检索结果-内蒙古大学图书馆

Inclusion of features derived from a mixture of time window sizes improved classification accuracy of machine learning algorithms for sheep grazing behaviours

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2020年 179卷 105857-105857页

作者： Hu, Shuwen Ingham, Aaron Schmoelzl, Sabine McNally, Jody Little, Bryce Smith, Daniel Bishop-Hurley, Greg Wang, You-Gan Li, Yutao Queensland Univ Technol Sch Math Sci Gardens Point Qld 4001 Australia CSIRO Agr & Food 306 Carmody Rd St Lucia Qld 4067 Australia CSIRO Agr & Food Armidale NSW 2350 Australia CSIRO DATA61 Private Bag 12 Hobart Tas 7001 Australia

Inertial motion sensors located on the animal have been used to study the behaviour of ruminant livestock. The time window size of segmented signal data can significantly affect the classification accuracy of animal behaviours. To date, there have been no studies evaluating the impact of a mixture of time window size features on the accuracy of animal behaviour classification. In this study, data was collected from accelerometers attached to the neck of 17 Merino sheep over a period of two days. We also recorded a ground truth dataset of behaviour recordings (grazing, ruminating, walking, and standing) over the same time period, We then investigated the ability of three machine learning (ML) approaches, Random Forest (RF), Support Vector Machine (SVM) and linear discriminant analysis (LDA), to accurately classify sheep behaviour. Our results clearly show that simultaneous inclusion of features derived from time windows of mixed sizes, ranging from 2 to 15 s, significantly improved the behaviour classification accuracy, in comparison to those determined from a single unique time window size. Of the three ML methods applied here, the RF approach yielded the best results. Together our results show that including features obtained from mixed window sizes improved the classification accuracy of sheep behaviours.

关键词： Mixture of time window sizes Features ranking classification algorithm Machine learning Sheep behaviour Accelerometer

来源：评论

学校读者我要写书评

暂无评论

Spark-Based Parallel Deep Neural Network Model for classification of Large Scale RNAs into piRNAs and Non-piRNAs

引用

IEEE ACCESS 2020年 8卷 136978-136991页

作者： Khan, Salman Khan, Mukhtaj Iqbal, Nadeem Li, Maozhen Khan, Dost Muhammad Abdul Wali Khan Univ Mardan Dept Comp Sci Mardan 23200 Pakistan Brunel Univ London Dept Elect & Comp Engn London UB8 3PN England

With recent advancement in computational biology, high throughput next generation sequencing technology has become a de facto standard technology for genes expression studies including DNAs, RNAs and proteins. As a promising technology, it has significant impact on medical sciences and genomic research. However, it generates several millions of short DNA and RNA sequences with several petabytes size in single run. In addition, the raw sequencing datasets such as RNAs are increasing exponentially leading to a big data analytics issue in computational biology. Due to the explosive growth of RNA sequences, the timely classification of RNAs sequence into piRNAs and non-piRNAs have become a challenging issue for traditional technology and conventional machine learning algorithms. Parallel and distributed computing models along with deep neural network have become a major computing platform for big data analytics now required in the field of computational biology. This paper presents a computational model based on parallel deep neural network for timely classification of large number of RNAs sequence into piRNAs and non-piRNAs, taking advantages of parallel and distributed computing platform. The performance of the proposed model was extensively evaluated using two-fold performance metrics. In the first fold, the performance of the proposed model was assessed using accuracy-based metrics such as accuracy, specificity, sensitivity and Matthews's correlation coefficient. In the second fold, computational-based metrics such as computation times, speedup and scalability were observed. Moreover, initially the performance of the proposed model was assessed using real benchmark dataset and subsequently the performance was assessed using replicated benchmark dataset. The evaluation results in both cases showed that the proposed model improved computation speedup in order of magnitude in comparison with sequential approach without affected accuracy level.

关键词： Computational modeling RNA Biological system modeling Data models Mathematical model Feature extraction Sparks Deep neural network spark big data piRNA classification algorithm artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Approximation with polynomial kernels and SVM classifiers

引用

ADVANCES IN COMPUTATIONAL MATHEMATICS 2006年第1-3期25卷 323-344页

作者： Zhou, Ding-Xuan Jetter, Kurt City Univ Hong Kong Dept Math Kowloon Hong Kong Peoples R China Univ Hohenheim Inst Angew Math & Stat D-70593 Stuttgart Germany

This paper presents an error analysis for classification algorithms generated by regularization schemes with polynomial kernels. Explicit convergence rates are provided for support vector machine (SVM) soft margin classifiers. The misclassification error can be estimated by the sum of sample error and regularization error. The main difficulty for studying algorithms with polynomial kernels is the regularization error which involves deeply the degrees of the kernel polynomials. Here we overcome this difficulty by bounding the reproducing kernel Hilbert space norm of Durrmeyer operators, and estimating the rate of approximation by Durrmeyer operators in a weighted L-1 space (the weight is a probability distribution). Our study shows that the regularization parameter should decrease exponentially fast with the sample size, which is a special feature of polynomial kernels.

关键词： classification algorithm regularization scheme polynomial kernel approximation by Durrmeyer operators support vector machine misclassification error

来源：评论

学校读者我要写书评

暂无评论

CRISP - An Interruption Management algorithm based on Collaborative Filtering 14

CRISP - An Interruption Management Algorithm based on Collab...

引用

32nd Annual ACM Conference on Human Factors in Computing Systems (CHI)

作者： Shrot, M. Tammar Rosenfeld, Avi Golbeck, Jennifer Kraus, Sarit Shamoon Coll Engn Dept Software Engn IL-84100 Beer Sheva Israel Jerusalem Coll Technol Dept Ind Engn IL-9116001 Jerusalem Israel Univ Maryland Inst Adv Comp Studies College Pk MD 20742 USA Bar Ilan Univ Dept Comp Sci IL-5290002 Ramat Gan Israel

ISBN: (纸本)9781450324731

Interruptions can have a significant impact on users working to complete a task. When people are collaborating, either with other users or with systems, coordinating interruptions is an important factor in maintaining efficiency and preventing information overload. Computer systems can observe user behavior, model it, and use this to optimize the interruptions to minimize disruption. However, current techniques often require long training periods that make them unsuitable for online collaborative environments where new users frequently participate. In this paper, we present a novel synthesis between Collaborative Filtering methods and machine learning classification algorithms to create a fast learning algorithm, CRISP. CRISP exploits the similarities between users in order to apply data from known users to new users, therefore requiring less information on each person. Results from user studies indicate the algorithm significantly improves users' performances in completing the task and their perception of how long it took to complete each task.

关键词： Interruption Management (Cost Estimation) Collaborative Filtering classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Impedance technique combined with supervised algorithms-based internal degradation state classification and its economic analysis for safety in retired battery pack

引用

JOURNAL OF ENERGY STORAGE 2023年 73卷

作者： Lee, Miyoung Han, Dongho Yoo, Kisoo Kim, Jonghoon Chungnam Natl Univ Dept Elect Engn Energy Storage & Convers Lab Daejeon 34134 South Korea Yeungnam Univ Sch Mech Engn Gyoungsan 38541 South Korea

As the growth of lithium-ion batteries (LIBs) applications accelerates, future problems for waste LIB disposal are also appeared. When LIB reaches 80 % of the initial capacity, it is defined as the End-of-life (EOL). Since power and capacity of the LIB abruptly decreases at this point, it is determined that the LIB can't be used. However, in the case of the battery pack, even if it reaches 80 % of its initial capacity, it can be reused with secondary applications such as energy storage devices and uninterruptible power supplies (UPS). Therefore, in order to reduce environmental problems, such a battery pack reuse technique is required. However, as the internal degradation state of the LIB differs depending on the operating environment, research is needed to select the LIB in the same state through classification algorithm and configure the waste battery pack. Since the internal degradation of LIB cannot be evaluated qualitatively with existing technology, like capacity and internal resistance, so a new qualitative evaluation factor is required. This research classified an internal degradation state according to LIB environment using an impedance technique and supervised algorithms (Decision tree, Support vector machine, K-nearest neighbor) that could qualitatively represent LIB degradation mechanism. And it is validated that new parameters are good at classifying operating environment compared with existing parameters. Also, Economic analysis was performed for comparison with existing methods, and as a result, it was proved that it showed superior performance compared to existing techniques in both classification accuracy and economic analysis.

关键词： Electrochemical impedance spectroscopy (EIS) classification algorithm Support vector machine (SVM) Decision tree algorithm K-nearest neighbor algorithm (KNN) Battery operating environment classification

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Based Approach for classification of Human Activities Using MEMS Sensors Data

引用

SENSORS 2023年第3期23卷 1275-1275页

作者： Khan, Yusuf Ahmed Imaduddin, Syed Singh, Yash Pratap Wajid, Mohd Usman, Mohammed Abbas, Mohamed Aligarh Muslim Univ Dept Elect Engn ZHCET Aligarh 202002 India King Khalid Univ Dept Elect Engn Abha 61411 Saudi Arabia King Khalid Univ Coll Engn Elect Engn Dept Abha 61421 Saudi Arabia Delta Univ Sci & Technol Coll Engn Elect & Commun Dept Gamasa 35712 Egypt

The integration of Micro Electronic Mechanical Systems (MEMS) sensor technology in smartphones has greatly improved the capability for Human Activity Recognition (HAR). By utilizing Machine Learning (ML) techniques and data from these sensors, various human motion activities can be classified. This study performed experiments and compiled a large dataset of nine daily activities, including Laying Down, Stationary, Walking, Brisk Walking, Running, Stairs-Up, Stairs-Down, Squatting, and Cycling. Several ML models, such as Decision Tree Classifier, Random Forest Classifier, K Neighbors Classifier, Multinomial Logistic Regression, Gaussian Naive Bayes, and Support Vector Machine, were trained on sensor data collected from accelerometer, gyroscope, and magnetometer embedded in smartphones and wearable devices. The highest test accuracy of 95% was achieved using the random forest algorithm. Additionally, a custom-built Bidirectional Long-Short-Term Memory (Bi-LSTM) model, a type of Recurrent Neural Network (RNN), was proposed and yielded an improved test accuracy of 98.1%. This approach differs from traditional algorithmic-based human activity detection used in current wearable technologies, resulting in improved accuracy.

关键词： Bi-LSTM network classification algorithm deep learning deep neural network human activity recognition machine learning MEMS sensors mobile & wearable devices recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

A classification-Based Machine Learning Approach to the Prediction of Cyanobacterial Blooms in Chilgok Weir, South Korea

引用

WATER 2022年第4期14卷 542页

作者： Kim, Jongchan Jonoski, Andreja Solomatine, Dimitri P. IHE Delft Inst Water Educ Hydroinformat Chair Grp NL-2611 AX Delft Netherlands K Water Human Resources Dev Inst Daejeon 34350 South Korea Delft Univ Technol Water Resources Sect NL-2628 CD Delft Netherlands Water Problems Inst RAS Gubkina 3 Moscow 117971 Russia

Cyanobacterial blooms appear by complex causes such as water quality, climate, and hydrological factors. This study aims to present the machine learning models to predict occurrences of these complicated cyanobacterial blooms efficiently and effectively. The dataset was classified into groups consisting of two, three, or four classes based on cyanobacterial cell density after a week, which was used as the target variable. We developed 96 machine learning models for Chilgok weir using four classification algorithms: k-Nearest Neighbor, Decision Tree, Logistic Regression, and Support Vector Machine. In the modeling methodology, we first selected input features by applying ANOVA (Analysis of Variance) and solving a multi-collinearity problem as a process of feature selection, which is a method of removing irrelevant features to a target variable. Next, we adopted an oversampling method to resolve the problem of having an imbalanced dataset. Consequently, the best performance was achieved for models using datasets divided into two classes, with an accuracy of 80% or more. Comparatively, we confirmed low accuracy of approximately 60% for models using datasets divided into three classes. Moreover, while we produced models with overall high accuracy when using logCyano (logarithm of cyanobacterial cell density) as a feature, several models in combination with air temperature and NO3-N (nitrate nitrogen) using two classes also demonstrated more than 80% accuracy. It can be concluded that it is possible to develop very accurate classification-based machine learning models with two features related to cyanobacterial blooms. This proved that we could make efficient and effective models with a low number of inputs.

关键词： cyanobacterial blooms machine learning classification algorithm feature selection imbalanced dataset oversampling

来源：评论

学校读者我要写书评

暂无评论

Intelligent System for Learning of Comfort Preferences to Help People with Mobility Limitations 4th

Intelligent System for Learning of Comfort Preferences to He...

引用

4th KES International Conference on Innovation in Medicine and Healthcare (InMed)

作者： Lopez, Sandra Baltazar, Rosario Lemus Zuniga, Lenin Angel Casillas, Miguel Alanis, Arnulfo Mateo Pla, Miguel A. Zamudio, Victor Mendez, Guillermo Inst Tecnol Leon Guanajuato Mexico Univ Politecn Valencia Valencia Spain Inst Tecnol Tijuana Tijuana Baja California Mexico

ISBN: (纸本)9783319396873;9783319396866

It is essential to provide better living conditions for vulnerable sectors of society using technology and it is important to consider that the technology must be friendly with users, and even adapt to their needs and desires. We can see in current systems the user has to learn to use the devices or services, but with an intelligence system, the technology is a very effective way to determine the needs of users. In this research, we present the physical implementation of a system to assist users and patients in daily activities or duties. The system include a architecture of agents where a Deliberative agent learns from the interaction with the user, in this way the system detects thermal comfort preferences for give an automatic assistance. We propose an algorithm with a proactive stage and learning stage adapting a classification algorithm. We select the classification algorithm with the best performance using cross validation. The algorithms of pattern recognition was Back Propagation neural network, Naive Bayes, Minimum Distance and KNN (k near neighbor). Our motivation of this work was to help people with motor difficulties or people who use wheelchairs, for this reason it was essential to use a wireless controller and use a friendly interface. The system was implemented in a testbed at the Leon Institute of Technology in Guanajuato, Mexico, and include sensors of humidity and temperature, windows actuators, wireless agents and other devices. Experimental tests were performed with data collected during a time period and using use cases. The results were satisfactory because it was not only possible remote assistance by the user but it was possible to obtain user information to learn comfort preferences using vector features proposed and selecting the classification algorithm with better performance.

关键词： Assist in daily activities Movement restrictions Architecture of agents Learning of thermal comfort Pattern recognition classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Cost-sensitive Classifiers in Credit Rating A Comparative Study on P2P Lending 7

Cost-sensitive Classifiers in Credit Rating A Comparative St...

引用

7th International Conference on Computers Communications and Control (ICCCC)

作者： Wang, Haomin Kou, Gang Peng, Yi Univ Elect Sci & Technol China Sch Management & Econ Chengdu Sichuan Peoples R China Southwestern Univ Finance & Econ Sch Business Adm Chengdu Sichuan Peoples R China

ISBN: (纸本)9781538619346

In credit rating, borrowers are classified into some grades, based on their past credit experience, to recognize potential borrowers who are of different probability of default. classification algorithms are commonly used, which is important to reduce loss for banks or investors. Since multiple classes are imbalanced, as well as losses of misclassification across classes are not uniform, multi-class cost-sensitive classifiers should be paid more attention in credit rating. Based on existing literatures, in this paper, we review several cost-sensitive classifiers and compare them with three assumed cost matrices. The empirical study utilizes data collected from Lending Club which is the largest U.S. P2P loan platform. The results are aimed at giving insights on cost-sensitive classifiers with various performances in credit rating, which are concerned by researchers and practitioners of credit lending.

关键词： data mining cost-sensitive learning classification algorithm credit rating P2P lending

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Explosive Detection from Electronic Nose Datasets 13

Machine Learning for Explosive Detection from Electronic Nos...

引用

13th International Conference on Knowledge and Smart Technology (KST)

作者： Wongwattanaporn, Supawit Phienthrakul, Tanasanee Mahidol Univ Fac Engn Dept Comp Engn Nakhon Pathom Thailand

ISBN: (纸本)9781728176024

An electronic nose has been applied in many areas such as the food industry, the environmental area, and this technology can be used to detect some explosives. Many classification machine learning techniques are applied for creating the model which manipulates data into a defined group to be used for customer grouping, marketing, anomaly detection, and medical analysis. The purpose of this research is to find a suitable classification technique to be applied in an electronic nose to imitate the ability of sniffer dogs to detect the chemical substances. This research compares the accuracy of eight different classification techniques, which are Logistic Regression, Support Vector Machine (SVM), Decision Tree, Random Forest (RF), Adaptive Boosting, K-Nearest Neighbors, Gaussian Naive Bayes, and Multilayer Perceptron in both binary and multi-class gas sensor array open source datasets. Experimental results show the top algorithms are RF, and SVM models, which give average score as 99.66 and 98.93, respectively.

关键词： electronic nose classification algorithm gas sensor array explosive detection

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：