检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Shin, Changmin Song, Jaeyong Jang, Hongsun Kim, Dogeun Sung, Jun Kwon, Taehee Ju, Jae Hyung Liu, Frank Choi, Yeonkyu Lee, Jinho Department of Electrical and Computer Engineering Seoul National University Korea Republic of School of Data Science Old Dominion Univeristy United States Samsung Electronics

Graph processing requires irregular, fine-grained random access patterns incompatible with contemporary off-chip memory architecture, leading to inefficient data access. This inefficiency makes graph processing an extremely memory-bound application. Because of this, existing graph processing accelerators typically employ a graph tiling-based or processing-in-memory (PIM) approach to relieve the memory bottleneck. In the tiling-based approach, a graph is split into chunks that fit within the on-chip cache to maximize data reuse. In the PIM approach, arithmetic units are placed within memory to perform operations such as reduction or atomic addition. However, both approaches have several limitations, especially when implemented on current memory standards (i.e., DDR). Because the access granularity provided by DDR is much larger than that of the graph vertex property data, much of the bandwidth and cache capacity are wasted. PIM is meant to alleviate such issues, but it is difficult to use in conjunction with the tiling-based approach, resulting in a significant disadvantage. Furthermore, placing arithmetic units inside a memory chip is expensive, thereby supporting multiple types of operation is thought to be impractical. To address the above limitations, we present Piccolo, an end-to-end efficient graph processing accelerator with fine-grained in-memory random scatter-gather. Instead of placing expensive arithmetic units in off-chip memory, Piccolo focuses on reducing the off-chip traffic with non-arithmetic function-in-memory of random scatter-gather. To fully benefit from in-memory scatter-gather, Piccolo redesigns the cache and miss-handling architecture (MHA) of the accelerator such that it can enjoy both the advantage of tiling and in-memory operations. Piccolo achieves a maximum speedup of 3.28× and a geometric mean speedup of 1.62×, along with up to 59.7% reduction in energy consumption across various and extensive benchmarks. © 2025, CC BY-NC-ND.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

A Novel Dynamic Watermarking for Secure data Protection from Cyber Theft Based on Artificial Intelligence Supervision 8

A Novel Dynamic Watermarking for Secure Data Protection from...

引用

8th IEEE International Conference on science, Technology, Engineering and Mathematics, ICONSTEM 2023

作者： Madala, Ravikiran Monica, R. Malwade, Sulakshana Sagar Selvakumaran, S. Budhavale, Shilpa Jivan Sathyabalaji, N. University of Cumberlands Information Technology DurhamNC United States Nandha Engineering College Department of Electronics and Communication Engineering Tamilnadu Erode52 India Dr.Vishwanath Karad School of Polytechnic and Skill Development Department of Computer Engineering Maharashtra Pune India Rajalakshmi Institute of Technology Department of Artificial Intelligence and Data Science Tamilnadu Chennai India Dr. Vishwanath Karad School of Polytechnic and Skill Development Department of Computer Engineering Maharashtra Pune India Jkk Munirajah College of Technology Department of Computer Science and Engineering Tamilnadu Erode India

ISBN: (纸本)9798350347791

One of the centre innovations of the Fourth Modern Insurgency (otherwise called Industry 4.0) is artificial intelligence (computer based intelligence), which can be utilized to shield Web associated gadgets from dangers, assaults, harm, and undesirable access. The current range of cyber security issues can be deftly handled by utilising well-known simulated intelligence techniques such as AI and profound learning procedures, the possibility of normal language handling, information portrayal and thinking, as well as the possibility of information or rule-based master frameworks displaying. In view of these man-made intelligence strategies, we give an exhaustive examination of "Simulated intelligence driven cyber security"in this article, which may be helpful for clever cyber security government agencies and the board. The cyber security registration method can be made more computerised and intelligent than the standard security frameworks by the security intelligence exhibiting in light of such simulated intelligence ***, we present various choices for future examination that fall inside the domain of our examination. At last, this paper's primary objective is to give direction and references to industry specialists in the field of cyber security, especially from a canny registering or simulated intelligence based specialized viewpoint. © 2023 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

MOT: A Multi-Omics Transformer for Multiclass Classification Tumour Types Predictions

MOT: A Multi-Omics Transformer for Multiclass Classification...

引用

16th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2023

作者： Abiodoun Osseni, Mazid Tossou, Prudencio Laviolette, FrancOis Corbeil, Jacques GRAAL Institute Intelligence and Data Department of Computer Science and Software Engineering Université Laval QuebecQC Canada Valence AI Discovery MontréalQC Canada Department of Molecular Medicine Université Laval QuebecQC Canada

Motivation: Breakthroughs in high-throughput technologies and machine learning methods have enabled the shift towards multi-omics modelling as the preferred means to understand the mechanisms underlying biological processes. Machine learning enables and improves complex disease prognosis in clinical settings. However, most multi-omic studies primarily use transcriptomics and epigenomics due to their over-representation in databases and their early technical maturity compared to others omics. For complex phenotypes and echanisms, not leveraging all the omics despite their varying degree of availability can lead to a failure to understand the underlying biological mechanisms and leads to less robust classifications and predictions. Results: We proposed MOT (Multi-Omic Transformer), a deep learning based model using the transformer architecture, that discriminates complex phenotypes (herein cancer types) based on five omics data types: transcriptomics (mRNA and miRNA), epigenomics (DNA methylation), copy number variations (CNVs), and proteomics. This model achieves an F1-score of 98:37% among 33 tumour types on a test set without missing omics views and an F1-score of 96:74% on a test set with missing omics views. It also identifies the required omic type for the best prediction for each phenotype and therefore could guide clinical decision-making when acquiring data to confirm a diagnostic. The newly introduced model can integrate and analyze five or more omics data types even with missing omics views and can also identify the essential omics data for the tumour multiclass classification tasks. It confirms the importance of each omic view. Combined, omics views allow a better differentiation rate between most cancer diseases. Our study emphasized the importance of multi-omic1 data to obtain a better multiclass cancer classification. Availability and implementation: MOT source code is available at predictions. © 2023 by SCITEPRESS – science and Technology Publications,

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE Q-NETWORK: ON-THE-FLY TARGET SELECTION FOR DEEP REINFORCEMENT LEARNING

arXiv

引用

arXiv 2024年

作者： Vincent, Théo Wahren, Fabian Peters, Jan Belousov, Boris D’Eramo, Carlo DFKI GmbH SAIROL Germany Department of Computer Science TU Darmstadt Germany Hessian.ai TU Darmstadt Germany Center for AI and Data Science University of Würzburg Germany

Deep Reinforcement Learning (RL) is well known for being highly sensitive to hyperparameters, requiring practitioners substantial efforts to optimize them for the problem at hand. This also limits the applicability of RL in real-world scenarios. In recent years, the field of automated Reinforcement Learning (AutoRL) has grown in popularity by trying to address this issue. However, these approaches typically hinge on additional samples to select well-performing hyperparameters, hindering sample-efficiency and practicality. Furthermore, most AutoRL methods are heavily based on already existing AutoML methods, which were originally developed neglecting the additional challenges inherent to RL due to its non-stationarities. In this work, we propose a new approach for AutoRL, called Adaptive Q-Network (AdaQN), that is tailored to RL to take into account the non-stationarity of the optimization procedure without requiring additional samples. AdaQN learns several Q-functions, each one trained with different hyperparameters, which are updated online using the Q-function with the smallest approximation error as a shared target. Our selection scheme simultaneously handles different hyperparameters while coping with the non-stationarity induced by the RL optimization procedure and being orthogonal to any critic-based RL algorithm. We demonstrate that AdaQN is theoretically sound and empirically validate it in MuJoCo control problems and Atari 2600 games, showing benefits in sample-efficiency, overall performance, robustness to stochasticity and training stability. Our code is available at https://***/theovincent/AdaDQN. © 2024, CC BY-NC-ND.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Learning Method for Thyroid Nodule Detection and Evaluation in Ultrasound Images 2

Advanced Deep Learning Method for Thyroid Nodule Detection a...

引用

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

作者： Sesha Vidhya, S. Sarkar, Swagata Rashmi, B.R. Suseendra, S. Prakash Kumar, P.S. Srimathi, S. RMK College of Engineering and Technology Department of ECE India Science Sri Sairam Engineering College Sai Leo Nagar West Tambaram Department of Artificial Intelligence and Data Chennai44 India Raja Rajeswari College of Engineering Department of Computer Science and Engineering Kumbalgodu Karnataka560074 India Panimalar Engineering College Department of Information Technology India K S R Institute for Engineering and Technology Department of Information Technology Tiruchengode Namakkal637215 India Saveetha School of Engineering SIMATS Department of Bio Technology Tamilnadu Chennai India

ISBN: (纸本)9798350327533

Thyroid nodule detection in its earliest stages is a difficult endeavor. Thyroid nodule diagnosis requires a lot of time and effort if done manually. The original ultrasound imaging of thyroid nodules is very variable due to differences in equipment and technicians. The issue with nodules is determining whether or not they are cancerous. Thyroid nodule evaluation through ultrasonography is presently advised as the first line of treatment. Ultrasound imaging can be helpful in making a diagnosis;But this relies heavily on the proficiency of the radiologist. There is a great need for faster and more efficient automated techniques of screening ultrasound pictures. This research study presents a deep learning method to detect thyroid nodules quickly and accurately. Some image processing techniques are required for optimal utilization of ultrasound imaging data of thyroid nodules. In this study, authors used deep neural networks InceptionResnet V2 and image augmentation to create a system for autonomous thyroid nodule categorization. For testing, neural networks with four-layer network nodes and the Local Laplacian Filtering technique are used to improve the image quality. The proposed method's reliability is evaluated by using the Thyroid Digital Image database (TDID), a freely available dataset. The comparative findings demonstrate that the proposed method is superior to the current state of advancement in machine learning. Based on experiments, it is evident that the proposed technique has an Accuracy 0.99, Precision 0.98, Recall 0.96, Fl-Score 0.98, AVC-ROC 0.99. © 2024 IEEE.

关键词： Deep Learning Image Augmentation INCEPTIONRESNET Thyroid Nodule Detection Ultrasound Imaging

来源：评论

学校读者我要写书评

暂无评论

Exploring Sub-Nyquist Sampling for Fine Image Reconstruction

Exploring Sub-Nyquist Sampling for Fine Image Reconstruction

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： M Nithya S Satheeshkumar M Dakshana K Gunalan P Anandan R Saveetha Department of Computer Technology Bannari Amman Institute of Technology Tamilnadu India Department of Artificial intelligence and data science Bannari Amman Institute of Technology Tamilnadu India Department of Physics Sathyabama Institute of Science and Technology Tamilnadu India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Compared to traditional methods, compressive sensing, a signal processing technique, allows for the effective acquisition and reconstruction of signals. A rate that is less than twice the highest frequency component of a signal is known as subNyquist sampling, allows for the digitization of wideband frequency-domain sparse signals without compromising reconstruction quality when employing compression sensing (CS). According to the CS framework, samples taken at sub- Nyquist sampling rates can be used to reconstruct signals with sparse representations in a known basis. Because of its inherent qualities, the Fourier domain is frequently used in compressive sensing applications. Use of a small number of Fourier transform coefficients in sparse signal recovery applications has led to successful resolutions of large-scale data recovery issues, including image recovery. During the measurement phase, input is systematically measured in blocks to obtain the necessary data, while in the recovery phase, all measurements from a single image are simultaneously utilized to reconstruct the complete image.

关键词： Phase measurement Image resolution Sparse approximation Frequency-domain analysis Matching pursuit algorithms Sensors Image reconstruction Compressed sensing Wideband Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Multilayer perceptron ensembles in a truly sparse training context

引用

Neural Computing and Applications 2025年

作者： van der Wal, Peter R. D. Strisciuglio, Nicola Azzopardi, George Mocanu, Decebal Constatin Information Systems Group Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Nijenborgh 9 Groningen9747 AG Netherlands Data Management and Biometrics Group Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Hallenweg 19 Enschede7522 NH Netherlands Department of Computer Science Faculty of Science Technology and Medicine University of Luxembourg Maison du Nombre 6 avenue de la Fonte Esch4364 Luxembourg

Ensemble learning for artificial neural networks (ANNs) is an effective method to enhance predictive performance. However, ANNs are computationally and memory intensive, and naively training multiple networks can lead to excessive training times and costs. An effective tool for improving ensemble efficiency is introducing topological sparsity. Even though several implementations of efficient ensembles have been proposed, none of them can provide actual benefits in terms of computational overhead as the sparsity is simulated using binary masks. In this paper, we address this issue by introducing a Truly Sparse Ensemble without binary masks and directly incorporate native sparsity. We also propose two algorithms for initializing new subnetworks within the ensemble, leveraging this native topological sparsity to enhance subnetwork diversity. We demonstrate the performance of the resulting models at high levels of sparsity on several datasets in terms of classification accuracy, floating point operations (FLOPs), and actual running time. The proposed methods outperform all baseline dense and truly sparse models on tabular data, successfully diversify the training trajectory of the subnetworks, and increase the topological distance between subnetworks after re-initialization. © The Author(s) 2025.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

Unified Binary and Multiclass Margin-Based Classification

arXiv

引用

arXiv 2023年

作者： Wang, Yutong Scott, Clayton Department of Electrical Engineering and Computer Science Michigan Institute of Data Science United States Department of Statistics University of Michigan Ann ArborMI48109 United States

The notion of margin loss has been central to the development and analysis of algorithms for binary classification. To date, however, there remains no consensus as to the analogue of the margin loss for multiclass classification. In this work, we show that a broad range of multiclass loss functions, including many popular ones, can be expressed in the relative margin form, a generalization of the margin form of binary losses. The relative margin form is broadly useful for understanding and analyzing multiclass losses as shown by our prior work (Wang and Scott, 2020, 2021). To further demonstrate the utility of this way of expressing multiclass losses, we use it to extend the seminal result of Bartlett et al. (2006) on classification-calibration of binary margin losses to multiclass. We then analyze the class of Fenchel-Young losses, and expand the set of these losses that are known to be classification-calibrated. © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Enhancing Pulmonary Nodule Classification performance with TriCaps-RL: A Capsule Network Reinforcement Learning Approach

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1441-1459页

作者： Zheng, Guang-Yuan Zhang, Fu-Quan Cheng, Chen Shan, Hong-Tao Soomro, Nouman Qadeer Liu, Yi College of Information Technology Shanghai Jian Qiao University Shanghai201306 China School of Mathematics and Computer Science Yanan University Shaanxi 716000 China School of Computer and Data Science Minjiang University No.200 Xiyuangong Road Fuzhou University Town Fuzhou350108 China Digital Media Art Key Laboratory of Sichuan Province Sichuan Conservatory of Music Chengdu610021 China Fuzhou Technology Innovation Center of intelligent Manufacturing information System Minjiang University Fuzhou350108 China Fujian Province University Fuzhou350300 China College of Business Shanghai Jian Qiao University Shanghai201306 China College of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai201620 China Software Department Mehran University of Engineering & Technology Sindh 76062 Pakistan

Distinguishing the manifestations of pulmonary nodules poses a significant challenge in the medical field, demanding the expertise of experienced radiologists. This complexity results in the high cost and inadequacy of sample labeling. In response, this study introduces a reinforcement learning approach, denoted as TriCaps-RL, for the classification of pulmonary nodules based on CT signs. This approach initially employs the Q-value loss to train a single CapsNet. When the performance of the CapsNet plateaus and further enhancement becomes challenging, the loss function is progressively replaced by a triplet metric to augment performance. Consequently, a more nuanced differentiation among various types of pulmonary nodules is achieved. The proposed method can improve its performance through interactions with radiologists during their CT image reading process, thereby mitigating the shortage of radiologists and addressing the time-consuming issue of training sample labeling in medical image research. This paper delves into the fine-grained classification of pulmonary nodules using deep reinforcement learning based on CT imaging signs. In comparison to previous studies that primarily concentrate on the benign/malignant classification of lung nodules, this fine-grained classification of nodules founded on CT imaging signs proves to be more valuable for medical practitioners in making accurate diagnostic decisions. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Intelligent Deep Learning Based Multi-Retinal Disease Diagnosis and Classification Framework

引用

computers, Materials & Continua 2022年第12期73卷 5543-5557页

作者： Thavavel Vaiyapuri S.Srinivasan Mohamed Yacin Sikkandar T.S.Balaji Seifedine Kadry Maytham N.Meqdad Yunyoung Nam College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj16278Saudi Arabia Saveetha School of Engineering Saveetha Institute of Medical and Technical SciencesSaveetha NagarThandalamChennai602105India Department of Medical Equipment Technology College of Applied Medical SciencesMajmaah UniversityAl Majmaah11952Saudi Arabia Saveetha School of Engineering Saveetha Institute of Medical and Technical SciencesChennai602105India Department of Electronics and Communication Engineering College of Engineering&TechnologySRM Institute of Science and TechnologyVadapalani CampusChennai600026India Department of Applied Data Science Noroff University CollegeKristiansand4608Norway Department of Computer Techniques Engineering Al-Mustaqbal University CollegeHillahBabil51001Iraq Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea

In past decades,retinal diseases have become more common and affect people of all age grounds over the *** examining retinal eye disease,an artificial intelligence(AI)based multilabel classification model is needed for automated *** analyze the retinal malady,the system proposes a multiclass and multi-label arrangement ***,the classification frameworks based on features are explicitly described by ophthalmologists under the application of domain knowledge,which tends to be time-consuming,vulnerable generalization ability,and unfeasible in massive ***,the automated diagnosis of multi-retinal diseases becomes essential,which can be solved by the deep learning(DL)*** this motivation,this paper presents an intelligent deep learningbased multi-retinal disease diagnosis(IDL-MRDD)framework using fundus *** proposed model aims to classify the color fundus images into different classes namely AMD,DR,Glaucoma,Hypertensive Retinopathy,Normal,Others,and Pathological ***,the artificial flora algorithm with Shannon’s function(AFA-SF)basedmulti-level thresholding technique is employed for image segmentation and thereby the infected regions can be properly *** addition,SqueezeNet based feature extractor is employed to generate a collection of feature ***,the stacked sparse Autoencoder(SSAE)model is applied as a classifier to distinguish the input images into distinct retinal *** efficacy of the IDL-MRDD technique is carried out on a benchmark multi-retinal disease dataset,comprising data instances from different *** experimental values pointed out the superior outcome over the existing techniques with the maximum accuracy of 0.963.

关键词： Multi-retinal disease computer aided diagnosis fundus images deep learning segmentation intelligent models

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：