检索结果-内蒙古大学图书馆

Innovation in technology (ASIANCON), Asian Conference on

作者： Yaswanth Gangula Snigdha Srivastava Aparna Mohanty Prakasam P School of Electronics Engineering Vellore Institute of Technology Vellore India Professional 1 Software Engineer DXC Technology Delhi India

Banknote authentication is a critical aspect of the financial industry, playing a vital role in ensuring the integrity of transactions and safeguarding against counterfeiting and fraudulent activities. The prevention of counterfeit banknotes is of utmost importance due to the significant economic and national security risks associated with such activities. To address this challenge, advanced techniques utilizing machine learning algorithms trained on extensive datasets are employed to identify distinctive features and patterns characteristic of authentic banknotes. This work focuses on comparing and evaluating the performance of various machine learning models in the task of banknote authentication. The models under consideration include Logistic Regression With LBFGS, Logistic Regression With SGD, SVM With SGD, Random Forest, XgBoost, and Neural Network. By analyzing various parameters, the study aims to identify the most accurate and efficient approach for verifying banknote authenticity, thereby ensuring the integrity and security of financial transactions. The impact of counterfeit banknotes extends beyond the financial sector, affecting the economy and public trust in the currency's value. Thus, an effective and accurate banknote authentication system is crucial for maintaining a stable economy. The findings from this study will contribute to improved accuracy and efficiency in detecting counterfeit banknotes, mitigating financial losses, and preserving the economy's security and stability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Feature Selection and SVM Parameter By Using Artificial Bee Colony Algorithm 22

Simultaneous Feature Selection and SVM Parameter By Using Ar...

引用

Proceedings of the 2022 6th International Conference on Electronic Information technology and Computer engineering

作者： Xiaomin Zhang Chuan Liu Lian Xue Heqiong Zeng School of Artificial Intelligence Wuhan Technology and Business University China School of Software Engineering Hubei Science and Technology College China

ISBN: (纸本)9781450397148

Support vector machine (SVM) is one of the most successful classifiers in data mining. The performance of SVM is mainly affected by the parameters and features used. Some approaches have been put forward to ensure the best performance of SVM, which usually utilized evolutionary computation algorithms or swarm intelligence algorithm to learn the optimal parameters or select the best subset for SVM. However, these procedures are conducted separately, which made it difficult to obtain the global optimal SVM classifier as features and parameters are interacted each other. In this paper, it proposes to simultaneously determine the parameters and accomplish feature selection for SVM by using Artificial Bee Colony Algorithm, which might acquire the overall optimal SVM classifier to the largest extent. The proposed method has been run on some UCI data set, as well, particle swarm optimization algorithm (PSO) and genetic algorithm (GA) are utilized to optimize SVM in the same way. Experimental results show that the proposed method has good adaptability and the classification accuracy, it can simultaneously obtain the optimal SVM classifier, which is better than PSO and GA in the term of optimization ability.

关键词： Support vector machine Feature selection Parameter optimization Artificial bee colony algorithm

来源：评论

学校读者我要写书评

暂无评论

Non-IT Program Students Learn Basic Web Language;The Preliminary Study of Affective and Cognitive Response on IVML Prototype 17th

Non-IT Program Students Learn Basic Web Language;The Prelimi...

引用

17th International Conference on Information technology and Applications, ICITA 2023

作者： Naim, Nur Faraha Mohd Ibrahim, Ag. Asri Ag. Baharum, Aslina Moung, Ervin Gubin Salimun, Carolyn Multimedia Technology Programme Faculty of Computing and Informatics Universiti Malaysia Sabah Kampus Antarabangsa Labuan Federal Territory of Labuan Malaysia Software Engineering Programme Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Sabah Malaysia User Experience Research Group Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Sabah Malaysia School of Engineering and Technology Sunway University Selangor Petaling Jaya Malaysia

ISBN: (纸本)9789819983230

This paper examines the response of affective and cognitive processes under human–computer interaction (HCI) toward interactive video mobile learning known as the IVML prototype. The idea is to determine the potential of the interactive elements in the educational video as the key factor that can influence learners’ engagement and comprehension of the presented topic. This paper aims to measure the level of affective and cognitive response of learners toward the subject learning that are not from their field, not exposed to, or not familiar with. The data analyze based on user experience, user interface, and human–computer interaction. The statistical result may produce a significant outcome that could contribute to the hyper video platform. The findings may confirm the significant role of technical aspects and psychological aspects included in video production style, hence heightening the hyper video platform in teaching and learning activities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient and Diverse Generative Model for Unconditional Human Motion Synthesis 24

Towards Efficient and Diverse Generative Model for Unconditi...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Yu, Hua Liu, Weiming Bai, Jiapeng Gui, Xu Hou, Yaqing Ong, Yewsoon Zhang, Qiang Key Laboratory of Social Computing and Cognitive Intelligence Ministry of Education School of Computer Science and Technology Dalian University of Technology Dalian China College of Computer Science Zhejiang University Hangzhou China National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University Dalian China College of Computing and Data Science Nanyang Technological University Singapore Singapore Yonsei University Seoul Korea Republic of

ISBN: (纸本)9798400706868

Recent generative methods have revolutionized the way of human motion synthesis, such as Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Denoising Diffusion Probabilistic Models (DMs). These methods have gained significant attention in human motion fields. However, there are still challenges in unconditionally generating highly diverse human motions from a given distribution. To enhance the diversity of synthesized human motions, previous methods usually employ deep neural networks (DNNs) to train a transport map that transforms Gaussian noise distribution into real human motion distribution. According to Figalli's regularity theory, the optimal transport map computed by DNNs frequently exhibits discontinuities. This is due to the inherent limitation of DNNs in representing only continuous maps. Consequently, the generated human motions tend to heavily concentrate on densely populated regions of the data distribution, resulting in mode collapse or mode mixture. To address the issues, we propose an efficient method called MOOT for unconditional human motion synthesis. First, we utilize a reconstruction network based on GRU and transformer to map human motions to latent space. Next, we employ convex optimization to match the noise distribution with the latent space distribution of human motions through the Optimal Transport (OT) map. Then, we combine the extended OT map with the generator of reconstruction network to generate new human motions. Thereby overcoming the issues of mode collapse and mode mixture. MOOT generates a latent code distribution that is well-behaved and highly structured, providing a strong motion prior for various applications in the field of human motion. Through qualitative and quantitative experiments, MOOT achieves state-of-the-art results surpassing the latest methods, validating its superiority in unconditional human motion generation. © 2024 ACM.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Classification of Subtypes of Acute Lymphoblastic Leukemia Using Feature Fusion from Blood Smear Images

Classification of Subtypes of Acute Lymphoblastic Leukemia U...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Ghazala Alhadi Eljadi Ahmed Lawgali Salwa Elakeili dept. Computer Sciences Faculty of Information Technology University of Benghazi Beghazi Libya dept. Software Engineering Faculty of Information Technology University of Benghazi Beghazi Libya

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Early detection of Acute Lymphoblastic Leukemia (ALL) is vital for providing appropriate treatment, which requires accurate diagnosis to identify the types of the disease. Therefore, this study focuses on evaluating the performance of deep learning models in classifying different types of leukemia using three pre-trained CNN models: MobileNet V2, DenseNet201, and EfficientNet, to extract deep features. These features are then combined into a single set. An information exchange technique was used to select the best features after merging, and SMOTEENN was employed to address feature imbalance. The results showed that combining features extracted by the pre-trained CNN models achieved high accuracy and reliability, reaching 99.66%, enhancing the performance in accurately and quickly classifying patients. This approach not only improves diagnostic accuracy but also contributes to accelerating the decision-making process for treatment, enabling doctors to better tailor therapies and thereby improve patient outcomes. The findings underscore the importance of ongoing research in this field and provide future recommendations for enhancing performance and increasing classification accuracy in similar medical applications.

关键词： Support vector machines Accuracy Merging Leukemia Medical treatment Feature extraction Convolutional neural networks Reliability Blood Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Multi-view Clustering via Joint Self-representation and Semi-nonnegative Matrix Factorizations

Multi-view Clustering via Joint Self-representation and Semi...

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Xiaochun Fu Xiangdong Zhang Qin Li School of Communication Engineering Xidian University Xi’an China School of Software Engineering Shenzhen Institute of Information Technology Shenzhen China

The traditional clustering methods, which rely on sample spacing to construct clusters, cannot be applied to high-dimensional data due to its intricate data structure and numerous irrelevant attributes. In practice, high-dimensional data often possess a latent low-dimensional subspace structure. Multi-view clustering achieves consistency and complementarity of multi-view data by uncovering the underlying *** recent years, researchers have proposed many subspace representation clustering methods, which have improved the performance of multi-view clustering to a certain extent. However, general clustering methods need to construct Adjacency matrix and calculate the Eigendecomposition of a matrix of its Laplacian matrix, which makes the algorithm very complex and restricts the use of clustering algorithms in large-scale problems, based on the above issues, we propose a new multi-view subspace clustering model. In our model, by learning a data-anchor connection bipartite graph to achieve a fast clustering process, the weights of the edges of the bipartite graph are used to represent the similarity between the corresponding data and anchors, and matrix decomposition is utilized to reduce the view dimension to a low-dimensional space. In addition, the non-negative matrix decomposition technology is used to reduce the view dimension to a low dimensional space, and the $\ell_{1,2}$-norm is used for the similarity matrix between views to mitigate the impact of outliers in the original data on the Matrix decomposition,and the Schatten p-norm based on t-SVD is employed to amplify the high-order correlation between different views. A multitude of experimental results on various multi-view datasets demonstrate the effectiveness of our proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of Area-Based Explosive Trace Detection Using Deep Transfer Learning

Development of Area-Based Explosive Trace Detection Using De...

引用

Innovative engineering Sciences and Technological Research (ICIESTR), International Conference on

作者： Monday F. Ohemu Ambrose A. Azeta Ibrahim A. Adeyanju Chukwuemeka C. Obasi Department of Electrical/Electronics Engineering Airforce Institute of Technology Kaduna Nigeria Department of Software Engineering Namibia University of Science and Technology Namibia Department of Computer Engineering Federal University Oye-Ekiti Nigeria Department of Computer Engineering Edo State University Uzairue

ISBN: (数字)9798350348637

ISBN: (纸本)9798350348644

Terrorism poses a significant global threat, necessitating comprehensive security measures to protect people and critical infrastructure. With the increasing frequency of explosive-based attacks, there is a pressing need for advanced detection systems to mitigate potential devastation. This paper presents the development of an area-based explosive trace detection system using deep transfer learning. Leveraging deep learning technology trained on a substantial dataset collected from sensor networks, the proposed model, named Deep Transfer Learning for Explosive Trace Detection (DTLETD), demonstrates remarkable capabilities in classifying explosive gases based on concentrations of Carbon (C), Hydrogen (H), Oxygen (O), and Nitrogen (N). The methodology involves converting the dataset into 2D data using a serial data to image generator, followed by the adaptation of a pre-trained model for transfer learning. The DTLETD model outperformed conventional Convolutional Neural Network (CNN) models, achieving a training time reduction of about 92 seconds compared to 1287 seconds for the CNN model. Additionally, the transfer learning model exhibits faster convergence with nearly zero losses during training and validation, yielding an impressive accuracy of 99.7% and an average AUC value of approximately 0.89. This research significantly advances the field of explosive trace detection by integrating machine learning-based approaches with deep transfer learning techniques, thereby enhancing security protocols and mitigating potential threats.

关键词： Training Adaptation models Accuracy Protocols Terrorism Transfer learning Pressing Explosives Data models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Harnessing the meteorological effect for predicting the retail price of rice in Bangladesh

引用

International Journal of Business Intelligence and Data Mining 2022年第4期20卷 440-455页

作者： Imran, Abdullah Al Wahid, Zaman Prova, Alpana Akhi Hannan, Md. Department of Computer Science and Engineering American International University-Bangladesh 408/1 Kuratoli Dhaka1229 Bangladesh Department of Software Engineering Daffodil International University Daffodil Road Ashulia Dhaka Bangladesh Department of Computer Science Islamic University of Technology K B Bazar Rd Gazipur1704 Bangladesh

Bangladesh has seen an absurd, steeper prize-hike for the last couple of years in one of the most consumed foods taken by millions of people every single day: rice. The impact of this phenomenon, however, is indispensably critical, especially to the one striving for daily meals. Thus, understanding the latent facts is vital to policymakers for better strategic measures and decision-making. In this paper, we have applied five different machine learning algorithms to predict the retail price of rice, find out the top-most factors responsible for the price hike, and determine the best model that produces higher prediction results. Leveraging six evaluation metrics, we found that random forest produces the best result with an explain variance score of 0.87 and an R2 score of 0.86 whereas gradient boosting produces the least, meanwhile discovering that average wind speed is the topmost reason for rice price hike in retail markets. © 2022 Inderscience Enterprises Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

VIDEO DERAINING VIA TEMPORAL AGGREGATION-AND-GUIDANCE

VIDEO DERAINING VIA TEMPORAL AGGREGATION-AND-GUIDANCE

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Ma, Long Liu, Risheng Zhang, Xuefeng Zhong, Wei Fan, Xin School of Software Technology Dalian University of Technology China International School of Information Science and Engineering Dalian University of Technology China Key Laboratory for Ubiquitous Network Service Software of Liaoning Province China

ISBN: (纸本)9781665438643

Learning-based video deraining methods generally integrate temporal correlation within the network. But their non-transparency (i.e., difficult to comprehend how to exploit temporal correlation) seriously limits the development for video deraining. To conquer it, this paper proposes a novel Temporal Aggregation-and-Guidance Network (TAG-Net). Concretely, we define a new temporal ensemble model with set representation by modeling correspondence between rain regions of the current frame and rain-free regions of adjacent frames. Further, we build a TAG-Net that contains: 1) temporal aggregation network derived from the ensemble model, which is with newly-designed self-directed attention acting on video sequences, it automatically learns temporal correlation from multiple adjacent frames to optimize the current frame. 2) temporal guidance network, which aims at eliminating rain streaks in intersected rain regions between the current and adjacent frames to enhance the previously-recovered frame. Extensive evaluations verify that TAG-Net yields the best performance against other advanced methods. © 2021 IEEE

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Dominating Set Database Selection for Visual Place Recognition

Dominating Set Database Selection for Visual Place Recogniti...

引用

International Conference on Advanced Robotics (ICAR)

作者： Anastasiia Kornilova Ivan Moskalenko Timofei Pushkin Fakhriddin Tojiboev Rahim Tariverdizadeh Gonzalo Ferrer Center for AI Technology (CAIT) Skolkovo Institute of Science and Technology (Skoltech) Software Engineering Department Saint Petersburg State University

This paper introduces a novel approach for creating a visual place recognition (VPR) database for localization in indoor environments from RGBD scanning sequences. The proposed method formulates the problem as a minimization challenge by utilizing a dominating set algorithm applied to a graph constructed from spatial information, referred to as the “DominatingSet” algorithm. Experimental results on various datasets, including 7-scenes, BundleFusion, RISEdb, and a specifically recorded sequences in a highly repetitive office setting, demonstrate that our technique significantly reduces database size while maintaining comparable VPR performance to state-of-the-art approaches in challenging environments. Additionally, our solution enables weakly-supervised labeling for all images from the sequences, facilitating the automatic fine-tuning of VPR algorithm to target environment. Additionally, this paper presents a fully automated pipeline for creating VPR databases from RGBD scanning sequences and introduces a set of metrics for evaluating the performance of VPR databases. The code and released data are available on our web-page —https://***/place-recognition-db/.

关键词：

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：