Pub Date : 2017-10-01DOI: 10.1109/UEMCON.2017.8249006
A. Odeh, Eman Abdelfattah
Wireless sensor networks are becoming increasingly the essential part of the digital world. Target tracking system is a significant part of wireless sensor networks. It has its own advantages and challenges. In this paper, a new Tree-Based target-tracking algorithm is proposed, by employing the minimum traffic rate to reduce the time and energy consumption. The proposed algorithm consists of four phases that create a tree structure from undirected and connected graph. It reduces the communication cost, overcomes message-flooding problem, maximizes the life time for each node to maximize the overall life time of the network.
{"title":"A new tree target tracking algorithm in WSNs","authors":"A. Odeh, Eman Abdelfattah","doi":"10.1109/UEMCON.2017.8249006","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249006","url":null,"abstract":"Wireless sensor networks are becoming increasingly the essential part of the digital world. Target tracking system is a significant part of wireless sensor networks. It has its own advantages and challenges. In this paper, a new Tree-Based target-tracking algorithm is proposed, by employing the minimum traffic rate to reduce the time and energy consumption. The proposed algorithm consists of four phases that create a tree structure from undirected and connected graph. It reduces the communication cost, overcomes message-flooding problem, maximizes the life time for each node to maximize the overall life time of the network.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130483445","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249043
Jimmy Liranzo, T. Hayajneh
Consumers have overwhelmingly adopted the use of Internet of Things (IoT) inside their homes, these devices are connected to the internet sending and receiving data 24/7, a security breach or privacy exposure from one of these devices could lead to more nightmares than horror movies. These have lead us to review the current capabilities of Cloud-Based IP Cameras, its existing security and privacy issues affecting these devices. We present an analysis of the main privacy and security concerns currently affecting thousands of consumers IP Cameras globally, the uncertainty of not knowing what happens to your data when is stored in the Cloud and propose set of recommendations to help protect consumer's IoT devices in the intimacy of their home. Stop those nightmares before they happen because there is no peace of mind knowing an unknown person may be watching your children baby monitor and tracking all your movement inside your home. Although there are still challenges to address, is better to be an educated consumer who knows and understand the risk of these devices and take measures to prevent unwanted exposure.
{"title":"Security and privacy issues affecting cloud-based IP camera","authors":"Jimmy Liranzo, T. Hayajneh","doi":"10.1109/UEMCON.2017.8249043","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249043","url":null,"abstract":"Consumers have overwhelmingly adopted the use of Internet of Things (IoT) inside their homes, these devices are connected to the internet sending and receiving data 24/7, a security breach or privacy exposure from one of these devices could lead to more nightmares than horror movies. These have lead us to review the current capabilities of Cloud-Based IP Cameras, its existing security and privacy issues affecting these devices. We present an analysis of the main privacy and security concerns currently affecting thousands of consumers IP Cameras globally, the uncertainty of not knowing what happens to your data when is stored in the Cloud and propose set of recommendations to help protect consumer's IoT devices in the intimacy of their home. Stop those nightmares before they happen because there is no peace of mind knowing an unknown person may be watching your children baby monitor and tracking all your movement inside your home. Although there are still challenges to address, is better to be an educated consumer who knows and understand the risk of these devices and take measures to prevent unwanted exposure.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124611481","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249008
Fatima Salahdine, Hassan El Ghazi
This paper describes a real time spectrum scanning method using software defined radio (SDR) units to perform and evaluate the wideband spectrum occupancy survey. The proposed method is based on compressive sensing in order to reduce the scanning time as the conventional spectrum scanning requires a great deal of processing time. It consists of performing spectrum scanning on the compressed measurements through the compressive sensing framework. Energy, autocorrelation, and Euclidean distance based sensing techniques were used to perform the spectrum sensing on the compressed signals instead of the entire signals. Also, an SNR estimation technique is used to enhance the scanning performance. The results of the experiments were analyzed and compared in terms of processing time, number of sensed channels, SNR, occupancy, detection rate, and false detection rate. Through analyzing the results, the proposed method is faster than the conventional spectrum scanning.
{"title":"A real time spectrum scanning technique based on compressive sensing for cognitive radio networks","authors":"Fatima Salahdine, Hassan El Ghazi","doi":"10.1109/UEMCON.2017.8249008","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249008","url":null,"abstract":"This paper describes a real time spectrum scanning method using software defined radio (SDR) units to perform and evaluate the wideband spectrum occupancy survey. The proposed method is based on compressive sensing in order to reduce the scanning time as the conventional spectrum scanning requires a great deal of processing time. It consists of performing spectrum scanning on the compressed measurements through the compressive sensing framework. Energy, autocorrelation, and Euclidean distance based sensing techniques were used to perform the spectrum sensing on the compressed signals instead of the entire signals. Also, an SNR estimation technique is used to enhance the scanning performance. The results of the experiments were analyzed and compared in terms of processing time, number of sensed channels, SNR, occupancy, detection rate, and false detection rate. Through analyzing the results, the proposed method is faster than the conventional spectrum scanning.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127100141","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8248987
K. Salah
In this paper and for the first time, a novel chaotic maps algorithm is proposed to be used in hardware on-chip security for real-time embedded systems. The aim is to cipher the original program rom by changing the contents and the locations of the original data to ban extracting designs of secure IPs. As we know, many strong ciphers have been applied widely, such as DES, AES and RSA. But most of them cannot be directly used to encrypt real-time embedded systems because their encryption speed is not fast enough and they are computationally intensive. So, in this work we present a fast chaotic-based encryption algorithm which is suitable for real-time embedded systems in terms of performance, area and power efficiency. To illustrate the effectiveness of the proposed algorithm, numerical simulations are presented. Moreover, the proposed chaotic algorithm is implemented using RTL-design. The proposed encryption gives 64 bits of encrypted data per clock cycle. The hardware implementation results give a synthesis clock frequency of 400 MHz and a throughput of 3.2 Gbps while using low area. This makes the proposed algorithm suitable for embedded systems. The RTL implementation results match the Matlab simulation results. The strong structural complexity of our proposed algorithm makes it difficult to predict the key and make it able to resist exhaustive attack, statistical attack and differential attack. All these features show that our proposed algorithm is very suitable for hardware on-chip security for real-time embedded systems. An exhaustive cryptanalysis was completed, allowing us to conclude that the system is secure. Moreover, it is cost-effective solution.
{"title":"Real time embedded system IPs protection using chaotic maps","authors":"K. Salah","doi":"10.1109/UEMCON.2017.8248987","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8248987","url":null,"abstract":"In this paper and for the first time, a novel chaotic maps algorithm is proposed to be used in hardware on-chip security for real-time embedded systems. The aim is to cipher the original program rom by changing the contents and the locations of the original data to ban extracting designs of secure IPs. As we know, many strong ciphers have been applied widely, such as DES, AES and RSA. But most of them cannot be directly used to encrypt real-time embedded systems because their encryption speed is not fast enough and they are computationally intensive. So, in this work we present a fast chaotic-based encryption algorithm which is suitable for real-time embedded systems in terms of performance, area and power efficiency. To illustrate the effectiveness of the proposed algorithm, numerical simulations are presented. Moreover, the proposed chaotic algorithm is implemented using RTL-design. The proposed encryption gives 64 bits of encrypted data per clock cycle. The hardware implementation results give a synthesis clock frequency of 400 MHz and a throughput of 3.2 Gbps while using low area. This makes the proposed algorithm suitable for embedded systems. The RTL implementation results match the Matlab simulation results. The strong structural complexity of our proposed algorithm makes it difficult to predict the key and make it able to resist exhaustive attack, statistical attack and differential attack. All these features show that our proposed algorithm is very suitable for hardware on-chip security for real-time embedded systems. An exhaustive cryptanalysis was completed, allowing us to conclude that the system is secure. Moreover, it is cost-effective solution.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":"1943 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129170371","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249042
Neha A. Rana, T. Hayajneh
Certificate authorities (CAs) are responsible for providing security for the online world. Anytime an individual enters personal information on a website, there are possibilities of interception by a hacker to reveal this data. For this purpose, security has been implemented on websites to protect data from being stolen. Not all websites are secured, but those that do, display some sort of notification indicating that a trusted CA has confirmed its legitimacy through digital signatures and validation. These visual indicators are meant to raise awareness, and in turn, allow the user to make an educated decision to proceed or seize in their next move. This paper investigates the studies conducted on visual cues. The goal is to find out how often Internet users actually look at these security indicators and how useful they actually consider them to be. This paper also attempts to explore if notifications are being ignored and if so, is it intentional and why, or do they go unnoticed due to the lack of knowledge. While researching this topic, it was found that there are other tools such as add-ons available to enhance security notifications but the valued impact was not significant. The focus of this paper is to determine if people find these visual cues to be ambiguous or a nuisance and over time discontinue using them, or do they go unnoticed all together? The conclusions made from researching this area of security is to resolve user behavior speculations and standardize visual cues with a teachable component.
{"title":"Reevaluating the effectiveness of visual cues for website security","authors":"Neha A. Rana, T. Hayajneh","doi":"10.1109/UEMCON.2017.8249042","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249042","url":null,"abstract":"Certificate authorities (CAs) are responsible for providing security for the online world. Anytime an individual enters personal information on a website, there are possibilities of interception by a hacker to reveal this data. For this purpose, security has been implemented on websites to protect data from being stolen. Not all websites are secured, but those that do, display some sort of notification indicating that a trusted CA has confirmed its legitimacy through digital signatures and validation. These visual indicators are meant to raise awareness, and in turn, allow the user to make an educated decision to proceed or seize in their next move. This paper investigates the studies conducted on visual cues. The goal is to find out how often Internet users actually look at these security indicators and how useful they actually consider them to be. This paper also attempts to explore if notifications are being ignored and if so, is it intentional and why, or do they go unnoticed due to the lack of knowledge. While researching this topic, it was found that there are other tools such as add-ons available to enhance security notifications but the valued impact was not significant. The focus of this paper is to determine if people find these visual cues to be ambiguous or a nuisance and over time discontinue using them, or do they go unnoticed all together? The conclusions made from researching this area of security is to resolve user behavior speculations and standardize visual cues with a teachable component.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129214062","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249005
Thomas Haakensen, P. Thulasiraman
Tactical wireless sensor networks (WSNs) are deployed over a region of interest for mission centric operations. The sink node in a tactical WSN is the aggregation point of data processing. Due to its essential role in the network, the sink node is a high priority target for an attacker who wishes to disable a tactical WSN. This paper focuses on the mitigation of sink-node vulnerability in a tactical WSN. Specifically, we study the issue of protecting the sink node through a technique known as k-anonymity. To achieve k-anonymity, we use a specific routing protocol designed to work within the constraints of WSN communication protocols, specifically IEEE 802.15.4. We use and modify the Lightweight Ad hoc On-Demand Next Generation (LOADng) reactive-routing protocol to achieve anonymity. This modified LOADng protocol prevents an attacker from identifying the sink node without adding significant complexity to the regular sensor nodes. We simulate the modified LOADng protocol using a custom-designed simulator in MATLAB. We demonstrate the effectiveness of our protocol and also show some of the performance tradeoffs that come with this method.
{"title":"Enhancing sink node anonymity in tactical sensor networks using a reactive routing protocol","authors":"Thomas Haakensen, P. Thulasiraman","doi":"10.1109/UEMCON.2017.8249005","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249005","url":null,"abstract":"Tactical wireless sensor networks (WSNs) are deployed over a region of interest for mission centric operations. The sink node in a tactical WSN is the aggregation point of data processing. Due to its essential role in the network, the sink node is a high priority target for an attacker who wishes to disable a tactical WSN. This paper focuses on the mitigation of sink-node vulnerability in a tactical WSN. Specifically, we study the issue of protecting the sink node through a technique known as k-anonymity. To achieve k-anonymity, we use a specific routing protocol designed to work within the constraints of WSN communication protocols, specifically IEEE 802.15.4. We use and modify the Lightweight Ad hoc On-Demand Next Generation (LOADng) reactive-routing protocol to achieve anonymity. This modified LOADng protocol prevents an attacker from identifying the sink node without adding significant complexity to the regular sensor nodes. We simulate the modified LOADng protocol using a custom-designed simulator in MATLAB. We demonstrate the effectiveness of our protocol and also show some of the performance tradeoffs that come with this method.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122525544","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249071
Sai Manogna Duttaluri, Bijan Karimi
The purpose of introducing Software Defined Networking in the architecture of data centers is to streamline the management of the network devices. Although this reduces the workload of configuring each network device, it gives rise to new problems in terms of security and design of the data center. In this paper, we will go through each ideal design structure for conventional data centers suggested by Cisco and recommend how to introduce an SDN Controller into each of those scenarios.
{"title":"Security solutions and design scenarios for software defined data centers","authors":"Sai Manogna Duttaluri, Bijan Karimi","doi":"10.1109/UEMCON.2017.8249071","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249071","url":null,"abstract":"The purpose of introducing Software Defined Networking in the architecture of data centers is to streamline the management of the network devices. Although this reduces the workload of configuring each network device, it gives rise to new problems in terms of security and design of the data center. In this paper, we will go through each ideal design structure for conventional data centers suggested by Cisco and recommend how to introduce an SDN Controller into each of those scenarios.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116967680","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249000
Humaid Alshamsi, Veton Këpuska, H. Meng
Automated human emotion detection is a topic of significant interest in the field of computer vision. Over the past decade, much emphasis has been on using facial expression recognition (FER) to extract emotion from facial expressions. In this paper, the proposed system presents a novel method of facial recognition based on the cloud model, in combination with the traditional facial expression system. The process of predicting emotions from facial expression images contains several stages. The first stage of this system is the pre-processing stage, which is applied by detecting the face in images and then resizing the images. The second stage involves extracting features from facial expression images using Facial Landmarks and Center of Gravity (COG) feature extraction algorithms, which generate the training and testing datasets that contain the expressions of Anger, Disgust, Fear, Happiness, Neutrality, Sadness, and Surprise. Support Vector Machine (SVM) classifiers are then used for the classification stage in order to predict the emotion. In addition, a Confusion Matrix (CM) technique is used to evaluate the performance of these classifiers. The proposed system is tested on CK+, JAFFE, and KDEF databases. However, the proposed system achieved a prediction rate of 96.3% when Facial Landmarks and the Center of Gravity (COG)+SVM method are used.
{"title":"Automated facial expression recognition app development on smart phones using cloud computing","authors":"Humaid Alshamsi, Veton Këpuska, H. Meng","doi":"10.1109/UEMCON.2017.8249000","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249000","url":null,"abstract":"Automated human emotion detection is a topic of significant interest in the field of computer vision. Over the past decade, much emphasis has been on using facial expression recognition (FER) to extract emotion from facial expressions. In this paper, the proposed system presents a novel method of facial recognition based on the cloud model, in combination with the traditional facial expression system. The process of predicting emotions from facial expression images contains several stages. The first stage of this system is the pre-processing stage, which is applied by detecting the face in images and then resizing the images. The second stage involves extracting features from facial expression images using Facial Landmarks and Center of Gravity (COG) feature extraction algorithms, which generate the training and testing datasets that contain the expressions of Anger, Disgust, Fear, Happiness, Neutrality, Sadness, and Surprise. Support Vector Machine (SVM) classifiers are then used for the classification stage in order to predict the emotion. In addition, a Confusion Matrix (CM) technique is used to evaluate the performance of these classifiers. The proposed system is tested on CK+, JAFFE, and KDEF databases. However, the proposed system achieved a prediction rate of 96.3% when Facial Landmarks and the Center of Gravity (COG)+SVM method are used.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114278950","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8248991
Zakareya Lasefr, Sai Shiva V. N. R. Ayyalasomayajula, K. Elleithy
Epilepsy is a neurological disorder characterized by epileptic seizures. Epileptic seizure can be analyzed through the normal and abnormal activity of the brain. This abnormal activity can be observed only through the use of an efficient algorithm. The process of an efficient algorithm always uses signal processing in which an epileptic signal can be considered as an input signal. This paper introduces a technique to detect epileptic signal and to compare the characteristics of the brain signals at different stages. Our algorithm is based on signal processing techniques to detect epilepsy in the EEG signal. The signal processing starts with sampling the signal at 178.6 Hz so that the signal operating frequency follows oversampling criteria. The sampled signal is given to the designed filter so that the unwanted noise can be removed and the signal is ready to be decomposed. Then, the signal is decomposed at five different signal levels so that its frequency spectrum is reduced to less than 200 Hz using different wavelet filters at each level. In the feature extraction, we have used signal features rather than statistical features so that we can still rely on time domain and frequency domain features for an EEG signal. These features are classified using Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Artificial Neural Networks (ANN) to detect the epilepsy in the EEG signal. The results were demonstrated for different sets of brain signal that show the normal behavior of the brain signals and epileptic behavior of the signal with seizure. A comparison of our work with the present traditional methodologies proves that our algorithm is more efficient in detecting epilepsy.
{"title":"An efficient automated technique for epilepsy seizure detection using EEG signals","authors":"Zakareya Lasefr, Sai Shiva V. N. R. Ayyalasomayajula, K. Elleithy","doi":"10.1109/UEMCON.2017.8248991","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8248991","url":null,"abstract":"Epilepsy is a neurological disorder characterized by epileptic seizures. Epileptic seizure can be analyzed through the normal and abnormal activity of the brain. This abnormal activity can be observed only through the use of an efficient algorithm. The process of an efficient algorithm always uses signal processing in which an epileptic signal can be considered as an input signal. This paper introduces a technique to detect epileptic signal and to compare the characteristics of the brain signals at different stages. Our algorithm is based on signal processing techniques to detect epilepsy in the EEG signal. The signal processing starts with sampling the signal at 178.6 Hz so that the signal operating frequency follows oversampling criteria. The sampled signal is given to the designed filter so that the unwanted noise can be removed and the signal is ready to be decomposed. Then, the signal is decomposed at five different signal levels so that its frequency spectrum is reduced to less than 200 Hz using different wavelet filters at each level. In the feature extraction, we have used signal features rather than statistical features so that we can still rely on time domain and frequency domain features for an EEG signal. These features are classified using Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Artificial Neural Networks (ANN) to detect the epilepsy in the EEG signal. The results were demonstrated for different sets of brain signal that show the normal behavior of the brain signals and epileptic behavior of the signal with seizure. A comparison of our work with the present traditional methodologies proves that our algorithm is more efficient in detecting epilepsy.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121805693","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 : 2017-10-01DOI: 10.1109/UEMCON.2017.8249030
N. DiMaria, Kristen Tan, Bruno Salgado, Wenkang Su, Gregg Vesonder
This paper examines the issue of providing appropriate and attentive care to an elderly population that is increasing. Using a TurtleBot 2 and a NAO robot, experiments were developed to test a number of ways in which robots might be used to improve the health and safety of an elderly person within his/her own home. A number of simulations were run in the lab in order to generate insight regarding the viability of implementing these robots in a real world setting. The tasks that the robots attempted addressed the following goals: remind an elderly person that it is time to take medication; determine if no motion has been detected in the home for n hours, locate the elderly person, and contact emergency services if necessary; and guide the elderly person out of his home in case of fire/emergency.
{"title":"Eldercare robotics revolution-explaining robotics for eldercare","authors":"N. DiMaria, Kristen Tan, Bruno Salgado, Wenkang Su, Gregg Vesonder","doi":"10.1109/UEMCON.2017.8249030","DOIUrl":"https://doi.org/10.1109/UEMCON.2017.8249030","url":null,"abstract":"This paper examines the issue of providing appropriate and attentive care to an elderly population that is increasing. Using a TurtleBot 2 and a NAO robot, experiments were developed to test a number of ways in which robots might be used to improve the health and safety of an elderly person within his/her own home. A number of simulations were run in the lab in order to generate insight regarding the viability of implementing these robots in a real world setting. The tasks that the robots attempted addressed the following goals: remind an elderly person that it is time to take medication; determine if no motion has been detected in the home for n hours, locate the elderly person, and contact emergency services if necessary; and guide the elderly person out of his home in case of fire/emergency.","PeriodicalId":403890,"journal":{"name":"2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130548688","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：