检索结果-内蒙古大学图书馆

DSANet: dilated spatial attention network for the detection of text, non-text and touching components in unconstrained handwritten documents

引用

Neural Computing and Applications 2024年第27期36卷 16959-16976页

作者： Bhowmik, Showmik Risat, Shaikh Sarkar, Bhaskar Research Lab Department of Computer Science and Engineering Ghani Khan Choudhury Institute of Engineering and Technology Malda India

Handwritten documents generated in our day-to-day office work, class room and other sectors of society carry vital information. Automatic processing of these documents is a pipeline of many challenging steps. The very first and crucial step is to identify text separately from the non-text as any OCR (optical character recognition) engine can only process the textual content. Separating text from non-text in unconstrained handwritten documents is a very complex task. In addition to other challenges, touching component is one of the major issues for text non-text separation in unconstrained handwritten documents. Detection of text, non-text along with touching component in such documents is an unexplored area of research. To address this issue, in this work, we develop a dilated spatial attention-based network for text, non-text and touching component detection. Additionally, in this work, we also prepare a realistic dataset for the said task. In the proposed dataset, the present model obtains overall accuracy of 87.85%. The performance of the present model is compared with seven feature-engineering-based methods and six deep learning-based methods. In most of the cases, the proposed model outperforms the comparing methods in the proposed dataset. The codes of our method are available here https://***/Showmik-Bhowmik/DSANet-Dilated-Spatial-Attention-.git. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

NEXUS: A 28nm 3.3pJ/SOP 16-Core Spiking Neural Network with a Diamond Topology for Real-Time Data Processing

引用

IEEE Transactions on Biomedical Circuits and Systems 2024年第3期19卷 1-13页

作者： Sadeghi, Maryam Rezaeiyan, Yasser Khatiboun, Dario Fernandez Eissa, Sherif Corradi, Federico Augustine, Charles Moradi, Farshad Department of Electrical and Computer Engineering Aarhus University Aarhus Denmark Department of Electrical Engineering Eindhoven University of Technology Eindhoven The Netherlands Circuit Research Lab Intel Hillsboro OR USA

The realization of brain-scale spiking neural networks (SNNs) is impeded by power constraints and low integration density. To address these challenges, multi-core SNNs are utilized to emulate numerous neurons with high energy efficiency, where spike packets are routed through a network-on-chip (NoC). However, the information can be lost in the NoC under high spike traffic conditions, leading to performance degradation. This work presents NEXUS, a 16-core SNN with a diamond-shaped NoC topology fabricated in 28-nm CMOS technology. It integrates 4096 leaky integrate-and-fire (LIF) neurons with 1M 4-bit synaptic weights, occupying an area of 2.16 mm2. The proposed NoC architecture is scalable to any network size, ensuring no data loss due to contending packets with a maximum routing latency of 5.1μs for 16 cores. The proposed congestion management method eliminates the need for FIFO in routers, resulting in a compact router footprint of 0.001 mm2. The proposed neurosynaptic core allows for increasing the processing speed by up to 8.5× depending on input sparsity. The SNN achieves a peak throughput of 4.7 GSOP/s at 0.9 V, consuming a minimum energy per synaptic operation (SOP) of 3.3 pJ at 0.55 V. A 4-layer feed-forward network is mapped onto the chip, classifying MNIST digits with 92.3% accuracy at 8.4Kclassification/ s and consuming 2.7-μJ/classification. Additionally, an audio recognition task mapped onto the chip achieves 87.4% accuracy at 215-μJ/classification. IEEE

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Partial Sum Attack on Round-Reduced AES Utilizing Parallel Computation Approaches

引用

SN computer Science 2025年第3期6卷 1-21页

作者： Pal, Debranjan Gupta, Ankit Das, Abhijit Chowdhury, Dipanwita Roy Crypto Research Lab Department of Computer Science and Engineering IIT Kharagpur West Bengal Kharagpur 721301 India

The Advanced Encryption Standard (AES) is a widely recognized, extensively utilized, and thoroughly studied industry-standard symmetric key block cipher. Consequently, cryptanalysis of AES is a highly relevant and significant task for cryptography researchers. In the field of cryptanalysis, the Square attack is a powerful key recovery technique used against symmetric ciphers. This study aims to provide two efficient implementations of the partial sum attack (PSA), a variant of the square attack, on reduced rounds of AES. The goal is to demonstrate the effectiveness of these implementations in terms of reduced time complexity for full key recovery. We demonstrate two efficient implementations of PSA on reduced rounds of AES. The first implementation is a GPU-based attack applied to five and six rounds of AES, achieving full key recovery in 0.8s and 7.58 days, respectively. The second implementation is cluster-based, applied to six rounds of AES, with an elapsed time of 2.5 days for full key recovery. Both implementations leverage parallelization to enhance performance, showing a significant reduction in attack time proportional to the number of working threads. The findings confirm that PSA effectively reduces the time complexity for full key recovery in reduced rounds of AES, demonstrating the practicality and efficiency of these implementations. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： AES Chosen plaintext Cluster GPU Parallel computing Partial sum attack Square attack

来源：评论

学校读者我要写书评

暂无评论

Advancements in Image Caption Bots: A Deep Learning Approach 6

Advancements in Image Caption Bots: A Deep Learning Approach

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Dabral, Adarsh Gusain, Raj Shekhar, Sushant Vidyarthi, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Computer Science Engineering Dehradun India Propagation Research Lab Department of Electronics and Communication Engineering Dehradun India Kanpur India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350306613

In recent years, artificial intelligence (AI) has changed the area of computer vision, and image captioning is one of the many applications that have benefited from these advancements. An image caption bot is an intelligent system that generates a textual description of an image. This research paper will explore the development of image caption bots, the underlying technologies, and the various techniques used to build these systems. Image caption bots are developed with the help of deep learning models (DLM) such as convolutional neural networks (CNNs) the most popular nowadays and recurrent neural networks (RNN s) which is also popular in researchers. Featureextraction has been done from the images with CNN sand RNN s are used to generate the captions. These deep-learning models have significantly improved the accuracy and performance of image captioning systems. During training, the CNN extracts the relevant features from the images, and the RNN generates the corresponding captions. In order to decrease the discrepancy between generated and ground truth captions, the model is trained. The accuracy and efficiency of image caption procedures could be greatly increased by using the image caption bots developed in this research. These systems have several applications and can greatly aid visually impaired individuals in understanding images, assist search engines to better index and search images, and improve the accessibility of social media platforms for users with disabilities. Further research in this field could lead to more accurate and comprehensive Image captioning systems. © 2024 IEEE.

关键词： Caption-Bots CNN Deep Learning Image caption bot RNN

来源：评论

学校读者我要写书评

暂无评论

Development of LiFi System for Communication and Control in Hilly Regions 6

Development of LiFi System for Communication and Control in ...

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Dabral, Adarsh Gusain, Raj Vidyarthi, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Computer Science Engineering Dehradun India Propagation Research Lab Department of Electronics and Communication Engineering Dehradun India Department of Electronics and Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350306613

In hilly regions where cable distribution is challenging and costly traditional communication systems often face difficulties. LiFi technology emerges as a promising solution in such contexts, leveraging communication through visible light. It uses light as a medium to provide data speeds that surpass those of Wi-Fi, This research paper presents an approach for a communication system specifically designed for hilly terrains using Light Fidelity (LiFi) technology. The proposed paper start with an introduction of LiFi technology and advantages of it over conventional communication methods in these regions. However, it also acknowledges the inherent limitations of Li-Fi, such as its low range, which is especially relevant in hilly topographies. The main body of the paper details the system's architecture, comprising a transmitter for sending data, a receiver to receive data, and dual operation: text for sending massage and operate devices, and audio for communication. To underscore its practicality, the system is showcased through two applications: an SOS emergency feature for hilly terrains and a device activation/deactivation application. In conclusion, the paper provides an in-depth examination of how this tailored system functions and its potential benefits for communities and operations in hilly landscapes. © 2024 IEEE.

关键词： Arduino Hilly region communication methods Laser LiFi Microcontroller Remote Station Communication

来源：评论

学校读者我要写书评

暂无评论

A hybrid memory architecture supporting fine-grained data migration

引用

Frontiers of computer Science 2024年第2期18卷 31-41页

作者： Ye CHI Jianhui YUE Xiaofei LIAO Haikun LIU Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Department of Computer Science Michigan Technological UniversityMichigan 49931USA

Hybrid memory systems composed of dynamic random access memory(DRAM)and Non-volatile memory(NVM)often exploit page migration technologies to fully take the advantages of different memory *** previous proposals usually migrate data at a granularity of 4 KB pages,and thus waste memory bandwidth and DRAM *** this paper,we propose Mocha,a non-hierarchical architecture that organizes DRAM and NVM in a flat address space physically,but manages them in a cache/memory *** the commercial NVM device-Intel Optane DC Persistent Memory Modules(DCPMM)actually access the physical media at a granularity of 256 bytes(an Optane block),we manage the DRAM cache at the 256-byte size to adapt to this feature of *** design not only enables fine-grained data migration and management for the DRAM cache,but also avoids write amplification for Intel Optane *** also create an Indirect Address Cache(IAC)in Hybrid Memory Controller(HMC)and propose a reverse address mapping table in the DRAM to speed up address translation and cache ***,we exploit a utility-based caching mechanism to filter cold blocks in the NVM,and further improve the efficiency of the DRAM *** implement Mocha in an architectural *** results show that Mocha can improve application performance by 8.2%on average(up to 24.6%),reduce 6.9%energy consumption and 25.9%data migration traffic on average,compared with a typical hybrid memory architecture-HSCC.

关键词： non-volatile memory hybrid memory system data migration fine-grained caching

来源：评论

学校读者我要写书评

暂无评论

In-band full-duplex MIMO PLC systems for relaying networks

引用

Digital Communications and Networks 2025年第1期11卷 145-159页

作者： Francisco J.Canete Gautham Prasad Lutz Lampe Communications and Signal Processing Lab Telecommunication Research Institute(TELMA)ETS Ingenieria TelecomunicacionUniversidad de MalagaSpain Ofinno RestonVAUSA Department of Electrical and Computer Engineering The University of British ColumbiaCanada

In Power Line Communications(PLC),there are regulatory masks that restrict the transmit power spectral density for electromagnetic compatibility reasons,which creates coverage issues despite the not too long ***,PLC networks often employ repeaters/relays,especially in smart grid neighborhood area *** in broadband indoor PLC systems that offer a notable data rate,relaying may pave the way to new applications like being the backbone for wireless technologies in a cost-effective manner to support the Internet-of-things *** this paper,we study Multiple-Input Multiple-Output(MIMO)PLC systems that incorporate inband full-duplex functionality in relaying *** present several MIMO configurations that allow end-to-end half-duplex or full-duplex operations and analyze the achievable performance with state-of-the-art PLC *** reach this analysis,we get channel realizations from random network layouts for indoor and outdoor *** adopt realistic MIMO channel and noise models and consider transmission techniques according to PLC *** concepts discussed in this work can be useful in the design of future PLC relay-aided networks for different applications that look for a coverage extension and/or throughput:smart grids with enhanced communications in outdoor scenarios,and“last meter”systems for high-speed connections everywhere in indoor ones.

关键词： PLC MIMO Relaying networks OFDM Spatial correlation Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Unleashing Future Donors Navigating Blood Contribution Propensity with Machine Learning Expertise 1

Unleashing Future Donors Navigating Blood Contribution Prope...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Dhami, Kavindra Singh Gusain, Raj Shekhar, Sushant Vidyarth, Anurag Prakash, Rishi Gowri, R. Propagation Research Lab Department of Civil Engineering Dehradun India Propagation Research Lab Department of Electronics & Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350377002

The study used machine learning techniques, which are an essential component of blood donation and health care. Data details of blood donation and service centers have been included in this study. Some of these variables include the number of times a person donates, the frequency of donations, and the time since the last donation. Modern technology machine learning methods analyze and consider key factors in the model. This is valuable information for physicians and blood transfusion centers because here we can predict when a donor may be able to donate blood again. Furthermore, our study aims to examine not only donor behavior but also whether blood donation will provide a continued flow of blood products to health systems in the future. The study of blood donation system is enhanced by this analysis method, which also provides an indication to take care of the health care of the society. We have taken our extensive analysis into account and used cross-validation and performance F1 scores. Donor confidentiality, equity and ethics are equally important to us in the development of our studies. Our approach can play an important role in the technological development sector. Our aim is to draw attention to how donor contact strategies will work, and to improve this, with a view to making the blood supply more reliable. © 2024 IEEE.

关键词： Blood Donation Donor Propensity Healthcare Optimization Machine Learning Stable Blood Supply

来源：评论

学校读者我要写书评

暂无评论

Beyond p-y method:A review of artificial intelligence approaches for predicting lateral capacity of drilled shafts in clayey soils

引用

Journal of Rock Mechanics and Geotechnical engineering 2024年第9期16卷 3812-3840页

作者： M.E.Al-Atroush A.E.Aboelela Ezz El-Din Hemdan Civil and Environmental Engineering Program Engineering Management DepartmentCollege of EngineeringPrince Sultan UniversityRiyadhSaudi Arabia Department of Structural Engineering Faculty of EngineeringAin Shams UniversityCairoEgypt Structure and Materials Research Lab Prince Sultan UniversityRiyadhSaudi Arabia Computer Science and Engineering Department Faculty of Electronic EngineeringMenoufia UniversityMenoufiaEgypt

In 2023,pivotal advancements in artificial intelligence(AI)have significantly *** that in mind,traditional methodologies,notably the p-y approach,have struggled to accurately model the complex,nonlinear soil-structure interactions of laterally loaded large-diameter drilled *** study undertakes a rigorous evaluation of machine learning(ML)and deep learning(DL)techniques,offering a comprehensive review of their application in addressing this geotechnical challenge.A thorough review and comparative analysis have been carried out to investigate various AI models such as artificial neural networks(ANNs),relevance vector machines(RVMs),and least squares support vector machines(LSSVMs).It was found that despite ML approaches outperforming classic methods in predicting the lateral behavior of piles,their‘black box'nature and reliance only on a data-driven approach made their results showcase statistical robustness rather than clear geotechnical insights,a fact underscored by the mathematical equations derived from these ***,the research identified a gap in the availability of drilled shaft datasets,limiting the extendibility of current findings to large-diameter *** extensive dataset,compiled from a series of lateral loading tests on free-head drilled shaft with varying properties and geometries,was introduced to bridge this *** paper concluded with a direction for future research,proposes the integration of physics-informed neural networks(PINNs),combining data-driven models with fundamental geotechnical principles to improve both the interpretability and predictive accuracy of AI applications in geotechnical engineering,marking a novel contribution to the field.

关键词： Laterally loaded drilled shaft load transfer and failure mechanisms Physics-informed neural networks(PINNs) P-y curves Artificial intelligence(AI) Dataset

来源：评论

学校读者我要写书评

暂无评论

LesNet: An Automated Skin Lesion Deep Convolutional Neural Network Classifier through Augmentation and Transfer Learning 2

LesNet: An Automated Skin Lesion Deep Convolutional Neural N...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Mir, Aqib Nazir Nissar, Iqra Rizvi, Danish Raza Kumar, Ankush Research Lab Department of Computer Engineering Jamia Millia Islamia New Delhi110025 India Department of Computer Science and Engineering Punjabi University Punjab 147002 India

Skin cancer is one of the most prevalent forms of cancer around the world. Initial diagnosis relies on visual assessment of the affected area, followed by detailed dermoscopic analysis. The development of an automated system for classifying skin lesions poses a considerable challenge due to inherent noise and subtle variability in lesion images. Deep convolutional neural networks have demonstrated exceptional proficiency in image classification tasks spanning diverse domains. This paper demonstrates an end-to-end classification architecture built on top of transfer learning with data augmentation. The proposed model capitalizes on pre-trained architectures such as DenseNet, VGG-16, and Inception for feature extraction, and employs fully connected dense layers for categorizing seven distinct types of lesions. Several data augmentation techniques are also used to handle the class imbalance problem. Extensive experimentation encompassing various hyperparameters, imbalanced data scenarios, and balanced datasets was conducted to refine the automated skin lesion system. The proposed approach achieved a notable accuracy of 98% on the HAM10000 dataset and 94% on the ISIC-2019 dataset. Importantly, the experimental findings surpassed the performance of current state-of-the-art models for lesion classification. Furthermore, this paper examines the impact of class imbalance and data augmentation on the model's accuracy. © 2024 Elsevier B.V.. All rights reserved.

关键词： 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：