检索结果-内蒙古大学图书馆

Potato diseases detection and classification using deep learning methods

MULTIMEDIA TOOLS AND applications 2023年第4期82卷 5725-5742页

作者： Arshaghi, Ali Ashourian, Mohsen Ghabeli, Leila Islamic Azad Univ Dept Elect Engn Cent Tehran Branch Tehran Iran Islamic Azad Univ Dept Elect Engn Majlesi Branch Esfahan Iran

Using machine vision and image processing methods has an important role in the identification of defects of agricultural products, especially potatoes. The applications of image processing and artificial intelligence in agriculture in identifying and classifying pests and diseases of plants and fruits have increased and research in this field is ongoing. In this paper, we use the convolution neural network (CNN) methods, also, we examined 5 classes of potato diseases with the names: Healthy, Black Scurf, Common Scab, Black Leg, Pink Rot. We used a database of 5000 potato images. We compared the results of potato defect classification our methods with other methods such as Alexnet, Googlenet, VGG, R-CNN, Transfer Learning. The results show that the accuracy of the deep learning proposed method is higher than other existing works. We get 100% and 99% accuracy in some of the classes, respectively.

关键词： Convolutional neural networks Deep learning Defect detection Potato diseases Potato classification

来源：评论

学校读者我要写书评

暂无评论

ENHANCED DETECTION OF SMALL OBJECTS IN AERIAL imageRY: A HIGH-RESOLUTION neural NETWORK APPROACH WITH AMPLIFIED FEATURE PYRAMID AND SIGMOID RE-WEIGHTING 31

ENHANCED DETECTION OF SMALL OBJECTS IN AERIAL IMAGERY: A HIG...

引用

2024 International conference on image processing

作者： Park, Chanyeong Jang, Junbo Kim, Heegwang Paik, Joonki Chung Ang Univ Dept Image Seoul South Korea Chung Ang Univ Dept Artificial Intelligence Seoul South Korea

ISBN: (纸本)9798350349405;9798350349399

Detecting small objects in drone-captured images or aerial videos is challenging due to their minimal representation. As data traverses deep learning networks, the information about small objects can diminish, making high-resolution images essential for enhanced detection performance. However, high-resolution images increase computational load undesirably. Leveraging this fact, we propose a streamlined neural network designed specifically for small object detection in high-resolution images. The proposed network encompasses three main components: i) Enhanced High-Resolution processing Module (EHRPM), ii) the Small Object Feature Amplified Feature Pyramid Network (SOFA-FPN) with its Edge Enhancement Module (EEM), Cross Lateral Connection Module (CLCM), and Dual Bottom-up Convolution Module (DBCM), and iii) the Sigmoid Re-weighting Module (SRM). Compared to several state-of-the-art networks, our method delivers superior performance with fewer parameters and a lower computational demand. The source code is available at https://***/datu0615/EHRPM.

关键词： Small Object Detection Aerial images Multi-scale Feature Fusion High-resolution processing

来源：评论

学校读者我要写书评

暂无评论

PDDM: Poisson-Distribution Diffusion Model with Multi-Step Weighted Fusion for Medical image Segmentation

PDDM: Poisson-Distribution Diffusion Model with Multi-Step W...

引用

International Joint conference on neural networks (IJCNN)

作者： Chen, Xingyu Chen, Junying South China Univ Technol Sch Software Engn Guangzhou Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Medical image segmentation is challenging because the boundaries of lesions are often hazy or unclear. As a result, how to better distinguish the lesion boundaries to improve segmentation accuracy has become the main focus of research in recent years. The diffusion model, a potent visual image generation model, has extended applications in medical image segmentation. In this work, we propose a Poisson-distribution diffusion model (PDDM), a novel conditional diffusion model based on the Poisson distribution, to fully use the diffusion model's enormous potential in medical image segmentation. To increase the segmentation diversity of diffusion models in discrete spaces and produce more precise segmentation maps, we first explore utilizing Poisson noise as the diffusion kernel rather than Gaussian noise. Then, by making use of the diffusion model's stochastic nature, our model repeatedly samples the original Poisson noise and intermediate latent variables at random to generate a variety of segmentation masks. Moreover, we include a multi-step weighted fusion (MSWF) module in the reasoning process to merge the output of the diffusion model at each step, to improve the robustness of the PDDM's prediction results. Finally, we validate the effectiveness and generalization of our model on three medical image segmentation datasets of different imaging modalities.

关键词： Conditional Diffusion Model Poisson Distribution Multi-Step Weighted Fusion Medical image Segmentation

来源：评论

学校读者我要写书评

暂无评论

Spatial Distribution Prediction and Migration Characteristic of Petroleum Hydrocarbons in Soil Based on artificial neural networks

引用

JOURNAL OF INFORMATION processing SYSTEMS 2024年第6期20卷 841-852页

作者： Gao, Aili Chen, Lan Wei, Xiaohan Liu, Chao Cheng, Lihua Qingdao Univ Technol Sch Environm & Municipal Engn Qingdao Peoples R China

Soil pollution resulting from petroleum hydrocarbons (PHCs) arising from industrialization and human activities has emerged as a progressively severe global concern. Establishing an accurate spatial distribution prediction model for PHCs through limited sampling data play an important role in understanding the migration characteristics of PHCs and effectively preventing soil pollution. This article employs soil samples within 8 m of a chemical plant, in conjunction with hydrogeological data, to model the spatial distribution of PHC content using a feedforward neural network (FNN). The prediction outcomes are characterized through three-dimensional visualization. The findings indicate that FNN demonstrates superior estimation accuracy compared to traditional interpolation method. Regarding the horizontal distribution within surface soil, there is pronounced lateral migration of PHC content in both the storage area and manufacturing shop, with migration aligning following the direction of groundwater. Vertically, PHC content exhibits a consistent pattern of increasing and then decreasing with greater depth. It is predominantly enriched in the lower section of the aeration zone and the upper part of the saturated zone, particularly within 4 m, under influence of groundwater. In this study, the prediction model offers an original approach to the spatial distribution of soil pollutants.

关键词： Feedforward neural networks Migration Characteristics Petroleum Hydrocarbon Spatial Distribution

来源：评论

学校读者我要写书评

暂无评论

Cancer Diagnosis With the Aid of artificial Intelligence Modeling Tools

引用

IEEE ACCESS 2022年 10卷 20816-20831页

作者： Danku, Alex Ede Dulf, Eva H. Banut, Raul Petru Silaghi, Horatiu Silaghi, Cristina Alina Tech Univ Cluj Napoca Dept Automat Cluj Napoca 400014 Romania Iuliu Hatieganu Univ Med & Pharm Cluj Napoca Dept Surg 5 Cluj Napoca 400012 Romania Iuliu Hatieganu Univ Med & Pharm Cluj Napoca Dept Endocrinol Cluj Napoca 400012 Romania

Cancer is one of the deadliest diseases in the present days. Its survivability is mostly corelated to early detection and treatment, which means that it is of utmost importance to successfully diagnose the patients. Unfortunately, even with years of experience human errors can happen which leads to the death of many individuals being misdiagnosed. Throughout the years there have been several applications created which could possibly aid doctors in the diagnosis. neural networks have always been a powerful tool which can be used in different applications that require an accurate model and the complexity of these models exceeds a human's computational capabilities. In image processing for example, a convolutional neural network can analyze each particular pixel and determine through the convolution function the common properties of different pictures. The objective of this study is to analyze different types of cancer diagnosing methods that have been developed and tested using image processing methods. The analyzed factors are training parameters, image processing technique and the obtained performances. This survey/review can be of significant value to researchers and professionals in medicine and computer science, highlighting areas where there are opportunities to make significant new contributions.

关键词： Cancer artificial intelligence Training neural networks Medical services image color analysis Ultrasonic imaging Cancer diagnosis image processing neural networks

来源：评论

学校读者我要写书评

暂无评论

A Real-time Demonstrator for image Classification using FPGA-based Logic neural networks

A Real-time Demonstrator for Image Classification using FPGA...

引用

conference on Real-Time processing of image, Depth, and Video Information

作者： Concha, David Garcia-Espinosa, Francisco J. Ramirez, Ivan Alberto Aranda, Luis Univ Rey Juan Carlos CAPO Res Grp Madrid 28933 Spain

ISBN: (纸本)9781510673199;9781510673182

Real-time image processing is a key area of focus, but computationally intensive. neural networks effectively address classification tasks, but they are not always a viable option, particularly in environments where high power consumption or computational requirements are limiting factors. Hardware devices such as Field-Programmable Gate Arrays (FPGAs) offer significant parallelization capabilities that can be fully exploited when the implemented circuit is composed solely of logic gates. In addition, FPGAs are also interesting alternatives to traditional GPU-based implementations in terms of power consumption and reconfiguration capabilities. They can be used as a demonstration platform to validate a hardware design that can be later manufactured, creating the final Application-Specific Integrated Circuit (ASIC). This paper introduces a practical demonstration platform based on an FPGA that highlights the great capabilities of logic neural networks, a type of neural network constructed exclusively with logic gates. By harnessing FPGA parallelization and logic gates, we have achieved a balance between computational power and real-time performance. This approach ensures that image classification occurs at speeds on the order of nanoseconds. This ultra-fast processing is well-suited for real-time image analysis applications across various domains. Industries that rely on quality control, such as manufacturing, will benefit from rapid and precise assessments. In the field of medical image processing, where quick diagnoses are crucial, this technology promises transformative advancements. The demonstration platform developed serves as a proof of concept for logic neural networks, offering a solution to the challenge of real-time image processing and representing the first step towards the implementation of future architectures of logic networks in hardware.

关键词： Deep Learning Field-Programmable Gate Array (FPGA) Logic neural Network (LNN) Real-time image Classification

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Recursive Context Aggregation Network for Semantic Segmentation 32

Multi-Scale Recursive Context Aggregation Network for Semant...

引用

32nd IEEE Signal processing and Communications applications conference (SIU)

作者： Yalcin, Abdullah Keskinoz, Mehmet Istanbul Tech Univ Bilgisayar Muhendisligi Bolumu Istanbul Turkiye

ISBN: (纸本)9798350388978;9798350388961

Convolution operations that are consecutively applied in a typical CNN architecture, cause the loss of original details in input image signals at the cost of extracting new features. Among these details are the coarse patterns the network model tries to capture in deeper layers. However, those coarse details can be easily detected in lower image resolutions and incorporated into the higher level features. Based on this hypothesis, in this study we propose a novel multi-scale multi-input recursive context aggregation network which works on semantic segmentation tasks and show that it outperforms baseline U-Net model by 2% in mIoU on Oxford-IIIT Pet dataset.

关键词： convolutional neural networks semantic segmentation multi-scale analysis image pyramid

来源：评论

学校读者我要写书评

暂无评论

Spectrum Translation for Refinement of image Generation (STIG) Based on Contrastive Learning and Spectral Filter Profile 38

Spectrum Translation for Refinement of Image Generation (STI...

引用

38th AAAI conference on artificial Intelligence (AAAI) / 36th conference on Innovative applications of artificial Intelligence / 14th Symposium on Educational Advances in artificial Intelligence

作者： Lee, Seokjun Jung, Seung-Won Seo, Hyunseok Korea Inst Sci & Technol Biomed Res Div Seoul South Korea Korea Univ Sch Elect Engn Seoul South Korea

ISBN: (纸本)1577358872

Currently, image generation and synthesis have remarkably progressed with generative models. Despite photo-realistic results, intrinsic discrepancies are still observed in the frequency domain. The spectral discrepancy appeared not only in generative adversarial networks but in diffusion models. In this study, we propose a framework to effectively mitigate the disparity in frequency domain of the generated images to improve generative performance of both GAN and diffusion models. This is realized by spectrum translation for the refinement of image generation (STIG) based on contrastive learning. We adopt theoretical logic of frequency components in various generative networks. The key idea, here, is to refine the spectrum of the generated image via the concept of image-to-image translation and contrastive learning in terms of digital signal processing. We evaluate our framework across eight fake image datasets and various cutting-edge models to demonstrate the effectiveness of STIG. Our framework outperforms other cutting-edges showing significant decreases in FID and log frequency distance of spectrum. We further emphasize that STIG improves image quality by decreasing the spectral anomaly. Additionally, validation results present that the frequency-based deepfake detector confuses more in the case where fake spectrums are manipulated by STIG.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Complex-Valued Federated Learning with Differential Privacy and MRI applications 9th

Complex-Valued Federated Learning with Differential Privacy ...

引用

27th International conference on Medical image Computing and Computer Assisted Intervention (MICCAI)

作者： Riess, Anneliese Ziller, Alexander Kolek, Stefan Rueckert, Daniel Schnabel, Julia Kaissis, Georgios Helmholtz Munich Inst Machine Learning Biomed Imaging Neuherberg Germany Tech Univ Munich Sch Computat Informat & Technol Munich Germany Helmholtz Munich Helmholtz AI Oberschleissheim Germany Tech Univ Munich Artificial Intelligence Healthcare & Med Munich Germany Ludwig Maximilians Univ Munchen Math Foundat AI Munich Germany Imperial Coll London Dept Comp London England Kings Coll London Sch Biomed Engn & Imaging Sci London England Tech Univ Munich Inst Diagnost & Intervent Radiol Munich Germany

ISBN: (纸本)9783031776090;9783031776106

Federated learning enhanced with Differential Privacy (DP) is a powerful privacy-preserving strategy to protect individuals sharing their sensitive data for processing in fields such as medicine and healthcare. Many medical applications, for example magnetic resonance imaging (MRI), rely on complex-valued signal processing techniques for data acquisition and analysis. However, the appropriate application of DP to complex-valued data is still underexplored. To address this issue, from the theoretical side, we introduce the complex-valued Gaussian mechanism, whose behaviour we characterise in terms of f-DP, (epsilon, delta)-DP and Renyi-DP. Moreover, we generalise the fundamental algorithm DP stochastic gradient descent to complex-valued neural networks and present novel complex-valued neural network primitives compatible with DP. Experimentally, we showcase a proof-of-concept by training federated complex-valued neural networks with DP on a real-world task (MRI pulse sequence classification in k-space), yielding excellent utility and privacy. Our results highlight the relevance of combining federated learning with robust privacy-preserving techniques in the MRI context.

关键词： Federated learning Differential Privacy Complex Numbers

来源：评论

学校读者我要写书评

暂无评论

A Comparative Review of Convolutional neural networks, Long Short-Term Memory, and Recurrent neural networks in Recommendation Systems

A Comparative Review of Convolutional Neural Networks, Long ...

引用

International conference on artificial Intelligence: Theory and applications (AITA)

作者： Tyagi, Geetanjali Ray, Susmita Manav Rachna Univ Faridabad Dept CST Faridabad India

ISBN: (纸本)9789819984756;9789819984763

Deep learning (DL) computing has emerged as the Gold Standard in the machine learning (ML) community in recent years. There are numerous recommender systems (RS) being used to treat information over-load problems in e-commerce, entertainment, and social media today. This review presents a comprehensive and comparative analysis of deep learning models based on Convolutional neural networks (CNNs), Long Short-Term Memory (LSTM), Recurrent neural networks (RNNs), Rectified Linear Unit-Deep neural Network (ReLU-DNN), Adaptive Deep Learning-based method for the Recommendation System (ADRS) model, and several other hybrid DL methodologies in the context of RS. Open research problems in the domain, such as collection and feedback of user data, cold start, data sparsity, and scalability have been explored and studies to tackle these issues have been highlighted. It also assesses potential areas for future research and development of hybrid methods combining strengths of a multitude of architectures and incorporating attention mechanisms to enhance the recommendation quality metrics. We analyze the strengths and limitations of each architecture and find that hybrid techniques, like LSTM-RNN, demonstrated outstanding efficacy in problems of text classification. Overall, this review provides a comprehensive understanding of the applications and capabilities of CNNs, LSTM, and RNNs in recommendation systems, serving as a valuable resource for researchers and practitioners in the field. Further, the study will be comprehended by identifying an efficient model with prominent accuracy reports.

关键词： Deep learning Recommender systems Natural language processing Content-based filtering system Convolutional neural network Hybrid recommendation system Long short-term memory Convolutional neural 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：