检索结果-内蒙古大学图书馆

Restoration of Data Structures Using machine learning Techniques

IEEE ACCESS 2023年 11卷 113077-113099页

作者： Cvijetic, Branislava Radivojevic, Zaharije Agcy Stat Bosnia & Herzegovina Sarajevo 71000 Bosnia & Herceg Univ Belgrade Sch Elect Engn Belgrade 11020 Serbia

Tabular data is the most common format used to represent real-world information. Almost all programs created for storing or processing data, such as relational database systems, spreadsheets, and statistical analysis software can import or export tabular data. These programs are not sufficiently robust to automatically solve the problems of importing messy delimited files or files that contain data from multiple tables. Additional messy datasets contain data delimited by multiple delimiters without the names of the table columns, and parts of the table rows have substituted or deleted columns. This paper proposes the STCExtract algorithm for reconstructing table structures and data in which the input file can be arranged. The STCExtract algorithm is designed to be domain-independent and modular according to machine learning algorithms and other parameters. The algorithm was developed as a two-phase process, in which the original data tables were recognized in the first phase and the columns of the original data tables in the second phase. The STCExtract algorithm was evaluated through expensive experiments using multiple real datasets. Multiple messy datasets were generated for the four experiments. Three experiments were conducted to determine the optimal parameters for the STCExtract algorithm. A fourth experiment was conducted to evaluate the proposed algorithm. The results show that the STCExtract algorithm correctly arranged the structure of the tables with an accuracy of 94.4% to 100%. The accuracy of the STCExtract algorithm in the second phase (when the data were allocated to columns) ranged from 59.7% to 90.2%.

关键词： Information extraction messy datasets machine learning algorithms schema discovery

来源：评论

学校读者我要写书评

暂无评论

Predicting Free Energies of Exfoliation and Solvation for Graphitic Carbon Nitrides Using machine learning

引用

ACS APPLIED MATERIALS & INTERFACES 2023年第46期15卷 53786-53801页

作者： Shahini, Ehsan Chaulagain, Narendra Shankar, Karthik Tang, Tian Univ Alberta Dept Mech Engn Edmonton AB T6G 1H9 Canada Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 1H9 Canada

As a metal-free and visible-light-responsive photocatalyst, graphitic carbon nitride (g-C3N4) has emerged as a new research hotspot and has attracted broad attention in the field of solar energy conversion and thin-film transistors. Liquid-phase exfoliation (LPE) is the best-known method for the synthesis of 2D g-C3N4 nanosheets. In LPE, bulk g-C3N4 is exfoliated in a solvent via high-shear mixing or sonication in order to produce a stable suspension of individual nanosheets. Two parameters of importance in gauging the performance of a solvent in LPE are the free energy required to exfoliate a unit area of layered materials into individual sheets in the solvent (Delta G(exf)) and the solvation free energy per unit area of a nanosheet (Delta G (sol)). While approximations for the free energies exist, they are shown in our previous work to be inaccurate and incapable of capturing the experimentally observed efficacy of LPE. Molecular dynamics (MD) simulations can provide accurate free-energy calculations, but doing so for every single solvent is time- and resource-consuming. Herein, machine learning (ML) algorithms are used to predict Delta G(exf) and Delta G(sol) for g-C3N4. First, a database for Delta G(exf )and Delta G(sol) is created based on a series of MD simulations involving 49 different solvents with distinct chemical structures and properties. The data set also includes values of critical descriptors for the solvents, including density, surface tension, dielectric constant, etc. Different ML methods are compared, accompanied by descriptor selection, to develop the most accurate model for predicting Delta G(exf) and Delta G(sol). The extra tree regressor is shown to be the best performer among the six ML methods studied. Experimental validation of the model is conducted by performing dispersibility tests in several solvents for which the free energies are predicted. Finally, the influence of the selected descriptors on the free energies is analyzed, and strat

关键词： graphitic carbon nitride molecular dynamics simulations machine learning algorithms free energy of exfoliation solvation free energy liquid-phase exfoliation

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of DDPG and PPO-Based Reinforcement learning algorithms for Autonomous Driving

引用

IEEE ACCESS 2023年 11卷 125094-125108页

作者： Siboo, Sanjna Bhattacharyya, Anushka Naveen Raj, Rashmi Ashwin, S. H. Manipal Acad Higher Educ Manipal Inst Technol Dept Informat & Commun Technol Manipal 576104 Karnataka India Stand Chartered Global Business Serv Madras 560103 Tamil Nadu India

Autonomous vehicles mitigate road accidents and provide safe transportation with a smooth traffic flow. They are expected to greatly improve the quality of the elderly or people with impairments by improving their mobility due to the ease of access to transportation. Autonomous vehicles sense the driving environment and navigate through it without human intervention. And, Deep Reinforcement learning (DRL) is witnessed as a powerful machine learning solution to address a sequential decision problem in autonomous vehicles. The detailed state-of-the-art work in autonomous vehicles using DRL algorithms along with future research directions is discussed. Due to the high dimensional action space, two continuous action space DRL algorithms: Deterministic Policy Gradient (DDPG) and Proximal Policy Optimization (PPO) are chosen to address the complex autonomous driving problem. The proposed DDPG and PPO based decision-making models are trained and tested using the TORC simulator. Both the algorithms are trained for the same number of episodes for lane keeping as well as multi-agent collision avoidance scenarios. To the best of our knowledge, this is the first paper to present the comparative performance analysis of these two algorithms, and DDPG is found to perform better in terms of higher reward and faster convergence than PPO. Hence, DDPG is a suitable option in the design of a decision model for autonomous driving.

关键词： Autonomous vehicles Sensors Feature extraction machine learning algorithms Brakes Task analysis Space vehicles machine learning Reinforcement learning Deep learning Gradient methods Optimization methods deep reinforcement learning deep deterministic policy gradient continuous space autonomous vehicles proximal policy optimization

来源：评论

学校读者我要写书评

暂无评论

Location Accuracy Optimization in Bluetooth Low Energy (BLE) 5.1-Based Indoor Positioning System (IPS)-A machine learning Approach

引用

IEEE ACCESS 2023年 11卷 140186-140201页

作者： Philips, Dasmond Roy Salami, Erfan Ramiah, Harikrishnan Kanesan, Jeevan Univ Malaya Fac Engn Dept Elect Engn Kuala Lumpur 50603 Malaysia

Indoor Positioning System (IPS) is a technology used to locate and track objects or people inside buildings, by using sensors, wireless networks, or other means to determine their position. IPS has many applications in various fields such as healthcare, retail, logistics, and security. Achieving IPS of high location accuracy is yet to be explored further. In this experimental research, an IPS based on Bluetooth Low Energy (BLE) 5.1 protocol is implemented and two optimization techniques, parameters calibration and application of machine learning Algorithm (MLA) are proposed to improve location accuracy. In Stage 1 of this experiment, the measured Root Mean Square Error (RMSE) value before optimization yielded location accuracy of 0.670m. In Stage 2, four different parameters which include elevation angle, tag height, data rate and walking pace are calibrated and tested. Besides, in Stage 2, three different algorithms which include Support Vector Regression (SVR), Decision Tree (DT) and K-Nearest Neighbor (KNN) are evaluated. As a result, parameters calibration decreased RMSE value down to 0.219m. Additionally, among all three MLAs, KNN illustrated the lowest RMSE value of 0.631m. In Stage 3, the lowest RMSE value of 0.015m is obtained by combining parameters calibration and MLA approaches which improved location accuracy up to 98.5%. The developed framework is operational at our industry partner, ams OSRAM's LED wafer fabrication cleanroom facility.

关键词： IP networks machine learning Training Wireless networks machine learning algorithms Tuning Testing Indoor navigation Bluetooth Root mean square Indoor positioning system (IPS) bluetooth low energy (BLE) 5.1 machine learning algorithm (MLA) root mean square error (RMSE)

来源：评论

学校读者我要写书评

暂无评论

Supervised learning Enhanced Quantum Circuit Transformation

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2023年第2期42卷 437-447页

作者： Zhou, Xiangzhen Feng, Yuan Li, Sanjiang Southeast Univ State Key Lab Millimeter Waves Nanjing 211189 Peoples R China Univ Technol Sydney Fac Engn & Informat Technol Ctr Quantum Software & Informat Ultimo NSW 2007 Australia

A quantum circuit transformation (QCT) is required when executing a quantum program in a real quantum processing unit (QPU). By inserting auxiliary SWAP gates, a QCT algorithm transforms a quantum circuit to one that satisfies the connectivity constraint imposed by the QPU. Due to the nonnegligible gate error and the limited qubit coherence time of the QPU, QCT algorithms that minimize gate number or circuit depth or maximize the fidelity of output circuits are in urgent need. Unfortunately, finding optimized transformations often involve exhaustive searches, which are extremely time consuming and not practical for most circuits. In this article, we propose a framework that uses a policy artificial neural network (ANN) trained by supervised learning on shallow circuits to help existing QCT algorithms select the most promising SWAP gate. ANNs can be trained offline in a distributed way and the trained ANN can be easily incorporated into QCT algorithms to enable them to search deeper without bringing too much overhead in time complexity. Exemplary embeddings of the trained ANNs into target QCT algorithms demonstrate that the transformation performance can be consistently improved on QPUs with various connectivity structures and random or realistic quantum circuits.

关键词： Logic gates Qubit Quantum circuit Artificial neural networks Supervised learning Heuristic algorithms machine learning algorithms Artificial neural network (ANN) machine learning quantum circuit transformation (QCT) supervised learning

来源：评论

学校读者我要写书评

暂无评论

High Performance Hierarchical Tucker Tensor learning Using GPU Tensor Cores

引用

IEEE TRANSACTIONS ON COMPUTERS 2023年第2期72卷 452-465页

作者： Huang, Hao Liu, Xiao-Yang Tong, Weiqin Zhang, Tao Walid, Anwar Wang, Xiaodong Shanghai Univ Sch Comp Engn & Sci Shanghai 201824 Peoples R China Columbia Univ Dept Elect Engn New York NY 10027 USA

Extracting information from large-scale high-dimensional data is a fundamentally important task in high performance computing, where the hierarchical Tucker (HT) tensor learning approach (learning a tensor-tree structure) has been widely used in many applications. However, HT tensor learning algorithms are compute-intensive due to the curse of dimensionality, i.e., the time complexity grows exponentially with the order of the data tensor. The computation of HT tensor learning algorithms boils down to tensor primitives, which are amenable to computing on GPU tensor cores. Existing work does not support HT tensor learning using GPU tensor cores. There are three main challenges to address: 1) to accelerate tensor learning primitives using GPU tensor cores;2) to implement the tensor learning algorithms using GPU tensor cores and multiple GPUs;3) to support large-scale data tensors exceeding the GPU memory capacity. In this paper, we present efficient HT tensor learning primitives using GPU tensor cores and demonstrate three applications. First, we utilize GPU tensor cores to optimize HT tensor learning primitives, including tensor contractions, tensor matricizations and tensor singular value decomposition (SVD). We employ the optimized primitives to optimize HT tensor decomposition algorithms for Big Data analysis. Second, we propose a novel HT tensor layer for deep neural networks, whose training process only involves a forward pass without back propagation. The forward pass consists of tensor operations, thus further exploiting the computing power of GPU tensor cores. Third, we apply the optimized primitives to develop a tensor-tree structured quantum machine learning algorithm tree-tensor network (TTN). Compared with TensorLy and TensorNetwork on NVIDIA A100 GPUs, our third-order HT tensor decomposition algorithm achieves up to 8.92x and 6.42x speedups, respectively, and our high-order case achieves up to 32.67x and 23.97x speedups, respectively. Our HT tensor layer

关键词： Tensors Graphics processing units machine learning algorithms Neural networks Matrix decomposition Parallel processing Deep learning GPU tensor cores hierarchical Tucker big data HT tensor layer quantum machine learning

来源：评论

学校读者我要写书评

暂无评论

Supervised learning of Multievent Transition Matrices in Fuzzy Discrete-Event Systems

引用

IEEE TRANSACTIONS ON CYBERNETICS 2023年第9期53卷 5596-5604页

作者： Lin, Feng Ying, Hao Wayne State Univ Dept Elect & Comp Engn Detroit MI 48202 USA

In this article, supervised learning of fuzzy discrete-event systems (FDES) is investigated. A learning algorithm that performs supervised learning for multievent transition matrices of a sequence of fuzzy discrete events is derived. FDES can be used to describe a large class of practical systems that consist of fuzzy discrete states, fuzzy discrete events, and transitions among fuzzy discrete states via fuzzy discrete events. Because fuzzy discrete states, fuzzy discrete events, and fuzzy transitions are well defined in FDES, the FDES model is highly explainable, which is important in many applications, especially in biomedical applications. Based on this explainable model, the proposed learning algorithm can be used to learn events and event sequences in the model. Hence, it allows system developers to build an explainable model for a complex system based on the data available. Simulations using MATLAB are conducted to verify the effectiveness of the proposed algorithm.

关键词： Supervised learning Mathematical models Biological system modeling machine learning machine learning algorithms learning automata Discrete-event systems Discrete-event systems (DESs) fuzzy DES (FDES) fuzzy systems supervised learning

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial Communication-Efficient Distributed learning Over Networks

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2023年第4期41卷 845-850页

作者： Cao, Xuanyu Basar, Tamer Diggavi, Suhas Eldar, Yonina C. Letaief, Khaled B. Poor, H. Vincent Zhang, Junshan Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China Univ Illinois Dept Elect & Comp Engn Urbana IL 61801 USA Univ Calif Los Angeles Dept Elect & Comp Engn Los Angeles CA 90095 USA Weizmann Inst Sci Dept Math & Comp Sci IL-7610001 Rehovot Israel Princeton Univ Dept Elect & Comp Engn Princeton NJ 08544 USA Univ Calif Davis Dept Elect & Comp Engn Davis CA 95616 USA

Distributed machine learning is envisioned as the bedrock of future intelligent networks, where agents exchange information with each other to train models collaboratively without uploading data to a central processor. Despite its broad applicability, a downside of distributed learning is the need for iterative information exchange between agents, which may lead to high communication overhead unaffordable in many practical systems with limited communication resources. To resolve this communication bottleneck, we need to devise communication-efficient distributed learning algorithms and protocols that can reduce the communication cost and simultaneously achieve satisfactory learning/optimization performance. Accomplishing this goal necessitates synergistic techniques from a diverse set of fields, including optimization, machine learning, wireless communications, game theory, and network/graph theory. This Special Issue is dedicated to communication-efficient distributed learning from multiple perspectives, including fundamental theories, algorithm design and analysis, and practical considerations.

关键词： Special issues and sections Distance learning Computer architecture Computer aided instruction machine learning machine learning algorithms Intelligent networks Information exchange Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Reinforcement learning algorithms for Distribution Network Reconfiguration With Deep Q-learning-Based Action Sampling

引用

IEEE ACCESS 2023年 11卷 13714-13723页

作者： Gholizadeh, Nastaran Kazemi, Nazli Musilek, Petr Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 2R3 Canada Univ Hradec Kralove Dept Appl Cybernet Hradec Kralove 50003 Czech Republic

Distribution network reconfiguration (DNR) is one of the most important methods to cope with the increasing electricity demand due to the massive integration of electric vehicles. Most existing DNR methods rely on accurate network parameters and lack scalability and optimality. This study uses model-free reinforcement learning algorithms for training agents to take the best DNR actions in a given distribution system. Five reinforcement algorithms are applied to the DNR problem in 33- and 136-node test systems and their performances are compared: deep Q-learning, dueling deep Q-learning, deep Q-learning with prioritized experience replay, soft actor-critic, and proximal policy optimization. In addition, a new deep Q-learning-based action sampling method is developed to reduce the size of the action space and optimize the loss reduction in the system. Finally, the developed algorithms are compared against the existing methods in literature.

关键词： Optimization Distribution networks Switches Load modeling Q-learning Mathematical models machine learning algorithms Distribution network reconfiguration reinforcement learning deep Q-learning data-driven control soft actor-critic proximal policy optimization

来源：评论

学校读者我要写书评

暂无评论

A Novel machine learning Approach for Android Malware Detection Based on the Co-Existence of Features

引用

IEEE ACCESS 2023年 11卷 15471-15484页

作者： Odat, Esraa Yaseen, Qussai M. Jordan Univ Sci & Technol Dept Comp Informat Syst Irbid 22110 Jordan Ajman Univ Coll Comp Engn & Informat Technol Artificial Intelligence Res Ctr AIRC Ajman U Arab Emirates

This paper proposes a machine learning model based on the co-existence of static features for Android malware detection. The proposed model assumes that Android malware requests an abnormal set of co-existed permissions and APIs in comparing to those requested by benign applications. To prove this assumption, the paper created a new dataset of co-existed permissions and API calls at different levels of combinations, which are the second level, the third level, the fourth level and the fifth level. The extracted datasets of co-existed features at different levels were applied on permissions only, APIs only, permissions and APIs, and APIs and APIs frequencies. To extract the most relevant co-existed features, the frequent pattern growth (FP-growth) algorithm, which is an association rule mining technique, was used. The new datasets were extracted using Android APK samples from the Drebin, Malgenome and MalDroid2020 datasets. To evaluate the proposed model, several conventional machine learning algorithms were used. The results show that the model can successfully classify Android malware with a high accuracy using machine learning algorithms and the co-existence of features. Moreover, the results show that the achieved classification accuracy depends on the classifier and the type of co-existed features. The maximum accuracy, which is 98%, was achieved using the Random Forest algorithm and the co-existence of permissions features at the second combination level. Furthermore, the results show that the proposed approach outperforms the state-of-the-art model. Using Malgenome dataset, the proposed approach achieved an accuracy of about 98%, while the state-of-the-art achieved an accuracy of about 87%. In addition, the experiments show that using the Drebin dataset, the proposed approach achieved an accuracy of about 95%, while the state-of-the-art achieved an accuracy of about 93%.

关键词： Malware Feature extraction machine learning algorithms Smart phones machine learning Heuristic algorithms Computational modeling Android co-existence FP-growth machine learning malware

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：