{"type":"ScholarlyArticle","title":"Bridging Cross-Tasks Gap for Cognitive Assessment via Fine-Grained Domain Adaptation","authors":[{"name":"Yingwei Zhang","slug":"yingwei-zhang","given":"Yingwei","family":"Zhang","affiliation":"Beijing Key Laboratory of Mobile Computing and Pervasive Device , Institute of Computing Technology , Chinese Academy of Sciences; University of Chinese Academy of Sciences"},{"name":"Yiqiang Chen","slug":"yiqiang-chen","given":"Yiqiang","family":"Chen","affiliation":"Beijing Key Laboratory of Mobile Computing and Pervasive Device , Institute of Computing Technology , Chinese Academy of Sciences; University of Chinese Academy of Sciences; Peng Cheng Laboratory"},{"name":"Hanchao Yu","slug":"hanchao-yu","given":"Hanchao","family":"Yu","affiliation":"Beijing Key Laboratory of Mobile Computing and Pervasive Device , Institute of Computing Technology , Chinese Academy of Sciences"},{"name":"Zeping Lv","slug":"zeping-lv","given":"Zeping","family":"Lv","affiliation":"Beijing Key Laboratory of Rehabilitation Technical Aids for Old-Age Disability , National Research Center for Rehabilitation Technical Aids"},{"name":"Qing Li","slug":"qing-li","given":"Qing","family":"Li","affiliation":"School of Biological Science and Medical Engineering , Beihang University"},{"name":"Xiaodong Yang","slug":"xiaodong-yang","given":"Xiaodong","family":"Yang","affiliation":"Beijing Key Laboratory of Mobile Computing and Pervasive Device , Institute of Computing Technology , Chinese Academy of Sciences; University of Chinese Academy of Sciences"}],"abstract":"Discriminating pathologic cognitive decline from the expected decline of normal aging is an important research topic for elderly care and health monitoring. However, most cognitive assessment methods only work when data distributions of the training set and testing set are consistent. Enabling existing cognitive assessment models to adapt to the data in new cognitive assessment tasks is a significant challenge. In this paper, we propose a novel domain adaptation method, namely the Fine-Grained Adaptation Random Forest (FAT), to bridge the cognitive assessment gap when the data distribution is changed. FAT is composed of two essential parts 1) information gain based model evaluation strategy (IGME) and 2) domain adaptation tree growing mechanism (DATG). IGME is used to evaluate every individual tree, and DATG is used to transfer the source model to the target domain. To evaluate the performance of FAT, we conduct experiments in real clinical environments. Experimental results demonstrate that FAT is significantly more accurate and efficient compared with other state-of-the-art methods.","doi":"10.24963/ijcai.2020/597","url":"https://ijcai.org/proceedings/2020/597","pdf":"https://ijcai.org/proceedings/2020/0597.pdf","markdown":"https://ijcai.org/proceedings/2020/597.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/597","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Special track on AI for CompSust and Human well-being","track":"Special track on AI for CompSust and Human well-being","number":597,"pages":{"first":4330,"last":4337},"keywords":["Machine Learning: Transfer, Adaptation, Multi-task Learning","Humans and AI: Cognitive Modeling","Humans and AI: Cognitive Systems","Humans and AI: Human-Computer Interaction"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24527/file_24527.m3u8","length_sec":271,"provider":"hls"}],"references":[{"position":1,"raw":"[Banerjee et al., 2018] Imon Banerjee, Alexis Crawley, Mythili Bhethanabotla, Heike E Daldrup-Link, and Daniel L Rubin. Transfer learning on fused multiparamet- ric mr images for classifying histopathological subtypes of rhabdomyosarcoma. Computerized Medical Imaging and Graphics, 65:167-175, 2018.","title":"Transfer learning on fused multiparametric mr images for classifying histopathological subtypes of rhabdomyosarcoma","authors":"Imon Banerjee, Alexis Crawley, Mythili Bhethanabotla, Heike E Daldrup-Link, Daniel L Rubin","year":"2018","venue":"Computerized Medical Imaging and Graphics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2018] Yiqiang Chen, Chunyu Hu, Bin Hu, Lisha Hu, Han Yu, and Chunyan Miao. Inferring cog- nitive wellness from motor patterns. IEEE Transactions on Knowledge and Data Engineering, 30(12):2340-2353, 2018.","title":"Inferring cognitive wellness from motor patterns","authors":"Yiqiang Chen, Chunyu Hu, Bin Hu, Lisha Hu, Han Yu, Chunyan Miao","year":"2018","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Gao et al., 2020] Fei Gao, Hyunsoo Yoon, Teresa Wu, and Xianghua Chu. A feature transfer enabled multi-task deep learning model on medical imaging. Expert Systems with Applications, 143:112957, 2020.","title":"A feature transfer enabled multi-task deep learning model on medical imaging","authors":"Fei Gao, Hyunsoo Yoon, Teresa Wu, Xianghua Chu","year":"2020","venue":"Expert Systems with Applications","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Garre-Olmo et al., 2017] Josep Garre-Olmo, Marcos Faúndez-Zanuy, Karmele López-de Ipiña, Laia Calvó- Perxas, and Oriol Turró-Garriga. Kinematic and pressure features of handwriting and drawing: preliminary re- sults between patients with mild cognitive impairment, alzheimer disease and healthy controls. Current Alzheimer research, 14(9):960-968, 2017.","title":"Karmele López-de Ipiña, Laia Calvó-Perxas, and Oriol Turró-Garriga. Kinematic and pressure features of handwriting and drawing: preliminary results between patients with mild cognitive impairment, alzheimer disease and healthy controls","authors":"Garre-Olmo","year":"2017","venue":"Current Alzheimer research","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gong et al., 2012] Boqing Gong, Yuan Shi, Fei Sha, and Kristen Grauman. Geodesic flow kernel for unsupervised domain adaptation. pages 2066-2073, 2012.","title":"Geodesic flow kernel for unsupervised domain adaptation","authors":"Gong","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hu et al., 2018] Chunyu Hu, Yiqiang Chen, Xiaohui Peng, Han Yu, Chenlong Gao, and Lisha Hu. A novel feature in- cremental learning method for sensor-based activity recog- nition. IEEE Transactions on Knowledge and Data Engi- neering, 31(6):1038-1050, 2018.","title":"A novel feature incremental learning method for sensor-based activity recognition","authors":"Chunyu Hu, Yiqiang Chen, Xiaohui Peng, Han Yu, Chenlong Gao, Lisha Hu","year":"2018","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kermany et al., 2018] Daniel S Kermany, Michael Gold- baum, Wenjia Cai, Carolina CS Valentim, Huiying Liang, Sally L Baxter, Alex McKeown, Ge Yang, Xiaokang Wu, Fangbing Yan, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172(5):1122-1131, 2018.","title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","authors":"Michael Daniel S Kermany, Wenjia Goldbaum, Carolina Cs Cai, Huiying Valentim, Sally L Liang, Alex Baxter, Ge Mckeown, Xiaokang Yang, Fangbing Wu, Yan","year":"2018","venue":"Cell","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Khatami et al., 2018] Amin Khatami, Morteza Babaie, Hamid R Tizhoosh, Abbas Khosravi, Thanh Nguyen, and Saeid Nahavandi. A sequential search-space shrinking us- ing cnn transfer learning and a radon projection pool for medical image retrieval. Expert Systems with Application- s, 100:224-233, 2018.","title":"A sequential search-space shrinking using cnn transfer learning and a radon projection pool for medical image retrieval","authors":"Amin Khatami, Morteza Babaie, Abbas Hamid R Tizhoosh, Thanh Khosravi, Saeid Nguyen, Nahavandi","year":"2018","venue":"Expert Systems with Applications","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Long et al., 2018] Mingsheng Long, Yue Cao, Zhangjie Cao, Jianmin Wang, and Michael I Jordan. Transfer- able representation learning with deep adaptation network- s. IEEE transactions on pattern analysis and machine in- telligence, 41(12):3071-3085, 2018.","title":"Transferable representation learning with deep adaptation networks","authors":"Mingsheng Long, Yue Cao, Zhangjie Cao, Jianmin Wang, Michael I Jordan","year":"2018","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Mathiowetz et al., 1985] Virgil G Mathiowetz, Gloria Vol- land, Nancy Kashman, and Karen Weber. Adult norms for the box and block test of manual dexterity. American Journal of Occupational Therapy, 39(6):386-391, 1985.","title":"Adult norms for the box and block test of manual dexterity","authors":"Gloria Virgil G Mathiowetz, Nancy Volland, Karen Kashman, Weber","year":"1985","venue":"American Journal of Occupational Therapy","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Montero-Odasso et al., 2009] Manuel Montero-Odasso, Howard Bergman, Natalie A Phillips, Chek H Wong, Nadia Sourial, and Howard Chertkow. Dual-tasking and gait in people with mild cognitive impairment. the effect of working memory. BMC geriatrics, 9(1):41, 2009.","title":"Dual-tasking and gait in people with mild cognitive impairment. the effect of working memory","authors":"Manuel Montero-Odasso, Howard Bergman, Natalie A Phillips, Chek H Wong, Nadia Sourial, Howard Chertkow","year":"2009","venue":"BMC geriatrics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Organization and others, 2017] World Health Organization et al. Global action plan on the public health response to dementia 2017-2025. 2017.","title":"al. Global action plan on the public health response to dementia","authors":null,"year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Pan and Yang, 2010] Sinno Jialin Pan and Qiang Yang. A survey on transfer learning. IEEE Transactions on Knowl- edge and Data Engineering, 22(10):1345-1359, 2010.","title":"A survey on transfer learning","authors":"Jialin Sinno, Qiang Pan, Yang","year":"2010","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Pan et al., 2011] Sinno Jialin Pan, Ivor W Tsang, James T Kwok, and Qiang Yang. Domain adaptation via transfer component analysis. IEEE Transactions on Neural Net- works, 22(2):199-210, 2011.","title":"Domain adaptation via transfer component analysis","authors":"Ivor W Sinno Jialin Pan, James T Tsang, Qiang Kwok, Yang","year":"2011","venue":"IEEE Transactions on Neural Networks","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Segev et al., 2017] Noam Segev, Maayan Harel, Shie Man- nor, Koby Crammer, and Ran Elyaniv. Learn on source, re- fine on target: A model transfer learning framework with random forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(9):1811-1824, 2017.","title":"Learn on source, refine on target: A model transfer learning framework with random forests","authors":"Segev","year":"2017","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Swati et al., 2019] Zar Nawab Khan Swati, Qinghua Zhao, Muhammad Kabir, Farman Ali, Zakir Ali, Saeed Ahmed, and Jianfeng Lu. Brain tumor classification for mr im- ages using transfer learning and fine-tuning. Computerized Medical Imaging and Graphics, 75:34-46, 2019.","title":"Brain tumor classification for mr images using transfer learning and fine-tuning","authors":"Zar Nawab, Khan Swati, Qinghua Zhao, Muhammad Kabir, Farman Ali, Zakir Ali, Saeed Ahmed, Jianfeng Lu","year":"2019","venue":"Computerized Medical Imaging and Graphics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Tian et al., 2019] Feng Tian, Xiangmin Fan, Junjun Fan, Yicheng Zhu, Jing Gao, Dakuo Wang, Xiaojun Bi, and Hongan Wang. What can gestures tell?: Detecting mo- tor impairment in early parkinson's from common touch gestural interactions. page 83, 2019.","title":"What can gestures tell?: Detecting motor impairment in early parkinson's from common touch gestural interactions","authors":"Feng Tian, Xiangmin Fan, Junjun Fan, Yicheng Zhu, Jing Gao, Dakuo Wang, Xiaojun Bi, Hongan Wang","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Utgoff, 1989] Paul E Utgoff. Incremental induction of deci- sion trees. Machine Learning, 4(2):161-186, 1989.","title":"Incremental induction of decision trees","authors":"Paul E Utgoff","year":"1989","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wang et al., 2018] Jindong Wang, Yiqiang Chen, Lisha Hu, Xiaohui Peng, and S Yu Philip. Stratified transfer learning for cross-domain activity recognition. In 2018 IEEE Inter- national Conference on Pervasive Computing and Com- munications (PerCom), pages 1-10. IEEE, 2018.","title":"Stratified transfer learning for cross-domain activity recognition","authors":"Jindong Wang, Yiqiang Chen, Lisha Hu, Xiaohui Peng, S Yu, Philip","year":"2018","venue":"2018 IEEE International Conference on Pervasive Computing and Communications (PerCom)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[WHO, 2019] World Health Organization WHO. Demen- tia. https://www.who.int/en/news-room/fact-sheets/detail/ dementia, 2019. Accessed September 19, 2019.","title":"World Health Organization WHO. Dementia","authors":"Who","year":"2019","venue":null,"doi":null,"url":"https://www.who.int/en/news-room/fact-sheets/detail/dementia,2019","internal_url":null},{"position":21,"raw":"[Yu et al., 2017] Yuhai Yu, Hongfei Lin, Jiana Meng, Xi- aocong Wei, Hai Guo, and Zhehuan Zhao. Deep trans- fer learning for modality classification of medical im- ages. Information-an International Interdisciplinary Jour- nal, 8(3):91, 2017.","title":"Deep transfer learning for modality classification of medical images","authors":"Yuhai Yu, Hongfei Lin, Jiana Meng, Xiaocong Wei, Hai Guo, Zhehuan Zhao","year":"2017","venue":"Information-an International Interdisciplinary Journal","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhang et al., 2020a] Yingwei Zhang, Yiqaing Chen, Han- chao Yu, Xiaodong Yang, and Wang Lu. Learning effec- tive spatial-temporal features for semg armband based ges- ture recognition. IEEE Internet of Things Journal, 2020.","title":"Learning effective spatial-temporal features for semg armband based gesture recognition","authors":"Zhang","year":"2020","venue":"IEEE Internet of Things Journal","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhang et al., 2020b] Yingwei Zhang, Yiqiang Chen, Han- chao Yu, Xiaodong Yang, and Wang Lu. Dual layer transfer learning for semg-based user-independent gesture recognition. Personal and Ubiquitous Computing, pages 1-12, 2020.","title":"Dual layer transfer learning for semg-based user-independent gesture recognition","authors":"Zhang","year":"2020","venue":"Personal and Ubiquitous Computing","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}