Pub Date : 2019-10-01DOI: 10.1109/wincom47513.2019.8942540
A. Maach, J. Alami, E. E. Mazoudi
About 339 million people worldwide suffer from asthma, one of the most common chronic diseases among children and adults. The World Asthma Burden Report 2018 reveals that 1,000 people die of asthma every day, which is of great concern because many of these deaths are preventable in an early stage of asthma, especially in low- and middle-income countries where the majority of people do not have access to high quality medical care and medicines. Recently, the use of fog-based health care support systems has proven to be an effective solution for continuous remote monitoring of patient's health, with the benefits of a high quality of life for patients and disease control. In this paper, a framework based on fog and the Internet of Things is proposed to assess the severity of asthma and prevent the risk of asthma exacerbation in this regard, an artificial neural network has been used. Experimental results reveal a high level of accuracy in predicting the risk of asthma exacerbation, and alerts are sent to patients and caregivers in order to control the asthma disease.
{"title":"A fog-driven IoT e-Health framework to monitor and control Asthma Exacerbation","authors":"A. Maach, J. Alami, E. E. Mazoudi","doi":"10.1109/wincom47513.2019.8942540","DOIUrl":"https://doi.org/10.1109/wincom47513.2019.8942540","url":null,"abstract":"About 339 million people worldwide suffer from asthma, one of the most common chronic diseases among children and adults. The World Asthma Burden Report 2018 reveals that 1,000 people die of asthma every day, which is of great concern because many of these deaths are preventable in an early stage of asthma, especially in low- and middle-income countries where the majority of people do not have access to high quality medical care and medicines. Recently, the use of fog-based health care support systems has proven to be an effective solution for continuous remote monitoring of patient's health, with the benefits of a high quality of life for patients and disease control. In this paper, a framework based on fog and the Internet of Things is proposed to assess the severity of asthma and prevent the risk of asthma exacerbation in this regard, an artificial neural network has been used. Experimental results reveal a high level of accuracy in predicting the risk of asthma exacerbation, and alerts are sent to patients and caregivers in order to control the asthma disease.","PeriodicalId":222207,"journal":{"name":"2019 International Conference on Wireless Networks and Mobile Communications (WINCOM)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125389124","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 : 2019-10-01DOI: 10.1109/wincom47513.2019.8942493
{"title":"[Copyright notice]","authors":"","doi":"10.1109/wincom47513.2019.8942493","DOIUrl":"https://doi.org/10.1109/wincom47513.2019.8942493","url":null,"abstract":"","PeriodicalId":222207,"journal":{"name":"2019 International Conference on Wireless Networks and Mobile Communications (WINCOM)","volume":"482 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122625820","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}
Traffic light detection and classification represent a major issue for autonomous driving. Although a number of works have been published on this topic, providing a real-time processing solution is still a challenging task. In this paper, we show, by experimenting three models, namely “Faster R-CNN”, “R-FCN” and “SSD” on and two datasets, namely “Bosch Small Traffic Light Dataset” and “Lisa Traffic Light Dataset”, that we can achieve a higher accuracy while reducing the detection and recognition time. In order to improve the overall performance and take the best score of the trained models, we used the ensembling modeling technique. The obtained results outperform the state-of-the-art.
{"title":"Real Time Traffic Light Detection and Classification using Deep Learning","authors":"Zakaria Ennahhal, Ismail Berrada, Khalid Fardousse","doi":"10.1109/wincom47513.2019.8942446","DOIUrl":"https://doi.org/10.1109/wincom47513.2019.8942446","url":null,"abstract":"Traffic light detection and classification represent a major issue for autonomous driving. Although a number of works have been published on this topic, providing a real-time processing solution is still a challenging task. In this paper, we show, by experimenting three models, namely “Faster R-CNN”, “R-FCN” and “SSD” on and two datasets, namely “Bosch Small Traffic Light Dataset” and “Lisa Traffic Light Dataset”, that we can achieve a higher accuracy while reducing the detection and recognition time. In order to improve the overall performance and take the best score of the trained models, we used the ensembling modeling technique. The obtained results outperform the state-of-the-art.","PeriodicalId":222207,"journal":{"name":"2019 International Conference on Wireless Networks and Mobile Communications (WINCOM)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134178989","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 : 2019-10-01DOI: 10.1109/wincom47513.2019.8942589
Chaimae Ouchicha, O. Ammor, M. Meknassi
The segmentation of magnetic resonance imaging (MRI) is an essential step for many applications in medical fields. The detection of the tumor region and the precise recognition of the size and location of the tumor play an important role in the diagnosis. This is a very difficult task because of the complex structure of the brain and the complexity of tumor size. Several approaches have been proposed to help a better visualization of the appearance and severity of the tumor concerned. In this paper, we compare the performance of five fuzzy segmentation methods and we apply them on medical imaging on the one hand to identify the tumor area and on the other hand to determine the algorithm that gives a better calculation time. The comparison is based on the segmentation of a database of three MRI images of the brain.
{"title":"Unsupervised Brain Tumor Segmentation from Magnetic Resonance Images","authors":"Chaimae Ouchicha, O. Ammor, M. Meknassi","doi":"10.1109/wincom47513.2019.8942589","DOIUrl":"https://doi.org/10.1109/wincom47513.2019.8942589","url":null,"abstract":"The segmentation of magnetic resonance imaging (MRI) is an essential step for many applications in medical fields. The detection of the tumor region and the precise recognition of the size and location of the tumor play an important role in the diagnosis. This is a very difficult task because of the complex structure of the brain and the complexity of tumor size. Several approaches have been proposed to help a better visualization of the appearance and severity of the tumor concerned. In this paper, we compare the performance of five fuzzy segmentation methods and we apply them on medical imaging on the one hand to identify the tumor area and on the other hand to determine the algorithm that gives a better calculation time. The comparison is based on the segmentation of a database of three MRI images of the brain.","PeriodicalId":222207,"journal":{"name":"2019 International Conference on Wireless Networks and Mobile Communications (WINCOM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131075882","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 : 2019-10-01DOI: 10.1109/wincom47513.2019.8942469
Mourad Jbene, Ahmed Drissi El Maliani, M. Hassouni
Texture is a fundamental characteristic of many types of images, especially those with significant rotation, scale illumination, and viewpoint change. Texture image classification is one of the challenging problems that have various applications such as remote sensing, material recognition, and computer-aided medical diagnosis, etc. Various Computer vision techniques have been used. More recently, Deep learning architectures demonstrated impressive results. This paper aims to investigate combining two feature extraction methods: Handcrafted-based and CNN-based in a two-stream neural network architecture. We believe that Statistical features could enhance the performance of the CNN architecture, especially in the case of small datasets. To test our approach we used two challenging datasets, the Describable Textures Dataset (DTD) and Flicker Material Database (FMD). Results showed that our two-stream neural network which has an image as a first stream and a statistical feature vector as a second stream achieve better results than a Convolutional neural network achieved with just the RGB image as input. The Xception network [9] combined with SIFT-FV demonstrated an accuracy superiority for both datasets.
{"title":"Fusion of Convolutional Neural Network and Statistical Features for Texture classification","authors":"Mourad Jbene, Ahmed Drissi El Maliani, M. Hassouni","doi":"10.1109/wincom47513.2019.8942469","DOIUrl":"https://doi.org/10.1109/wincom47513.2019.8942469","url":null,"abstract":"Texture is a fundamental characteristic of many types of images, especially those with significant rotation, scale illumination, and viewpoint change. Texture image classification is one of the challenging problems that have various applications such as remote sensing, material recognition, and computer-aided medical diagnosis, etc. Various Computer vision techniques have been used. More recently, Deep learning architectures demonstrated impressive results. This paper aims to investigate combining two feature extraction methods: Handcrafted-based and CNN-based in a two-stream neural network architecture. We believe that Statistical features could enhance the performance of the CNN architecture, especially in the case of small datasets. To test our approach we used two challenging datasets, the Describable Textures Dataset (DTD) and Flicker Material Database (FMD). Results showed that our two-stream neural network which has an image as a first stream and a statistical feature vector as a second stream achieve better results than a Convolutional neural network achieved with just the RGB image as input. The Xception network [9] combined with SIFT-FV demonstrated an accuracy superiority for both datasets.","PeriodicalId":222207,"journal":{"name":"2019 International Conference on Wireless Networks and Mobile Communications (WINCOM)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124544007","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 : 2019-10-01DOI: 10.1109/wincom47513.2019.8942547
S. B. Alaoui, E. Tissir, N. Chaibi
Mitigating the effect of Distributed Denial of Service (DDoS) attacks in wired/wireless networks is a problem of extreme importance. The present paper investigates this problem and proposes a secure AQM to encounter the effects of DDoS attacks on queue's router. The employed method relies on modelling the TCP/AQM system subjected to different DoS attack rate where the resulting closed-loop system is expressed as new Markovian Jump Linear System (MJLS). Sufficient delay-dependent conditions which guarantee the syntheses of a stabilizing control for the closed-loop system with a guaranteed cost J* are derived. Finally, a numerical example is displayed.
{"title":"Modelling, analysis and design of active queue management to mitigate the effect of denial of service attack in wired/wireless network","authors":"S. B. Alaoui, E. Tissir, N. Chaibi","doi":"10.1109/wincom47513.2019.8942547","DOIUrl":"https://doi.org/10.1109/wincom47513.2019.8942547","url":null,"abstract":"Mitigating the effect of Distributed Denial of Service (DDoS) attacks in wired/wireless networks is a problem of extreme importance. The present paper investigates this problem and proposes a secure AQM to encounter the effects of DDoS attacks on queue's router. The employed method relies on modelling the TCP/AQM system subjected to different DoS attack rate where the resulting closed-loop system is expressed as new Markovian Jump Linear System (MJLS). Sufficient delay-dependent conditions which guarantee the syntheses of a stabilizing control for the closed-loop system with a guaranteed cost J* are derived. Finally, a numerical example is displayed.","PeriodicalId":222207,"journal":{"name":"2019 International Conference on Wireless Networks and Mobile Communications (WINCOM)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116978630","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 : 2019-10-01DOI: 10.1109/wincom47513.2019.8942518
Hazim A. Abdulsada, S. Sharma, Huma Razzaq
An omnidirectional antenna has a non-directional pattern; however, for some applications, it is necessary to focus on a specific direction. An antenna can focus its radiation to a particular direction in space is characterized by directivity. This project aims to design, simulate, analyse and compare between Dipole and Patch antennas array (Di-Patch) for high-speed wireless communication systems. The antenna is a crucial component which transmits and receives radio signals. Two common types of antennas usually used are proposed in this paper. The performance is compared between the dipole antenna array and the patch antenna array taking into account the radiation pattern, directivity and radiation angles for a typical at 2.4 GHz.
{"title":"Di-Patch Antenna Array Comparison","authors":"Hazim A. Abdulsada, S. Sharma, Huma Razzaq","doi":"10.1109/wincom47513.2019.8942518","DOIUrl":"https://doi.org/10.1109/wincom47513.2019.8942518","url":null,"abstract":"An omnidirectional antenna has a non-directional pattern; however, for some applications, it is necessary to focus on a specific direction. An antenna can focus its radiation to a particular direction in space is characterized by directivity. This project aims to design, simulate, analyse and compare between Dipole and Patch antennas array (Di-Patch) for high-speed wireless communication systems. The antenna is a crucial component which transmits and receives radio signals. Two common types of antennas usually used are proposed in this paper. The performance is compared between the dipole antenna array and the patch antenna array taking into account the radiation pattern, directivity and radiation angles for a typical at 2.4 GHz.","PeriodicalId":222207,"journal":{"name":"2019 International Conference on Wireless Networks and Mobile Communications (WINCOM)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121909076","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 : 2019-10-01DOI: 10.1109/wincom47513.2019.8942395
Nabila Azdad, Mohamed el Boukhari
Recently, the applicability of IEEE 802.15.4 standard over Wireless Body Area Networks (WBANs) has attracted increasing interest due to some of its key features such as energy efficiency, scalability and design flexibility. However, it is unable to support high data rate applications (>250 Kbps), whereas the overall traffic load in a WBAN may vary over a wide range. Since the operation of this norm depends on different MAC parameters, it will be useful to understand how these parameters affect the performance of the deployed networks, and if it is possible to improve the performance of this norm under high data rates conditions just by manipulating the configuration of MAC parameters, which form the focus of this paper.
{"title":"Performance analysis of the beacon-enabled operation of IEEE 802.15.4 under WBANs","authors":"Nabila Azdad, Mohamed el Boukhari","doi":"10.1109/wincom47513.2019.8942395","DOIUrl":"https://doi.org/10.1109/wincom47513.2019.8942395","url":null,"abstract":"Recently, the applicability of IEEE 802.15.4 standard over Wireless Body Area Networks (WBANs) has attracted increasing interest due to some of its key features such as energy efficiency, scalability and design flexibility. However, it is unable to support high data rate applications (>250 Kbps), whereas the overall traffic load in a WBAN may vary over a wide range. Since the operation of this norm depends on different MAC parameters, it will be useful to understand how these parameters affect the performance of the deployed networks, and if it is possible to improve the performance of this norm under high data rates conditions just by manipulating the configuration of MAC parameters, which form the focus of this paper.","PeriodicalId":222207,"journal":{"name":"2019 International Conference on Wireless Networks and Mobile Communications (WINCOM)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132612893","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 : 2019-10-01DOI: 10.1109/wincom47513.2019.8942486
Yifei Sun, Hang Zou, S. Lasaulce, M. Kieffer, L. Saludjian
The conventional approach to pre-process data for compression is to apply transforms such as the Fourier, the Karhunen-Loeve, or wavelet transforms. One drawback from adopting such an approach is that it is independent of the use of the compressed data, which may induce significant optimality losses when measured in terms of final utility (instead of being measured in terms of distortion). We therefore revisit this paradigm by tayloring the data pre-processing operation to the utility function of the decision-making entity using the compressed (and therefore noisy) data. More specifically, the utility function consists of an Lp-norm, which is very relevant in the area of smart grids. Both a linear and a non-linear use-oriented transforms are designed and compared with conventional data pre-processing techniques, showing that the impact of compression noise can be significantlv reduced.
{"title":"A New Approach of Data Pre-processing for Data Compression in Smart Grids: Invited Paper","authors":"Yifei Sun, Hang Zou, S. Lasaulce, M. Kieffer, L. Saludjian","doi":"10.1109/wincom47513.2019.8942486","DOIUrl":"https://doi.org/10.1109/wincom47513.2019.8942486","url":null,"abstract":"The conventional approach to pre-process data for compression is to apply transforms such as the Fourier, the Karhunen-Loeve, or wavelet transforms. One drawback from adopting such an approach is that it is independent of the use of the compressed data, which may induce significant optimality losses when measured in terms of final utility (instead of being measured in terms of distortion). We therefore revisit this paradigm by tayloring the data pre-processing operation to the utility function of the decision-making entity using the compressed (and therefore noisy) data. More specifically, the utility function consists of an Lp-norm, which is very relevant in the area of smart grids. Both a linear and a non-linear use-oriented transforms are designed and compared with conventional data pre-processing techniques, showing that the impact of compression noise can be significantlv reduced.","PeriodicalId":222207,"journal":{"name":"2019 International Conference on Wireless Networks and Mobile Communications (WINCOM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133609705","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 : 2019-10-01DOI: 10.1109/wincom47513.2019.8942569
Aicha Dridi, Chérifa Boucetta, Abubakar Yau Alhassan, Hassine Moungla, H. Afifi, H. Labiod
Electrical vehicular (EV) energy management is a promising trend. Forecasting vehicular trajectories and delay is crucial for EV energy management. The presented work is devoted to the study and the application of deep learning techniques on specific road trajectories. First, exhaustive deep learning algorithms are considered. Second, road traces are converted to time series. Then, delays and road trajectories are analyzed. In fact, we consider two Recurrent Neural Networks (RNN): LSTM (Long Short Term Memory) and GRU (Gated Recurrent Units). Neural Networks are adapted and trained on 60 days of real urban traffic of Rome in Italy. We calculate the Loss function for both machine learning techniques which is defined by mean square error (MSE) and Root mean square error (RMSE). Experimental results demonstrate that both LSTM and GRU are adequate for the context of EV in terms of route trajectory and delay prediction.
{"title":"Deep Learning Approaches for Electrical Vehicular Mobility Management: Invited Paper","authors":"Aicha Dridi, Chérifa Boucetta, Abubakar Yau Alhassan, Hassine Moungla, H. Afifi, H. Labiod","doi":"10.1109/wincom47513.2019.8942569","DOIUrl":"https://doi.org/10.1109/wincom47513.2019.8942569","url":null,"abstract":"Electrical vehicular (EV) energy management is a promising trend. Forecasting vehicular trajectories and delay is crucial for EV energy management. The presented work is devoted to the study and the application of deep learning techniques on specific road trajectories. First, exhaustive deep learning algorithms are considered. Second, road traces are converted to time series. Then, delays and road trajectories are analyzed. In fact, we consider two Recurrent Neural Networks (RNN): LSTM (Long Short Term Memory) and GRU (Gated Recurrent Units). Neural Networks are adapted and trained on 60 days of real urban traffic of Rome in Italy. We calculate the Loss function for both machine learning techniques which is defined by mean square error (MSE) and Root mean square error (RMSE). Experimental results demonstrate that both LSTM and GRU are adequate for the context of EV in terms of route trajectory and delay prediction.","PeriodicalId":222207,"journal":{"name":"2019 International Conference on Wireless Networks and Mobile Communications (WINCOM)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123245337","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：