User-friendly Activity Recognition Using SVM Classifier and Informative Features

被引：0
|
作者：
Phong Nguyen [1 ]
Akiyama, Takayuki [1 ]
Ohashi, Hiroki [1 ]
Nakahara, Goh [2 ]
Yamasaki, Katsuya [2 ]
Hikaru, Saito [2 ]
机构：
[1] Hitachi Ltd, Ctr Technol Innovat Syst Engn, Tokyo, Japan
[2] Hitachi Adv Syst Co Ltd, Yokohama, Kanagawa, Japan
来源：
2015 INTERNATIONAL CONFERENCE ON INDOOR POSITIONING AND INDOOR NAVIGATION (IPIN) | 2015年
关键词：
indoor positioning; activity recognition; smartphone; machine learning; PEDESTRIAN TRACKING;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
For accurate indoor positioning, a moving activity recognition (AR) method has been developed that is based on a smartphone's sensor data. Prior methods can only recognize moving activities if the smartphone is held in a predefined place. We propose a method that works in various holding places to increase the usability. An SVM classifier is chosen because of its strength in utilizing features. New features are added such as percentiles of acceleration, air pressure, and acceleration magnitude. We have achieved 94.3% overall accuracy in various holding places: in users' hands, belt pouches, pant back pockets, and pant side pockets.
引用
收藏
页数：8
相关论文
共 50 条
  • [1] Activity Recognition from Smartphones Using Hybrid Classifier PCA-SVM-HMM
    Abidine, M'hamed Bilal
    Fergani, Belkacem
    Menhour, Ihssene
    2019 INTERNATIONAL CONFERENCE ON WIRELESS NETWORKS AND MOBILE COMMUNICATIONS (WINCOM), 2019, : 47 - 51
  • [2] A Robust and User-Friendly Alternative to Densitometry Using Origami Biosensors and Digital Logic
    Russell, Steven M.
    Alba-Patino, Alejandra
    Borges, Marcio
    de la Rica, Roberto
    ACS SENSORS, 2018, 3 (09): : 1712 - 1718
  • [3] Novel Approach for Stress Recognition using EEG Signal by SVM Classifier
    Gaikwad, Pallavi
    Paithane, A. N.
    2017 INTERNATIONAL CONFERENCE ON COMPUTING METHODOLOGIES AND COMMUNICATION (ICCMC), 2017, : 967 - 971
  • [4] A User-friendly Approach for the Diagnosis of Diabetic Retinopathy Using ChatGPT and Automated Machine Learning
    Mohammadi, S. Saeed
    Nguyen, Quan Dong
    OPHTHALMOLOGY SCIENCE, 2024, 4 (04):
  • [5] Classifier comparison using EEG features for emotion recognition process
    Martinez-Tejada, Laura Alejandra
    Yoshimura, Natsue
    Koike, Yasuharu
    2020 IEEE 18TH WORLD SYMPOSIUM ON APPLIED MACHINE INTELLIGENCE AND INFORMATICS (SAMI 2020), 2020, : 225 - 229
  • [6] Classifier Personalization for Activity Recognition Using Wrist Accelerometers
    Mannini, Andrea
    Intille, Stephen S.
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2019, 23 (04) : 1585 - 1594
  • [7] Analysis of mutations in precision oncology using the automated, accurate, and user-friendly web tool PredictONCO
    Khan, Rayyan Tariq
    Pokorna, Petra
    Stourac, Jan
    Borko, Simeon
    Dobias, Adam
    Planas-Iglesias, Joan
    Mazurenko, Stanislav
    Arefiev, Ihor
    Pinto, Gaspar
    Szotkowska, Veronika
    Sterba, Jaroslav
    Damborsky, Jiri
    Slaby, Ondrej
    Bednar, David
    COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL, 2024, 24 : 734 - 738
  • [8] A New Framework Using PCA, LDA and KNN-SVM to Activity Recognition Based SmartPhone's Sensors
    Menhour, Ihssene
    Abidine, M'hamed Bilal
    Fergani, Belkacem
    PROCEEDINGS OF 2018 6TH INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS (ICMCS), 2018, : 110 - 114
  • [9] Leveraging AI and Machine Learning to Develop and Evaluate a Contextualized User-Friendly Cough Audio Classifier for Detecting Respiratory Diseases: Protocol for a Diagnostic Study in Rural Tanzania
    Isangula, Kahabi Ganka
    Haule, Rogers John
    JMIR RESEARCH PROTOCOLS, 2024, 13
  • [10] The Pixel Anomaly Detection Tool: a user-friendly GUI for classifying detector frames using machine-learning approaches
    Ketawala, Gihan
    Reiter, Caitlin M.
    Fromme, Petra
    Botha, Sabine
    JOURNAL OF APPLIED CRYSTALLOGRAPHY, 2024, 57 (Pt 2) : 529 - 538
12345