Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers最新文献
Air pollution has become one of the major threats to human health. Conventional approaches for air pollution monitoring use precise professional devices, but cannot achieve dense deployment due to high cost. Therefore, systems consisting of low-cost sensors are applied as a supplement to obtain fine-grained pollution information. In order to maintain the accuracy of these low-cost sensors, it is essential to calibrate them to minimize the impact from sensor drifts. Existing field calibration methods utilize the real-time data from spatially-adjacent official air quality stations as reference. However, the real-time reference is not always accessible under existing station deployment. In this paper, we propose the Robust Calibration approach using Historical data (RCH) for low-cost air quality sensors. Our method corrects the sensor drift by adapting sensitivity and offset based on pollutant's concentration distribution. Experiments on NO2 data from real-world deployment in Foshan, China show that RCH has the similar performance compared with existing field calibration methods using real-time and spatially-adjacent references. It demonstrates that RCH can improve the accuracy and consistency of low-cost air quality sensors without the help of real-time and nearby reference data.
{"title":"RCH","authors":"Guodong Li, R. Ma, Xinyu Liu, Yue Wang, Lin Zhang","doi":"10.1145/3410530.3414322","DOIUrl":"https://doi.org/10.1145/3410530.3414322","url":null,"abstract":"Air pollution has become one of the major threats to human health. Conventional approaches for air pollution monitoring use precise professional devices, but cannot achieve dense deployment due to high cost. Therefore, systems consisting of low-cost sensors are applied as a supplement to obtain fine-grained pollution information. In order to maintain the accuracy of these low-cost sensors, it is essential to calibrate them to minimize the impact from sensor drifts. Existing field calibration methods utilize the real-time data from spatially-adjacent official air quality stations as reference. However, the real-time reference is not always accessible under existing station deployment. In this paper, we propose the Robust Calibration approach using Historical data (RCH) for low-cost air quality sensors. Our method corrects the sensor drift by adapting sensitivity and offset based on pollutant's concentration distribution. Experiments on NO2 data from real-world deployment in Foshan, China show that RCH has the similar performance compared with existing field calibration methods using real-time and spatially-adjacent references. It demonstrates that RCH can improve the accuracy and consistency of low-cost air quality sensors without the help of real-time and nearby reference data.","PeriodicalId":7183,"journal":{"name":"Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73972553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sannara Ek, François Portet, P. Lalanda, Germán Vega
Pervasive computing promotes the integration of connected electronic devices in our living spaces in order to assist us through appropriate services. Two major developments have gained significant momentum recently: a better use of fog resources and the use of AI techniques. Specifically, interest in machine learning approaches for engineering applications has increased rapidly. This paradigm seems to fit the pervasive environment well. However, federated learning has been applied so far to specific services and remains largely conceptual. It needs to be tested extensively on pervasive services partially located in the fog. In this paper, we present experiments performed in the domain of Human Activity Recognition on smartphones in order to evaluate existing algorithms.
{"title":"Evaluation of federated learning aggregation algorithms: application to human activity recognition","authors":"Sannara Ek, François Portet, P. Lalanda, Germán Vega","doi":"10.1145/3410530.3414321","DOIUrl":"https://doi.org/10.1145/3410530.3414321","url":null,"abstract":"Pervasive computing promotes the integration of connected electronic devices in our living spaces in order to assist us through appropriate services. Two major developments have gained significant momentum recently: a better use of fog resources and the use of AI techniques. Specifically, interest in machine learning approaches for engineering applications has increased rapidly. This paradigm seems to fit the pervasive environment well. However, federated learning has been applied so far to specific services and remains largely conceptual. It needs to be tested extensively on pervasive services partially located in the fog. In this paper, we present experiments performed in the domain of Human Activity Recognition on smartphones in order to evaluate existing algorithms.","PeriodicalId":7183,"journal":{"name":"Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers","volume":"77 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83117103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Existing performance metrics assess classifiers on single granularity layer. Having multi-layer labels is also possible such as activity recognition datasets. Semantic annotations could be given with multiple granularity layers in these datasets e.g., activity and the current step within that activity like: cooking and taking ingredients from fridge. Recognizing both layers is important i.e., remote monitoring of patients with dementia. To evaluate a classifier for both layers concurrently, a new performance metric is required. However, it is not easy to design as there are many underlying issues: the relation between the layers and the impact of class imbalance. This work proposes a new metric for evaluating multi-layer labeled dataset considering the mentioned factors and is applied on two datasets. It is found that it can assess the performance of a model classifying activities at two different granularity layers and give more insightful results i.e. reflecting performance for each layer.
{"title":"MCoMat","authors":"S. S. Alia, P. Lago, Sozo Inoue","doi":"10.1145/3410530.3414364","DOIUrl":"https://doi.org/10.1145/3410530.3414364","url":null,"abstract":"Existing performance metrics assess classifiers on single granularity layer. Having multi-layer labels is also possible such as activity recognition datasets. Semantic annotations could be given with multiple granularity layers in these datasets e.g., activity and the current step within that activity like: cooking and taking ingredients from fridge. Recognizing both layers is important i.e., remote monitoring of patients with dementia. To evaluate a classifier for both layers concurrently, a new performance metric is required. However, it is not easy to design as there are many underlying issues: the relation between the layers and the impact of class imbalance. This work proposes a new metric for evaluating multi-layer labeled dataset considering the mentioned factors and is applied on two datasets. It is found that it can assess the performance of a model classifying activities at two different granularity layers and give more insightful results i.e. reflecting performance for each layer.","PeriodicalId":7183,"journal":{"name":"Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77277608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Arafat Rahman, Nazmun Nahid, I. Hassan, Md Atiqur Rahman Ahad
Nurse care activity recognition is a new challenging research field in human activity recognition (HAR) because unlike other activity recognition, it has severe class imbalance problem and intra-class variability depending on both the subject and the receiver. In this paper, we applied the Random Forest-based resampling method to solve the class imbalance problem in the Heiseikai data, nurse care activity dataset. This method consists of resampling, feature selection based on Gini impurity, and model training and validation with Stratified KFold cross-validation. By implementing the Random Forest classifier, we achieved 65.9% average cross-validation accuracy in classifying 12 activities conducted by nurses in both lab and real-life settings. Our team, "Britter Baire" developed this algorithmic pipeline for "The 2nd Nurse Care Activity Recognition Challenge Using Lab and Field Data".
{"title":"Nurse care activity recognition: using random forest to handle imbalanced class problem","authors":"Arafat Rahman, Nazmun Nahid, I. Hassan, Md Atiqur Rahman Ahad","doi":"10.1145/3410530.3414334","DOIUrl":"https://doi.org/10.1145/3410530.3414334","url":null,"abstract":"Nurse care activity recognition is a new challenging research field in human activity recognition (HAR) because unlike other activity recognition, it has severe class imbalance problem and intra-class variability depending on both the subject and the receiver. In this paper, we applied the Random Forest-based resampling method to solve the class imbalance problem in the Heiseikai data, nurse care activity dataset. This method consists of resampling, feature selection based on Gini impurity, and model training and validation with Stratified KFold cross-validation. By implementing the Random Forest classifier, we achieved 65.9% average cross-validation accuracy in classifying 12 activities conducted by nurses in both lab and real-life settings. Our team, \"Britter Baire\" developed this algorithmic pipeline for \"The 2nd Nurse Care Activity Recognition Challenge Using Lab and Field Data\".","PeriodicalId":7183,"journal":{"name":"Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91202911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vocabulary acquisition is the basis of learning a language, and using flashcards applications is a popular method for learners to memorize the meaning of unknown words. Unfortunately, this method alone is not effective for learners to remember the meaning of words when they appear in sentences. To solve this, we developed the Mobile Vocabulometer which allows users to acquire new vocabulary with context-based learning. Based on the correlation between comprehension and interests, we use the learning materials that adapt to users' interests and language skills. This system harnesses the power of the original Vocabulometer, and modifies it to be effective for mobile learning. An experiment on Japanese university students showed that, overall, learners achieved better results compared to using a simple flashcard application. This result indicates that this system provides a significant advantage over context-free learning systems.
{"title":"Mobile vocabulometer: a context-based learning mobile application to enhance English vocabulary acquisition","authors":"K. Yamaguchi, M. Iwata, Andrew W. Vargo, K. Kise","doi":"10.1145/3410530.3414406","DOIUrl":"https://doi.org/10.1145/3410530.3414406","url":null,"abstract":"Vocabulary acquisition is the basis of learning a language, and using flashcards applications is a popular method for learners to memorize the meaning of unknown words. Unfortunately, this method alone is not effective for learners to remember the meaning of words when they appear in sentences. To solve this, we developed the Mobile Vocabulometer which allows users to acquire new vocabulary with context-based learning. Based on the correlation between comprehension and interests, we use the learning materials that adapt to users' interests and language skills. This system harnesses the power of the original Vocabulometer, and modifies it to be effective for mobile learning. An experiment on Japanese university students showed that, overall, learners achieved better results compared to using a simple flashcard application. This result indicates that this system provides a significant advantage over context-free learning systems.","PeriodicalId":7183,"journal":{"name":"Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers","volume":"41 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79405187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Given the pandemic and the high air pollution in large parts of the world, masks have become ubiquitous. In this poster, we present our vision and work-in-progress (WIP) towards leveraging the ubiquity of masks for health sensing and persuasion. We envision masks to monitor health-related parameters such as i) temperature; ii) lung activity, among others. We also envision that retrofitting masks with sensors and display to show localized pollution can create awareness about air pollution. In this WIP, we present a smart mask, Naqaab1, that measures forced vital capacity (FVC) of the lung using a retrofitted microphone. We evaluated the measured lung parameter on eight persons using an Incentive Spirometer2 and found that our smart mask accurately measures incentive lung capacity. Naqaab also measures pollution exposure and indicates via different LED colours. We envision using such a system for eco feedback.
{"title":"Naqaab: towards health sensing and persuasion via masks","authors":"Rishiraj Adhikary, Tanmay Srivastava, Prerna Khanna, Aabhas Asit Senapati, Nipun Batra","doi":"10.1145/3410530.3414403","DOIUrl":"https://doi.org/10.1145/3410530.3414403","url":null,"abstract":"Given the pandemic and the high air pollution in large parts of the world, masks have become ubiquitous. In this poster, we present our vision and work-in-progress (WIP) towards leveraging the ubiquity of masks for health sensing and persuasion. We envision masks to monitor health-related parameters such as i) temperature; ii) lung activity, among others. We also envision that retrofitting masks with sensors and display to show localized pollution can create awareness about air pollution. In this WIP, we present a smart mask, Naqaab1, that measures forced vital capacity (FVC) of the lung using a retrofitted microphone. We evaluated the measured lung parameter on eight persons using an Incentive Spirometer2 and found that our smart mask accurately measures incentive lung capacity. Naqaab also measures pollution exposure and indicates via different LED colours. We envision using such a system for eco feedback.","PeriodicalId":7183,"journal":{"name":"Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78668340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The use of text-to-speech (TTS) technology to generate radio content is largely unexplored, despite the importance of radio, in particular in remote parts of the world where TTS offers a robust means of transforming existing data into media for low-literate audiences and those without regular internet access. Is synthetic speech able to meet the expectations of radio listeners and add value to community radio stations in remote areas? We present a preliminary analysis of the design and use of TTS applications in the context of two emerging community radio stations in rural Romania. We find that while the applications developed so far are generally perceived as useful for the running of the station, future work should focus on identifying additional use cases that add value beyond that of 'filling time' or simply replacing the need for a human voice.
{"title":"Implementing text-to-speech tools for community radio in remote regions of Romania","authors":"Kristen M. Scott, S. Ashby, R. Cibin","doi":"10.1145/3410530.3414410","DOIUrl":"https://doi.org/10.1145/3410530.3414410","url":null,"abstract":"The use of text-to-speech (TTS) technology to generate radio content is largely unexplored, despite the importance of radio, in particular in remote parts of the world where TTS offers a robust means of transforming existing data into media for low-literate audiences and those without regular internet access. Is synthetic speech able to meet the expectations of radio listeners and add value to community radio stations in remote areas? We present a preliminary analysis of the design and use of TTS applications in the context of two emerging community radio stations in rural Romania. We find that while the applications developed so far are generally perceived as useful for the running of the station, future work should focus on identifying additional use cases that add value beyond that of 'filling time' or simply replacing the need for a human voice.","PeriodicalId":7183,"journal":{"name":"Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88237054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kieran Woodward, E. Kanjo, David J. Brown, B. Inkster
Children can find it challenging to communicate their emotions especially when experiencing mental health challenges. Technological solutions may help children communicate digitally and receive support from one another as advances in networking and sensors enable the real-time transmission of physical interactions. In this work, we pursue the design of multiple tangible user interfaces designed for children containing multiple sensors and feedback actuators. Bluetooth is used to provide communication between Tangible Toys (TangToys) enabling peer to peer support groups to be developed and allowing feedback to be issued whenever other children are nearby. TangToys can provide a non-intrusive means for children to communicate their wellbeing through play.
{"title":"TangToys","authors":"Kieran Woodward, E. Kanjo, David J. Brown, B. Inkster","doi":"10.1145/3410530.3414375","DOIUrl":"https://doi.org/10.1145/3410530.3414375","url":null,"abstract":"Children can find it challenging to communicate their emotions especially when experiencing mental health challenges. Technological solutions may help children communicate digitally and receive support from one another as advances in networking and sensors enable the real-time transmission of physical interactions. In this work, we pursue the design of multiple tangible user interfaces designed for children containing multiple sensors and feedback actuators. Bluetooth is used to provide communication between Tangible Toys (TangToys) enabling peer to peer support groups to be developed and allowing feedback to be issued whenever other children are nearby. TangToys can provide a non-intrusive means for children to communicate their wellbeing through play.","PeriodicalId":7183,"journal":{"name":"Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers","volume":"59 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89074693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nature and outdoor open spaces are good for our mental and physical health; providing space for exercise, relaxation, socializing and exploring nature. Technology plays an important role in how people explore the outdoors, however, despite the prevalence of mobile technologies that promote outdoor mobility, they are often not accessible to people with disabilities. This PhD project explores technologies to promote nature connectedness in blind and partially sighted people. We have conducted formative studies exploring the needs of blind and partially sighted people and barriers that limit their experiences. The next phase of my research will focus on designing auditory augmented reality systems to augment the natural elements in open spaces which are presented to the user in real-time as they navigate the space. We aim to design, implement, and evaluate pervasive auditory augmented reality systems that enhance people's immersive experience and engagement with nature.
{"title":"Audio AR to support nature connectedness in people with visual disabilities","authors":"Maryam Bandukda, C. Holloway","doi":"10.1145/3410530.3414332","DOIUrl":"https://doi.org/10.1145/3410530.3414332","url":null,"abstract":"Nature and outdoor open spaces are good for our mental and physical health; providing space for exercise, relaxation, socializing and exploring nature. Technology plays an important role in how people explore the outdoors, however, despite the prevalence of mobile technologies that promote outdoor mobility, they are often not accessible to people with disabilities. This PhD project explores technologies to promote nature connectedness in blind and partially sighted people. We have conducted formative studies exploring the needs of blind and partially sighted people and barriers that limit their experiences. The next phase of my research will focus on designing auditory augmented reality systems to augment the natural elements in open spaces which are presented to the user in real-time as they navigate the space. We aim to design, implement, and evaluate pervasive auditory augmented reality systems that enhance people's immersive experience and engagement with nature.","PeriodicalId":7183,"journal":{"name":"Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers","volume":"96 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76009912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Keiichi Yaguchi, Kazukiyo Ikarigawa, R. Kawasaki, Wataru Miyazaki, Yuki Morikawa, Chihiro Ito, M. Shuzo, Eisaku Maeda
An activity recognition method developed by Team DSML-TDU for the Sussex-Huawei Locomotion-Transportation (SHL) recognition challenge was descrived. Since the 2018 challenge, our team has been developing human activity recognition models based on a convolutional neural network (CNN) using Fast Fourier Transform (FFT) spectrograms from mobile sensors. In the 2020 challenge, we developed our model to fit various users equipped with sensors in specific positions. Nine modalities of FFT spectrograms generated from the three axes of the linear accelerometer, gyroscope, and magnetic sensor data were used as input data for our model. First, we created a CNN model to estimate four retention positions (Bag, Hand, Hips, and Torso) from the training data and validation data. The provided test data was expected to from Hips. Next, we created another (pre-trained) CNN model to estimate eight activities from a large amount of user 1 training data (Hips). Then, this model was fine-tuned for different users by using the small amount of validation data for users 2 and 3 (Hips). Finally, an F-measure of 96.7% was obtained as a result of 5-fold-cross validation.
{"title":"Human activity recognition using multi-input CNN model with FFT spectrograms","authors":"Keiichi Yaguchi, Kazukiyo Ikarigawa, R. Kawasaki, Wataru Miyazaki, Yuki Morikawa, Chihiro Ito, M. Shuzo, Eisaku Maeda","doi":"10.1145/3410530.3414342","DOIUrl":"https://doi.org/10.1145/3410530.3414342","url":null,"abstract":"An activity recognition method developed by Team DSML-TDU for the Sussex-Huawei Locomotion-Transportation (SHL) recognition challenge was descrived. Since the 2018 challenge, our team has been developing human activity recognition models based on a convolutional neural network (CNN) using Fast Fourier Transform (FFT) spectrograms from mobile sensors. In the 2020 challenge, we developed our model to fit various users equipped with sensors in specific positions. Nine modalities of FFT spectrograms generated from the three axes of the linear accelerometer, gyroscope, and magnetic sensor data were used as input data for our model. First, we created a CNN model to estimate four retention positions (Bag, Hand, Hips, and Torso) from the training data and validation data. The provided test data was expected to from Hips. Next, we created another (pre-trained) CNN model to estimate eight activities from a large amount of user 1 training data (Hips). Then, this model was fine-tuned for different users by using the small amount of validation data for users 2 and 3 (Hips). Finally, an F-measure of 96.7% was obtained as a result of 5-fold-cross validation.","PeriodicalId":7183,"journal":{"name":"Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers","volume":"56 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77467663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：