检索结果-内蒙古大学图书馆

5th International Conference on Artificial Intelligence and Speech Technology, AIST 2023

作者： Deekshitha Reddy, M. Vadali, Geetika Jaiswal, Garima Rani, Ritu Dev, Amita Department of AI and DS Indira Gandhi Delhi Technical University for Women Delhi India Department of Computer Science Bennett University Greater Noida India Department of Electronics and Communication Engineering Bhagwan Parshuram Institute of Technology Delhi India Center of Excellence-Artificial Intelligence Indira Gandhi Delhi Technical University for Women Delhi India

ISBN: (纸本)9783031751660

In the current landscape, Venture capitalists are opting for more data-driven decision-making to achieve high returns while mitigating risks. All VCs seek a home run in their portfolio, for which it is essential to select the optimal exit. The process can be smoothed with the prediction of the type of exit- IPO, M&A, or the next funding round. Further,it is also to gauge which type of exit yields maximum profit for the particular climate. In this paper, through the utilisation of six machine learning models - Elastic Net, SVR, Kernel Ridge, Gradient Boost, XGBoost, and Random Forest, trained on factual data sourced from Crunchbase. The machine learning models are evaluated on the basis of 2 metrics- RMSLE and R-squared Score. We propose an ensemble learning model with Root Mean Square Logarithmic Error (RMSLE) score of 0.29 and R-squared score of 0.76. This weight-averaged ensemble has been validated to predict the optimal exit for a startup under six broad labels - IPO, Acquisition, Leveraged Buyout, Merger, Acquihire, and Management Buyout. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fixed-point iterations for several dissimilarity measure barycenters in the Gaussian case

arXiv

引用

arXiv 2022年

作者： D'Ortenzio, Alessandro Manes, Costanzo Orguner, Umut Department of Information Engineering Computer Science and Mathematics University of L'Aquila Italy Center of Excellence EX-EMERGE University of L'Aquila Italy Department of Electrical and Electronics Engineering Middle East Technical University Turkey

In practical contexts like sensor fusion or computer vision, it is not unusual to deal with a large number of Gaussian densities that encode the available information. In such cases, if the computational capabilities are limited, a data compression is required, often done by finding the barycenter of the set of Gaussians. However, such computation strongly depends on the chosen loss function (dissimilarity measure) to be minimized, and most often it must be performed by means of numerical methods, since the barycenter can rarely be computed analytically. Some constraints, like the covariance matrix symmetry and positive definiteness can make non-trivial the numerical computation of the Gaussian barycenter. In this work, a set of Fixed-Point Iteration algorithms are presented in order to allow for the agile computation of Gaussian barycenters according to several dissimilarity measures. Copyright © 2022, The Authors. All rights reserved.

关键词： Data compression

来源：评论

学校读者我要写书评

暂无评论

MGC: Multiple-Gray-Code for 3D NAND Flash based High-Density SSDs

MGC: Multiple-Gray-Code for 3D NAND Flash based High-Density...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Yina Lv Liang Shi Qiao Li Congming Gao Yunpeng Song Longfei Luo Youtao Zhang School of Computer Science and Technology East China Normal University Shanghai China Ministry of Education Software/Hardware Co-Design Engineering Research Center School of Informatics Xiamen University Xiamen China Computer Science Department University of Pittsburgh Pittsburgh USA

QLC (4-bit-per-cell) and more-bit-per-cell 3D NAND flash memories are increasingly adopted in large storage systems. While achieving significant cost reduction, these memories face degraded performance and reliability issues. The industry has adopted two-step programming (TSP), rather than one-step programming, to perform fine-granularity program control and choose gray-code encoding, as well as LDPC (Low-Density Parity-Check Code) for error correction. Different flash manufacturers often integrate different gray-codes in their products, which exhibit different performance and reliability characteristics. Unfortunately, a fixed gray-code encoding design lacks the ability to meet the dynamic read and program performance requirements at both application and device *** this paper, we propose MGC, a multiple-gray-code encoding strategy, that adaptively chooses the best gray-code to meet the optimization goals at runtime. In particular, MGC first extracts the performance and reliability requirements based on application-level access patterns and detects the reliability degree of SSD. It then determines the appropriate gray-code to encode the data, either from host/user application or due to garbage collection, before writing the pages to the flash memory. MGC is integrated in FTL (flash translation layer) and enhances the flash controller to enable runtime gray-code arbitration. We evaluate the proposed MGC scheme. The results show that MGC achieves better performance and lifetime guarantee compared with state-of-the-arts and introduces little overhead.

关键词： Performance evaluation Three-dimensional displays Runtime Programming Writing Encoding Parity check codes

来源：评论

学校读者我要写书评

暂无评论

Defining Thin Objects in computer Vision

Defining Thin Objects in Computer Vision

引用

ICT Conference (AICTC), Arab

作者： Rabeea Jaffari Syed Saad Ahmed Manzoor Ahmed Hashmani Syed Fahad Ahmed Software Engineering Department Mehran University of Engineering and Technology Jamshoro Sindh Pakistan Universiti Teknologi Petronas Seri Iskander Perak Malaysia Electronics Engineering Department Universiti Tunku Abdul Rahman Kampar Perak Malaysia Computer and Information Sciences Department High Performance Cloud Computing Center (HPC3) Universiti Teknologi Petronas Perak Seri Iskander Malaysia UI/UX Designer Technoholic Advance Solutions Houston Texas USA

ISBN: (数字)9798350342086

ISBN: (纸本)9798350342093

Thin image objects detection in computer vision is a challenging task due to the compactness, slenderness, and extremely small coverage of these objects in the images. This makes these objects difficult to detect especially in the presence of background clutter. Efficient detection of thin image objects is of utmost importance in research areas including but not limited to electrical transmission and mooring fault detection systems, medical analysis, collision and obstacle detection in unmanned aerial and autonomous vehicles, plant stem detection in biological studies, road-lane-line detection and so on. Despite the significance of thin objects detection from images, there is no formal and accurate definition of what thin objects in computer vision are. In this research work, we propose and formalize the criteria for defining thin objects in computer vision. We conduct various experiments to identify the parameters and formalize the measures for describing thin objects in several computer vision research applications and other novel scenarios. The proposed research work can be utilized in the future research for the design and development of efficient thin objects detection and localization datasets, algorithms and other relevant tasks.

关键词： Location awareness computer vision Plants (biology) Fault detection Object detection Biology Object recognition Clutter Autonomous vehicles Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Coevolutionary Algorithm for Building Robust Decision Trees under Minimax Regret

arXiv

引用

arXiv 2023年

作者： Zychowski, Adam Perrault, Andrew Mańdziuk, Jacek Faculty of Mathematics and Information Science Warsaw University of Technology Poland Department of Computer Science and Engineering The Ohio State University United States Faculty of Computer Science AGH University of Krakow Poland Center of Excellence in Artificial Intelligence AGH University of Krakow Poland

In recent years, there has been growing interest in developing robust machine learning (ML) models that can withstand adversarial attacks, including one of the most widely adopted, efficient, and interpretable ML algorithms—decision trees (DTs). This paper proposes a novel coevolutionary algorithm (CoEvoRDT) designed to create robust DTs capable of handling noisy high-dimensional data in adversarial contexts. Motivated by the limitations of traditional DT algorithms, we leverage adaptive coevolution to allow DTs to evolve and learn from interactions with perturbed input data. CoEvoRDT alternately evolves competing populations of DTs and perturbed features, enabling construction of DTs with desired properties. CoEvoRDT is easily adaptable to various target metrics, allowing the use of tailored robustness criteria such as minimax regret. Furthermore, CoEvoRDT has potential to improve the results of other state-of-the-art methods by incorporating their outcomes (DTs they produce) into the initial population and optimize them in the process of coevolution. Inspired by the game theory, CoEvoRDT utilizes mixed Nash equilibrium to enhance convergence. The method is tested on 20 popular datasets and shows superior performance compared to 4 state-of-the-art algorithms. It outperformed all competing methods on 13 datasets with adversarial accuracy metrics, and on all 20 considered datasets with minimax regret. Strong experimental results and flexibility in choosing the error measure make CoEvoRDT a promising approach for constructing robust DTs in real-world applications. © 2023, CC BY.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Intelligence Surface Assisted Opportunistic Multiple Access in UAV-IoT Networks

引用

IEEE Internet of Things Journal 2025年

作者： Zhang, Xi-Ran Sun, Wen-Bin Zhang, Zhaolin Wang, Ling Gao, Ang Cheng, Nan Meng, Wei-Xiao Leung, Victor C. M. Northwestern Polytechnical University School of Electronics And Information Xi'an China Xidian University State Key Laboratory of ISN Xi'an710071 China Xidian University School of Cyber Engineering Xi'an710071 China Harbin Institute of Technology Communication Research Center Harbin150001 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T1Z4 Canada

Due to the advantages of flexible deployment and strong environmental adaptability of an unmanned aerial vehicle (UAV), UAVs serve as aerial base stations (BSs) to meet Quality of Services (QoSs) of ground users in internet of things (IoT) networks. NOMA (Non-Orthogonal Multiple Access) is a potential technique in wireless communications area, which can significantly improve sum spectrum efficiency (SE) of systems. To avoid the limitation of perfect CSI, opportunistic beamforming (OBF) is proposed, where a set of randomly generated weights is used to preprocess transmitted signals. Due to multiuser diversity gain introduced by OBF, OBF-NOMA systems can achieve approximate sum SE to conventional NOMA systems. Additionally, reconfigurable intelligent surfaces (RISs) are involved to overcome obstruction and obtain further improvements of SE. Therefore, this paper proposes a RIS-aid OBF-NOMA system in UAV-IoT networks, where random weights and opportunistic phase matrix are respectively applied in a UAV and RIS. Statistical characteristics of equivalent channels are derived in Nakagami-m (m≥1) fading channels. Theoretical asymptotic analyses of SE and bit error rate (BER) are then presented. Furthermore, a non-convex optimization problem is formulated to maximize SE. To obtain the optimal solution, we divide the problem into two sub-optimization problems and apply a joint iterative algorithm. Numerical results show that the proposed method achieves a satisfactory SE without complex channel estimation and perfect CSI. © 2014 IEEE.

关键词： Micro air vehicle (MAV)

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm-Based Feature Selection for Accurate Breast Cancer Classification

Genetic Algorithm-Based Feature Selection for Accurate Breas...

引用

IT and Industrial Technologies (ICIT), International Conference on

作者： Attia Shabbir Raja Hashim Ali Muhammad Zeeshan Shabbir Zain Ul Abideen Talha Ali Khan Ali Zeeshan Ijaz Nisar Ali Muhammad Imad Muhammad Abu Bakar Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany Department of Electrical Engineering University of Engineering & Technology (UET) Lahore Pakistan BCMaterials Basque Center for Materials Applications & Nanostructure Leioa Basque Country Spain Faculty of Electronic Systems Engineering University of Regina Regina Canada

Breast cancer is a significant global healthcare challenge, particularly in developing and underdeveloped countries, with profound physical, emotional, and psychological consequences, including mortality. Timely diagnosis and accurate treatment are crucial in addressing this issue. We propose the utilization of a feature selection technique to identify the most relevant features from among all features for breast cancer diagnosis, and show that Genetic Algorithms are impressive for this task. The study compares the results of GA with no selection and an alternative method, Principle Component Analysis (PCA). Three machine learning models, all based on supervised learning with data split into training and test data, are employed for binary classification using the selected feature subset. The evaluation metrics employed encompass accuracy, precision, recall, and F1-score. Among the selected models, Random Forest demonstrates the most favorable outcomes, achieving an accuracy score of 0.96, precision score of 0.96, recall value of 0.98, and an F1-score of 0.97. These results underscore the effectiveness of GA in feature selection for breast cancer diagnosis. Consequently, the integration of Genetic Algorithms (GA) with Random Forest showcases the superior performance among the evaluated models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum Algorithms and Experiment Implementations Based on IBM Q

引用

computers, Materials & Continua 2020年第11期65卷 1671-1689页

作者： Wenjie Liu Junxiu Chen Yinsong Xu Jiahao Tang Lian Tong Xiaoyu Song Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and TechnologyNanjing210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China School of Information Engineering Jiangsu Maritime InstituteNanjing211100China Department of Electrical and Computer Engineering Portland State UniversityOregon97207USA

With the rapid development of quantum theory and technology in recent years,especially the emergence of some quantum cloud computing platforms,more and more researchers are not satisfied with the theoretical derivation and simulation verification of quantum computation(especially quantum algorithms),experimental verification on real quantum devices has become a new *** this paper,three representative quantum algorithms,namely Deutsch-Jozsa,Grover,and Shor algorithms,are briefly depicted,and then their implementation circuits are presented,*** program these circuits on python with QISKit to connect the remote real quantum devices(i.e.,ibmqx4,ibmqx5)on IBM Q to verify these *** experimental results not only show the feasibility of these algorithms,but also serve to evaluate the functionality of these devices.

关键词： Quantum algorithms implementation circuit IBM Q QISKit program

来源：评论

学校读者我要写书评

暂无评论

Neural Rendering and Flow-assisted Unsupervised Multi-view Stereo for Real-time Monocular Tracking and Scene Perception

引用

IEEE Transactions on Automation Science and engineering 2025年

作者： Tong, Kevin W. Cai, Yandong Jie, Yu-Wen Duan, Ya Hou, Yuhong Wu, Edmond Q. Nanjing University of Posts and Telecommunications College of Automation College of Artificial Intelligence Nanjing210023 China Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Dalian116024 China Shanxi University School of Automation and Software Engineering Shanxi 237016 China Flight Test Technology and Engineering Center of the Chinese Flight Test Establishment Xian710089 China China Civil Aviation Shanghai Aircraft Airworthiness Certification Center Shanghai200335 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China

The existing camera tracking and perception methods mainly rely on sparse SLAM, which limits the dense perception ability of the scene and affects the reliability of auxiliary decision-making. Different from this, this work proposes a real-time tracking and unsupervised dense sensing framework. Firstly, the dense depth value of the scene is predicted by unsupervised multi-view stereo to remove the dependence on labeled data. Then, the quality of synthetic pseudo-reference image is quantified according to the predicted depth map and used as a weighted guidance to train the unsupervised model, thus reducing the ambiguity of feature matching in areas such as specular reflection. Moreover, the sparse optical flow of the keyframes is solved by real-time and robust ORB feature matching operator, which assists the high-precision training of unsupervised depth inference model. To increase the prediction accuracy of occluded area, a novel rendering consistency loss via neural radiance fields is designed to constrain the geometric characteristics of object surface. Finally, dense direct image alignment is performed from a global model to improve the tracking robustness, which is incrementally constructed from dense depth prediction. Extensive experiments on synthetic datasets and real datasets validate the effectiveness and practicability of the proposed work, which is an effective supplement to the existing SLAM work. © 2025 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Parkinson's Disease Classification from Scanned Images of Spiral Drawings

Parkinson's Disease Classification from Scanned Images of Sp...

引用

Artificial Intelligence for Medicine, Health and Care (AIMHC), IEEE International Conference on

作者： Anusid Wachiracharownong Panyawut Sri-iesaranusorn Decho Surangsrirat Pattara Leelaprute Pattamon Panyakaew Roongroj Bhidayasiri Department of Computer Engineering Faculty of Engineering Kasetsart University Bangkok Thailand National Science and Technology Development Agency Assistive Technology and Medical Devices Research Center Pathum Thani Thailand Chulalongkorn Centre of Excellence for Parkinson's Disease & Related Disorders Thai Red Cross Society Chulalongkorn University and King Chulalongkorn Memorial Hospital Bangkok Thailand

Early detection of Parkinson's disease is crucial to minimize its impact on patients. Tremor is a prevalent symptom, yet traditional diagnostic methods require physical examinations. These can pose challenges for elderly patients, particularly as the disease progresses. To address this issue, we proposed a method that analyzes Archimedean spiral drawings from a scanned image. It enables users to perform screening tests at home without the need for any special equipment, making it accessible and user-friendly for people of all ages, especially seniors. We conducted experiments on 88 individuals, including 35 healthy control participants and 53 PD patients. To achieve high accuracy, we applied data augmentation techniques to the training data and tested multiple pre-trained convolutional neural network models. Our results indicate that InceptionV3achieved a respectable performance with 82% accuracy and an F1 score of 0.81 ± 0.02. Our proposed method offers a cost-effective and convenient alternative for early PD detection and screening. It enables at-home patient screening without specialized equipment or visiting a medical facility. This is especially beneficial for individuals in rural or remote areas who may have limited access to medical facilities.

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：