Pub Date : 2019-09-30DOI: 10.5121/ijaia.2019.10502
Zlata Jelačić, Haris Velijević
With the advent and rising usage of Internet of Things (IoT) eco-systems, there is a consequent, parallel rise in opportunities where technology can find its place to improve a number of human conditions. However, this is nothing new - we have been perfecting the usage of tools to aid our daily living throughout history. The true evolution lies in the interaction between us and the tools we create. Tools are now smart devices, yielding an opportunity where human-device interaction is giving us the very knowledge on how to improve that particular synthesis. From improving our fitness to detecting bradycardia and response of traumatic brain injury patient, we have come to a point where we are able to gain actionable insight into a lot of aspects of our health and condition. This creates a certain autonomy in understanding the unique make-up of every single person, in addition to yielding information that can be used by health practitioners to help in diagnosis, determination of medical approach and right recovery and follow-up methods. All of this supported by two major factors: IoT platforms and Big Data Analysis (BDA). This paper takes a deep dive into exemplary set-up of IoT platform and BDA framework necessary to support the improvement of human condition. Our SmartLeg prosthetic device integrates advanced prosthetic and robotic technology with the state-of-the-art machine learning algorithms capable of adapting the working of the prosthesis to the optimal gait and power consumption patterns, which provide means to customize the device to a particular user.
{"title":"Application of Big Data Analysis and Internet of Things to the Intelligent Active Robotic Prosthesis for Transfemoral Amputees","authors":"Zlata Jelačić, Haris Velijević","doi":"10.5121/ijaia.2019.10502","DOIUrl":"https://doi.org/10.5121/ijaia.2019.10502","url":null,"abstract":"With the advent and rising usage of Internet of Things (IoT) eco-systems, there is a consequent, parallel rise in opportunities where technology can find its place to improve a number of human conditions. However, this is nothing new - we have been perfecting the usage of tools to aid our daily living throughout history. The true evolution lies in the interaction between us and the tools we create. Tools are now smart devices, yielding an opportunity where human-device interaction is giving us the very knowledge on how to improve that particular synthesis. From improving our fitness to detecting bradycardia and response of traumatic brain injury patient, we have come to a point where we are able to gain actionable insight into a lot of aspects of our health and condition. This creates a certain autonomy in understanding the unique make-up of every single person, in addition to yielding information that can be used by health practitioners to help in diagnosis, determination of medical approach and right recovery and follow-up methods. All of this supported by two major factors: IoT platforms and Big Data Analysis (BDA). This paper takes a deep dive into exemplary set-up of IoT platform and BDA framework necessary to support the improvement of human condition. Our SmartLeg prosthetic device integrates advanced prosthetic and robotic technology with the state-of-the-art machine learning algorithms capable of adapting the working of the prosthesis to the optimal gait and power consumption patterns, which provide means to customize the device to a particular user.","PeriodicalId":93188,"journal":{"name":"International journal of artificial intelligence & applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5121/ijaia.2019.10502","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41687172","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}
Pub Date : 2019-09-30DOI: 10.5121/ijaia.2019.10503
Manal Mostafa Ali
This paper presents an automatic method for extracting, processing, and analysis of customer opinions on Arabic social media. We present a four-step approach for mining of Arabic tweets. First, Natural Language Processing (NLP) with different types of analyses had performed. Second, we present an automatic and expandable lexicon for Arabic adjectives. The initial lexicon is built using 1350 adjectives as seeds from processing of different datasets in Arabic language. The lexicon is automatically expanded by collecting synonyms and morphemes of each word through Arabic resources and google translate. Third, emotional analysis was considered by two different methods; Machine Learning (ML) and rulebased method. Finally, Feature Selection (FS) is also considered to enhance the mining results. The experimental results reveal that the proposed method outperforms counterpart ones with an improvement margin of up to 4% using F-Measure.
{"title":"Customer Opinions Evaluation: A Case Study on Arabic Tweets","authors":"Manal Mostafa Ali","doi":"10.5121/ijaia.2019.10503","DOIUrl":"https://doi.org/10.5121/ijaia.2019.10503","url":null,"abstract":"This paper presents an automatic method for extracting, processing, and analysis of customer opinions on Arabic social media. We present a four-step approach for mining of Arabic tweets. First, Natural Language Processing (NLP) with different types of analyses had performed. Second, we present an automatic and expandable lexicon for Arabic adjectives. The initial lexicon is built using 1350 adjectives as seeds from processing of different datasets in Arabic language. The lexicon is automatically expanded by collecting synonyms and morphemes of each word through Arabic resources and google translate. Third, emotional analysis was considered by two different methods; Machine Learning (ML) and rulebased method. Finally, Feature Selection (FS) is also considered to enhance the mining results. The experimental results reveal that the proposed method outperforms counterpart ones with an improvement margin of up to 4% using F-Measure.","PeriodicalId":93188,"journal":{"name":"International journal of artificial intelligence & applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48644586","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}
Pub Date : 2019-09-30DOI: 10.5121/ijaia.2019.10501
Lin Zhang, Shengchao Li, Hao Xiong, Xiumin Diao, Ou Ma
Due to the rapidly increasing need of human-robot interaction (HRI), more intelligent robots are in demand. However, the vast majority of robots can only follow strict instructions, which seriously restricts their flexibility and versatility. A critical fact that strongly negates the experience of HRI is that robots cannot understand human intentions. This study aims at improving the robotic intelligence by training it to understand human intentions. Different from previous studies that recognizing human intentions from distinctive actions, this paper introduces a method to predict human intentions before a single action is completed. The experiment of throwing a ball towards designated targets are conducted to verify the effectiveness of the method. The proposed deep learning based method proves the feasibility of applying convolutional neural networks (CNN) under a novel circumstance. Experiment results show that the proposed CNN-vote method out competes three traditional machine learning techniques. In current context, the CNN-vote predictor achieves the highest testing accuracy with relatively less data needed.
{"title":"An Application of Convolutional Neural Networks on Human Intention Prediction","authors":"Lin Zhang, Shengchao Li, Hao Xiong, Xiumin Diao, Ou Ma","doi":"10.5121/ijaia.2019.10501","DOIUrl":"https://doi.org/10.5121/ijaia.2019.10501","url":null,"abstract":"Due to the rapidly increasing need of human-robot interaction (HRI), more intelligent robots are in demand. However, the vast majority of robots can only follow strict instructions, which seriously restricts their flexibility and versatility. A critical fact that strongly negates the experience of HRI is that robots cannot understand human intentions. This study aims at improving the robotic intelligence by training it to understand human intentions. Different from previous studies that recognizing human intentions from distinctive actions, this paper introduces a method to predict human intentions before a single action is completed. The experiment of throwing a ball towards designated targets are conducted to verify the effectiveness of the method. The proposed deep learning based method proves the feasibility of applying convolutional neural networks (CNN) under a novel circumstance. Experiment results show that the proposed CNN-vote method out competes three traditional machine learning techniques. In current context, the CNN-vote predictor achieves the highest testing accuracy with relatively less data needed.","PeriodicalId":93188,"journal":{"name":"International journal of artificial intelligence & applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5121/ijaia.2019.10501","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48747972","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}
Pub Date : 2019-09-30DOI: 10.5121/ijaia.2019.10506
Sherif Kamel Hussein Hassan Ratib
The main objective of this paper is to build Smart Brain Controlled wheelchair (SBCW) intended for patient of Amyotrophic Lateral Sclerosis (ALS). Brain control interface (BCI) gave solutions for a patients having a low rate of data exchange, alsoby using the BCIthe user should have the ability to meditate and tension to let the signal get received. Using the BCI continuously is very much exhausted for the patients, Theproposed system is trying to give all handicapped people and ALS patients the simplest way to let them have a life at least near to the normal life. The system will mainly depend on the Electroencephalogram (EEG) signalsand also on the Electromyography (EMG) signals to put the system in command and out of command. The system will interface with user through a tablet and it will be secured by sensors and tracking system to avoid any obstacle. The proposed system is safe and easily built with lower cost compared with other similar systems.
{"title":"A Smart Brain Controlled Wheelchair Based Microcontroller System","authors":"Sherif Kamel Hussein Hassan Ratib","doi":"10.5121/ijaia.2019.10506","DOIUrl":"https://doi.org/10.5121/ijaia.2019.10506","url":null,"abstract":"The main objective of this paper is to build Smart Brain Controlled wheelchair (SBCW) intended for patient of Amyotrophic Lateral Sclerosis (ALS). Brain control interface (BCI) gave solutions for a patients having a low rate of data exchange, alsoby using the BCIthe user should have the ability to meditate and tension to let the signal get received. Using the BCI continuously is very much exhausted for the patients, Theproposed system is trying to give all handicapped people and ALS patients the simplest way to let them have a life at least near to the normal life. The system will mainly depend on the Electroencephalogram (EEG) signalsand also on the Electromyography (EMG) signals to put the system in command and out of command. The system will interface with user through a tablet and it will be secured by sensors and tracking system to avoid any obstacle. The proposed system is safe and easily built with lower cost compared with other similar systems.","PeriodicalId":93188,"journal":{"name":"International journal of artificial intelligence & applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5121/ijaia.2019.10506","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46303793","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}
Pub Date : 2019-09-30DOI: 10.5121/ijaia.2019.10505
Maram.G Alaslni, Lamiaa A. Elrefaei
Iris is one of the common biometrics used for identity authentication. It has the potential to recognize persons with a high degree of assurance. Extracting effective features is the most important stage in the iris recognition system. Different features have been used to perform iris recognition system. A lot of them are based on hand-crafted features designed by biometrics experts. According to the achievement of deep learning in object recognition problems, the features learned by the Convolutional Neural Network (CNN) have gained great attention to be used in the iris recognition system. In this paper, we proposed an effective iris recognition system by using transfer learning with Convolutional Neural Networks. The proposed system is implemented by fine-tuning a pre-trained convolutional neural network (VGG-16) for features extracting and classification. The performance of the iris recognition system is tested on four public databases IITD, iris databases CASIA-Iris-V1, CASIA-Iris-thousand and, CASIA-Iris-Interval. The results show that the proposed system is achieved a very high accuracy rate.
{"title":"Transfer Learning with Convolutional Neural Networks for IRIS Recognition","authors":"Maram.G Alaslni, Lamiaa A. Elrefaei","doi":"10.5121/ijaia.2019.10505","DOIUrl":"https://doi.org/10.5121/ijaia.2019.10505","url":null,"abstract":"Iris is one of the common biometrics used for identity authentication. It has the potential to recognize persons with a high degree of assurance. Extracting effective features is the most important stage in the iris recognition system. Different features have been used to perform iris recognition system. A lot of them are based on hand-crafted features designed by biometrics experts. According to the achievement of deep learning in object recognition problems, the features learned by the Convolutional Neural Network (CNN) have gained great attention to be used in the iris recognition system. In this paper, we proposed an effective iris recognition system by using transfer learning with Convolutional Neural Networks. The proposed system is implemented by fine-tuning a pre-trained convolutional neural network (VGG-16) for features extracting and classification. The performance of the iris recognition system is tested on four public databases IITD, iris databases CASIA-Iris-V1, CASIA-Iris-thousand and, CASIA-Iris-Interval. The results show that the proposed system is achieved a very high accuracy rate.","PeriodicalId":93188,"journal":{"name":"International journal of artificial intelligence & applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5121/ijaia.2019.10505","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42556763","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}
Pub Date : 2019-09-30DOI: 10.5121/ijaia.2019.10504
Dali Wang, Ying Bai, David Hamblin
The goal of this research is to develop an algorithm to automatically classify measurement types from NASA’s airborne measurement data archive. The product has to meet specific metrics in term of accuracy, robustness and usability, as the initial decision-tree based development has shown limited applicability due to its resource intensive characteristics. We have developed an innovative solution that is much more efficient while offering comparable performance. Similar to many industrial applications, the data available are noisy and correlated; and there is a wide range of features that are associated with the type of measurement to be identified. The proposed algorithm uses a decision tree to select features and determine their weights.A weighted Naive Bayes is used due to the presence of highly correlated inputs. The development has been successfully deployed in an industrial scale, and the results show that the development is well-balanced in term of performance and resource requirements.
{"title":"A Hybrid Learning Algorithm in Automated Text Categorization of Legacy Data","authors":"Dali Wang, Ying Bai, David Hamblin","doi":"10.5121/ijaia.2019.10504","DOIUrl":"https://doi.org/10.5121/ijaia.2019.10504","url":null,"abstract":"The goal of this research is to develop an algorithm to automatically classify measurement types from NASA’s airborne measurement data archive. The product has to meet specific metrics in term of accuracy, robustness and usability, as the initial decision-tree based development has shown limited applicability due to its resource intensive characteristics. We have developed an innovative solution that is much more efficient while offering comparable performance. Similar to many industrial applications, the data available are noisy and correlated; and there is a wide range of features that are associated with the type of measurement to be identified. The proposed algorithm uses a decision tree to select features and determine their weights.A weighted Naive Bayes is used due to the presence of highly correlated inputs. The development has been successfully deployed in an industrial scale, and the results show that the development is well-balanced in term of performance and resource requirements.","PeriodicalId":93188,"journal":{"name":"International journal of artificial intelligence & applications","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41549516","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}
Pub Date : 2019-07-31DOI: 10.5121/IJAIA.2019.10401
V. Kamp, Jean Pierre Knust, R. Moratz, Kevin Stehn, Soeren Stoehrmann
Data mining enables an innovative, largely automatic meta-analysis of the relationship between political and economic geography analyses of crisis regions. As an example, the two approaches Global Conflict Risk Index (GCRI) and Fragile States Index (FSI) can be related to each other. The GCRI is a quantitative conflict risk assessment based on open source data and a statistical regression method developed by the Joint Research Centre of the European Commission. The FSI is based on a conflict assessment framework developed by The Fund for Peace in Washington, DC. In contrast to the quantitative GCRI, the FSI is essentially focused on qualitative data from systematic interviews with experts. Both approaches therefore have closely related objectives, but very different methodologies and data sources. It is therefore hoped that the two complementary approaches can be combined to form an even more meaningful meta-analysis, or that contradictions can be discovered, or that a validation of the approaches can be obtained if there are similarities. We propose an approach to automatic meta-analysis that makes use of machine learning (data mining). Such a procedure represents a novel approach in the meta-analysis of conflict risk analyses.
{"title":"Data Mining for Integration and Verification of Socio-Geographical Trend Statements in the Context of Conflict Risk","authors":"V. Kamp, Jean Pierre Knust, R. Moratz, Kevin Stehn, Soeren Stoehrmann","doi":"10.5121/IJAIA.2019.10401","DOIUrl":"https://doi.org/10.5121/IJAIA.2019.10401","url":null,"abstract":"Data mining enables an innovative, largely automatic meta-analysis of the relationship between political and economic geography analyses of crisis regions. As an example, the two approaches Global Conflict Risk Index (GCRI) and Fragile States Index (FSI) can be related to each other. The GCRI is a quantitative conflict risk assessment based on open source data and a statistical regression method developed by the Joint Research Centre of the European Commission. The FSI is based on a conflict assessment framework developed by The Fund for Peace in Washington, DC. In contrast to the quantitative GCRI, the FSI is essentially focused on qualitative data from systematic interviews with experts. Both approaches therefore have closely related objectives, but very different methodologies and data sources. It is therefore hoped that the two complementary approaches can be combined to form an even more meaningful meta-analysis, or that contradictions can be discovered, or that a validation of the approaches can be obtained if there are similarities. We propose an approach to automatic meta-analysis that makes use of machine learning (data mining). Such a procedure represents a novel approach in the meta-analysis of conflict risk analyses.","PeriodicalId":93188,"journal":{"name":"International journal of artificial intelligence & applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5121/IJAIA.2019.10401","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44960478","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}
Pub Date : 2019-07-31DOI: 10.5121/IJAIA.2019.10404
Santosh Giri, Basanta Joshi
Image classification is a popular machine learning based applications of deep learning. Deep learning techniques are very popular because they can be effectively used in performing operations on image data in large-scale. In this paper CNN model was designed to better classify images. We make use of feature extraction part of inception v3 model for feature vector calculation and retrained the classification layer with these feature vector. By using the transfer learning mechanism the classification layer of the CNN model was trained with 20 classes of Caltech101 image dataset and 17 classes of Oxford 17 flower image dataset. After training, network was evaluated with testing dataset images from Oxford 17 flower dataset and Caltech101 image dataset. The mean testing precision of the neural network architecture with Caltech101 dataset was 98 % and with Oxford 17 Flower image dataset was 92.27 %.
{"title":"Transfer Learning Based Image Visualization Using CNN","authors":"Santosh Giri, Basanta Joshi","doi":"10.5121/IJAIA.2019.10404","DOIUrl":"https://doi.org/10.5121/IJAIA.2019.10404","url":null,"abstract":"Image classification is a popular machine learning based applications of deep learning. Deep learning techniques are very popular because they can be effectively used in performing operations on image data in large-scale. In this paper CNN model was designed to better classify images. We make use of feature extraction part of inception v3 model for feature vector calculation and retrained the classification layer with these feature vector. By using the transfer learning mechanism the classification layer of the CNN model was trained with 20 classes of Caltech101 image dataset and 17 classes of Oxford 17 flower image dataset. After training, network was evaluated with testing dataset images from Oxford 17 flower dataset and Caltech101 image dataset. The mean testing precision of the neural network architecture with Caltech101 dataset was 98 % and with Oxford 17 Flower image dataset was 92.27 %.","PeriodicalId":93188,"journal":{"name":"International journal of artificial intelligence & applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5121/IJAIA.2019.10404","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45144980","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}
Pub Date : 2019-07-31DOI: 10.5121/IJAIA.2019.10405
Qili Chen, Bofan Liang, Jiuhe Wang
With an aging population that continues to grow, the protection and assistance of the older persons has become a very important issue. Fallsare the main safety problems of the elderly people, so it is very important to predict the falls. In this paper, a gait prediction method is proposed based on two kinds of LSTM. Firstly, the lumbar posture of the human body is measured by the acceleration gyroscope as the gait feature, and then the gait is predicted by the LSTM network. The experimental results show that the RMSE between the gait trend predicted by the method and the actual gait trend can be reached a level of 0.06 ± 0.01. And the Phased LSTM has a shorter training time. The proposed method can predict the gait trend well.
{"title":"A Comparative Study of LSTM and Phased LSTM for Gait Prediction","authors":"Qili Chen, Bofan Liang, Jiuhe Wang","doi":"10.5121/IJAIA.2019.10405","DOIUrl":"https://doi.org/10.5121/IJAIA.2019.10405","url":null,"abstract":"With an aging population that continues to grow, the protection and assistance of the older persons has become a very important issue. Fallsare the main safety problems of the elderly people, so it is very important to predict the falls. In this paper, a gait prediction method is proposed based on two kinds of LSTM. Firstly, the lumbar posture of the human body is measured by the acceleration gyroscope as the gait feature, and then the gait is predicted by the LSTM network. The experimental results show that the RMSE between the gait trend predicted by the method and the actual gait trend can be reached a level of 0.06 ± 0.01. And the Phased LSTM has a shorter training time. The proposed method can predict the gait trend well.","PeriodicalId":93188,"journal":{"name":"International journal of artificial intelligence & applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5121/IJAIA.2019.10405","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44902377","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}
Pub Date : 2019-07-31DOI: 10.5121/IJAIA.2019.10402
Jing Zhu, ShuoJin Li, Ruonan Ma, Jingwang Cheng
The development of convolutional neural networks(CNN) has provided a new tool to make classification and prediction of human's body motion. This project tends to predict the drop point of a ball thrown out by experimenters by classifying the motion of their body in the process of throwing. Kinect sensor v2 is used to record depth maps and the drop points are recorded by a square infrared induction module. Firstly, convolutional neural networks are made use of to put the data obtained from depth maps in and get the prediction of drop point according to experimenters' motion. Secondly, huge amount of data is used to train the networks of different structure, and a network structure that could provide high enough accuracy for drop point prediction is established. The network model and parameters are modified to improve the accuracy of the prediction algorithm. Finally, the experimental data is divided into a training group and a test group. The prediction results of test group reflect that the prediction algorithm effectively improves the accuracy of human motion perception.
{"title":"Motion Prediction Using Depth Information of Human Arm Based on Alexnet","authors":"Jing Zhu, ShuoJin Li, Ruonan Ma, Jingwang Cheng","doi":"10.5121/IJAIA.2019.10402","DOIUrl":"https://doi.org/10.5121/IJAIA.2019.10402","url":null,"abstract":"The development of convolutional neural networks(CNN) has provided a new tool to make classification and prediction of human's body motion. This project tends to predict the drop point of a ball thrown out by experimenters by classifying the motion of their body in the process of throwing. Kinect sensor v2 is used to record depth maps and the drop points are recorded by a square infrared induction module. Firstly, convolutional neural networks are made use of to put the data obtained from depth maps in and get the prediction of drop point according to experimenters' motion. Secondly, huge amount of data is used to train the networks of different structure, and a network structure that could provide high enough accuracy for drop point prediction is established. The network model and parameters are modified to improve the accuracy of the prediction algorithm. Finally, the experimental data is divided into a training group and a test group. The prediction results of test group reflect that the prediction algorithm effectively improves the accuracy of human motion perception.","PeriodicalId":93188,"journal":{"name":"International journal of artificial intelligence & applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.5121/IJAIA.2019.10402","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44241292","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}
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：