检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Qu, Zheyan Yin, Lu Yu, Zitong Wang, Wenbo Zhang, Xing Wireless Signal Processing and Network Laboratory Beijing University of Posts and Telecommunications Beijing Department of Computer Science University of Aberdeen UK

Large language models (LLMs) have demonstrated astonishing capabilities in natural language processing (NLP) tasks, sparking interest in their application to professional domains with higher specialized requirements. However, restricted access to closed-source LLMs via APIs and the difficulty in collecting massive high-quality datasets pose obstacles to the development of large language models in education fields of various courses. Given these challenges, we propose CourseGPT-zh, a course-oriented education LLM that supports customization and low-cost deployment. To address the comprehensiveness and diversity requirements of course-specific corpora, we design a high-quality question-answering corpus distillation framework incorporating prompt optimization, which effectively mines textbook knowledge and enhances its diversity. Moreover, considering the alignment of LLM responses with user needs, a novel method for discrete prompt optimization based on LLM-as-Judge is introduced. During optimization, this framework leverages the LLM’s ability to reflect on and exploit error feedback and patterns, allowing for prompts that meet user needs and preferences while saving response length. Lastly, we obtain CourseGPT-zh based on the open-source LLM using parameter-efficient fine-tuning. Experimental results show that our discrete prompt optimization framework effectively improves the response quality of ChatGPT, and CourseGPT-zh exhibits strong professional capabilities in specialized knowledge question-answering, significantly outperforming comparable open-source models. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Tracing Signs of Urbanity in the Finnish Fiction Film of the 1950s: Toward a Multimodal Analysis of Audiovisual Data 6

Tracing Signs of Urbanity in the Finnish Fiction Film of the...

引用

6th Digital Humanities in the Nordic and Baltic Countries Conference, DHNB 2022

作者： Grósz, Tamás Kallioniemi, Noora Kiiskinen, Harri Laine, Kimmo Moisio, Anssi Römpötti, Tommi Virkkunen, Anja Salmi, Hannu Kurimo, Mikko Laaksonen, Jorma Department of Signal Processing and Acoustics Aalto University Finland Department of Cultural History University of Turku Finland Department of Media Studies University of Turku Finland Department of Computer Science Aalto University Finland

This paper traces signs of urban culture in Finnish fiction films from the 1950s by drawing on a multimodal analysis of audiovisual content. The Finnish National Filmography includes 208 feature films released between 1950-1959. Our approach to the automatic analysis of media content includes aural and visual object recognition and speech recognition. We concentrate on features that epitomize urbanity, including visual objects, such as forms of transportation (cars, horses) and sounds (rural and urban sounds, speech). Based on the scores and frequencies of these recognitions, we observe quantitative changes that took place during the 1950s. The paper demonstrates that aural and visual object recognition, as well as speech recognition, can successfully be applied in film historical analysis. The overall results support the idea that Finnish filmmakers fueled the imagination of urban life in the 1950s, paving the way for modern technologies and gradually pushing aside the signs of rural life. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Bee Identification for DNA Strands

Data-Driven Bee Identification for DNA Strands

引用

2023 IEEE International Symposium on Information Theory, ISIT 2023

作者： Singhvi, Shubhransh Boruchovsky, Avital Kiah, Han Mao Yaakobi, Eitan International Institute of Information Technology Signal Processing & Communications Research Center Hyderabad India Technion - Israel Institute of Technology Department of Computer Science Haifa3200003 Israel Nanyang Technological University School of Physical and Mathematical Sciences Singapore

ISBN: (纸本)9781665475549

We study a data-driven approach to the bee identification problem for DNA strands. The bee-identification problem, introduced by Tandon et al. (2019), requires one to identify M bees, each tagged by a unique barcode, via a set of M noisy measurements. Later, Chrisnata et al. (2022) extended the model to case where one observes N noisy measurements of each bee, and applied the model to address the unordered nature of DNA storage *** such systems, a unique address is typically prepended to each DNA data block to form a DNA strand, but the address may possibly be corrupted. While clustering is usually used to identify the address of a DNA strand, this requires M2 data comparisons (when M is the number of reads). In contrast, the approach of Chrisnata et al. (2022) avoids data comparisons completely. In this work, we study an intermediate, data-driven approach to this identification *** the binary erasure channel, we first show that we can almost surely correctly identify all DNA strands under certain mild assumptions. Then we propose a data-driven pruning procedure and demonstrate that on average the procedure uses only a fraction of M2 data comparisons. Specifically, for M = 2n and erasure probability p, the expected number of data comparisons performed by the procedure is ?M2, where (1 + 2p - p2/2)n = ? = (1 + p/2)n. © 2023 IEEE.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

Enhancing Autism Spectrum Classification using Super Resolution GAN and ViT based Embedding

Enhancing Autism Spectrum Classification using Super Resolut...

引用

International Bhurban Conference on Applied sciences & Technology, IBCAST

作者： Muhammad Farooq Muhammad Haris Bin Amir Usama Abdullah Ejaz Raza Ali Adeel Mumtaz Department of Computer Science National University of Science and Technology Department of Control and Signal Processing Center of Excellence in Science and Applied Technologies Islamabad Pakistan

ISBN: (数字)9798350308259

ISBN: (纸本)9798350308266

Autism spectrum disorder(ASD) poses challenges in recognizing and socializing with others very challenging. Early detection is crucial for improved outcomes in individuals with ASD. In this research we present a novel approach for autism classification using facial images. Our approach utilizes the GAN based super-resolution techniques in conjunction with a Pretrained ResNet18 and vision transformer based embedding by combining their features. Our study focuses on enhancing image quality through super resolution, enabling finer details to be captured for mode accurate analysis. CNN based ResNet18 captures the local features from image while ViT, attention based network captures more global details. By combining the features of both networks our propose model performs robust and discriminative feature extraction. The integration of super-resolution techniques and fine-tuned deep learning models provides a comprehensive framework for early detection of autism in children. To correctly detect the autism disorder, more robust ResNet18 features and vision transform based embedding are extracted from enhanced image details. The enhanced image quality aids in capturing subtle facial expressions, critical for accurate classification. Our findings demonstrate the effectiveness of our proposed model in achieving notable improvements in accuracy and reliability with test accuracy of 91% and AUC of 96.42%. This research contributes to the growing body of knowledge in autism classification, highlighting the potential of advanced computer vision techniques and deep learning algorithms. By enabling early detection, out approach provides a positive impact on the lives of children with ASD, facilitating timely interventions and support for better outcomes and increased independence.

关键词： Image quality Deep learning Autism computer vision Accuracy Superresolution Feature extraction Transformers Generative adversarial networks Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Deep Generative Models for Bayesian Inference on High-Rate Sensor Data: Applications in Automotive Radar and Medical Imaging

arXiv

引用

arXiv 2025年

作者： Stevens, Tristan S.W. Overdevest, Jeroen Nolan, Oisín van Nierop, Wessel L. van Sloun, Ruud J.G. Eldar, Yonina C. Department of Electrical Engineering University of Technology Eindhoven Netherlands Signal Processing Algorithms NXP Semiconductors Netherlands Faculty of Mathematics and Computer Science Weizmann institute of Science Israel

Deep generative models have been studied and developed primarily in the context of natural images and computer vision. This has spurred the development of (Bayesian) methods that use these generative models for inverse problems in image restoration, such as denoising, inpainting, and super-resolution. In recent years, generative modeling for Bayesian inference on sensory data has also gained traction. Nevertheless, the direct application of generative modeling techniques initially designed for natural images on raw sensory data is not straightforward, requiring solutions that deal with high dynamic range signals acquired from multiple sensors or arrays of sensors that interfere with each other, and that typically acquire data at a very high rate. Moreover, the exact physical data-generating process is often complex or unknown. As a consequence, approximate models are used, resulting in discrepancies between model predictions and the observations that are non-Gaussian, in turn complicating the Bayesian inverse problem. Finally, sensor data is often used in real-time processing or decision-making systems, imposing stringent requirements on, e.g., latency and throughput. In this paper, we will discuss some of these challenges and offer approaches to address them, all in the context of high-rate real-time sensing applications in automotive radar and medical imaging. © The Authors. Published by the Royal Society under the terms of the Creative Commons Attribution License http://***/licenses/by/4.0/, which permits unrestricted use, provided the original author and source are credited. © 2025, CC BY-SA.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Enhancement of spoken digits recognition for under-resourced languages: case of Algerian and Moroccan dialects

引用

International Journal of Speech Technology 2022年第2期25卷 443-455页

作者： Lounnas, Khaled Abbas, Mourad Lichouri, Mohamed Hamidi, Mohamed Satori, Hassan Teffahi, Hocine Laboratory of Spoken Communication and Signal Processing USTHB Algiers Algeria High Council for the Arabic Language HCLA Algiers Algeria Computational Linguistics Department CRSTDLA Algiers Algeria Multimedia and Arts department FLLA UIT Kenitra Morocco LISAC Department of Mathematics and Computer Science FSDM USMBA Fes Morocco

In this paper, we present a set of experiments aiming to improve the recognition of spoken digits for under-resourced dialects of the Maghrebi region, using a hybrid system. Indeed, integrating a Dialect Identification module into an Automatic Speech Recognition (ASR) system has shown its efficiency in previous works. In order to make the ASR system able to recognize digits spoken in different dialects, we trained our hybrid system on Moroccan Berber Dialect "MBD," Moroccan Arabic Dialect "MAD," and Algerian Arabic dialect "AAD," in addition to Modern Standard Arabic. We have investigated five machine learning based classifiers and two deep learning models: the first one is based on Convolutional Neural Network (CNN), and the second one uses two pre-trained models: Residual Deep Neural Network (Resnet50 and Resnet101). The findings show that the CNN model outperforms the other proposed methods and consequently enhances the performance of spoken digit recognition system by 20% for both Algerian and Moroccan dialects. © 2022, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

Face Deepfakes - A Comprehensive Review

arXiv

引用

arXiv 2025年

作者： Fernando, Tharindu Priyasad, Darshana Sridharan, Sridha Ross, Arun Fookes, Clinton Signal Processing Artificial Intelligence & Vision Technologies Queensland University of Technology Australia Michigan State University Department of Computer Science and Engineering United States

In recent years, remarkable advancements in deepfake generation technology have led to unprecedented leaps in its realism and capabilities. Despite these advances, we observe a notable lack of structured and deep analysis deepfake technology. The principal aim of this survey is to contribute a thorough theoretical analysis of state-of-the-art face deepfake generation and detection methods. Furthermore, we provide a coherent and systematic evaluation of the implications of deepfakes on face biometric recognition approaches. In addition, we outline key applications of face deepfake technology, elucidating both positive and negative applications of the technology, provide a detailed discussion regarding the gaps in existing research, and propose key research directions for further investigation. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effects of the Flatness Network Parameter Threshold on the Performance of the Rectified Linear Unit Memristor-Like Activation Function in Deep Learning

引用

SN computer science 2024年第8期5卷 1-10页

作者： Tchepgoua Mbakop, Marcelle Mboupda Pone, Justin Roger Chassem Kamdem, Priva Kengne, Romanic Research Unit of Condensed Matter Electronics and Signal Processing (RU-MACETS) Department of Physics Faculty of Science University of Dschang P. O. Box 67 Dschang Cameroon Research Unit of Automation and Applied Computer (RU-AIA) Electrical Engineering Department of IUT-FV University of Dschang P.O. Box 134 Bandjoun Cameroon Research Unit of Fundamental Computer Sciences and Artificial Intelligence (RU-FCSAI) Department of Computer Sciences Faculty of Science University of Dschang P. O. Box 67 Dschang Cameroon

In this contribution, we improve of the performance of the Rectified Linear Unit Memristor Like Activation Function with the implication to help training process of CNN without a lot of epochs by computing the best value of the flatness network parameter (p). In this regards the flatness network parameter threshold (p) has been investigated and a good performance of the activation function has been discovered at p = 4.5. We firstly used the MNIST and the CIFAR-10 datasets to trained and test the Alex-Net architecture model of convolutional neural network (CNN) and we showed better performances of Rectified Linear Unit Memristor-like Activation Function compared to those of the literature. We noticed that the performance of Alex-Net also improved and the better performance was recorded when p = 4.5 with 99.50%, 99.25%, 98.81% for training, validation and testing accuracy respectively when using the MNIST. These results open the outcome to reduce the training time of neural networks when this activation function is used. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Activation function Artificial intelligence Deep learning Flatness network parameter threshold Memristive windows function Neural network

来源：评论

学校读者我要写书评

暂无评论

Multimedia Classification via Tensor Linear Discriminant Analysis

引用

IEEE Transactions on Broadcasting 2024年第4期70卷 1139-1152页

作者： Chang, Shih-Yu Wu, Hsiao-Chun Yan, Kun Chih-Hao Huang, Scott Wu, Yiyan San Jose State University Department Of Applied Data Science San JoseCA95192 United States Louisiana State University School Of Electrical Engineering And Computer Science Baton RougeLA70803 United States Yuan Ze University Innovation Center For Ai Applications Taoyuan32003 Taiwan Guilin University Of Electronic Technology Guangxi Key Laboratory Of Wireless Wideband Communication And Signal Processing Department Of Information And Telecommunication Guilin541004 China National Tsing Hua University Department Of Electrical Engineering Hsinchu300 Taiwan Western University Department Of Electrical And Computer Engineering LondonONN6A 3K7 Canada

Linear discriminant analysis (LDA) is a well-known feature-extraction technique for data analytic and pattern classification. As the dimensionality of multimedia data has increased in this big era, it is often to characterize data by tensors. Over the past two decades, researchers have thus explored to extend LDA to the general tensor space, especially in two common ways: LDA of tensors using tensor decomposition methods (by conversion of tensors to matrices) and LDA of tensors built upon the T-product. However, both of the aforementioned approaches have restrictions thereby. A critical problem about how to carry out LDA of arbitrary scatter tensors based on the Einstein product still remains unsolved by the existing methods. Therefore, we propose a novel tensor LDA (a.k.a. TLDA) approach, which can carry out the LDA of arbitrary-dimensional scatter-tensors without any need of tensor decomposition. Besides, for reducing the computation time, we also design a parallel paradigm to execute our proposed TLDA in this work. Numerical experiments conducted over real multimedia data demonstrate the efficacy of our proposed new TLDA in terms of classification accuracy. Moreover, the comparison of the classification accuracies, computational-complexities, and memory-complexities of our proposed novel TLDA scheme and other existing tensor-based LDA methods is made. By leveraging TLDA for high-dimensional feature extraction, segmentation, and user-item interaction data processing, future multimedia recommendation systems can facilitate more accurate, engaging, and satisfactory user experience over the Internet. © 1963-12012 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Particle Flow Gaussian Sum Particle Filter

Particle Flow Gaussian Sum Particle Filter

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Karthik Comandur Yunpeng Li Santosh Nannuru Signal Processing and Communication Research Centre IIIT Hyderabad India Department of Computer Science University of Surrey UK

The particle flow Gaussian particle filter (PFGPF) uses an invertible particle flow to generate a proposal density. It approximates the predictive and posterior distributions as Gaussian densities. In this paper, we use a bank of PFGPF filters to construct a Particle flow Gaussian sum particle filter (PFGSPF), which approximates the prediction and posterior as Gaussian mixture model. This approximation is useful in complex estimation problems where a single Gaussian approximation is inadequate. We compare the performance of this proposed filter with the PFGPF and others in challenging numerical simulations.

关键词： Filter banks Estimation signal processing Numerical simulation Particle filters Acoustics Proposals

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：