检索结果-内蒙古大学图书馆

Offline handwritten signature authentication using Graph Neural Network methods

International Journal of Information Technology (Singapore) 2024年 1-11页

作者： Badie, Ali Sajedi, Hedieh Department of Computer Science University of Tehran Kish International Campus Tehran Iran Department of Mathematics Statistics and Computer Science University of Tehran Tehran Iran

Due to their uniqueness and simplicity, handwritten signatures are used as a behavioral biometric feature to identify and authenticate individuals. Due to the increase in the criminal activity of forgers in forging signatures, organizations are forced to use computer systems to verify the authenticity of signatures. For this reason, offline signature verification system is widely used in most organizations. Despite the abundance of research conducted on signature verification, it is difficult to distinguish real and forged signature samples due to the lack of information in the signing process. On the other hand, the small number of training samples is a challenge for offline signature recognition systems. In recent years, to improve these problems, systems based on machine learning and deep learning methods have been presented. In this paper, we have proposed a graph neural network-based architecture for offline signature verification. In this work, the features in the signature images, which are the pixels that make up the signature, are extracted by the SIFT algorithm and sent to the graph-based neural network as a graph structure. After training the network, the data of the test samples are classified into one of two classes, genuine or forged. The proposed model was evaluated on two datasets, MCYT-75 and UTSig, and Accuracy (Acc), Average Error Rate (AER), False Acceptance Rate (FAR) and False Positive Rate (FPR) were considered as performance measures. In this model, the values of Acc, AER, FAR and FPR for the MCYT-75 data set are equal to 1,0, 0, and 0, respectively, and for the UTSig database, these values are equal to 0.092, 0.007, 0.014 and 0. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Graph neural network SIFT Signature verification

来源：评论

学校读者我要写书评

暂无评论

Drug sales forecasting in the pharmaceutical market using deep neural network algorithms

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2024年第3期8卷 63-83页

作者： Qassrawi, Noura Azzeh, Mohammad Hijjawi, Mohammad Department of Computer Science Applied Science Private University Amman Jordan Department of Data Science Princess Sumaya University for Technology Amman Jordan

Drug sales and price forecasting have become an attractive investigation topic due to their important role in the pharmaceutical industry, A sales forecast helps every business to make better business decisions in overall business planning, budgeting, marketing, and risk management. The traditional forecasting method focuses on a conventional statistical model, which highly depends on the availability of historical sales data. However, for new drug entities, where not enough historical data is available, new methods of Machine Learning are applied. The aim of this paper is to identify an efficient Deep Neural Network algorithm suitable to forecast drug sales and pricing by applying Deep Neural Network Algorithms such as Multilayer Perceptron, Convolutional Neural Network, and Long Short-Term Memory, which are expected to perform well on this issue. The results are carried out to determine the efficiency of these algorithms by evaluating the performances of the models using MAE and RMSE performance metrics to identify the best algorithm for Drug Sales and Price Forecasting. The accepted accuracy should be more than 80\% of the actual value for quantity which is less than three thousand by unit and less than two dollars (USD) for price, Based on the results of the experiments Long Short Term Memory performed better than MLP and CNN for generating predictions with average Root Mean Square Error of for sales is 1.28(k) and Mean Absolute Error of about 0.85(k), and with average Root Mean Square Error for USD Prices is about 0.75, and Mean Absolute Error is about 0.44. The forecasts are then used to adjust stock levels according to the predictions. © (2024), (Society of Sytematic Innovation). All rights reserved.

关键词： Convolutional Neural Network Drug sales Forecasting Long Short-Term Memory Multilayer Perceptron

来源：评论

学校读者我要写书评

暂无评论

NeuroProbe: A Performance Profiling Feed Forward Neural Network Simulator for Hardware Interaction Analysis

引用

SN computer science 2025年第5期6卷 1-22页

作者： Ayyappan, Binu Kumar, G. Santhosh Department of Computer Science Cochin University of Science and Technology Kochi India Department of Artificial Intelligence and Data Science Rajagiri School of Engineering & Technology Kochi India

NeuroProbe is a simple neural network simulator designed by authors specifically for educational purposes focusing on simulating inference phase on a computationally capable embedded hardware, aiming to provide a deeper understanding of hardware interactions and performance improvement. This simulator incorporates performance profiling capabilities, allowing students and educators to analyze and optimize the performance of a simulated trained neural network. By simulating the intricate hardware interactions, NeuroProbe enables users to gain insights into how various components impact the overall performance of neural networks. Using this simulator, learners can experiment with different configurations and architectures, identify potential bottlenecks, and explore optimization strategies to enhance neural network performance before deploying the model on an Edge Computing environment. It also enriches computer science education by enabling learners to gain deeper insights into hardware interactions and performance improvement. By identifying performance bottlenecks, learners can refine their understanding of neural networks and develop skills in optimizing their models for enhanced performance. In conclusion, NeuroProbe empowers users to bridge the gap between theoretical knowledge and practical implementation of neural network on an embedded device, fostering a more comprehensive understanding of neural networks and their hardware requirements. Currently, it is focused solely on single-threaded CPU-based computation enabling SSE, AVX. At present, NeuroProbe does not support SIMD extensions such as AVX-FMA, AVX-512, multi-threaded computation, and accelerators such as NPU, TPU, and GPU. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Hardware–software interactions Neural network simulator NeuroProbe Performance bottlenecks Performance profiling Simulations

来源：评论

学校读者我要写书评

暂无评论

Exploring Invertible Encoding for Deep Video Compression

引用

IEEE Transactions on Broadcasting 2025年第2期71卷 517-528页

作者： Guo, Haifeng Kwong, Sam Zhou, Mingliang City University of Hong Kong Department of Computer Science Hong Kong Hong Kong Lingnan University School of Data Science Hong Kong Hong Kong Chongqing University School of Computer Science Chongqing400044 China

Deep video compression methods typically use autoencoder-style networks for encoding and decoding, which can result in the loss of information during encoding that cannot be retrieved during decoding. To address this issue, recent work has explored the use of invertible neural networks for enhanced invertible encoding, which has successfully mitigated spatial information loss for better image compression. In this paper, we propose a new approach that extends invertible encoding to temporal information and introduces an encoding-decoding network for deep video compression. Our network incorporates a novel attentive channel squeeze module to improve compression performance while also leveraging a conditional coding framework for motion compression. The entire framework is optimized via a single loss function that balances bit cost and frame quality. The experimental results demonstrate the effectiveness of our approach, which achieves 15.45%/57.92% bit savings in terms of PSNR/MS-SSIM compared with the high-efficiency video coding low-delay P configuration. © 2025 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

ENHANCED LABEL PROPAGATION THROUGH AFFINITY MATRIX FUSION FOR SOURCE-FREE DOMAIN ADAPTATION 3

ENHANCED LABEL PROPAGATION THROUGH AFFINITY MATRIX FUSION FO...

引用

3rd Conference on Lifelong Learning Agents, CoLLAs 2024

作者： Guo, Li Xia, Yuxuan Wang, Shengjie Department of Computer Science and Data Science New York University Shanghai China

Source-free domain adaptation (SFDA) has gained significant attention as a method to transfer knowledge from a pre-trained model on source domains toward target domains without accessing the source data. Recent research in SFDA has predominately adopted a self-training paradigm, focusing on utilizing local consistency constraints to refine pseudo-labels during self-training. These methods aim to encourage similar predictions among samples residing in local neighborhoods. However, despite their effectiveness, the significance of global consistency is often overlooked in such approaches. Moreover, such self-training based adaptation processes suffer from the "confirmation bias": models use self-generated sub-optimal pseudo-labels to guide their subsequent training, resulting in a loop of self-reinforcing errors. In this study, we address the aforementioned limitations through two key contributions. Firstly, we introduce a label propagation method that seamlessly enforces both local and global consistency, leading to more coherent label predictions within the target domain. Secondly, to mitigate the "confirmation bias", we aggregate the affinity matrix derived from current and historical models during the label propagation process. This approach takes advantage of different snapshots of the model to obtain a more accurate representation of the underlying graph structure, significantly enhancing the efficacy of label propagation and resulting in more refined pseudo-labels. Extensive experimental evaluations demonstrate the superiority of our approach over existing methods by a large margin. Our findings not only highlight the significance of incorporating global consistency within the SFDA framework but also offer a novel approach to mitigate the confirmation bias that arises from the use of noisy pseudo-labels in the self-training paradigm. © 2024 CoLLAs. All Rights Reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Conformal Prediction for Deep Classifier via Label Ranking 41

Conformal Prediction for Deep Classifier via Label Ranking

引用

41st International Conference on Machine Learning, ICML 2024

作者： Huang, Jianguo Xi, Huajun Zhang, Linjun Yao, Huaxiu Qiu, Yue Wei, Hongxin Department of Statistics and Data Science Southern University of Science and Technology China The School of Information Science and Technology ShanghaiTech University China Department of Statistics Rutgers University United States Department of Computer Science University of North Carolina Chapel Hill United States College of Mathematics and Statistics Chongqing University China

Conformal prediction is a statistical framework that generates prediction sets containing ground-truth labels with a desired coverage guarantee. The predicted probabilities produced by machine learning models are generally miscalibrated, leading to large prediction sets in conformal prediction. To address this issue, we propose a novel algorithm named Sorted Adaptive Prediction Sets (SAPS), which discards all the probability values except for the maximum softmax probability. The key idea behind SAPS is to minimize the dependence of the non-conformity score on the probability values while retaining the uncertainty information. In this manner, SAPS can produce compact prediction sets and communicate instance-wise uncertainty. Extensive experiments validate that SAPS not only lessens the prediction sets but also broadly enhances the conditional coverage rate of prediction sets. Copyright 2024 by the author(s)

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Neural quantum embedding: Pushing the limits of quantum supervised learning

引用

Physical Review A 2024年第2期110卷 022411-022411页

作者： Tak Hur Israel F. Araujo Daniel K. Park Department of Statistics and Data Science Department of Applied Statistics

Quantum embedding is a fundamental prerequisite for applying quantum machine learning techniques to classical data and has substantial impacts on performance outcomes. In this study, we present neural quantum embedding (NQE), a method that efficiently optimizes quantum embedding beyond the limitations of positive and trace-preserving maps by leveraging classical deep-learning techniques. NQE enhances the lower bound of the empirical risk, leading to substantial improvements in classification performance. Moreover, NQE improves robustness against noise. To validate the effectiveness of NQE, we conduct experiments on IBM quantum devices for image data classification, resulting in a remarkable accuracy enhancement from 0.52 to 0.96. In addition, numerical analyses highlight that NQE simultaneously improves the trainability and generalization performance of quantum neural networks, as well as of the quantum kernel method.

关键词： Deep learning Machine learning Quantum algorithms Quantum information theory

来源：评论

学校读者我要写书评

暂无评论

Automated face recognition using deep learning technique and center symmetric multivariant local binary pattern

引用

Neural Computing and Applications 2025年第1期37卷 263-281页

作者： Sekhar, J.C. Josephson, P. Joel Chinnasamy, A. Maheswari, M. Sankar, S. Kalangi, Ruth Ramya Department of Computer Science and Engineering NRI Institute of Technology Andhra Pradesh Guntur India Department of Electronics and Communication Engineering Malla Reddy Engineering College Telangana Hyderabad India Department of Data Science and Business Systems School of Computing SRMIST Kattankulathur Chennai India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vijayawada India

Researchers have recently created several deep learning strategies for various tasks, and facial recognition has made remarkable progress in employing these techniques. Face recognition is a noncontact, nonobligatory, acceptable, and harmonious biometric recognition method with a promising national and social security future. The purpose of this paper is to improve the existing face recognition algorithm, investigate extensive data-driven face recognition methods, and propose a unique automated face recognition methodology based on generative adversarial networks (GANs) and the center symmetric multivariable local binary pattern (CS-MLBP). To begin, this paper employs the center symmetric multivariant local binary pattern (CS-MLBP) algorithm to extract the texture features of the face, addressing the issue that C2DPCA (column-based two-dimensional principle component analysis) does an excellent job of removing the global characteristics of the face but struggles to process the local features of the face under large samples. The extracted texture features are combined with the international features retrieved using C2DPCA to generate a multifeatured face. The proposed method, GAN-CS-MLBP, syndicates the power of GAN with the robustness of CS-MLBP, resulting in an accurate and efficient face recognition system. Deep learning algorithms, mainly neural networks, automatically extract discriminative properties from facial images. The learned features capture low-level information and high-level meanings, permitting the model to distinguish among dissimilar persons more successfully. To assess the proposed technique’s GAN-CS-MLBP performance, extensive experiments are performed on benchmark face recognition datasets such as LFW, YTF, and CASIA-WebFace. Giving to the findings, our method exceeds state-of-the-art facial recognition systems in terms of recognition accuracy and resilience. The proposed automatic face recognition system GAN-CS-MLBP provides a solid basis for a

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

See Detail Say Clear: Towards Brain CT Report Generation via Pathological Clue-driven Representation Learning

See Detail Say Clear: Towards Brain CT Report Generation via...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zheng, Chengxin Ji, Junzhong Shi, Yanzhao Zhang, Xiaodan Qu, Liangqiong College of Computer Science Beijing University of Technology Beijing China Department of Statistics and Actuarial Science School of Computing and Data Science The University of Hong Kong Hong Kong

ISBN: (纸本)9798891761681

Brain CT report generation is significant to aid physicians in diagnosing cranial diseases. Recent studies concentrate on handling the consistency between visual and textual pathological features to improve the coherence of report. However, there exist some challenges: 1) Redundant visual representing: Massive irrelevant areas in 3D scans distract models from representing salient visual contexts. 2) Shifted semantic representing: Limited medical corpus causes difficulties for models to transfer the learned textual representations to generative layers. This study introduces a Pathological Clue-driven Representation Learning (PCRL) model to build cross-modal representations based on pathological clues and naturally adapt them for accurate report generation. Specifically, we construct pathological clues from perspectives of segmented regions, pathological entities, and report themes, to fully grasp visual pathological patterns and learn cross-modal feature representations. To adapt the representations for the text generation task, we bridge the gap between representation learning and report generation by using a unified large language model (LLM) with task-tailored instructions. These crafted instructions enable the LLM to be flexibly fine-tuned across tasks and smoothly transfer the semantic representation for report generation. Experiments demonstrate that our method outperforms previous methods and achieves SoTA performance. Our code is available at https://***/ChaunceyJheng/PCRL-MRG. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning to Predict Mental Health Disorders and Interpret Feature Importance 3

Application of Machine Learning to Predict Mental Health Dis...

引用

3rd International Symposium on computer Technology and Information science, ISCTIS 2023

作者： Li, Yifan Faculty of Science and Technology Department of Statistics and Data Science Zhuhai China

ISBN: (纸本)9798350325386

The mental health and mental illness crisis has become increasingly acute in recent years, and many digital solutions with artificial intelligence at their core offer hope for reversing the deterioration of our mental health. Machine deep learning techniques can be used to analyse big data to build predictive models for psycho-education, assessment and screening to assess the mental health status of subjects, and can help the clinical community discover information that is not available to many traditional psychological research tools. This paper presents an in-depth analysis of a mental health survey and examines how it can be applied to the Al/ML domain of mental health research and how machine learning models can be used in this domain for fitting and prediction. Based on this, the importance of the presence or absence of current mental health disorders on other characteristics of respondents is assessed and visualised. It was found that the Cross Gradient Booster (Random Forest) model gave the best prediction fit among the various types of machine learning models, and the Grid Search algorithm was used to confirm that the final model had the highest accuracy of 0.79784 at a learning rate of 0.1. The Permutation Importance analysis revealed that the most important characteristic is whether or not the person has suffered from a mental health disorder in the past. © 2023 IEEE.

关键词： Forecasting

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：