Research Article
BibTex RIS Cite

DISCRIMINATIVE FEATURES FOR ENERGY-CONSTRAINED DEVICES ON TRANSPORTATION MODE DETECTION

Year 2019, Volume: 7 Issue: 1, 90 - 102, 25.03.2019
https://doi.org/10.21923/jesd.427863

Abstract

Personal transportation form has a substantial impact
on traffic planning and human health. Analyzing transportation
preferences/habits of people could result in planning new public routes in a
more efficient manner. One of the ways to detect such habits is to process the data
collected from the sensors located on smartphones and smart watches. Thus, the
widespread usage of these type devices makes the way for more publication about
transport mode detection. On the other hand, due to their energy-constrained
architecture, mobile applications about transport mode detection should be
designed taking energy consumption into consideration. Therefore, the selected
features for transport mode detection are quite critical.  In this study, time-domain and frequency
domain features are extracted from the data collected from accelerometer,
gyroscope, magnetometer and orientation sensor. The impact of time-domain
features, frequency-domain features and time-frequency domain features on
success rate are compared using 5 different classification algorithms including
J48, Random Forest, Support Vector Machines (SVM), k Nearest Neighbor (k-NN)
and Multi-Layer Perceptron. Test results show that Random Forest algorithm
outperforms the rest with a success rate of 95.06%, whereas exploiting both
time and frequency features increases the classification rate only by 0.5%
compared to using only time-domain features.

References

  • Waga, K., Tabarcea, A., Chen, M., & Franti, P. (2012, October). Detecting movement type by route segmentation and classification. In Collaborative computing: networking, applications and worksharing (CollaborateCom), 2012 8th International Conference on (pp. 508-513). IEEE.
  • Widhalm, P., Nitsche, P., & Brändie, N. (2012, November). Transport mode detection with realistic smartphone sensor data. In Pattern Recognition (ICPR), 2012 21st International Conference on (pp. 573-576). IEEE.
  • Xiao, Z., Wang, Y., Fu, K., & Wu, F. (2017). Identifying different transportation modes from trajectory data using tree-based ensemble classifiers. ISPRS International Journal of Geo-Information, 6(2), 57.
  • Su, H. X., Caceres, H., & He, Q. (2015). Travel mode identification with smartphones. Sensors, 15, 16.
  • Das, R. D., & Winter, S. (2016). Detecting urban transport modes using a hybrid knowledge driven framework from GPS trajectory. ISPRS International Journal of Geo-Information, 5(11), 207.
  • Ballı, S., Sağbaş, E. A. (2016), Akıllı telefon algılayıcıları ve makine öğrenmesi kullanılarak ulaşım türü tespiti, Pamukkale Univ Muh Bilim Dergisi, 22(5), 376-383.
  • Bedogni, L., Di Felice, M., & Bononi, L. (2016). Context‐aware Android applications through transportation mode detection techniques. Wireless Communications and Mobile Computing, 16(16), 2523-2541.
  • Siirtola, P., & Röning, J. (2012). Recognizing human activities user-independently on smartphones based on accelerometer data. IJIMAI, 1(5), 38-45.
  • Byon, Y., Liang, S. (2014), Real-Time Transportation Mode Detection Using Smartphones
and Artificial Neural Networks: Performance Comparisons Between Smartphones and Conventional Global Positioning System Sensors. Journal of Intelligent Transportation Systems, 18(3), 264-272.
  • Jahangiri, A., & Rakha, H. A. (2015). Applying machine learning techniques to transportation mode recognition using mobile phone sensor data. IEEE transactions on intelligent transportation systems, 16(5), 2406-2417.
  • Sonderon, T. (2016), Detection of Transportation Mode Solely Using Smartphones.
  • Cardoso, N., Madureira, J., & Pereira, N. (2016, September). Smartphone-based transport mode detection for elderly care. In e-Health Networking, Applications and Services (Healthcom), 2016 IEEE 18th International Conference on (pp. 1-6). IEEE.
  • Su, X., Caceres, H., Tong, H., & He, Q. (2016). Online travel mode identification using smartphones with battery saving considerations. IEEE Transactions on Intelligent Transportation Systems, 17(10), 2921-2934.
  • Hemminki, S., Nurmi, P., & Tarkoma, S. (2013, November). Accelerometer-based transportation mode detection on smartphones. In Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems (p. 13). ACM.
  • Yan, Z., Subbaraju, V., Chakraborty, D., Misra, A., & Aberer, K. (2012, June). Energy-efficient continuous activity recognition on mobile phones: An activity-adaptive approach. In Wearable Computers (ISWC), 2012 16th International Symposium on (pp. 17-24). IEEE.
  • Xia, H., Qiao, Y., Jian, J., & Chang, Y. (2014). Using smart phone sensors to detect transportation modes. Sensors, 14(11), 20843-20865.
  • Zhou, X., Yu, W., & Sullivan, W. C. (2016). Making pervasive sensing possible: Effective travel mode sensing based on smartphones. Computers, Environment and Urban Systems, 58, 52-59.
  • Fang, S. H., Liao, H. H., Fei, Y. X., Chen, K. H., Huang, J. W., Lu, Y. D., & Tsao, Y. (2016). Transportation modes classification using sensors on smartphones. Sensors, 16(8), 1324.
  • Fang, S. H., Fei, Y. X., Xu, Z., & Tsao, Y. (2017). Learning Transportation Modes From Smartphone Sensors Based on Deep Neural Network. IEEE Sensors Journal, 17(18), 6111-6118.
  • Shin, D., Aliaga, D., Tunçer, B., Arisona, S. M., Kim, S., Zünd, D., & Schmitt, G. (2015). Urban sensing: Using smartphones for transportation mode classification. Computers, Environment and Urban Systems, 53, 76-86.
  • Shafique, M. A., & Hato, E. (2016). Travel mode detection with varying smartphone data collection frequencies. Sensors, 16(5), 716.
  • Lan, G., Xu, W., Khalifa, S., Hassan, M., & Hu, W. (2016, March). Transportation mode detection using kinetic energy harvesting wearables. In Pervasive Computing and Communication Workshops (PerCom Workshops), 2016 IEEE International Conference on (pp. 1-4). IEEE.
  • Nikolic, M., & Bierlaire, M. (2017). Review of transportation mode detection approaches based on smartphone data. In 17th Swiss Transport Research Conference (No. EPFL-CONF-229181).
  • Figo, D., Diniz, P. C., Ferreira, D. R., & Cardoso, J. M. (2010). Preprocessing techniques for context recognition from accelerometer data. Personal and Ubiquitous Computing, 14(7), 645-662.
  • Guvensan, M. A., Dusun, B., Can, B., & Turkmen, H. (2017). A Novel Segment-Based Approach for Improving Classification Performance of Transport Mode Detection. Sensors, 18(1), 87.
  • Aktas, M. S., & Kalıpsız, O. (2015, September). Veri Madenciliğinde Öznitelik Seçim Tekniklerinin Bankacılık Verisine Uygulanması Üzerine Araştırma ve Karşılaştırmalı Uygulama. In Proceedings of the 9th Turkish National Software Engineering Symposium (UYMS 2015), Yasar University, Izmir, Turkey.
  • Çalışkan, S. K., & Soğukpınar, İ. (2008). KxKNN: K-Means ve K En Yakin Komşu Yöntemleri İle Ağlarda Nüfuz Tespiti. EMO Yayınları, 120-24.
  • Radenković P., Random Forest, University Of Belgrade, 2015.
  • Karaatlı, M., Helvacıoğlu, Ö. C., Ömürbek, N., & Tokgöz, G. (2012). Yapay Sinir Ağları Yöntemi İle Otomobil Satış Tahmini. Uluslararası Yönetim İktisat ve İşletme Dergisi, 8(17), 87-100.
  • Bilişik, M. T. (2011). Destek Vektör Makinesi, Çoklu Regresyon Ve Doğrusal Olmayan Programlama İle Perakendecilik Sektöründe Gelir Yönetimi İçin Dinamik Fiyatlandırma.

ULAŞIM TÜRÜ TANIMADA ENERJİ KISITLI CİHAZLAR İÇİN AYIRT EDİCİ ÖZELLİKLER

Year 2019, Volume: 7 Issue: 1, 90 - 102, 25.03.2019
https://doi.org/10.21923/jesd.427863

Abstract

Bireysel ulaşım şekli,
trafik planlama ve insan sağlığı araştırmalarında önemli bir etkiye sahiptir.
Kişilerin ulaşım alışkanlıkları analiz edilerek şehirlerde yeni hatların
planlaması çok daha verimli bir şekilde yapılabilir. Bu alışkanlıkları tespit etmenin
yollarından bir tanesi de kişilerin kullandıkları akıllı telefonlar veya
saatler üzerinden toplanan algılayıcı verilerinin işlenerek ulaşım türü tespiti
yapılmasıdır. Akıllı telefonların ve saatlerin hayatımıza girmesiyle, ulaşım
türü belirleme üzerine yapılan çalışmalar artmıştır. Öte yandan, bu cihazların
enerji kısıtları olması sebebiyle ulaşım türü tanıma uygulamalarının mümkün
olduğunca az enerji tüketmesi istenmektedir. Bu nedenle ulaşım türü tanımada
kullanılan öznitelikler oldukça önemlidir. Bu çalışmada akıllı telefon üzerinde
bulunan ivme ölçer, jiroskop, mıknatıs ölçer ve yön algılayıcıları kullanılarak
toplanan ham veriden zaman ve frekans alanında öznitelikler elde edilmiştir. Öznitelikler,
Zaman, Frekans, Zaman+Frekans tiplerine göre ayırılarak, farklı sınıflandırma
algoritmaları üzerindeki başarıya etkileri incelenmiştir. Sınıflandırma
algoritması olarak J48, Rastgele Orman (Random Forest), Destek Vektör
Makineleri (SVM), En Yakın k Komşuluk (k-NN) ve Çok Katmanlı Algılayıcı
algoritmaları kullanılmıştır. Yapılan testler sonucunda en başarılı algoritma
%95,06 ile Rastgele Orman algoritması olurken, Zaman+Frekans alanında elde
edilen özniteliklerin Zaman alanındaki özniteliklere göre sadece %0,5 daha iyi
sonuç ürettiği görülmüştür.

References

  • Waga, K., Tabarcea, A., Chen, M., & Franti, P. (2012, October). Detecting movement type by route segmentation and classification. In Collaborative computing: networking, applications and worksharing (CollaborateCom), 2012 8th International Conference on (pp. 508-513). IEEE.
  • Widhalm, P., Nitsche, P., & Brändie, N. (2012, November). Transport mode detection with realistic smartphone sensor data. In Pattern Recognition (ICPR), 2012 21st International Conference on (pp. 573-576). IEEE.
  • Xiao, Z., Wang, Y., Fu, K., & Wu, F. (2017). Identifying different transportation modes from trajectory data using tree-based ensemble classifiers. ISPRS International Journal of Geo-Information, 6(2), 57.
  • Su, H. X., Caceres, H., & He, Q. (2015). Travel mode identification with smartphones. Sensors, 15, 16.
  • Das, R. D., & Winter, S. (2016). Detecting urban transport modes using a hybrid knowledge driven framework from GPS trajectory. ISPRS International Journal of Geo-Information, 5(11), 207.
  • Ballı, S., Sağbaş, E. A. (2016), Akıllı telefon algılayıcıları ve makine öğrenmesi kullanılarak ulaşım türü tespiti, Pamukkale Univ Muh Bilim Dergisi, 22(5), 376-383.
  • Bedogni, L., Di Felice, M., & Bononi, L. (2016). Context‐aware Android applications through transportation mode detection techniques. Wireless Communications and Mobile Computing, 16(16), 2523-2541.
  • Siirtola, P., & Röning, J. (2012). Recognizing human activities user-independently on smartphones based on accelerometer data. IJIMAI, 1(5), 38-45.
  • Byon, Y., Liang, S. (2014), Real-Time Transportation Mode Detection Using Smartphones
and Artificial Neural Networks: Performance Comparisons Between Smartphones and Conventional Global Positioning System Sensors. Journal of Intelligent Transportation Systems, 18(3), 264-272.
  • Jahangiri, A., & Rakha, H. A. (2015). Applying machine learning techniques to transportation mode recognition using mobile phone sensor data. IEEE transactions on intelligent transportation systems, 16(5), 2406-2417.
  • Sonderon, T. (2016), Detection of Transportation Mode Solely Using Smartphones.
  • Cardoso, N., Madureira, J., & Pereira, N. (2016, September). Smartphone-based transport mode detection for elderly care. In e-Health Networking, Applications and Services (Healthcom), 2016 IEEE 18th International Conference on (pp. 1-6). IEEE.
  • Su, X., Caceres, H., Tong, H., & He, Q. (2016). Online travel mode identification using smartphones with battery saving considerations. IEEE Transactions on Intelligent Transportation Systems, 17(10), 2921-2934.
  • Hemminki, S., Nurmi, P., & Tarkoma, S. (2013, November). Accelerometer-based transportation mode detection on smartphones. In Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems (p. 13). ACM.
  • Yan, Z., Subbaraju, V., Chakraborty, D., Misra, A., & Aberer, K. (2012, June). Energy-efficient continuous activity recognition on mobile phones: An activity-adaptive approach. In Wearable Computers (ISWC), 2012 16th International Symposium on (pp. 17-24). IEEE.
  • Xia, H., Qiao, Y., Jian, J., & Chang, Y. (2014). Using smart phone sensors to detect transportation modes. Sensors, 14(11), 20843-20865.
  • Zhou, X., Yu, W., & Sullivan, W. C. (2016). Making pervasive sensing possible: Effective travel mode sensing based on smartphones. Computers, Environment and Urban Systems, 58, 52-59.
  • Fang, S. H., Liao, H. H., Fei, Y. X., Chen, K. H., Huang, J. W., Lu, Y. D., & Tsao, Y. (2016). Transportation modes classification using sensors on smartphones. Sensors, 16(8), 1324.
  • Fang, S. H., Fei, Y. X., Xu, Z., & Tsao, Y. (2017). Learning Transportation Modes From Smartphone Sensors Based on Deep Neural Network. IEEE Sensors Journal, 17(18), 6111-6118.
  • Shin, D., Aliaga, D., Tunçer, B., Arisona, S. M., Kim, S., Zünd, D., & Schmitt, G. (2015). Urban sensing: Using smartphones for transportation mode classification. Computers, Environment and Urban Systems, 53, 76-86.
  • Shafique, M. A., & Hato, E. (2016). Travel mode detection with varying smartphone data collection frequencies. Sensors, 16(5), 716.
  • Lan, G., Xu, W., Khalifa, S., Hassan, M., & Hu, W. (2016, March). Transportation mode detection using kinetic energy harvesting wearables. In Pervasive Computing and Communication Workshops (PerCom Workshops), 2016 IEEE International Conference on (pp. 1-4). IEEE.
  • Nikolic, M., & Bierlaire, M. (2017). Review of transportation mode detection approaches based on smartphone data. In 17th Swiss Transport Research Conference (No. EPFL-CONF-229181).
  • Figo, D., Diniz, P. C., Ferreira, D. R., & Cardoso, J. M. (2010). Preprocessing techniques for context recognition from accelerometer data. Personal and Ubiquitous Computing, 14(7), 645-662.
  • Guvensan, M. A., Dusun, B., Can, B., & Turkmen, H. (2017). A Novel Segment-Based Approach for Improving Classification Performance of Transport Mode Detection. Sensors, 18(1), 87.
  • Aktas, M. S., & Kalıpsız, O. (2015, September). Veri Madenciliğinde Öznitelik Seçim Tekniklerinin Bankacılık Verisine Uygulanması Üzerine Araştırma ve Karşılaştırmalı Uygulama. In Proceedings of the 9th Turkish National Software Engineering Symposium (UYMS 2015), Yasar University, Izmir, Turkey.
  • Çalışkan, S. K., & Soğukpınar, İ. (2008). KxKNN: K-Means ve K En Yakin Komşu Yöntemleri İle Ağlarda Nüfuz Tespiti. EMO Yayınları, 120-24.
  • Radenković P., Random Forest, University Of Belgrade, 2015.
  • Karaatlı, M., Helvacıoğlu, Ö. C., Ömürbek, N., & Tokgöz, G. (2012). Yapay Sinir Ağları Yöntemi İle Otomobil Satış Tahmini. Uluslararası Yönetim İktisat ve İşletme Dergisi, 8(17), 87-100.
  • Bilişik, M. T. (2011). Destek Vektör Makinesi, Çoklu Regresyon Ve Doğrusal Olmayan Programlama İle Perakendecilik Sektöründe Gelir Yönetimi İçin Dinamik Fiyatlandırma.
There are 30 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Araştırma Articlessi \ Research Articles
Authors

Fethiye Yaslı This is me 0000-0002-2430-4303

M. Amaç Güvensan 0000-0002-2728-8900

Publication Date March 25, 2019
Submission Date May 31, 2018
Acceptance Date December 4, 2018
Published in Issue Year 2019 Volume: 7 Issue: 1

Cite

APA Yaslı, F., & Güvensan, M. A. (2019). ULAŞIM TÜRÜ TANIMADA ENERJİ KISITLI CİHAZLAR İÇİN AYIRT EDİCİ ÖZELLİKLER. Mühendislik Bilimleri Ve Tasarım Dergisi, 7(1), 90-102. https://doi.org/10.21923/jesd.427863