Intelligence and Machine Learning applications Theme: Healthcare and Internet of Things (AIMLA), International Conference on

作者： G. R. Sreekanth R. S. Latha R. Roja S. Sankarnanth A. Gayathri Department of Computer Science and Engineering Kongu Engineering College Erode India Department of Computer Technology Kongu Engineering College Erode India

ISBN: (数字)9798350349221

ISBN: (纸本)9798350349238

Corn, a grain categorized within the grass family, stands as a fundamental staple crop globally. It plays a crucial role in supplying sustenance for both humans and livestock, in addition to serving as a raw material for various industries. In 2017, Africa produced 7.4% of the 1135 million tons produced worldwide in 40 million hectares. Throughout its growing process, corn plant is impacted by numerous illnesses. Lack of early detection of its diseases may result in a loss in productivity and even crop failure. It is proposed to analyze the leaves of the corn plant for identifying the diseases by exploiting deep learning methods. A wide range of deep learning algorithms are being utilized to detect the corn leaf with infection with good range of accuracy. To categorize the leaf, image processing models are mostly used for these kind of disease detections. Since it has in-built convolutional layer, CNN can reduce the image with high dimensionality without losing any kind of information. In this proposed work CNN with Adam optimizer has been implemented for better results and achieved 91.68 % of accuracy.

关键词： Deep learning Productivity Crops Medical services Raw materials Convolutional neural networks Internet of Things

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：