Effects of feature selection on lane-change maneuver recognition: an analysis of naturalistic driving data

PurposeFeature selection is crucial for machine learning to recognize lane-change (LC) maneuver as there exist a large number of feature candidates. Blindly using feature could take up large storage and excessive computation time, while insufficient feature selection would cause poor performance. Selecting high contributive features to classify LC and lane-keep behavior is effective for maneuver recognition. This paper aims to propose a feature selection method from a statistical view based on an analysis from naturalistic driving data.Design/methodology/approachIn total, 1,375 LC cases are analyzed. To comprehensively select features, the authors extract the feature candidates from both time and frequency domains with various LC scenarios segmented by an occupancy schedule grid. Then the effect size (Cohen’s d) andp-value of every feature are computed to assess their contribution for each scenario.FindingsIt has been found that the common lateral features, e.g. yaw rate, lateral acceleration and time-to-lane crossing, are not strong features for recognition of LC maneuver as empirical knowledge. Finally, cross-validation tests are conducted to evaluate model performance using metrics of receiver operating characteristic. Experimental results show that the selected features can achieve better recognition performance than using all the features without purification.Originality/valueIn this paper, the authors investigate the contributions of each feature from the perspective of statistics based on big naturalistic driving data. The aim is to comprehensively figure out different types of features in LC maneuvers and select the most contributive features over various LC scenarios.

Download Full-text

AN EFFECTIVE COLOR FACE RECOGNITION BASED ON BEST COLOR FEATURE SELECTION ALGORITHM USING WEIGHTED FEATURES FUSION SYSTEM

INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY ◽

10.24297/ijct.v8i2.3386 ◽

2013 ◽

Vol 8 (2) ◽

pp. 787-795

Author(s):

Sasi Kumar Balasundaram ◽

J. Umadevi ◽

B. Sankara Gomathi

Keyword(s):

Feature Selection ◽

Face Recognition ◽

Feature Fusion ◽

Recognition Performance ◽

Feature Selection Method ◽

Recognition Method ◽

Color Feature ◽

Color Component ◽

Pose Variation ◽

Color Face Recognition

This paper aims to achieve the best color face recognition performance. The newly introduced feature selection method takes advantage of novel learning which is used to find the optimal set of color-component features for the purpose of achieving the best face recognition result. The proposed color face recognition method consists of two parts namely color-component feature selection with boosting and color face recognition solution using selected color component features. This method is better than existing color face recognition methods with illumination, pose variation and low resolution face images. This system is based on the selection of the best color component features from various color models using the novel boosting learning framework. These selected color component features are then combined into a single concatenated color feature using weighted feature fusion. The effectiveness of color face recognition method has been successfully evaluated by the public face databases.

Download Full-text

Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and Validation (Preprint)

10.2196/preprints.24402 ◽

2020 ◽

Author(s):

Qiaoqin Li ◽

Yongguo Liu ◽

Jiajing Zhu ◽

Zhi Chen ◽

Lang Liu ◽

...

Keyword(s):

Feature Selection ◽

Upper Limb ◽

Time Domain ◽

Recognition Performance ◽

Feature Selection Method ◽

Selection Method ◽

Sensor Data ◽

Motion Recognition ◽

Wrapper Method ◽

Motion Types

BACKGROUND For rehabilitation training systems, it is essential to automatically record and recognize exercises, especially when more than one type of exercise is performed without a predefined sequence. Most motion recognition methods are based on feature engineering and machine learning algorithms. Time-domain and frequency-domain features are extracted from original time series data collected by sensor nodes. For high-dimensional data, feature selection plays an important role in improving the performance of motion recognition. Existing feature selection methods can be categorized into filter and wrapper methods. Wrapper methods usually achieve better performance than filter methods; however, in most cases, they are computationally intensive, and the feature subset obtained is usually optimized only for the specific learning algorithm. OBJECTIVE This study aimed to provide a feature selection method for motion recognition of upper-limb exercises and improve the recognition performance. METHODS Motion data from 5 types of upper-limb exercises performed by 21 participants were collected by a customized inertial measurement unit (IMU) node. A total of 60 time-domain and frequency-domain features were extracted from the original sensor data. A hybrid feature selection method by combining filter and wrapper methods (FESCOM) was proposed to eliminate irrelevant features for motion recognition of upper-limb exercises. In the filter stage, candidate features were first selected from the original feature set according to the significance for motion recognition. In the wrapper stage, k-nearest neighbors (kNN), Naïve Bayes (NB), and random forest (RF) were evaluated as the wrapping components to further refine the features from the candidate feature set. The performance of the proposed FESCOM method was verified using experiments on motion recognition of upper-limb exercises and compared with the traditional wrapper method. RESULTS Using kNN, NB, and RF as the wrapping components, the classification error rates of the proposed FESCOM method were 1.7%, 8.9%, and 7.4%, respectively, and the feature selection time in each iteration was 13 seconds, 71 seconds, and 541 seconds, respectively. CONCLUSIONS The experimental results demonstrated that, in the case of 5 motion types performed by 21 healthy participants, the proposed FESCOM method using kNN and NB as the wrapping components achieved better recognition performance than the traditional wrapper method. The FESCOM method dramatically reduces the search time in the feature selection process. The results also demonstrated that the optimal number of features depends on the classifier. This approach serves to improve feature selection and classification algorithm selection for upper-limb motion recognition based on wearable sensor data, which can be extended to motion recognition of more motion types and participants.

Download Full-text

Improving the prediction accuracy in blended learning environment using synthetic minority oversampling technique

Information Discovery and Delivery ◽

10.1108/idd-08-2018-0036 ◽

2019 ◽

Vol 47 (2) ◽

pp. 76-83 ◽

Cited By ~ 2

Author(s):

Gabrijela Dimic ◽

Dejan Rancic ◽

Nemanja Macek ◽

Petar Spalevic ◽

Vida Drasute

Keyword(s):

Feature Selection ◽

Learning Environment ◽

Blended Learning ◽

Prediction Accuracy ◽

Design Methodology ◽

Feature Vector ◽

Feature Selection Method ◽

Feature Subset ◽

Content Type ◽

Correlation Based Feature Selection

Purpose This paper aims to deal with the previously unknown prediction accuracy of students’ activity pattern in a blended learning environment. Design/methodology/approach To extract the most relevant activity feature subset, different feature-selection methods were applied. For different cardinality subsets, classification models were used in the comparison. Findings Experimental evaluation oppose the hypothesis that feature vector dimensionality reduction leads to prediction accuracy increasing. Research limitations/implications Improving prediction accuracy in a described learning environment was based on applying synthetic minority oversampling technique, which had affected results on correlation-based feature-selection method. Originality/value The major contribution of the research is the proposed methodology for selecting the optimal low-cardinal subset of students’ activities and significant prediction accuracy improvement in a blended learning environment.

Download Full-text

Predictive analytics for blood glucose concentration: an empirical study using the tree-based ensemble approach

Library Hi Tech ◽

10.1108/lht-08-2019-0171 ◽

2020 ◽

Vol 38 (4) ◽

pp. 835-858

Author(s):

Jiaming Liu ◽

Liuan Wang ◽

Linan Zhang ◽

Zeming Zhang ◽

Sicheng Zhang

Keyword(s):

Feature Selection ◽

Predictive Analytics ◽

Feature Selection Method ◽

Information Criterion ◽

Selection Method ◽

Prediction Performance ◽

Majority Voting ◽

Ensemble Model ◽

Lasso Regression ◽

Content Type

PurposeThe primary objective of this study was to recognize critical indicators in predicting blood glucose (BG) through data-driven methods and to compare the prediction performance of four tree-based ensemble models, i.e. bagging with tree regressors (bagging-decision tree [Bagging-DT]), AdaBoost with tree regressors (Adaboost-DT), random forest (RF) and gradient boosting decision tree (GBDT).Design/methodology/approachThis study proposed a majority voting feature selection method by combining lasso regression with the Akaike information criterion (AIC) (LR-AIC), lasso regression with the Bayesian information criterion (BIC) (LR-BIC) and RF to select indicators with excellent predictive performance from initial 38 indicators in 5,642 samples. The selected features were deployed to build the tree-based ensemble models. The 10-fold cross-validation (CV) method was used to evaluate the performance of each ensemble model.FindingsThe results of feature selection indicated that age, corpuscular hemoglobin concentration (CHC), red blood cell volume distribution width (RBCVDW), red blood cell volume and leucocyte count are five most important clinical/physical indicators in BG prediction. Furthermore, this study also found that the GBDT ensemble model combined with the proposed majority voting feature selection method is better than other three models with respect to prediction performance and stability.Practical implicationsThis study proposed a novel BG prediction framework for better predictive analytics in health care.Social implicationsThis study incorporated medical background and machine learning technology to reduce diabetes morbidity and formulate precise medical schemes.Originality/valueThe majority voting feature selection method combined with the GBDT ensemble model provides an effective decision-making tool for predicting BG and detecting diabetes risk in advance.

Download Full-text

A Comparative Analysis of Filter-Based Feature Selection Methods for Software Fault Prediction

Research and Development on Information and Communication Technology ◽

10.32913/mic-ict-research-vn.v2021.n1.969 ◽

2021 ◽

pp. 1-7

Author(s):

Thị Minh Phương Hà ◽

Thi My Hanh Le ◽

Thanh Binh Nguyen

Keyword(s):

Feature Selection ◽

Prediction Models ◽

Information Gain ◽

Feature Selection Method ◽

Computation Time ◽

Fault Prediction ◽

Software Systems ◽

Selection Methods ◽

Software Fault Prediction

The rapid growth of data has become a huge challenge for software systems. The quality of fault predictionmodel depends on the quality of software dataset. High-dimensional data is the major problem that affects the performance of the fault prediction models. In order to deal with dimensionality problem, feature selection is proposed by various researchers. Feature selection method provides an effective solution by eliminating irrelevant and redundant features, reducing computation time and improving the accuracy of the machine learning model. In this study, we focus on research and synthesis of the Filter-based feature selection with several search methods and algorithms. In addition, five filter-based feature selection methods are analyzed using five different classifiers over datasets obtained from National Aeronautics and Space Administration (NASA) repository. The experimental results show that Chi-Square and Information Gain methods had the best influence on the results of predictive models over other filter ranking methods.

Download Full-text

Psychophysiological Modeling of Trust In Technology

Proceedings of the ACM on Human-Computer Interaction ◽

10.1145/3459745 ◽

2021 ◽

Vol 5 (EICS) ◽

pp. 1-25

Author(s):

Ighoyota Ben Ajenaghughrure ◽

Sonia Cláudia Da Costa Sousa ◽

David Lamas

Keyword(s):

Feature Selection ◽

Risk Perception ◽

Autonomous Vehicles ◽

Electrodermal Activity ◽

Feature Selection Method ◽

Model Performance ◽

Selection Method ◽

Primary Objective ◽

Selection Methods ◽

Trust In Technology

Trust as a precursor for users' acceptance of artificial intelligence (AI) technologies that operate as a conceptual extension of humans (e.g., autonomous vehicles (AVs)) is highly influenced by users' risk perception amongst other factors. Prior studies that investigated the interplay between risk and trust perception recommended the development of real-time tools for monitoring cognitive states (e.g., trust). The primary objective of this study was to investigate a feature selection method that yields feature sets that can help develop a highly optimized and stable ensemble trust classifier model. The secondary objective of this study was to investigate how varying levels of risk perception influence users' trust and overall reliance on technology. A within-subject four-condition experiment was implemented with an AV driving game. This experiment involved 25 participants, and their electroencephalogram, electrodermal activity, and facial electromyogram psychophysiological signals were acquired. We applied wrapper, filter, and hybrid feature selection methods on the 82 features extracted from the psychophysiological signals. We trained and tested five voting-based ensemble trust classifier models using training and testing datasets containing only the features identified by the feature selection methods. The results indicate the superiority of the hybrid feature selection method over other methods in terms of model performance. In addition, the self-reported trust measurement and overall reliance of participants on the technology (AV) measured with joystick movements throughout the game reveals that a reduction in risk results in an increase in trust and overall reliance on technology.

Download Full-text

Incorporating Computation Time Measures During Heterogeneous Features Selection in a Boosted Cascade People Detector

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001416550223 ◽

2016 ◽

Vol 30 (08) ◽

pp. 1655022

Author(s):

Alhayat Ali Mekonnen ◽

Frédéric Lerasle ◽

Ariane Herbulot ◽

Cyril Briand

Keyword(s):

Feature Selection ◽

Pareto Front ◽

Feature Selection Method ◽

Computation Time ◽

Frame Rate ◽

Features Selection ◽

The Novel ◽

Binary Integer Programming ◽

Selection Scheme ◽

Heterogeneous Features

In this paper, we investigate the notion of incorporating feature computation time (CT) measures during feature selection in a boosted cascade people detector utilizing heterogeneous pool of features. We present various approaches based on pareto-front analysis, CT weighted adaboost, and Binary Integer Programming (BIP) with comparative evaluations. The novel feature selection method proposed based on BIP — the main contribution — mines heterogeneous features taking both detection performance and CT explicitly into consideration. The results demonstrate that the detector using this feature selection scheme exhibits low miss rates (MRs) with significant boost in frame rate. For example, it achieves a [Formula: see text] less MR at [Formula: see text] FPPW compared to Dalal and Triggs HOG detector with a [Formula: see text]x speed improvement. The presented extensive experimental results clearly highlight the improvements the proposed framework brings to the table.

Download Full-text

Title: Cardiac MRI derived radiomics based machine learning (ML) models in identifying pulmonary hypertension (PH)- Impact of segmentation, radiomics side experiments and DAFIT approach on model performance

10.21203/rs.3.rs-242269/v1 ◽

2021 ◽

Author(s):

Sarv Priya ◽

Tanya Aggarwal ◽

Caitlin Ward ◽

Girish Bathla ◽

Mathews Jacob ◽

...

Keyword(s):

Machine Learning ◽

Pulmonary Hypertension ◽

Feature Selection ◽

Subgroup Analysis ◽

Cardiac Mri ◽

Model Performance ◽

Poor Performance ◽

Superior Performance ◽

Feature Filtering ◽

The Impact

Abstract Side experiments are performed on radiomics models to improve their reproducibility. We measure the impact of myocardial masks, radiomic side experiments and data augmentation for information transfer (DAFIT) approach to differentiate patients with and without pulmonary hypertension (PH) using cardiac MRI (CMRI) derived radiomics. Feature extraction was performed from the left ventricle (LV) and right ventricle (RV) myocardial masks using CMRI in 82 patients (42 PH and 40 controls). Various side study experiments were evaluated: Original data without and with intraclass correlation (ICC) feature-filtering and DAFIT approach (without and with ICC feature-filtering). Multiple machine learning and feature selection strategies were evaluated. Primary analysis included all PH patients with subgroup analysis including PH patients with preserved LVEF (≥ 50%). For both primary and subgroup analysis, DAFIT approach without feature-filtering was the highest performer (AUC 0.957–0.958). ICC approaches showed poor performance compared to DAFIT approach. The performance of combined LV and RV masks was superior to individual masks alone. There was variation in top performing models across all approaches (AUC 0.862–0.958). DAFIT approach with features from combined LV and RV masks provide superior performance with poor performance of feature filtering approaches. Model performance varies based upon the feature selection and model combination.

Download Full-text

Stable trajectory planning and energy-efficience control allocation of lane change maneuver for autonomous electric vehicle

Journal of Intelligent and Connected Vehicles ◽

10.1108/jicv-12-2017-0002 ◽

2018 ◽

Vol 1 (2) ◽

pp. 55-65

Author(s):

Liwei Xu ◽

Guodong Yin ◽

Guangmin Li ◽

Athar Hanif ◽

Chentong Bian

Keyword(s):

Control System ◽

Energy Consumption ◽

Electric Vehicles ◽

Lateral Acceleration ◽

Lane Change ◽

Stability Boundaries ◽

Content Type ◽

Yaw Rate ◽

Stable Trajectory ◽

Autonomous Electric Vehicles

Purpose The purpose of this paper is to investigate problems in performing stable lane changes and to find a solution to reduce energy consumption of autonomous electric vehicles. Design/methodology/approach An optimization algorithm, model predictive control (MPC) and Karush–Kuhn–Tucker (KKT) conditions are adopted to resolve the problems of obtaining optimal lane time, tracking dynamic reference and energy-efficient allocation. In this paper, the dynamic constraints of vehicles during lane change are first established based on the longitudinal and lateral force coupling characteristics and the nominal reference trajectory. Then, by optimizing the lane change time, the yaw rate and lateral acceleration that connect with the lane change time are limed. Furthermore, to assure the dynamic properties of autonomous vehicles, the real system inputs under the restraints are obtained by using the MPC method. Based on the gained inputs and the efficient map of brushless direct-current in-wheel motors (BLDC IWMs), the nonlinear cost function which combines vehicle dynamic and energy consumption is given and the KKT-based method is adopted. Findings The effectiveness of the proposed control system is verified by numerical simulations. Consequently, the proposed control system can successfully achieve stable trajectory planning, which means that the yaw rate and longitudinal and lateral acceleration of vehicle are within stability boundaries, which accomplishes accurate tracking control and decreases obvious energy consumption. Originality/value This paper proposes a solution to simultaneously satisfy stable lane change maneuvering and reduction of energy consumption for autonomous electric vehicles. Different from previous path planning researches in which only the geometric constraints are involved, this paper considers vehicle dynamics, and stability boundaries are established in path planning to ensure the feasibility of the generated reference path.

Download Full-text

Metode Deteksi Intrusi Menggunakan Algoritme Extreme Learning Machine dengan Correlation-based Feature Selection

Jurnal Teknologi Informasi dan Ilmu Komputer ◽

10.25126/jtiik.0813358 ◽

2021 ◽

Vol 8 (1) ◽

pp. 103

Author(s):

Sulandri Sulandri ◽

Achmad Basuki ◽

Fitra Abdurrachman Bachtiar

Keyword(s):

Feature Selection ◽

Intrusion Detection ◽

Extreme Learning Machine ◽

Computing Time ◽

Feature Selection Method ◽

Computation Time ◽

Selection Method ◽

Computational Time ◽

Correlation Based Feature Selection ◽

Learning Machine

Deteksi intrusi pada jaringan komputer merupakan kegiatan yang sangat penting dilakukan untuk menjaga keamanan data dan informasi. Deteksi intrusi merupakan proses monitor traffic pada sebuah jaringan untuk mendeteksi adanya pola data yang dianggap mencurigakan, yang memungkinkan terjadinya serangan jaringan. Penelitian ini melakukan analisis pada traffic jaringan untuk mengetahui apakah paket tersebut mengandung intrusi atau merupakan paket normal. Data traffic yang digunakan untuk deteksi intrusi pada penelitian ini diambil dari dataset KDD Cup. Metode yang digunakan untuk melakukan deteksi intrusi dengan cara klasifikasi yaitu dengan menggunakan metode Extreme Learning Machine (ELM). Namun, dengan menggunakan metode ELM saja tidak mampu untuk menghasilkan akurasi yang baik maka, pada metode ELM perlu ditambahkan metode seleksi fitur Correlation-Based Feature Selection (CFS) untuk meningkatkan hasil akurasi dan waktu komputasi. Hasil penelitian yang dilakukan dengan menggunakan metode ELM menunjukkan tingkat akurasi mencapai 81,97% dengan waktu komputasi 3,39 detik. Setelah ditambahkan metode seleksi fitur CFS pada ELM tingkat akurasi meningkat secara signifikan menjadi 98,00% dengan waktu komputasi 2,32 detik. AbstractIntrusion detection of computer networks is a very important activity carried out to maintain data and information security. Intrusion detection is the process of monitoring traffic on a network to detect any data patterns that are considered suspicious, which allows network attacks. This research analyzes the network traffic to find out whether the packet contains intrusion or is a normal packet. Traffic data used for intrusion detection in this study were taken from the KDD Cup dataset. The method used to do intrusion detection by classification is using the Extreme Learning Machine (ELM) method. However, using the ELM method alone is not able to produce good accuracy, so the ELM method needs to be added to the Correlation-Based Feature Selection (CFS) feature selection method to improve the accuracy and computational time. The results of the research conducted using the ELM method showed an accuracy rate of 81.97% with a computation time of 3.39 seconds. After adding the CFS feature selection method to ELM the accuracy level increased significantly to 98.00% with a computing time of 2.32 seconds.

Download Full-text