检索结果-内蒙古大学图书馆

11th IEEE International Conference on Cloud computing in Emerging Markets, CCEM 2023

作者： Govindarajan, Priya Surendran, Aswin P. Kumar, Sanjeev S. Tesfahun, Abebe Department of Computer Science Amrita School of Computing Amrita Vishwa Vidyapeetham Mysuru Campus India School of Electrical & Computer Engineering Scientific Director Debre Markos Institute of Technology Debre Markos University Ethiopia

ISBN: (纸本)9798350360059

The rampant spread of deepfake videos, a significant threat to media integrity, occurs widely on social media and news platforms. Detecting Deepfakes is a formidable challenge. The proposed study involves a novel algorithm to detect the deepfake. The model comprises of various pre-existing classifiers and a novel algorithm named ForenShield – which detects the deepfakes with an accuracy of 97%. The proposed novel technique works on voting strategy and it outperforms all the pre-existing classifiers, exhibiting the models excellence through the same. ©2023 IEEE.

关键词： Classifiers Deepfake ForenShield Voting Strategy

来源：评论

学校读者我要写书评

暂无评论

Yoga in digital Age: A Hybrid Approach using ML and computer vision 11

Yoga in digital Age: A Hybrid Approach using ML and Computer...

引用

11th IEEE International Conference on Cloud computing in Emerging Markets, CCEM 2023

作者： Govindarajan, Priya Achaiah, K.K. Pramod, Arjun S. Tesfahun, Abebe Department of Computer Science Amrita School Of Computing Amrita Vishwa Vidyapeetham Mysuru campus India School of Electrical & Computer Engineering Scientific Director Debre Markos Institute of Technology Debre Markos University Ethiopia

ISBN: (纸本)9798350360059

—In today’s fast-paced world, stress and pressure affect people of all ages, both physically and mentally. Yoga has emerged as a highly sought-after solution due to its numerous benefits. In the present technology-dependent era of digital age, it’s only natural that we turn to technology for assistance in their yoga journey. This is where the proposed article comes into play, serving as one’s digital Yoga Guru. In this paper, seven classifiers, out of which six are Machine Learning classifiers namely Support Vector Machine, Naïve Bayes, Random Forest, K-Nearest Neighbor, Logistic Regression, and Ensembler are employed to classify the dataset. These classifiers exhibit a promising average accuracy exceeding 90%. Additionally, the proposed method incorporates a Deep Learning model, specifically the Multi-Perceptron Neural Network, which has been trained to predict outputs with an impressive accuracy of 92%. This Paper utilizes the power of MediaPipe, a cutting-edge technology that plays a pivotal role in this innovative approach to yoga. MediaPipe is capable of identifying individuals on the screen and provides 33 key-points, including critical markers like facial key-points, and main keypoints of the body such as shoulders, elbows, knees, feet, wrists, and etc. These key points are essential for pose recognition, and assessing the correctness of yoga postures. What sets the proposed method apart is its real-time, live tracing feature, boasting an impressive accuracy rate of 99%. As one engages in yoga practice, this technology tracks their movements, and compares them to the ideal yoga postures. This immediate feedback ensures that one performs each pose correctly, promoting better results and minimizing the risk of injury. In essence, the proposed method bridges the gap between ancient yoga wisdom and modern technology, offering a digital Yoga Guru that guides one to achieve physical and mental well-being with precision and confidence. ©2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Multitask learning for Arabic Dialects Identification and Machine Translation

Multitask learning for Arabic Dialects Identification and Ma...

引用

International Conference on Artificial Intelligence and Its Practical Applications in the Age of Digital Transformation, I2COMSAPP 2024

作者： Dhleima, Mohamed Tourad, Mohamedou Cheikh Telmoud, Cheikh Abdelkader Ahmed Abdelmounaim, Abdali Nanne, Mohamedade Farouk Scientific Computing Computer Science and Data Science Research Unit University of Nouakchott Nouakchott Mauritania Research Team Control and Informatics for Intelligent Systems and Green Energy FST cadi Ayyad Marrakech Morocco

ISBN: (纸本)9783031714283

Multitask learning (MTL) is a popular approach in natural language processing (NLP) to improve the performance of related functions. This paper presents a comprehensive approach to address dialect identification and translation challenges in Arabic NLP. The proposed model utilizes state-of-the-art transformer architectures for both tasks, ensuring robust performance in capturing contextual dependencies and linguistic nuances inherent in Arabic dialects. The primary objectives are to accurately identify Arabic dialects and facilitate their translation to Modern Standard Arabic (MSA) using a shared representation learning approach. The model architecture consists of a shared embedding layer followed by a transformer encoder for each task, employing multi-head self-attention mechanisms for hierarchical contextual information extraction. The model’s performance is evaluated using the F1-score for dialect classification, and the BLEU-score for translation performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Integrating nature-inspired optimization algorithms to K-means clustering

Integrating nature-inspired optimization algorithms to K-mea...

引用

7th International Conference on Digital Information Management, ICDIM 2012

作者： Tang, Rui Fong, Simon Yang, Xin-She Deb, Suash Department of Computer and Information Science University of Macau Taipa China Mathematics and Scientific Computing National Physical Laboratory Teddington United Kingdom Department of Computer Science and Engineering C. V. Raman College of Engineering Bidyanagar India

ISBN: (纸本)9781467324281

Although K-means clustering algorithm is simple and popular, it has a fundamental drawback of falling into local optima that depend on the randomly generated initial centroid values. Optimization algorithms are well known for their ability to guide iterative computation in searching for global optima. They also speed up the clustering process by achieving early convergence. Contemporary optimization algorithms inspired by biology, including the Wolf, Firefly, Cuckoo, Bat and Ant algorithms, simulate swarm behavior in which peers are attracted while steering towards a global objective. It is found that these bio-inspired algorithms have their own virtues and could be logically integrated into K-means clustering to avoid local optima during iteration to convergence. In this paper, the constructs of the integration of bio-inspired optimization methods into K-means clustering are presented. The extended versions of clustering algorithms integrated with bio-inspired optimization methods produce improved results. Experiments are conducted to validate the benefits of the proposed approach. © 2012 IEEE.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Wolf search algorithm with ephemeral memory

Wolf search algorithm with ephemeral memory

引用

7th International Conference on Digital Information Management, ICDIM 2012

ISBN: (纸本)9781467324281

In computer science, a computational challenge exists in finding a globally optimized solution from a tremendously large search space. Heuristic optimization methods have therefore been created that can search the very large spaces of candidate solutions. These methods have been extensively studied in the past, and progressively extended in order to suit a wide range of optimization problems. Researchers recently have invented a collection of heuristic optimization methods inspired by the movements of animals and insects (e.g., Firefly, Cuckoos, Bats and Accelerated PSO) with the advantages of efficient computation and easy implementation. This paper proposes a new bio-inspired heuristic optimization algorithm called the Wolf Search Algorithm (WSA) that imitates the way wolves search for food and survive by avoiding their enemies. The contribution of the paper is twofold: 1. for verifying the efficacy of the WSA the algorithm is tested quantitatively and compared to other heuristic algorithms under a range of popular non-convex functions used as performance test problems for optimization algorithms;2. The WSA is investigated with respective to its memory requirement. Superior results are observed in most tests. © 2012 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network for Cancer Treatment Response Prediction

Convolutional Neural Network for Cancer Treatment Response P...

引用

International computer Engineering Conference (ICENCO)

作者： Hanan Ahmed Howida A. Shedeed Safwat Hamad Ashraf S. Hussein Scientific Computing Faculty of computer and Information science Cairo Egypt

ISBN: (纸本)9781665458962

Recently, efforts are exerted on cancer treatment prediction based on the biomarkers related to the tumor. Many biomarkers are used to discriminate cancer but there is no accurate evidence which is more accurate. To save resources and due to the enormous computational power, the analysis of huge sequences such as DNA (DesoxyriboNucleic Acid) becomes a valid process. Machine learning and deep learning algorithms have been used to predict drug response. The indicators show that the performance of deep learning models is better than the performance of machine learning based one. In this paper, we introduce the use of Convolutional Neural Network (CNN) to predict the response of 265 different drugs using the gene expression profile and mutation profile of 19702 genes. DeepInsight algorithm used to convert the input data to images to be more suitable as input to the CNN. We proposed eight CNNs with different architectures. At first, the whole data input passes through the DeepInsight model which converts the gene expression data and mutation data to images. Dimension reduction is then applied using the helper technique inside the DeepInsignt. The CNN are trained with different settings such as image size, no of nodes in layers…etc. Comparative analysis shows that the proposed architectures improve the prediction accuracy in a range between 16% and 24% as a reduction in mean squared error (MSE).

关键词： Drugs Deep learning Machine learning algorithms Cancer treatment computer architecture Biomarkers Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Sequence Submodular Maximization Meets Streaming 13th

Sequence Submodular Maximization Meets Streaming

引用

13th Annual International Conference on Combinatorial Optimization and Applications, COCOA 2019

作者： Yang, Ruiqi Xu, Dachuan Guo, Longkun Zhang, Dongmei Department of Operations Research and Scientific Computing Beijing University of Technology Beijing100124 China College of Mathematics and Computer Science Fuzhou University Fuzhou350116 China School of Computer Science and Technology Shandong Jianzhu University Jinan250101 China

ISBN: (纸本)9783030364113

In this paper, we consider the streaming sequence submodular maximization problem, in which the utility function is defined on sequences of element instead of element sets. We encode the values of different sequences by a weighted directed acyclic graph (W-DAG), where the weight of vertex reveals the utility value in selecting single element and the weight of an edge proclaims the additional benefit according to a certain selected order. In addition, the edges are revealed in a streaming fashion that one edge is known in one time slot. The aim is to output a sequence of vertices of length bounded by a given constant k, such that the utility function value is maximized. In this work, we first provide the framework of the sequence submodular maximization under streaming. By utilizing an edge-based thresholding principle, we derive a one pass, -approximation algorithm with memory and update time per edge, where and is the maximum in-degree (out-degree) of the constructed W-DAG. At last, we present a further improved streaming algorithm, which also requires one pass over the stream and attains the same approximation ratio but is with a decreased memory complexity of. © 2019, Springer Nature Switzerland AG.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Beware of "Explanations" of AI

arXiv

引用

arXiv 2025年

作者： Martens, David Shmueli, Galit Evgeniou, Theodoros Bauer, Kevin Janiesch, Christian Feuerriegel, Stefan Gabel, Sebastian Goethals, Sofie Greene, Travis Klein, Nadja Kraus, Mathias Kühl, Niklas Perlich, Claudia Verbeke, Wouter Zharova, Alona Zschech, Patrick Provost, Foster University of Antwerp Department of Engineering Management Antwerp2000 Belgium National Tsing Hua University Institute of Service Science Hsinchu30013 Taiwan INSEAD Technology and Business Fontainebleau77300 France Goethe University Frankfurt Department of Information Systems Frankfurt60629 Germany TU Dortmund University Department of Computer Science Dortmund44227 Germany LMU Munich Munich Center for Machine Learning Munich80539 Germany Erasmus University Rotterdam School of Management Rotterdam3062 Netherlands Copenhagen Business School Department of Digitalization Copenhagen2000 Denmark Karlsruhe Institute of Technology Scientific Computing Center Karlsruhe76131 Germany University of Regensburg Faculty of Informatics and Data Science Regensburg93053 Germany University of Bayreuth Faculty of Law Business and Economics Bayreuth95440 Germany New York University Department of Technology Operations and Statistics New YorkNY10012 United States KU Leuven Faculty of Economics and Business Leuven3000 Belgium Humboldt-Universität zu Berlin School of Business and Economics Berlin10099 Germany Leipzig University Faculty of Economics and Management Science Leipzig04109 Germany

Understanding the decisions made and actions taken by increasingly complex AI system remains a key challenge. This has led to an expanding field of research in explainable artificial intelligence (XAI), highlighting the potential of explanations to enhance trust, support adoption, and meet regulatory standards. However, the question of what constitutes a "good" explanation is dependent on the goals, stakeholders, and context. At a high level, psychological insights such as the concept of mental model alignment can offer guidance, but success in practice is challenging due to social and technical factors. As a result of this ill-defined nature of the problem, explanations can be of poor quality (e.g. unfaithful, irrelevant, or incoherent), potentially leading to substantial risks. Instead of fostering trust and safety, poorly designed explanations can actually cause harm, including wrong decisions, privacy violations, manipulation, and even reduced AI adoption. Therefore, we caution stakeholders to beware of explanations of AI: while they can be vital, they are not automatically a remedy for transparency or responsible AI adoption, and their misuse or limitations can exacerbate harm. Attention to these caveats can help guide future research to improve the quality and impact of AI explanations. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tree wavelet approximations with applications

引用

science China Mathematics 2005年第5期48卷 680-702页

作者： XU Yuesheng & ZOU Qingsong Department of Mathematics, Syracuse University, Syracuse, NY 13244, USA Institute of Mathematics, Academy of Mathematics and System sciences, Chinese Academy of sciences, Beijing 100080, China Department of scientific computing and computer science, Zhongshan University, Guangzhou 510275, China 1. Department of Mathematics Syracuse University 13244 Syracuse NY USA 2. Institute of Mathematics Academy of Mathematics and System Sciences Chinese Academy of Sciences 100080 Beijing China 3. Department of Scientific Computing and Computer Science Zhongshan University 510275 Guangzhou China

We construct a tree wavelet approximation by using a constructive greedy scheme (CGS). We define a function class which contains the functions whose piecewise polynomial approximations generated by the CGS have a prescribed global convergence rate and establish embedding properties of this class. We provide sufficient conditions on a tree index set and on bi-orthogonal wavelet bases which ensure optimal order of convergence for the wavelet approximations encoded on the tree index set using the bi-orthogonal wavelet bases. We then show that if we use the tree index set associated with the partition generated by the CGS to encode a wavelet approximation, it gives optimal order of convergence.

关键词： greedy algorithms tree wavelet approximations Besov spaces.

来源：评论

学校读者我要写书评

暂无评论

Topology exploration with hierarchical landscapes

Topology exploration with hierarchical landscapes

引用

Workshop at SIGGRAPH Asia 2012, WASA 2012

作者： Demir, Dogan Beketayev, Kenes Weber, Gunther H. Bremer, Peer-Timo Pascucci, Valerio Hamann, Bernd Scientific Computing and Imaging Institute School of Computing University of Utah United States Computational Research Divisition Lawrence Berkeley National Laboratory United States Center for Applied Scientific Computing Lawrence Livermore National Laboratory United States Institute for Data Analysis and Visualization Computer Science Department University of California Davis CA United States

ISBN: (纸本)9781450318358

Topological landscapes have been proposed as a visual metaphor for contour trees that does not require an understanding of the theory involved in defining contour trees. The idea is to create a representative terrain with the same topological structure as a given contour tree. This representation exploits the natural human ability to interpret topography and results in an intuitive visualization of otherwise abstract information. However, topological landscapes still suffer from some of the same limitations as traditional contour tree visualization. Most notable is the fact that for complex functions landscapes can quickly become highly complex, exceeding the limits of human comprehension as well as the available computing resources. To address this challenge, we propose a new framework for the dynamic creation and visualization of hierarchical topological landscapes. Our system provides an interactive visualization of complex functions by utilizing a hierarchical decomposition of the contour tree as well as focus+context type interactions. For three dimensional data, we link the landscape display to flexible isosurface extraction in order to correlate terrain features with their corresponding three dimensional counterparts. We demonstrate the utility and versatility of our approach on a variety of both low and high dimensional data sets. © 2012 ACM.

关键词： Visualization

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：