检索结果-内蒙古大学图书馆

11th IEEE International Conference on Signal Processing and Integrated Networks, SPIN 2024

作者： Pansara, Ronak Ravjibhai Kasula, Balaram Yadav Gupta, Piyush Kumar Khan, Tabrej Ahamad Alam, Naved Whig, Pawan Master Data Specialist Tesla United States University of the Cumberlands Dept. of Information Technology WilliamsburgKY United States Jamia Hamdard Department of Computer Science and Engineering New Delhi India Research Scholar Jamia Millia Islamia New Delhi India Whig Research Scientist Threws VIPS-TC New Delhi India

ISBN: (纸本)9798350308433

This study explores the quantitative impact of Master data Management (MDM) implementation on Internet of Things (IoT) ecosystems. Employing a comparative analysis methodology, pre-And post-MDM integration metrics were assessed within the IoT environment. Results showcased a notable enhancement in data accuracy by 20%, attributed to minimized errors and improved consistency following MDM adoption. Operational efficiency exhibited a significant 30% reduction in data integration time across diverse IoT platforms, contributing to streamlined processes. Financially, operational costs decreased by 15%, primarily due to reduced data cleansing efforts post-MDM implementation. Decision-making processes benefited from a 25% faster response time to real-Time analytics derived from IoT data insights. Additionally, the IoT ecosystem's scalability increased by 40%, indicating amplified adaptability to accommodate higher data volumes without compromising performance. These quantitative findings highlight the substantial impact of MDM on fortifying the reliability, efficiency, and scalability of IoT ecosystems, providing empirical evidence for the transformative potential of MDM in optimizing IoT applications. © 2024 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis

Learning on Transformers is Provable Low-Rank and Sparse: A ...

引用

Sensor Array and Multichannel Signal Processing Workshop

作者： Hongkang Li Meng Wang Shuai Zhang Sijia Liu Pin-Yu Chen Dept. Electrical Computer and System Engineering Rensselaer Polytechnic Institute Troy NY USA Dept. Data Science New Jersey Institute of Technology Newark NJ USA Dept. Computer Science and Engineering Michigan State University East Lansing MI USA IBM Thomas J. Watson Research Center Yorktown Heights NY USA

ISBN: (数字)9798350344813

ISBN: (纸本)9798350344820

Efficient training and inference algorithms, such as low-rank adaption and model pruning, have shown impressive performance for learning Transformer-based large foundation models. However, due to the technical challenges of the non-convex optimization caused by the complicated architecture of Transformers, the theoretical study of why these methods can be applied to learn Transformers is mostly elusive. To the best of our knowledge, this paper shows the first theoretical analysis of the property of low-rank and sparsity of one-layer Transformers by characterizing the trained model after convergence using stochastic gradient descent. By focusing on a data model based on label-relevant and label-irrelevant patterns, we quantify that the gradient updates of trainable parameters are low-rank, which de-pends on the number of label-relevant patterns. We also analyze how model pruning affects the generalization while improving computation efficiency and conclude that proper magnitude-based pruning has a slight effect on the testing performance. We implement numerical experiments to support our findings.

关键词： Training Analytical models Adaptation models computational modeling Neurons Stochastic processes Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Balancing Performance, Efficiency and Robustness in Open-World Machine Learning via Evolutionary Multi-objective Model Compression

Balancing Performance, Efficiency and Robustness in Open-Wor...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Javier Del Ser Aitor Martinez-Seras Miren Nekane Bilbao Jesus L. Lobo Ibai Laña Francisco Herrera TECNALIA Basque Research and Technology Alliance (BRTA) Derio Spain University of the Basque Country (UPV/EHU) Bilbao Spain Dept. of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Granada Spain

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

When deploying machine learning models on resource-constrained hardware, reducing the memory footprint required by the model without compromising its performance is critical. Moreover, in open-world scenarios models often operate in dynamic and unpredictable environments where the data distribution evolves over time. Robust models can generalize well to unforeseen circumstances, including out-of-distribution inputs that may not have been encountered during the training phase. This adaptability is essential to handle the inherent variability of real-world data. This work formulates a multi-objective optimization problem that aims at optimizing the quantization resolution of the parameters of an already trained machine learning model based on three conflicting goals: maximizing the performance of the model on its designated learning task, minimizing the memory footprint of the compressed model, and enhancing its robustness against out-of-distribution data. Given the complexity of the resulting combinatorial optimization problem, we employ multi-objective evolutionary algorithms to efficiently obtain an approximation of the Pareto front balancing among the aforementioned objectives. Experiments with a randomized neural network compressed under the proposed formulation are run over several benchmark classification datasets. Different multi-objective solvers are employed to compare their effectiveness in terms of the convergence and diversity of their produced Pareto estimations. Additionally, we assess the achieved equilibrium between the three objectives against a floating-point implementation of the same model. Our experiments reveal that both the computational resources and the robustness of the model can be optimized via evolutionary quantization without significantly sacrificing its performance for the task at hand.

关键词： Training Adaptation models Quantization (signal) computational modeling Neural networks Machine learning Evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

The impact of entrepreneurship education on entrepreneurship intention in the engineering studies

引用

Procedia Computer science 2023年 225卷 3919-3928页

作者： Karin Kurata Kodama Kota Takashi Morinaga Hiromasa Ohnishi Sou Takahashi Jun Sato Kuniaki Yajima Dept. of Creative Engineering National Institute of Technology Tsuruoka College Tsuruoka 997-8511 Japan School of Data Science Nagoya City University Nagoya 467-8501 Japan Dept. of Creative Engineering National Institute of Technology Sendai College Sendai 989-3128 Japan

Entrepreneurship education is characterized by interactive learning linked to business and community initiatives. In entrepreneurship course, activity sessions include (1) Causation, and effectuation (2) Devil's River, Valley of Death, and Darwin's Sea, (3) Case Studies, (4) Guest Speaker Sessions, (5) Lean Startup, Business Model Canvas (BMC), Value Proposition Canvas (VPC), etc. are often addressed. The goal of entrepreneurship education is to change students' mindsets in terms of how they view innovative and risk-taking activities in business. There are several ways to measure the change derived from entrepreneurship education, including affective, cognitive, and skill-based outcomes. A previous study examined the effect of entrepreneurship education on entrepreneurship in relation to three independent variables: perceived behavioral control (PBC), attitude (AT), and subjective norm (SN). Combined with the results of the Generic Skill measure, this study proposes an evaluation method for entrepreneurship education that focuses on entrepreneurship intention.

关键词： Type your keywords here separated by semicolons

来源：评论

学校读者我要写书评

暂无评论

IsoGAN: A Gan Based Method for Isometric View Images Generation From Three Orthographic Views Contour Drawings

IsoGAN: A Gan Based Method for Isometric View Images Generat...

引用

Image Processing Challenges (ICIPC), IEEE International Conference on

作者： Thao Nguyen Phuong Hidetomo Sakaino Vinh Nguyen Duy Data Solution Dept. (FCJ.ABC) FPT Consulting Japan AI-Image Group FPT Software Department of Computer Science and Communications Engineering Waseda University

ISBN: (数字)9798331515942

ISBN: (纸本)9798331515959

Reconstructing the 2D or 3D shape of an object from several 2D drawings is a crucial problem in computer-aided design (CAD). Despite the advancement of deep neural networks, automatic isometric image generation from three orthographic views line drawings using deep learning remains unresolved. Existing image-to-image translation techniques often generate images from just one input image. In this paper, we propose a novel method for the above task using a GAN-based model, namely IsoGAN. This method takes three images of object’s front, side, and top view as input, then analyzes the spatial and geometrical relations between each view and finally generates the corresponding isometric view image of the object. Extensive experiments on SPARE3D dataset show promising results of IsoGAN on isometric view generation task, demonstrating the effectiveness of the proposed IsoGAN.

关键词： Deep learning Solid modeling Design automation Three-dimensional displays Image synthesis Shape Transforms Vectors Generators Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Actively Adaptive Multi-Armed Bandit Based Beam Tracking for mmWave MIMO Systems

Actively Adaptive Multi-Armed Bandit Based Beam Tracking for...

引用

IEEE Conference on Wireless Communications and Networking

作者： Ashim Kumar Arghyadip Roy Ratnajit Bhattacharjee Dept. of Electronics and Electrical Engineering Indian Institute of Technology Guwahati India Mehta Family School of Data Science and Artificial Intelligence (MFSDSAI) Indian Institute of Technology Guwahati India Dept. of Electronics and Electrical Engineering & MFSDSAI Indian Institute of Technology Guwahati India

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Beam tracking methods are instrumental for efficient use of the multi-gigahertz bandwidth available at mmWave frequencies. In this paper, we propose a Multi-armed Bandit (MAB) based Reinforcement Learning (RL) algorithm to periodically select transmitter-receiver beam pairs so as to maximize the average spectral efficiency. Contrary to a traditional Bayesian MAB-based approach, the MAB algorithm proposed by us can track a user as it moves across multiple correlation distances. The algorithm keeps track of the received signal strength to detect a change in the channel correlation and adjusts its strategy to adapt to the new channel conditions. We derive an upper bound on the regret of the proposed algorithm. The proposed algorithm is evaluated on channel data generated using the open-source simulator NYUSIM and is observed to outperform existing algorithms, thus removing the requirement of repeated initial access procedures.

关键词： Correlation Upper bound Protocols Tracking Change detection algorithms Spectral efficiency Instruments

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network-based image tamper detection with Error Level Analysis

Convolutional Neural Network-based image tamper detection wi...

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： Manjunatha S Swetha M D Rashmi S Ananda Kumar Subramanian Vinoth Kumar V Mallikarjuna Swamy S Department of Information Science and Engineering Global Academy of Technology Bengaluru India Department of Computer Science and Engineering BNM Institute of Technology Bengaluru India Department of Computer Science and Engineering (Data Science) Dayananda Sagar College of Engineering Bengaluru India Dept of Computational Intelligence School of Computer Science Engineering VIT – University Vellore India School of Computer Science Engineering and Information Systems VIT – University Vellore India Dept of Electronics and Communication Engineering JSS Academy of Technical Education Bengaluru India

Photography is the most important, powerful, and reliable means of expression. Today, digital images not only provide disinformation but also act as agents for secret communication. Users and editing professionals work with digital images for a variety of purposes. Images are often regarded as facts or proof of reality, so they are misleading and fake news or publications of any form that use images manipulated in a highly misleading way. To recognize image tampering needs multiple image data and a model that can handle all the pixels in the image. Furthermore, training the data more efficiently and needed flexibility support everyday use. Models based on Deep learning such as Convolutional Neural Networks with error level analysis (ELA) are the perfect solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Question Categorizer: An Automated Approach For Organizing Queries

Question Categorizer: An Automated Approach For Organizing Q...

引用

Networking and Communications (ICNWC), International Conference on

作者： Naina Roy Khushi Upadhyay Payal Doshi Tatwadarshi P. Nagarhalli Dept. of Artificial Intelligence and Data Science Vidyavardhini’s College of Engineering and Technology Mumbai India Prime SofTech Solutions Pvt. Ltd. Pune India

ISBN: (数字)9798350365269

ISBN: (纸本)9798350365276

Question categorization is an essential task in natural language processing (NLP) and information retrieval which is the process of automatically assigning a category or class label to a given question based on its content. Categorizing questions plays a pivotal role in enhancing comprehension and facilitating targeted responses. This paper delves into the development and implementation of an advanced question categorization system which classifies questions into eight distinct categories: Analytical, definition, Theoretical, Inferential, Formulation, Differential, Mathematical and Statistical thereby encompassing a wide spectrum of question types. The foundation of this system lies in the integration of a sophisticated BERT architecture, natural language processing techniques, and domain-specific expertise. The system autonomously processes input queries, identifying the underlying characteristics that define each category and assigns the category to the input data. The model is trained on a curated set of data and the proposed methodology achieved promising results with an accuracy score of 0.98 for the 8 categories multiclass classification.

关键词： Training Transformers Information retrieval Natural language processing data models Robustness Filling

来源：评论

学校读者我要写书评

暂无评论

PV-Cap: 3D Dynamic Scene Understanding Through Open Physics-based Vocabulary

PV-Cap: 3D Dynamic Scene Understanding Through Open Physics-...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Hidetomo Sakaino Thao Nguyen Phuong Vinh Nguyen Duy Data Solution Dept. AI-Image Group (FCJ.ABC) FPT Consulting Japan FPT Software Department of Computer Science and Communications Engineering Waseda University

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Recently, large Vision Language (VL) models, i.e., CLIP, have demonstrated impressive capabilities in training solely on internet-scale image-language pairs. Moreover, almost all VL models have tackled indoor objects under controlled illumination and camera views. However, outdoor 3D environments are time-varying uncontrolled scenes under natural phenomena. Therefore, captions from such unseen scenes and objects are hard to obtain in a state-of-the-art (SOTA) one-shot algorithm, resulting in insufficient captions. This paper proposes PV-Cap (Physics-based Vocabulary for Caption) for enhancing 3D scene understanding through enriched captions. Since many tasks in understanding 3D dynamic scenes are hard to deal with, PVCap aims to disentangle such complexities through multiple grouped Deep Learning and Vision Language models step-wisely. Proposed i-VQA (iterative VQA) and 3D-CPP (3D Contrastive Physical-Scale Pretraining) extended from SOTA 2D-CLIP also contribute to generating physical and 3D-based captions. Using many images with 3D dynamic events, i.e., road scenes with traffic flow and accidents, experiments have demonstrated the usability and effectiveness of proposed PV-Cap over SOTA models in terms of segmentation and captions.

关键词： Deep learning Training Solid modeling Vocabulary Three-dimensional displays Roads Cameras

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of IoT data Diversity on Machine Learning Model

Exploring the Impact of IoT Data Diversity on Machine Learni...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： Dhananjay Bisen Nookala Venu Aditya Dubey Priyanka Garg Suresh Salendra T. Lakshmi Devi Center for Internet of Things Madhav Institute of Technology & Science Gwalior M.P India Data Science and Quantum Computing ABV Indian Institute of Information Technology and Management Gwalior M.P India Dept. of Compter Science and Engineering Balaji Institute of Technology & Science Warangal Telangana India Dept.of CSE-Data Science Siddhartha Institute of Engineering and Technology Hyderabad India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

The past few years have witnessed a remarkable change by the rapid expansion of the Internet of Things (IoT). The increasing spread of networked devices in various areas of the Internet of Things has resulted in a huge amount of machine data. This data contains rich information that can be harnessed across domains such as healthcare, agriculture, smart cities, and manufacturing. To effectively analyze and capitalize this information, the integration of machine learning (ML) methods is essential. Thus, well-known machine learning techniques including Logistic Regression, Decision Tree, KNN, SVM, Random Forest, and Naive Bayes are used in paper. The performance of the algorithms is analyzed using three diverse IoT datasets and compared to one another using pre-defined measures such as accuracy, precision, recall, F1-score and execution time. Furthermore, test findings shown that the random forest algorithm consistently outperformed other algorithms for a variety of datasets with up to 98% accuracy.

关键词： Support vector machines Logistic regression Accuracy Machine learning algorithms Nearest neighbor methods Real-time systems Bayes methods Internet of Things Decision trees Random forests

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：