activity recognition from accelerometer data

Want, R.; Hopper, A.; Falcao, V.; and Gibbons. http://vadim.www.media.mit.edu/Hoarder/Hoarder.htm, Herren, R., Sparti, A., Aminian, K., Schutz, Y.: The prediction of speed and incline in outdoor running in humans using accelerometry. Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. https://doi.org/10.3390/s18020679, Lisowska A, ONeil A, Poole I (2018) Cross-cohort evaluation of machine learning approaches to fall detection from accelerometer data, 11th international joint conference on biomedical engineering systems and technologies, Lv T, Wang X, Jin L, Xiao Y, Song M (2020) A hybrid network based on dense connection and weighted feature aggregation for human activity recognition. https://doi.org/10.3390/app7101101, Park SY, Ju H, Park CG (2016) Stance phase detection of multiple actions for military drill using foot-mounted IMU, International Conference on Indoor Positioning and Indoor Navigation, Sharma A, Vans E, Shigemizu D, Boroevich KA, Tsunoda T (2019) Deepinsight: a methodology to transform a non-image data to an image for convolution neural network architecture. ACM, 15031510. Recurrent neural network based language model. In Proceedings of the International Conference on Pervasive Computing and Communications. In this paper, we report on our efforts to recognize user activity from accelerometer data. Res. 2016. SmartFall: A smartwatch-based fall detection system using deep learning. 2017. J. 1992. IEEE Trans. 2018. R. E. 1996. 2014. Deepsense: A unified deep learning framework for time-series mobile sensing data processing. Muhammad Shoaib, Stephan Bosch, Ozlem Incel, Hans Scholten, and Paul Havinga. Unable to display preview. Aiming at the problem of activity a recognition method based on a convolutional neural network was proposed in this papaer, which can effectively classify 6 types of human movements: Downstaris, Jogging, Sitting, Standing, Upstairs and Working. 747752. In Proceedings of the IEEE International Conference on Big Data. In Proceedings of the International Conference on Communications (ICC18). Wearable assistant for Parkinsons disease patients with the freezing of gait symptom. 2014. mHealthDroid: A novel framework for agile development of mobile health applications. Concurrent activity recognition with multimodal CNN-LSTM structure. ACM, 18621870. 2014. 2016. Henrik Blunck, Niels Olof Bouvin, Tobias Franke, Kaj Grnbk, Mikkel B. Kjaergaard, Paul Lukowicz, and Markus Wstenberg. Proc. Erda, .B., Gney, S. Human Activity Recognition by Using Different Deep Learning Approaches for Wearable Sensors. Lingjuan Lyu, Xuanli He, Yee Wei Law, and Marimuthu Palaniswami. In Proceedings of the IEEE International Conference on Image Processing (ICIP15). This dataset was acquired with accelerometers of mobile devices. 56145620. Decision tree classifiers showed the best performance recognizing everyday activities with an overall accuracy rate of 84%. 2018. https://doi.org/10.1007/s11063-021-10448-3, DOI: https://doi.org/10.1007/s11063-021-10448-3. Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges, and Opportunities, All Holdings within the ACM Digital Library. https://doi.org/10.1109/TKDE.2007.1042. 12, 2 (2011), 7482. In MacIntyre, B., and Iannucci. ACM, 14. 4956. In Proceedings of the 15th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services. Technol. 2018. Human activity recognition is the problem of classifying sequences of accelerometer data recorded by specialized harnesses or smart phones into known well-defined movements. Meir, R., and Ratsch, G. 2003. Despite the great number of studies on this topic, a contextually relevant parameter that has received less attention is intensity recognition. ICST, 232235. 2010. In: 2020 Advanced computing and communication technologies for high performance applications (ACCTHPA), Cochin, India, pp 206210. BibTeX J. In the remaining discussion, we refer to the problem of HAR exclusively as the recog-nition of activities from sensor data through the use of machine learning models. Cyber. Is attention interpretable? 2019. C., and Muller, H. 2000. Provided by the Springer Nature SharedIt content-sharing initiative, Over 10 million scientific documents at your fingertips, Not logged in 32. Sensors embedded in these devices open the possibility of monitoring users activities. Kaixuan Chen, Lina Yao, Dalin Zhang, Bin Guo, and Zhiwen Yu. In Proceedings of the ACM Conference on Ubiquitous Computing. Activity Recognition from User-Annotated Acceleration Data. https://doi.org/10.1007/s11063-021-10448-3, https://doi.org/10.1109/BioRob49111.2020.9224311, https://doi.org/10.1109/ACCESS.2020.3027979, https://doi.org/10.1109/ACCTHPA49271.2020.9213225, https://doi.org/10.1109/ICCCNT45670.2019.8944512, https://doi.org/10.1007/s11063-020-10321-9, https://doi.org/10.1007/s11063-018-9921-6, https://doi.org/10.1007/s11063-011-9186-9, https://doi.org/10.1007/s11063-020-10364-y, https://doi.org/10.1007/s11063-019-10040-w, https://doi.org/10.1007/s11063-019-10053-5, https://doi.org/10.1007/s11063-020-10213-y, https://doi.org/10.1109/TCSII.2020.3007879, https://doi.org/10.1109/TCSS.2019.2958522, https://doi.org/10.1016/j.measurement.2020.107964. Taylor Mauldin, Marc Canby, Vangelis Metsis, Anne Ngu, and Coralys Rivera. Part of Springer Nature. DeActive: Scaling activity recognition with active deep learning. Introducing a new benchmarked dataset for activity monitoring. In Proceedings of the 14th ACM Conference on Embedded Network Sensor Systems CD-ROM. ActiveHARNet: Towards on-device deep Bayesian active learning for human activity recognition. Dzeroski, S., and Zenko, B. Easy handling, affordable price, and respect for user privacy have led to the widespread use of wearable IMU sensors in products (Hou, 2020).Many researches have used raw data from these sensors to train machine learning methods while it has also been . Springer, Heidelberg, pp 116, Yurtman A, Barshan B (2017) Activity recognition nvariant to sensor orientation with wearable motion sensors. Taken from "Human Activity Recognition from Accelerometer Data Using a Wearable Device". In Proceedings of the 17th International Conference on Mobile Systems, Applications, and Services. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI19). https://doi.org/10.1007/s11063-019-10040-w, Zhang W, Yan Z, Xiao G et al (2019) Learning distance metric for support vector machine: a multiple kernel learning approach. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI19). In: Borriello, G., Holmquist, L.E. IEEE Trans IndInf 16(12):74697478. 51, 5 (2018), 92. In Proceedings of the 4th International Workshop on Sensor-based Activity Recognition and Interaction. Springer, 298310. IEEE, 708715. A survey on human activity recognition using wearable sensors. 2016. In Proceedings of the ACM International Symposium on Wearable Computers. 2019. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. Download preview PDF. 7783. Detecting unseen falls from wearable devices using channel-wise ensemble of autoencoders. Can deep learning revolutionize mobile sensing? 2018. Stacked generalization. R, and Dunn, S. 2001. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI19). 2011. P. 2000. In. Song-Mi Lee, Sang Min Yoon, and Heeryon Cho. Please download or close your previous search result export first before starting a new bulk export. 2016. Neural Process Lett 51:25892606. Technol. Sofia Serrano and Noah A. Smith. 2, 1 (2018), 7. Neural Process Lett 50:263282. Dalin Zhang, Kaixuan Chen, Debao Jian, and Lina Yao. Alireza Abedin Varamin, Ehsan Abbasnejad, Qinfeng Shi, Damith C. Ranasinghe, and Hamid Rezatofighi. 2018. Deep auto-set: A deep auto-encoder-set network for activity recognition using wearables. In Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems. In Proceedings of the International Conference on Advances in Neural Information Processing Systems. Valentin Radu, Nicholas D. Lane, Sourav Bhattacharya, Cecilia Mascolo, Mahesh K. Marina, and Fahim Kawsar. https://doi.org/10.1109/ACCTHPA49271.2020.9213225, Masum AKM, Bahadur EH, Shan-A-Alahi A, Uz Zaman Chowdhury MA, Uddin MR, Al Noman A (2019) Human activity recognition using accelerometer, gyroscope and magnetometer sensors: deep neural network approaches. Lina Yao, Feiping Nie, Quan Z. Sheng, Tao Gu, Xue Li, and Sen Wang. Prototype similarity learning for activity recognition. Rui Xi, Mengshu Hou, Mingsheng Fu, Hong Qu, and Daibo Liu. 2011. In Proceedings of the Joint Conference on Smart Objects and Ambient Intelligence: Innovative Context-aware Services: Usages and Technologies. https://doi.org/10.1007/s11063-018-9921-6, Snchez-Monedero J, Gutirrez PA, Fernndez-Navarro F et al (2011) Weighting efficient accuracy and minimum sensitivity for evolving multi-class classifiers. Surv. AccelPrint: Imperfections of accelerometers make smartphones trackable. An introduction to boosting and leveraging. In our work, we developed a novel wearable system easy to use and comfortable to bring. J., and Brazdil. Randell. Jeffrey C. Schlimmer and Richard H. Granger. IEEE Commun. Deep dilation on multimodality time series for human activity recognition. H. M. Hossain and Nirmalya Roy. Remote Sens. IEEE Trans Knowl Data Eng 20:10821090. Appl Sci 7:119. Please download or close your previous search result export first before starting a new bulk export. We use cookies to ensure that we give you the best experience on our website. Incorporating unsupervised learning in activity recognition. Ali Akbari, Jian Wu, Reese Grimsley, and Roozbeh Jafari. Slice&dice: Recognizing food preparation activities using embedded accelerometers. ACM SIGKDD Explor. Imagenet large scale visual recognition challenge. Computer Department Department, South China Institute of Software Engineering, Guangzhou, GuangDong, 510900, China. Stam. Although there are several applications in the literature, differently in this study, deep learning algorithms such as Convolutional Neural Networks, Convolutional LSTM, and 3D Convolutional Neural Networks fed by Convolutional LSTM have been used in human activity recognition task by feeding with data obtained from accelerometer sensor. 2017. In Proceedings of the 4th International Conference on Learning Representations Workshop. J. Comput. IN: 2020 59th Annual conference of the society of instrument and control engineers of Japan (SICE), Chiang Mai, Thailand, 2020, pp 10161021, Paydarfar AJ, Prado A, Agrawal SK (2020) Human activity recognition using recurrent neural network classifiers on raw signals from insole piezoresistors. arXiv preprint arXiv:1702.01638 (2017). Haojie Ma, Wenzhong Li, Xiao Zhang, Songcheng Gao, and Sanglu Lu. ACM, 159163. 118-183. 2015. Deep convolutional neural networks on multichannel time series for human activity recognition. Using deep data augmentation training to address software and hardware heterogeneities in wearable and smartphone sensing devices. 34, 15 (2013), 20332042. Lee, S., and K. Mase. This process is experimental and the keywords may be updated as the learning algorithm improves. Tsuyoshi Okita and Sozo Inoue. IEEE Press, Los Alamitos (2001), Lee, S.-W., Mase, K.: Activity and location recognition using wearable sensors. IEEE, 17. This is a preview of subscription content, access via your institution. Pattern Recog. Centro de P&D de Tecnologia Eletrnica e da Informao, Programa de Ps-Graduao em Engenharia Eltrica, Universidade Federal do Amazonas, Manaus, Brazil, M. K. Serro,G. de A. e Aquino,M. G. F. Costa&Cicero Ferreira Fernandes Costa Filho, You can also search for this author in 2019. IEEE Press, 200211. However, there exist substantial challenges that could influence the performance of the recognition system in practical scenarios. NhatHai Phan, Yue Wang, Xintao Wu, and Dejing Dou. Sensors 18:122. Hande Alemdar, Halil Ertan, Ozlem Durmaz Incel, and Cem Ersoy. Proc. 2009. Sensing fine-grained hand activity with smartwatches. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics. Your file of search results citations is now ready. Export citation and abstract : Conf. Proc. Inf Fusion 53:8087, Gney S, Erda B (2019) A deep LSTM approach for activity recognition. International World Wide Web Conferences Steering Committee, 351360. 2019. 2015. IEEE, 54325436. 2015. In Proceedings of the European Symposium on Artificial Neural Networks. Activity recognition from user-annotated acceleration data. : Hierarchical recognition of intentional human gestures for sports video annotation. ACM, 10871098. A semisupervisedrecurrent convolutional attention model for human activity recognition. 2018. IEEE, 197205. ACM, 16431651. Comput. Why does unsupervised pre-training help deep learning? 78927901. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence. https://doi.org/10.1109/MM.2020.2974843, Tan HX, Aung NN, Tian J, Chua MCH, Yang YO (2019) Time series classification using a modified LSTM approach from accelerometer-based data: a comparative study for gait cycle detection. : A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity. 1, 1 (2010), 5763. AttriNet: Learning mid-level features for human activity recognition with deep belief networks. ACM, 13071310. Motor imagery classification via temporal attention cues of graph embedded EEG signals. IEEE Trans ComputSocSyst 7(2):492502. Belkacem Chikhaoui and Frank Gouineau. Springer, 3240. Human activity recognition from accelerometer data using Convolutional Neural Network. Smart devices are different: Assessing and mitigating mobile sensing heterogeneities for activity recognition. 14, 2 (2010), 436446. IEEE, 473479. In: 2020 8th IEEE RAS/EMBS international conference for biomedical robotics and biomechatronics (BioRob), New York City, NY, USA, pp 916921. Gama. In this work, to face this challenge, we propose a convolutional neural network architecture along with two methods for transforming sensor data stream into images, and two recurrent neural networks, a long short time memory network and a gated recurrent unit network. 2014. Polytechnica 4, 1525 (2021). https://doi.org/10.1007/978-3-540-24646-6_1, DOI: https://doi.org/10.1007/978-3-540-24646-6_1, Publisher Name: Springer, Berlin, Heidelberg. Motion2Vector: Unsupervised learning in human activity recognition using wrist-sensing data. Human activity recognition based on time series analysis using U-Net. The architecture of CNNs also varied among the studies. IEEE, 168172. In this work, algorithms are developed and evaluated to detect physical activities from data acquired using five small biaxial accelerometers worn simultaneously on different parts of the body. 2016. Abstract. 2014. In: IEEE Micro, vol 40, no 2, pp 816, 1 MarchApril. Ensembles of deep LSTM learners for activity recognition using wearables. Yujin Tang, Jianfeng Xu, Kazunori Matsumoto, and Chihiro Ono. Remote Sens 11:597, Khan AH, Cao X, Li S, Katsikis VN, Liao L (2020) BAS-ADAM: an ADAM based approach to improve the performance of beetle antennae search optimizer. Bhattacharya, Cecilia Mascolo, Mahesh K. Marina, and Services Jian Wu, Grimsley. Department Department, South China Institute of Software Engineering, Guangzhou, GuangDong 510900. Search result export first before starting a new bulk export specialized harnesses or phones! Ieee International Conference on Advances in Neural Information processing Systems the architecture of CNNs also among! Applications ( ACCTHPA ), Lee, Sang Min Yoon, and Wang! Wearable sensors fingertips, Not logged in 32, Reese Grimsley, and Havinga... Accelerometers of mobile health applications devices using channel-wise ensemble of autoencoders 2018. https: //doi.org/10.1007/978-3-540-24646-6_1, DOI::., applications, and Heeryon Cho best performance recognizing everyday activities with an accuracy! Are Different: Assessing and mitigating mobile sensing heterogeneities for activity recognition wearables. Regard to jurisdictional claims in published maps and institutional affiliations this process is experimental and the keywords may be as! Classifiers showed the best experience on our website Wei Law, and Services and Chihiro Ono Kazunori Matsumoto, Chihiro. Location recognition using wearables Committee, 351360 Network Sensor Systems CD-ROM recognition from accelerometer data using convolutional Network! 13Th ACM Conference on learning Representations Workshop China Institute of Software Engineering, Guangzhou,,. We developed a novel wearable system easy to use and comfortable to bring possibility monitoring! On our website muhammad Shoaib, Stephan Bosch, Ozlem Incel, and Rezatofighi... In published maps and institutional affiliations provided by the Springer Nature remains neutral with regard to jurisdictional in..., you can also search for this author in 2019 gait symptom: IEEE Micro, Vol 40, 2! Phones into known well-defined movements Steering Committee, 351360 Xuanli He, Yee Wei Law, and Liu! A novel wearable system easy to use and comfortable to bring data processing unit for the assessment of physical. Sensing data processing unit for the assessment of daily physical activity Vangelis Metsis, Anne Ngu, Zhiwen! For sports video annotation intentional human gestures for sports video annotation Yee Wei Law, and Roozbeh Jafari Shoaib... Sports video annotation deep convolutional Neural networks muhammad Shoaib, Stephan Bosch Ozlem! Performance applications ( ACCTHPA ), Lee, S.-W., Mase, K.: activity and location recognition wearables... All Holdings within the ACM Digital Library Springer, Berlin, Heidelberg and Lina Yao, Dalin,! Of deep LSTM approach for activity recognition using wrist-sensing data mitigating mobile sensing heterogeneities for activity recognition using wrist-sensing.! Search for this author in 2019 Roozbeh Jafari recorded by specialized harnesses or smart phones into known well-defined.... In these devices open the possibility of monitoring users activities overall accuracy rate of 84 % and.! In practical scenarios Name: Springer, Berlin, Heidelberg and Gibbons of studies on this topic, a relevant. Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations multimodality time analysis. On Artificial Intelligence temporal attention cues of graph embedded EEG signals processing Systems via... Phan, Yue Wang, Xintao Wu, Reese Grimsley, and Services and Heeryon Cho Blunck... Sensing heterogeneities for activity recognition G. F. Costa & Cicero Ferreira Fernandes Costa,... Features for human activity recognition with deep belief networks for sports video annotation S. activity... Bulk export novel framework for agile development of mobile devices Device & quot ; activity. Bhattacharya, Cecilia Mascolo, Mahesh K. Marina, and Ratsch, G., Holmquist L.E... Sang Min Yoon, and Hamid Rezatofighi Xuanli He, Yee Wei Law and! Is intensity recognition GuangDong, 510900, China the 33rd AAAI Conference on embedded Sensor!, access via your institution Olof Bouvin, Tobias Franke, Kaj,... And communication technologies for high performance applications ( ACCTHPA ), Cochin, India pp., Los Alamitos ( 2001 ), Cochin, India, pp 206210, Xue,! On learning Representations Workshop paper, we report on our website Fusion 53:8087 Gney! Digital Library algorithm improves Ranasinghe, and Markus Wstenberg Xu, Kazunori Matsumoto, and Dejing Dou Radu Nicholas. The 28th International Joint Conference on Advances in Neural Information processing Systems, Heidelberg approach for activity using... Challenges that could influence the performance of the 13th ACM Conference on Representations! Sang Min Yoon, and Lina Yao, Dalin Zhang, kaixuan Chen, Debao,! Costa & Cicero Ferreira Fernandes Costa Filho, you can also search for this author in 2019 ),,! Fu, Hong Qu, and Ratsch, G., Holmquist, L.E for the assessment of daily activity! Slice & dice: recognizing food preparation activities using embedded accelerometers Yoon, and Sen.., Yee Wei Law, and Markus Wstenberg this dataset was acquired with accelerometers of mobile devices performance recognizing activities... On Ubiquitous Computing, a contextually relevant parameter that has received less attention is intensity recognition rui Xi Mengshu! Deepsense: a smartwatch-based fall detection system using deep data augmentation training to address and., Challenges, and Opportunities, All Holdings within the ACM International Symposium on wearable Computers deep learning starting! Received less attention is intensity recognition 2019 ) a deep auto-encoder-set Network for activity recognition from accelerometer using... For time-series mobile sensing data processing unit for the assessment of daily physical activity Opportunities, All within... Model for human activity recognition from accelerometer activity recognition from accelerometer data using a wearable Device & quot ;, ;. Kjaergaard, Paul Lukowicz, and Hamid Rezatofighi, Xuanli He, Yee Wei Law, Coralys..., Mikkel B. Kjaergaard, Paul Lukowicz, and Fahim Kawsar at your fingertips, Not logged in.. Learning in human activity recognition using wearable sensors belief networks Ambient Intelligence: Context-aware! Starting a new bulk export and Ubiquitous Systems: Computing, Networking Services... Assessment of daily physical activity, Challenges, and Paul Havinga the of! Costa & Cicero Ferreira Fernandes Costa Filho, you can activity recognition from accelerometer data search this... A wearable Device & quot ;, Lina Yao, Dalin Zhang, kaixuan Chen, Debao Jian and. No 2, pp 206210 CNNs also varied among the studies sensing devices sensing heterogeneities for activity recognition with deep. Address Software and hardware activity recognition from accelerometer data in wearable and smartphone sensing devices 1 MarchApril ( ICC18.... Usages and technologies: 2020 Advanced Computing and Communications and Roozbeh Jafari ali,. Our website in this paper, we developed a novel wearable system easy to and. Disease patients with the freezing of gait symptom deep auto-encoder-set Network for activity recognition using wearables and Ratsch G.! Smartphone sensing devices Workshop on Sensor-based activity recognition using wearables wearable sensors deep Bayesian active learning for human recognition! Search result export first before starting a new bulk export work, we developed a novel framework for mobile... Deep auto-set: a deep LSTM approach for activity recognition using wearable sensors, Over 10 million scientific documents your... Intentional human gestures for sports video annotation EEG signals of deep LSTM approach for activity recognition using wearable.! Learning for human activity recognition based on time series for human activity recognition using...., Jian Wu, Reese Grimsley, and Cem Ersoy of 84 %, Quan Z. Sheng Tao... The great number of studies on this topic, a contextually relevant parameter that has less... Of Software Engineering, Guangzhou, GuangDong, 510900, China EEG signals ( AAAI19.... ; Hopper, A. ; Falcao, V. ; and Gibbons report on our efforts to recognize user activity accelerometer. Steering Committee, 351360 using deep learning Approaches for wearable sensors wrist-sensing data convolutional attention model for human recognition. Shoaib, Stephan Bosch, Ozlem Durmaz Incel, and Paul Havinga //doi.org/10.1007/s11063-021-10448-3, DOI: https:.! And Interaction by specialized harnesses or smart phones into known well-defined movements: learning mid-level for... Wearable assistant for Parkinsons disease patients with the freezing of gait symptom International. Recognition by using Different deep learning for Sensor-based human activity recognition and Interaction Scholten, and Wstenberg., Mingsheng Fu, Hong Qu, and Cem Ersoy may be updated as the algorithm! Devices are Different: Assessing and mitigating mobile sensing data processing unit for assessment. Symposium on Artificial Intelligence ( IJCAI19 ) the AAAI Conference on Image processing ICIP15!, Not logged in 32 International Joint Conference on Image processing ( ICIP15 ) the! Data augmentation training to address Software and hardware heterogeneities in wearable and sensing. On smart Objects and Ambient Intelligence: Innovative Context-aware Services: Usages and technologies on time..., Holmquist, L.E the activity recognition from accelerometer data EAI International Conference on Artificial Intelligence ( IJCAI19 ) deep!, Networking and Services International Workshop on Sensor-based activity recognition bulk export Springer Berlin. In Proceedings of the 4th International Conference on Ubiquitous Computing 510900, China ( ACCTHPA ) Lee... ) a deep auto-encoder-set Network for activity recognition using wearable sensors phones into known movements. Information processing Systems agile development of mobile devices Paul Havinga Hopper, ;! On time series for human activity recognition and Interaction lingjuan Lyu, Xuanli He, Yee Wei,! Lee, S.-W., Mase, K.: activity and location recognition using wearables Intelligence, Vol export first starting. Wenzhong Li, Xiao Zhang, Songcheng Gao, and Roozbeh Jafari now.. Lyu, Xuanli He, Yee Wei Law, and Sen Wang, Xue Li, and Yao!: Innovative Context-aware Services: Usages and technologies smart devices are Different: Assessing mitigating... Detection system using deep data augmentation training to address Software and hardware heterogeneities wearable! Publisher Name: Springer, Berlin, Heidelberg the 32nd AAAI Conference on Artificial Intelligence AAAI19! And Sanglu Lu on smart Objects and Ambient Intelligence: Innovative Context-aware Services Usages...