检索结果-内蒙古大学图书馆

International Conference on image processing and Capsule networks, ICIPCN 2020

作者： Silva, Jesus Varela, Noel Patiño-Saucedo, Janns A. Lezama, Omar Bonerge Pineda Universidad de la Costa St. 58 #66 BarranquillaAtlántico Colombia San Pedro Sula Honduras

ISBN: (纸本)9783030518585

In the last few decades, the constant growth of digital images, as the main source of information representation for scientific applications, has made image classification a challenging task. To achieve high classification yields, different pattern recognition techniques have been proposed, among which are the deep learning methods that today focus their study on image processing and computer vision. In this approach, the most popular architecture for the image classification task is the convolutional neural network (CNN), a network constructed of multiple layers and where each layer models a receptive field of the visual cortex making it much more effective in artificial vision tasks [1]. This paper proposes a convolutional network architecture with a performance-enhancing approach, a hierarchical structure that is easy to build, adaptive, and easy to train with good performance in image classification tasks. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Interpreting the Latent Space of GANs via Measuring Decoupling

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial Intelligence 2021年第1期2卷 58-70页

作者： Li, Ziqiang Tao, Rentuo Wang, Jie Li, Fu Niu, Hongjing Yue, Mingdao Li, Bin The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems University of Science and Technology of China Hefei230052 China The Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230052 China The School of Information Science and Technology University of Science and Technology of China Hefei230052 China The College of Mechanical and Electrical Engineering Suzhou University Suzhou234000 China

With the success of generative adversarial networks (GANs) on various real-world applications, the controllability and security of GANs have raised more and more concerns from the community. Specifically, understanding the latent space of GANs, i.e., obtaining the completely decoupled latent space, is essential for applications in some secure scenarios. At present, there is no quantitative method to measure the decoupling of latent space, which is not conducive to the development of the community. In this article, we propose two methods to measure the sensitivity of latent dimensions: one is a sequential intervention method, and the other is an optimization-based method that measures the sensitivity in both the value and the direction. With these two methods, the decoupling of latent space can be measured by the sparsity of the sensitivity vector obtained. The effectiveness of the proposed methods has been verified by experiments on the representative GANs. Code will be available at https://***/iceli1007/latent-analysis-of. Impact Statement-Generative adversarial networks (GANs) is a popular technology in image generation. Benefiting from the development of neural networks, GANs have been widely used in many real-world tasks, such as super-resolution, image translation, and image inpainting. However, the understanding of the generator in GANs as a map from latent space (represented in a multidimensional vector) to image space is incomplete. To make better use of GANs, more insight into the generation process is required. The motivation of this article is to develop methods to analyze the influence of each dimension of latent space on the generated results, and to measure the decoupling of latent space, the knowledge obtained will be useful for the development of more precise controllable image generation technology. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Highly Accurate Stochastic Spiking neural Network

Design and Implementation of a Highly Accurate Stochastic Sp...

引用

35th IEEE Workshop on Signal processing Systems (IEEE SiPS)

作者： Tang, Chengcheng Han, Jie Univ Alberta Dept Elect & Comp Engn Edmonton AB Canada

ISBN: (纸本)9781665401449

The emergence of spiking neural networks (SNNs) provide a promising approach to the energy efficient design of artificial neural networks (ANNs). The rate encoded computation in SNNs utilizes the number of spikes in a time window to encode the intensity of a signal, in a similar way to the information encoding in stochastic computing. Inspired by this similarity, this paper presents a hardware design of stochastic SNNs that attains a high accuracy. A design framework is elaborated for the input, hidden and output layers. This design takes advantage of a priority encoder to convert the spikes between layers of neurons into index-based signals and uses the cumulative distribution function of the signals for spike train generation. Thus, it mitigates the problem of a relatively low information density and reduces the usage of hardware resources in SNNs. This design is implemented in field programmable gate arrays (FPGAs) and its performance is evaluated on the MNIST image recognition dataset. Hardware costs are evaluated for different sizes of hidden layers in the stochastic SNNs and the recognition accuracy is obtained using different lengths of stochastic sequences. The results show that this stochastic SNN framework achieves a higher accuracy compared to other SNN designs and a comparable accuracy as their ANN counterparts. Hence, the proposed SNN design can be an effective alternative to achieving high accuracy in hardware constrained applications.

关键词： Field programmable gate arrays (FPGAs) priority encoder stochastic computing spiking neural networks

来源：评论

学校读者我要写书评

暂无评论

UAV obstacle detection with bio-motivated computer vision 17

UAV obstacle detection with bio-motivated computer vision

引用

17th International Workshop on Cellular Nanoscale networks and their applications, CNNA 2021

作者： Petho, Mate Zsedrovits, Tamas Eötvös Lorand University Department of Physiology and Neurobiology Budapest Hungary Pazmany Peter Catholic University Faculty of Information Technology and Bionics Budapest Hungary

ISBN: (纸本)9781665439480

Unmanned aerial vehicles (UAVs) are becoming more and more common. They show excellent potential for multiple types of autonomous work, although they must achieve these tasks safely. For flight safety, it must be assured that the UA V will not endanger its surroundings during autonomous operations;it will avoid collision with any objects in its flight path. Camera-based computer vision and artificial neural networks have shown to be effective in many applications. However, biological vision systems and the brain areas responsible for visual processing may hold solutions capable of acquiring information effectively. Previous work has shown the usability of biologically motivated algorithms using vision systems of insects or even behavioral patterns to solve computer vision problems. We are proposing a novel system, which performs visual cue extraction with algorithms based on the structure and functionality of the retina and the visual cortex of the mammalian visual system. We are also developing a modular artificial neural network with a training dataset, which will perform autonomous obstacle recognition tasks using the data from the image processing algorithm. © 2021 IEEE.

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

4th International Conference on Recent Trends in image processing and Pattern Recognition, RTIP2R 2021

4th International Conference on Recent Trends in Image Proce...

引用

4th International Conference on Recent Trends in image processing and Pattern Recognition, RTIP2R 2021

ISBN: (纸本)9783031070044

The proceedings contain 33 papers presendted at a virtual meeting. The special focus in this conference is on Recent Trends in image processing and Pattern Recognition. The topics include: Real-Time Face Recognition for Organisational Attendance Systems;Harnessing Sustainable Development in image Recognition Through No-Code AI applications: A Comparative Analysis;evaluating Performance of Adam Optimization by Proposing Energy Index;an Alignment-Free Fingerprint Template Protection Technique Based on Minutiae Triplets;early Prediction of Complex Business Processes Using Association Rule Based Mining;A Framework for Masked-image Recognition System in COVID-19 Era;A Deep-Learning Based Automated COVID-19 Physical Distance Measurement System Using Surveillance Video;Detection of Male Fertility Using AI-Driven Tools;face Mask Detection Using Deep Hybrid Network Architectures;a Super Feature Transform for Small-Size image Forgery Detection;UHTelHwCC: A Dataset for Telugu Off-line Handwritten Character Recognition;inflectional and Derivational Hybrid Stemmer for Sentiment Analysis: A Case Study with Marathi Tweets;adaptive Threshold-Based Database Preparation Method for Handwritten image Classification;a Graph-Based Holistic Recognition of Handwritten Devanagari Words: An Approach Based on Spectral Graph Embedding;Imagined Object Recognition Using EEG-Based Neurological Brain Signals;a Fast and Efficient K-Nearest Neighbor Classifier Using a Convex Envelope;single Channel Speech Enhancement Using Masking Based on Sinusoidal Modeling;extraction of Temporal Features on Fibonacci Space for Audio Based Vehicle Classification;an Empirical Study of Vision Transformers for Cervical Precancer Detection;An Improved Technique for Preliminary Diagnosis of COVID-19 via Cough Audio Analysis;agricultural Field Analysis Using Satellite Hyperspectral Data and Autoencoder;Development of NDVI Prediction Model Using artificial neural networks;time Series Forecasting of Soil Moisture Using Sa

关键词：

来源：评论

学校读者我要写书评

暂无评论

Toward improved surveillance of Aedes aegypti breeding grounds through artificially augmented data

引用

ENGINEERING applications OF artificial INTELLIGENCE 2023年第PartC期123卷

作者： Passos, Wesley L. Barreto, Cesar da S. Araujo, Gabriel M. Haque, Ubydul Netto, Sergio L. da Silva, Eduardo A. B. Univ Fed Rio de Janeiro Elect Engn Program POB 68504 BR-22941972 Rio De Janeiro RJ Brazil Fed Ctr Technol Educ Celso Suckow da Fonseca Estr Adrianopolis 1317 BR-26041271 Nova Iguacu RJ Brazil Rutgers Global Hlth Inst 112 Paterson St New Brunswick NJ 08901 USA Rutgers State Univ Sch Publ Hlth Dept Biostat & Epidemiol 683 Hoes Ln W Piscataway NJ 08854 USA

The Aedes aegypti mosquito transmits several diseases, including dengue, zika, and chikungunya. To prevent these diseases, identifying and removing mosquito breeding sites is essential, but it is a time-consuming and labor-intensive task. To improve efficiency, computer vision and machine learning can be used to detect potential breeding grounds automatically. In this context, we explore the use of data augmentation strategies including random scaling, rotation, as well as color and brightness adjustments for improving the automatic detection of potential Aedes aegypti breeding grounds using videos acquired by a drone. The faster region-based convolutional neural network (Faster R-CNN) and the you only look once (YOLO) v5 object detectors are used on a database of aerial videos containing breeding-related objects. When employing the data augmentation, tire-detection results show F1 scores of 0.79 and 0.81 for the Faster R-CNN and YOLOv5 networks, respectively, surpassing current state-of-the-art values. The detection performance of the algorithms increased by up to 14.1%, which is a significant improvement. These results indicate that artificial data augmentation reduces overfitting, improving the models' robustness. The developed system can be employed to help health agencies in locating potential Aedes aegypti outbreaks more efficiently.

关键词： Vector control Aedes aegypti Aerial images Convolutional neural networks image and video processing Data augmentation Object detection

来源：评论

学校读者我要写书评

暂无评论

A Short Survey on Deep Learning-Based Frameworks for Knowledge Graph applications

A Short Survey on Deep Learning-Based Frameworks for Knowled...

引用

Computer Technologies (ICCTech), International Conference on

作者： Abdulkarim Kushk Krzysztof Kochut School of Computing University of Georgia Athens GA USA

Knowledge Graphs (KG) are repositories of structured, machine-readable data stored as relational triples. DBpedia, Freebase, and YAGO are examples of KGs that have been playing a vital role in many applications, including question answering systems, recommendation systems, and expert systems. Deep learning is a subset of machine learning techniques that consists of layers of artificial neural networks. It is a relatively young technology that, in a very short amount of time, has achieved state-of-the-art performance in many fields of science, business, and government. For instance, convolutional networks have achieved major breakthroughs in processing image, video, and audio files. Moreover, recurrent networks have a similar effect in processing sequential data, such as texts and time series [1]. In this survey, we shed light on the development deep learning has brought about in two KG tasks: entity summarization and entity linking. Experiments on standard performance measures and benchmark datasets show that deep learning-based models generally outperform other models by a considerable margin.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI Dermatologist: Skin Cancer Detection with Deep Learning Technique

AI Dermatologist: Skin Cancer Detection with Deep Learning T...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Afraz Ul Haque Rupak Sadman Sadik Khan Alaya Parvin Alo Rupa Ghosh Md Fatin Ishrak Md Sanowar Hossain Sabuj Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Department of Computer Science and Engineering Khulna University Khulna Bangladesh Department of Electrical and Electronic Engineering North South University Dhaka Bangladesh College of Business Administration International University of Business Agriculture and Technology Dhaka Bangladesh

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This paper explores the application of deep learning technologies in the detection and diagnosis of skin cancer, leveraging advanced convolutional neural networks (CNNs) such as VGG-16, ResNet50, and MobileNetV2. Given the increasing incidence of skin cancer worldwide, there is a critical need for more accurate and efficient diagnostic methods. Our study employs transfer learning to enhance the capability of these networks, enabling them to detect skin cancer from dermoscopic images with a high degree of accuracy, often surpassing human expert performance. We detail the process of data collection, preprocessing, model training, and evaluation, emphasizing the adaptation of these models to skin cancer detection. The results demonstrate significant improvements in diagnostic accuracy, with MobileNetV2 showing notable efficiency in processing and resource utilization—qualities that are ideal for real-time diagnostic applications. In MobileNetV2 we achieved 97% accuracy. Furthermore, the study addresses the challenges of adversarial attacks and the integration of non-image data to refine diagnostic procedures. Our findings highlight the transformative potential of AI in medical diagnostics, suggesting that deep learning could become a cornerstone in the early detection and treatment of skin cancer, thereby improving patient outcomes substantially.

关键词： Deep learning Training Adaptation models Accuracy Transfer learning Real-time systems Convolutional neural networks artificial intelligence Skin cancer Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Gender Recognition Based on Face image Using Deep Learning Method

Gender Recognition Based on Face Image Using Deep Learning M...

引用

International Conference on Cyber and IT Service Management (CITSM)

作者： Mochamad Wahyudi Waeisul Bismi Firmansyah Mugi Raharjo Untung Rahardja Lise Pujiastuti Departement of Computer Science Universitas Bina Sarana Informatika Jakarta Indonesia Departement of Informatics University Nusa Mandiri Jakarta Indonesia Departement of Digital Business University Raharja Tangerang Indonesia Departement of Information System STMIK Antar Bangsa Tangerang Indonesia

Gender recognition based on facial images is one of the interesting applications in the field of image processing and artificial intelligence. Deep Learning methods, particularly artificial neural networks, have emerged as an effective tool for extracting complex facial features and classifying gender with high accuracy. This research outlines a study that aims to develop an employee gender recognition system based on facial images using Deep Learning methods. The method used in this study proposes the inceptionV3 model as well as the OpenCV and matplotlib libraries in Python in involving the collection of facial image datasets covering different genders with a total of 1024 facial images, each with 40 attributes. This dataset was used to train a deep artificial neural network to recognize patterns and features that are unique to male and female genders and validated. Furthermore, the artificial neural network was tested with a dataset of never-before-seen facial images to evaluate the performance of the system. The results show that the InceptionV3 Deep Learning model has great potential in gender recognition based on facial images. The developed system was able to achieve a high level of accuracy in classifying the gender of individuals from facial images with a total accuracy of 94.8% against the test data, even in complex situations such as variations in facial expressions and lighting.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nom Document Background Removal Using Generative Adversarial Network 7

Nom Document Background Removal Using Generative Adversarial...

引用

7th IEEE International Conference on Signal and image processing applications, ICSIPA 2021

作者： Ho, Loc Tan Tran, Son Thai Dinh, Dien Faculty of Information Technology University of Science Ho Chi Minh City70000 Viet Nam

ISBN: (纸本)9781665435925

In this research, we present a new technique to improve the performance of a Nom-character recognition system. Nom-character recognition is a challenging problem in pattern recognition. Especially these characters are not only blurred or distorted in a paper of a historical document containing ink strokes and symbols created by readers. Generative Adversarial Network (GAN) is one of the advanced versions of deep neural networks applied to generate artificial photos of objects [28]. Many versions of GAN have been malfunctioned recently to help the learning process be more stable and realistic to maximize features extracted from the data. We have been using a recent version of GAN to extract characters from images with complex backgrounds and brightness. This task is to retrieve clean text images from complex and noisy background sources. To the best of our knowledge, we perform the test on the Nom Dataset, which characterizes by multiple noise forms. The results demonstrate that this approach can help to improve any Nom-character recognition system. © 2021 IEEE

关键词： Generative adversarial networks

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：