检索结果-内蒙古大学图书馆

A Hybrid Deep Learning Framework for Automatic Detection of Brain Tumours Using Different Modalities

ieee TRANSACTIONS ON EMERGING TOPICS IN computational intelligence 2025年第2期9卷 1216-1225页

作者： Sahu, Adyasha Das, Pradeep Kumar Paul, Indraneel Meher, Sukadev VIT Bhopal Univ Sch Comp Sci Engn & Artificial Intelligence Bhopal 466114 India Vellore Inst Technol Sch Elect Engn Vellore 632014 India Natl Inst Technol Rourkela Dept Elect & Commun Engn Rourkela 769008 India

Nowadays, deep convolutional neural networks (DCNNs) are the focus of substantial research for classification and detection applications in medical image processing. However, the limited availability and unequal data distribution of publicly available datasets impede the broad use of DCNNs for medical image processing. This work proposes a novel deep learning-based framework for efficient detection of brain tumors across different openly accessible datasets of different sizes and modalities of images. The introduction of a novel end-to-end Cumulative Learning Strategy (CLS) and Multi-Weighted New Loss (MWNL) function reduces the impact of unevenly distributed datasets. In the suggested framework, the DCNN model is incorporated with regularization, such as DropOut and DropBlock, to mitigate the problem of over-fitting. Furthermore, the suggested augmentation approach, Modified RandAugment, successfully deals with the issue of limited availability of data. Finally, the employment of K-nearest neighbor (KNN) improves the classification performance since it retains the benefits of both deep learning and machine learning. Moreover, the effectiveness of the proposed framework is also validated over small and imbalanced datasets. The proposed framework outperforms others with an accuracy of up to $ 99.70\%$.

关键词： Tumors Databases Accuracy Magnetic resonance imaging Training Brain modeling Nearest neighbor methods Brain tumors convolutional neural network data augmentation deep learning machine learning MRI

来源：评论

学校读者我要写书评

暂无评论

Generative Artificial intelligence for Hyperspectral Sensor Data: A Review

引用

ieee JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 6422-6439页

作者： Abuhani, Diaa Addeen Zualkernan, Imran Aldamani, Raghad Alshafai, Mohamed Amer Univ Sharjah Dept Comp Sci & Engn Sharjah 26666 U Arab Emirates

Airborne platforms and satellites provide rich sensor data in the form of hyperspectral images (HSI), which are crucial for numerous vision-related tasks, such as feature extraction, image enhancement, and data synthesis. This article reviews the contextual importance and applications of generative artificial intelligence (GAI) in the advancement of HSI processing. GAI methods address the inherent challenges of HSI data, such as high dimensionality, noise, and the need to preserve spectral-spatial correlations, rendering them indispensable for modern HSI analysis. Generative neural networks, including generative adversarial networks and denoising diffusion probabilistic models, are highlighted for their superior performance in classification, segmentation, and object identification tasks, often surpassing traditional approaches, such as U-Nets, autoencoders, and deep convolutional neural networks. Diffusion models showed competitive performance in tasks, such as feature extraction and image resolution enhancement, particularly in terms of inference time and computational cost. Transformer architectures combined with attention mechanisms further improved the accuracy of generative methods, particularly for preserving spectral and spatial information in tasks, such as image translation, data augmentation, and data synthesis. Despite these advancements, challenges remain, particularly in developing computationally efficient models for super-resolution and data synthesis. In addition, novel evaluation metrics tailored to the complex nature of HSI data are needed. This review underscores the potential of GAI in addressing these challenges while presenting its current strengths, limitations, and future research directions.

关键词： Feature extraction Hyperspectral imaging image segmentation Satellites Spatial resolution Machine learning Neural networks Reviews Noise measurement Data models Diffusion models generative adversarial networks (GANs) generative artificial intelligence (GAI) generative neural networks (GNNs) hyperspectral images

来源：评论

学校读者我要写书评

暂无评论

2025 ieee symposium on computational intelligence in Health and Medicine, CIHM 2025

2025 IEEE Symposium on Computational Intelligence in Health ...

引用

2025 ieee symposium on computational intelligence in Health and Medicine, CIHM 2025

ISBN: (纸本)9798331508333

The proceedings contain 17 papers. The topics discussed include: transforming medical practice: harnessing the power of big data and machine learning for predictive precision medicine;algebraic reproduction of triage decision making on simple heuristics of Boolean multivalued logic;deep learning on Hester Davis scores for inpatient fall prediction;comparative analysis and evaluation of well-being activity-infused fine-tuned language models with benchmark models;application of fuzzy-based uncertainty in cardiac MRI segmentation;images of stress: investigating image encodings and transfer learning for stress detection;training deep neural networks with multi-objective Adam optimizer for medical image classification;and deep-learning classifiers for small data orthopedic radiology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simultaneously Learning Deep Quaternion Reconstruction and Noise Convolutional Dictionary for Color image Denoising

引用

ieee TRANSACTIONS ON EMERGING TOPICS IN computational intelligence 2025年第2期9卷 1766-1779页

作者： Zhou, Zheng Chen, Yongyong Zhou, Yicong Univ Macau Dept Comp & Informat Sci Macau 999078 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Shenzhen 518055 Peoples R China

Recently, many deep convolutional dictionary learning-based methods, integrating the traditional image representation methods with deep neural networks, have achieved great success in various image processing tasks. However, the existing approaches can be further improved with the following considerations: (1) They congenitally suffer from the high cross-channel correlation loss for color image processing tasks since they usually treat each color channel independently, not in a whole perspective. (2) They only build up a single reconstruction dictionary learning model to directly approximate images using several single dictionary atoms, which cannot make full use of the representative ability of the model. In this paper, we propose a simultaneously learning deep quaternion reconstruction and noise convolutional dictionary model. To fully explore the cross-channel correlation, we use the quaternion method to process the color image in a holistic way. An adaptive attentional weight of reconstruction and noise learning module is also developed for the optimal combination between reconstruction and noise learning. Experimental results for synthesis and real color image denoising have demonstrated the superiority of the proposed method over other state-of-the-art methods.

关键词： Quaternions Dictionaries Color image reconstruction image color analysis Convolution Noise reduction Deep unfolding learning color image denoising quaternion

来源：评论

学校读者我要写书评

暂无评论

Multilogic Sense Amplifier With a Circuit for Dynamic Reference Voltage Generation

引用

ieee TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2025年

作者： Chang, Yen-Jen Tsai, Kun-Lin Cheng, Chun Chen, Xu-Yao Natl Chung Hsing Univ Dept Comp Sci & Engn Taichung 402202 Taiwan Tunghai Univ Dept Elect Engn Taichung 407224 Taiwan Tunghai Univ Res Ctr Smart Sustainable Circular Econ Taichung 407224 Taiwan

The rapid development of artificial intelligence (AI) systems has engendered a considerable increase in the computational power required in data-intensive applications, including facial recognition and image processing applications. The conventional von Neumann architecture, in which large quantities of data are transmitted between processing units and memory units, creates a bottleneck in AI applications. In-memory computing (IMC) offers an efficient solution to this problem by enabling computations within memory units, thus reducing the need for data transmission. This paper proposes a multilogic sense amplifier (MSA) with a dynamic reference voltage (DRV) generation circuit (hereafter denoted as MSA-DRV) to enhance the performance and reduce the power consumption of static random-access memory (SRAM)-based IMC. The proposed MSA-DRV performs six logic operations, namely the AND, NAND, OR, NOR, XOR, and XNOR operations, within an SRAM array by using a novel DRV circuit. The DRV circuit enables the voltage threshold to be adaptively changed according to the requirements of different operations. Experimental results indicated that the proposed MSA-DRV had lower computational latency (on average 29.9% lower) and power consumption (on average 30.6% lower) than did a conventional sense amplifier design and reconfigurable assist sense amplifier. Thus, the proposed design can overcome the von Neumann bottleneck to facilitate high-speed, energy-efficient data processing, which is crucial for AI-based and other data-intensive applications.

关键词： Circuits Logic Transistors Discharges (electric) Power demand SRAM cells Artificial intelligence Voltage Logic gates High-voltage techniques Dynamic reference voltage (DRV) in-memory computing (IMC) multilogic operations sense amplifier

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Deep Learning for Cloud Detection Onboard Nanosatellite

引用

ieee JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 9968-9985页

作者： Khalil, Imane Daghouri, Amina Chanoui, Mohammed Alae Guennoun, Zouhair Addaim, Adnane Mohammed V Univ Univ Ctr Res Space Technol Mohammadia Sch Engineers Rabat Morocco

Deep learning has been increasingly utilized for cloud detection in Earth observation nanosatellites, offering effective solutions to enhance mission performance. Traditional methods of image capture, onboard storage, and transmission face challenges such as bandwidth limitations and the transmission of cloud-obstructed images, highlighting the need for efficient onboard artificial intelligence. However, energy consumption remains a critical consideration for onboard processing, particularly in nanosatellites where resource constraints are significant. To address these challenges, we propose an optimized SegNet-based deep learning model implemented on the STM32H7 microcontroller for real-time cloud detection, designed to operate within the nanosatellite's strict energy budget. This work, conducted within the project of the UM5-EOSat nanosatellite mission, utilized captured images from the Gecko imager for model evaluation. The customized SegNet architecture, tailored with minimal kernels and layers, achieved an accuracy of 93.50%, effectively balancing performance and computational efficiency. Quantization further optimized energy consumption, achieving a reduction of 82.2% at 280 MHz. The quantized model demonstrated a memory footprint of 304 KB RAM and 110 KB Flash memory, with an inference time of 0.21 s and an energy consumption of 31.41 mJ, ensuring compatibility with the nanosatellite's resource constraints.

关键词： computational modeling Accuracy Energy consumption Clouds Memory management Artificial intelligence Deep learning computational efficiency Power demand Microcontrollers Cloud detection deep learning energy consumption nanosatellite TinyML

来源：评论

学校读者我要写书评

暂无评论

A Novel Clutter Suppression Algorithm for Airborne Radar via Subspace Projection

引用

ieee SENSORS JOURNAL 2025年第1期25卷 962-970页

作者： Zhang, Xinying Wang, Tong Cui, Weichen Wang, Degen Xidian Univ Natl Key Lab Radar Signal Proc Xian 710071 Peoples R China Beijing Aerosp Automatic Control Inst Natl Key Lab Sci & Technol Aerosp Intelligence Con Beijing 100854 Peoples R China Southwest China Res Inst Elect Equipment Chengdu 610036 Peoples R China

Strong ground clutter submerges the moving targets and hinders the radar image analysis. An effective technique called space-time adaptive processing (STAP) is used to suppress clutter in airborne radar systems but has the disadvantage of large training sample requirements. Sparse recovery STAP (SR-STAP) has the benefit of improving the algorithm performance when the training sample size is small. However, the computational burden and storage space restrict the practical application of SR-STAP. To address this issue, a fast subspace-based SR-STAP algorithm is proposed in this article. Using the Bayesian framework, the proposed algorithm selects the most matched atoms to span a clutter subspace by minimizing the likelihood function. In comparison with the existing SR-STAP algorithm, the proposed algorithm avoids the time-consuming sparse reconstruction process. Moreover, the estimated subspace can be applied to gain-phase error calibration. The proposed algorithm is experimentally demonstrated to have superior performances in terms of clutter suppression, target detection, and computational complexity.

关键词： Clutter Vectors Noise Training Sensors Airborne radar Signal processing algorithms Object detection Bayes methods Atoms Clutter suppression gain-phase errors space-time adaptive processing (STAP) sparse recovery subspace estimated

来源：评论

学校读者我要写书评

暂无评论

Special Vehicle Classification Algorithm-Based System for Dedicated Parking Zone Violation Detection in South Korea

引用

ieee ACCESS 2025年 13卷 7883-7901页

作者： Park, Hyunseong Kim, Kapyeol Jeong, Incheol Jung, Jungil Cho, Jinsoo Gachon Univ Coll IT Dept IT Convergence Engn Seongnam Si 13120 South Korea PCT Co Ltd Seongnam Si 13449 South Korea Gachon Univ Dept Comp Engn Seongnam Si 13120 South Korea

To address the problem of managing dedicated parking zones arising from the increasing number of electric vehicles and vehicles for the physically challenged, this paper proposes a license plate recognition (LPR)-based parking control system that combines the YOLO and MobileNet algorithms. These two algorithms are designed for real-time object detection and efficient preprocessing, respectively, and can operate in real time in resource-constrained edge-device environments. In tests using data from more than 51,000 vehicles, the system achieved an accuracy rate of 95.76% in classifying electric vehicles and 97.18% in classifying vehicles for the physically challenged. The average CPU and RAM utilizations of the system were 34.54% and 45.04%, respectively. In addition, the processing time per image was recorded as approximately 1.04 s, demonstrating its potential to run reliably on edge devices. These results are expected to facilitate the efficient resolution of parking management problems in smart cities and effective operation of parking zones reserved for electric vehicles and vehicles for the physically challenged.

关键词： Real-time systems YOLO Accuracy License plate recognition Classification algorithms Artificial intelligence Feature extraction computational modeling computational efficiency Smart cities bounding box license plate recognition (LPR) MobileNet optical character recognition (OCR) video processing

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Neural Architecture Search Framework With Masked Encoding Mechanism for Point Cloud Registration

引用

ieee TRANSACTIONS ON EMERGING TOPICS IN computational intelligence 2025年

作者： Wu, Yue Gong, Peiran Yuan, Yongzhe Gong, Maoguo Ma, Wenping Miao, Qiguang Xidian Univ Sch Comp Sci & Technol Minist Educ Key Lab Collaborat Intelligence Syst Xian 710071 Peoples R China Xidian Univ Sch Elect Engn Minist Educ Key Lab Collaborat Intelligence Syst Xian 710071 Peoples R China Inner Mongolia Normal Univ Acad Artificial Intelligence Coll Math Sci Hohhot 010022 Peoples R China Xidian Univ Sch Artificial Intelligence Minist Educ Key Lab Intelligent Percept & Image Understanding Xian 710071 Peoples R China

Deep learning-based point cloud registration (PCR) has received increasing attention in the field of computer vision. However, the lack of expertise in deep neural network architecture design remains a large obstacle for end-users with registration needs. While neural architecture search (NAS) indeed addresses the architecture automation design problem and has undergone substantial development, the majority of existing NAS approaches are tailored for image processing. Because of significant differences in data characteristics and network structures, directly transferring the existing NAS approaches for PCR is infeasible. Hence, this work proposes an evolutionary neural architecture search framework for PCR, which can fit the different types of PCR networks. The framework, equipped with the designed masked encoding mechanism, can seamlessly integrate with the majority of evolutionary computation-based optimization algorithms, thereby reducing the additional cost of operator design. Based on the above framework, the users can freely select the advanced network components and optimization algorithms depending on their needs. Experimental results on synthetic and real-world datasets, ModelNet40 and KITTI, demonstrate the superiority of the proposed framework in terms of registration precision and architecture complexity.

关键词： Feature extraction Point cloud compression Encoding Computer architecture Data mining Accuracy Three-dimensional displays Decoding Transformers Neural architecture search Point cloud registration evolutionary neural architecture search novel encoding mechanism

来源：评论

学校读者我要写书评

暂无评论

CVIformer: Cross-View Interactive Transformer for Efficient Stereoscopic image Super-Resolution

引用

ieee TRANSACTIONS ON EMERGING TOPICS IN computational intelligence 2025年第2期9卷 1107-1118页

作者： Zhang, Dongyang Liang, Shuang He, Tao Shao, Jie Qin, Ke Univ Elect Sci & Technol China Inst Intelligent Comp Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Peoples R China

Inspired by the great success of the Transformer in computer vision, some works have started to explore the use of the Transformer for super-resolution (SR). However, with regard to stereoscopic SR, which aims to recover details from input pairs, how to efficiently integrate cross-view interactions into the Transformer architecture is still an ongoing development. Additionally, most existing stereoscopic SR methods only adopt a parallax mechanism in the middle of the network, and another issue is that the feature correlation from different viewpoints inevitably weakens as the network depth increases. To address these issues, we first utilize an efficient residual transformer block (ERTB) as the backbone for long-range intra-view feature extraction. Subsequently, we propose a novel multi-Dconv cross attentive block (MCAB) to enhance the cross-view interactions at the rear part of the Transformer architecture. Notably, the proposed MCAB promotes feature fusion from two viewpoints by employing bidirectional cross-attention, as opposed to an unidirectional flow from left to right or vice versa. This approach results in an efficient cross-view interaction from both branches. By leveraging the advantages of the proposed ERTB and MCAB, we introduce an efficient cross-view interaction Transformer (CVIformer) for stereoscopic SR. This architecture is capable of incorporating long-range intra-view and cross-view information with an acceptable computational overhead. Without excessive complexity, extensive experiments conducted on four public datasets demonstrate that our model achieves state-of-the-art results using only 1.17 million parameters, with approximately a 40% reduction in parameters compared to leading methods like iPASSR.

关键词： Transformers Stereo image processing Feature extraction Superresolution Spatial resolution Cameras Task analysis Stereoscopic image processing lightweight transformer super-resolution (SR)

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：