检索结果-内蒙古大学图书馆

On DNA Synthesis Using Shortmers and the Capacity of Non-Deterministic Costly Constrained Graphs

IEEE Transactions on Information Theory 2025年第4期71卷 2397-2442页

作者： Abu-Sini, Maria Lenz, Andreas Technion—Israel Institute of Technology Department of Computer Science Haifa32000 Israel Technical University of Munich Department of Computer Engineering Munich80333 Germany Technical University of Munich Institute for Communications Engineering Munich80333 Germany

In conventional DNA synthesis machines, usually many strands are synthesized in parallel by iterating through a supersequence s and adding in each cycle the next nucleotide to a programmable subset of the strands. The length of s determines the number of the cycles, hence the time and the cost of the synthesis process. Recently, in order to reduce the number of synthesis cycles, researchers have suggested to append in each cycle a shortmer, i.e., a sequence of nucleotides, instead of a single one. The present work studies this synthesis technique from a theoretical point of view. In particular, it discusses which shortmers are the best to use (in order to reduce the number of cycles), and how to calculate the number of cycles required to synthesize in parallel a set of strands using a given set of shormers. Lastly, and following a previously described connection between the DNA synthesis problem and costly constrained graphs, this paper investigates calculating the capacity of non-deterministic costly constrained graphs. © 1963-2012 IEEE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Linear Algorithmic Checksums for Deep-Neural-Network Error Detection: Fundamentals and Recent Advancements

IEEE Design and Test

引用

IEEE Design and Test 2025年第3期42卷 26-40页

作者： Ozen, Elbruz Ozerdem, Ozgur Orailoglu, Alex University of California at San Diego Department of Computer Science and Engineering La Jolla CA92093 United States

The widespread adoption of deep neural networks in safety-critical systems necessitates the examination of the safety issues raised by hardware errors. The consequent interest in fault tolerance methods that can deliver comprehensive coverage yet are sufficiently low-cost to meet the margin requirements of consumer deep learning applications can be satisfied through a rigorous exploration of the mathematical properties of the deep neural network computations. Concretely, this stringent set of requirements can be satisfied through a novel technique, Sanity-Check, that delivers error detection in fully-connected and convolutional layers through the use of linear algorithmic checksums. The interest in Sanity-Check was accentuated by its purely software-based implementation in a variety of off-the-shelf hardware platforms. Meanwhile, dedicated hardware extensions seamlessly integrate with modern deep learning accelerators and eliminate the performance overhead of the software-based implementation. The perfect critical error coverage of Sanity-Check offers a promising alternative for low-cost error detection in safety-critical deep neural network applications. The success of this approach in delivering frugal and highly comprehensive error detection has spurred a slew of subsequent research work, which we survey in this article. © 2013 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Double Averaging and Gradient Projection: Convergence Guarantees for Decentralized Constrained Optimization

引用

IEEE Transactions on Automatic Control 2025年第5期70卷 3433-3440页

作者： Shahriari-Mehr, Firooz Panahi, Ashkan Chalmers University of Technology University of Gothenburg Department of Computer Science and Engineering SE-412 96 Gothenburg Sweden

We consider a generic decentralized constrained optimization problem over static, directed communication networks, where each agent has exclusive access to only one convex, differentiable, local objective term and one convex constraint set. For this setup, we propose a novel decentralized algorithm, called double averaging and gradient projection (DAGP). We achieve global optimality through a novel distributed tracking technique we call distributed null projection. Further, we show that DAGP can be used to solve unconstrained problems with nondifferentiable objective terms with a problem reduction scheme. Assuming only smoothness of the objective terms, we study the convergence of DAGP and establish sublinear rates of convergence in terms of feasibility, consensus, and optimality, with no extra assumption (e.g., strong convexity). For the analysis, we forego the difficulties of selecting Lyapunov functions by proposing a new methodology of convergence analysis, which we refer to as aggregate lower-bounding. To demonstrate the generality of this method, we also provide an alternative convergence proof for the standard gradient descent algorithm with smooth functions. © 1963-2012 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancement of receptive field using dilated convolution for camouflaged human segmentation in RGB images

引用

Multimedia Tools and Applications 2025年第11期84卷 8707-8724页

作者： Kumar, Vikash Singh, Raghuraj Department of Computer Science and Engineering Harcourt Butler Technical University Nawabganj Uttar Pradesh Kanpur208002 India

Detection of camouflaged human intruder in RGB images is a challenging problem and is of much interest to defence forces and security agencies. Limited research has been undertaken in this area due to various reasons including non-availability of a suitable dataset. In this context, our work has the following contributions. First, the construction of a manually annotated dataset called Camouflaged human dataset (CHD3.5K) consisting of images of humans camouflaged in background. Second, using dilated convolution on image features extracted using deep neural network for the segmentation of camouflaged human intruder in an image using our own CHD3.5K dataset. We experimented using different kinds of loss functions and deduced that the use of hybrid loss function yielded superior results compared to other popular loss functions. The results obtained on CHD3.5K dataset have been bench-marked against twelve different state of the art baseline methods using three popular evaluation metrics. Qualitative and quantitative performance analysis on the CHD3.5K dataset has shown encouraging results. We used ablation analysis to highlight the importance of key elements of detection network. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Construction of Cascaded Deep Neural Network with Optimization-Based Feature Selection in CT Images for Detecting Laryngeal Cancer 5th

Construction of Cascaded Deep Neural Network with Optimizati...

引用

5th International Conference on Innovative Product Design and Intelligent Manufacturing Systems, ICIPDIMS 2023

作者： Naga Padmavathi, P. Sree Devi, M. Maheswara Rao, V.V.R. Gopala Gupta, Amara S. A. L. G. Department of Computer Science and Engineering Amrita Sai Institute of Science and Technology AP Paritala India Department of Computer Science and Engineering Shri Vishnu Engineering College for Women AP Bhimavaram India Department of Computer Science and Engineering KoneruLakshmaiah Education Foundation AP Vaddeswaram India

ISBN: (纸本)9789819767311

A sin laryngeal carcinoma is the most common kind of head and neck cancer to damage the soft tissues of the larynx. To prevent further medical difficulties and to provide better patient care, early stage laryngeal cancer identification is essential. The primary objective of this research is to provide computer-aided cancer diagnosis driven by deep learning. In order to do this, we create a brand-new Optimization-Based Cascaded Deep Neural Network (OCDNN) that distinguishes between good and unhealthy/cancerous tissues. Additionally, we also provide cascaded patch-based CNN (CP-CNN) picture segmentation. The models are assessed using accepted measures that are unique to the biomedical field. When compared to other models, the performance of our suggested OCDNN architecture was exceptional. Additionally, it fared better than other cutting-edge CNN models applied to medical domain challenges. The findings suggest that the suggested method is quite successful in identifying early indications of laryngeal cancer. The results demonstrate that the suggested strategy may help doctors identify laryngeal carcinoma early and precisely. The suggested OCDNN is discovered to attain 98.4% accuracy, 94% precision, 97.5% recall, and 98% *** paragraph of about 100 words to give a brief introduction to your work. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

QANet: quaternion attention network for video summarization

引用

Journal of Electronic Imaging 2025年第2期34卷

作者： Garg, Vaani Parihar, Anil Singh Delhi Technological University Machine Learning Research Laboratory Department of Computer Science and Engineering Delhi Rohini India

With the rapid increase in video data, automatic video summarization has become paramount in video processing and content analysis. Video summarization aims to generate a concise version of a video that highlights only the most important content, allowing viewers to quickly understand the video's essence without watching it in full. Although existing methods for automatic video summarization have achieved notable success, they still face challenges such as high computational costs. To address this, we propose a quaternion attention network for video summarization, designed to be both lightweight and efficient. The proposed approach comprises three main components: spatial feature extraction (SFE), learnable frame embedding (LFE) module, and quaternion temporal attention (QTA) module. The SFE module extracts spatial features from each frame, whereas the LFE module generates learned embeddings for the frames. These embeddings are then fed into the QTA module, which captures temporal inter-frame correlations by leveraging quaternion space representations. The proposed approach reduces computational requirements and memory usage while achieving state-of-the-art performance on the SumMe and TVSum datasets. © 2025 SPIE and IS&T.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Next-Generation IoT Intrusion Detection: Leveraging Hybrid Deep Learning Algorithms for Enhanced Security 2

Next-Generation IoT Intrusion Detection: Leveraging Hybrid D...

引用

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Urvashi Agarwal, Parul Raghuvanshi, Kamlesh Kumar Ahmed, Jawed Department of Computer Science and Engineering Jamia Hamdard University Delhi India Department of Computer Science University of Delhi Delhi India

ISBN: (纸本)9798331530389

Wireless sensor node and DDoS (Distributed Denial of Service) is a major attack way that can exhaust the energy of a sensor, disrupt the communication traffic of an IoT network. We must be on the lookout for these attacks. With the quantity of sensor nodes, traditional methods face difficulty in detecting network traffic analysis requiring big data analysis. This paper is dedicated to Network Traffic analysis using Big Data environment and detecting attacks using Deep Learning. Implemented with PySpark in Google Colab, using Keras and Scikit-Learn built-in libraries. To be more specific, training and testing are conducted on the 'CICIoT2023'/'TON IoT' datasets, respectively. When we use a correlation feature reducer, it virtually considers the most significant features for inclusion and reduces all of our features. The first contains a hybrid deep leaning model combining one-dimensional EfficientDet and Gradient Boosting Machine (GBM), comparing it with ten other algorithms. It gen- erated 99.95% binary classification accuracy for the CICIoT2023 dataset and 99.75% for TON IoT data. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

A cancelable biometric authentication scheme based on geometric transformation

引用

Multimedia Tools and Applications 2025年第15期84卷 15407-15428页

作者： Champaneria, Vivek H. Patel, Sankita J. Zaveri, Mukesh A. Department of Computer Science And Engineering Sardar Vallabhbhai National Institute of Technology Icchanath Gujarat Surat395007 India

In digital identification technologies, fingerprint-based biometric systems are extensively utilized for authentication. Fingerprint authentication systems usually store the original minutiae points as user templates in the database which consist of minutiae bifurcation and ridge end points. Storing original minutiae points in the database can create a potential security risk to a person’s identity. An adversary might attack the database and compromise the user template. Various studies have demonstrated the feasibility of reconstructing the original fingerprint by utilizing the minutiae points. Existing research methods still need to be improved, and therefore, it is essential to provide security and robustness to fingerprint-based biometric systems. In this paper, a novel template protection technique using non-invertible transformation is proposed to create a secure and robust template. The transformation function uses the original minutiae positions, orientation details, and user key set values. The results demonstrated equal error rates of 1.5%, 0.85%, and 2.71% for the FVC2002 DB1, DB2, and DB3 fingerprint databases. The proposed method has demonstrated noteworthy performance improvement compared to other notable contributions. The outcome of the proposed method demonstrates practicality and effectiveness. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Crop disease detection via ensembled-deep-learning paradigm and ABC Coyote pack optimization algorithm (ABC-CPOA)

引用

Multimedia Tools and Applications 2025年第1期84卷 37-62页

作者： Chithambarathanu, M. Jeyakumar, M.K. Department of Computer Science and Engineering Noorul Islam Centre for Higher Education Tamil Nadu Kumarakoil Nagercoil India

Crop disease is a significant issue that affects the growth and yield of crops, leading to financial loss for farmers. Identification and treatment of crop diseases have become challenging due to the increase in the variety of diseases and the lack of knowledge among farmers. To address this issue, this investigate uses an ensembled-deep-learning paradigm to propose a deep learning-based model for crop disease identification trained with an ABC-CPOA. Initially, collected raw images are pre-processed via Bilateral filter and gamma correction Feature Extraction: Then, from the pre-processed images, the features like texture feature (Local Quinary Pattern (LQP), Local Gradient Pattern (LGP), Enriched Local Binary Pattern (E-LBP), color features (Color Histogram, Color Moments), shape features (Contour-based features, Convex Hull). Optimal feature selection- Among the extracted features, the optimal features is designated by means of a self-improved meta-heuristic optimization model referred as ABC-CPOA. This ABC-CPOA model is an extended version of standard Coyote Optimization Algorithm (COA). Crop disease detection phase is modelled with a new ensembled-deep-learning paradigm. Ensembled-deep-learning paradigm comprises Attention-based Bi-LSTM, Recurrent Neural Networks (RNNs) and Optimized Deep Neural Network (O-DNN). The weight function of O-DNN is fine-tuned using the new ABC-CPOA. Precision, recall, sensitivity, and specificity, in addition to TPR, FPR, FNR, and TNR, F1-score, and accuracy are used to assess the suggested approach. The implementation was performed by the MATLAB tool (version: 2022B). © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Identification of Different Medicinal Plants Using Machine Learning and Image Processing 5th

Identification of Different Medicinal Plants Using Machine L...

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： Pokkuluri, Kiran Sree Phaneendra Varma, Ch Gurujukota, Ramesh Babu Raja Rao, P.B.V. Usha Devi N, S.S.S.N. Prasad, M. Pamarthi, Nagaraju Shalem Raju, P.J.R. Department of Computer Science and Engineering Shri Vishnu Engineering College for Women Bhimavaram India Department of Computer Science and Engineering University College of Engineering JNTU Kakinada Kakinada India

ISBN: (纸本)9783031770746

Medicinal plants have been an essential source of remedies and treatments for various ailments throughout human history. This paper presents an innovative approach that combines machine learning and image processing to identify various medicinal plants and extract information about their traditional and modern uses. This method offers efficiency and dependability by automating the identification procedure, which lessens the reliance on human expertise and may hasten the discovery and application of medicinal plants for therapeutic purposes. In this work identification of the medical plats is done thought the shape of the plant leave, text features using digital image processing techniques, color using Convolutional Neural Works (CNN). We have achieved an accuracy of 98.6% in identifying the medical plants and we have compared our work with the existing literature with various parameters like precision, accuracy and f1 score. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Adversarial machine learning

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：