The focus of user authentication is shifting from password based systems to biometrics based systems. The issue with biometrics is that they are susceptible to modifications and when attacked, can not be changed like a password. It is also required that a biometric trait used to access one system should not be used to access other systems. This paper proposes a multimodal solution where the iris of a person is modified using the minutia from the fingerprint image by treating the minutia as a watermark. The experimental results show the effectiveness of the proposed approach where the recognition rate after the watermarking process is only slightly decreased. The proposed approach satisfies the diversity requirement where a template stolen from one biometric based authentication system can not be used to access another system as the fingerprint minutia are watermarked in a unique way for every authentication system. The proposed approach also outperforms traditional biometric systems in-terms of execution time.
{"title":"Securing Biometric Authentication Through Multimodal Watermarking","authors":"Wadood Abdul","doi":"10.1109/AIMS.2015.85","DOIUrl":"https://doi.org/10.1109/AIMS.2015.85","url":null,"abstract":"The focus of user authentication is shifting from password based systems to biometrics based systems. The issue with biometrics is that they are susceptible to modifications and when attacked, can not be changed like a password. It is also required that a biometric trait used to access one system should not be used to access other systems. This paper proposes a multimodal solution where the iris of a person is modified using the minutia from the fingerprint image by treating the minutia as a watermark. The experimental results show the effectiveness of the proposed approach where the recognition rate after the watermarking process is only slightly decreased. The proposed approach satisfies the diversity requirement where a template stolen from one biometric based authentication system can not be used to access another system as the fingerprint minutia are watermarked in a unique way for every authentication system. The proposed approach also outperforms traditional biometric systems in-terms of execution time.","PeriodicalId":121874,"journal":{"name":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129096955","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 difficulties of data streams, i.e. Infinite length, the occurrence of concept-drift and the possible emergence of novel classes, are topics of high relevance in the field of recognition systems. To overcome all of these problems, the system should be updated continuously with new data while the amount of processing time should be kept small. We propose an incremental Parzen window kernel density estimator (IncPKDE) which addresses the problems of data streaming using a model that is insensitive to the training set size and has the ability to detect novelties within multi-class recognition systems. The results show that the IncPKDE approach has superior properties especially regarding processing time and that it is robust to wrongly labelled samples if used in a semi-supervised learning scenario.
{"title":"Incremental Learning and Novelty Detection of Gestures in a Multi-class System","authors":"Husam Al-Behadili, A. Grumpe, C. Wohler","doi":"10.1109/AIMS.2015.55","DOIUrl":"https://doi.org/10.1109/AIMS.2015.55","url":null,"abstract":"The difficulties of data streams, i.e. Infinite length, the occurrence of concept-drift and the possible emergence of novel classes, are topics of high relevance in the field of recognition systems. To overcome all of these problems, the system should be updated continuously with new data while the amount of processing time should be kept small. We propose an incremental Parzen window kernel density estimator (IncPKDE) which addresses the problems of data streaming using a model that is insensitive to the training set size and has the ability to detect novelties within multi-class recognition systems. The results show that the IncPKDE approach has superior properties especially regarding processing time and that it is robust to wrongly labelled samples if used in a semi-supervised learning scenario.","PeriodicalId":121874,"journal":{"name":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","volume":"108 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130533437","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}
Few companies in developing countries are now claiming to provide Smart Nano Grid Applications which can help the smart home residents get a reliable, cost effective and uninterrupted power supply. As the technology of Smart Nano Grid is an emerging technology comprising the features of Smart Grids and Nano Grids, no significant work has been done for providing guidance on acceptance testing procedures. As a result, these companies feel it complicated to test these applications from the user's perspective. Furthermore, the majority of the consumers doesn't have any criteria to determine whether or not accept the system. This paper presents a complete Acceptance Test Procedure to assist the companies developing Smart Nano Grid Applications to test these applications according to end user perspective.
{"title":"Designing Acceptance Test Procedures (ATPs) for Smart Nano Grid Applications","authors":"Kiran Choudhry, S. Khan","doi":"10.1109/AIMS.2015.49","DOIUrl":"https://doi.org/10.1109/AIMS.2015.49","url":null,"abstract":"Few companies in developing countries are now claiming to provide Smart Nano Grid Applications which can help the smart home residents get a reliable, cost effective and uninterrupted power supply. As the technology of Smart Nano Grid is an emerging technology comprising the features of Smart Grids and Nano Grids, no significant work has been done for providing guidance on acceptance testing procedures. As a result, these companies feel it complicated to test these applications from the user's perspective. Furthermore, the majority of the consumers doesn't have any criteria to determine whether or not accept the system. This paper presents a complete Acceptance Test Procedure to assist the companies developing Smart Nano Grid Applications to test these applications according to end user perspective.","PeriodicalId":121874,"journal":{"name":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124562291","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}
In undersea environment, development of low-cost communication module is highly important for dissemination of undersea wireless sensor networks. Some undersea wireless sensor network applications do not require high performance communication capability such as transmission distance. If the terrestrial low-cost communication module can be used in the undersea environment, it is possible to use the module in some undersea wireless sensor networks. In this paper, we evaluate the communication capability of a commercially available WiFi device in an undersea environment. In the experiment, we use a mobile access point as a sender node and an Android tablet as a receiver node. Through evaluations, we show that the transmission distance of WiFi device is around 0.1 m in an undersea environment. In addition, we evaluate a fish farm monitoring system based on WiFi modules through simulations.
{"title":"Experimental Evaluation of a WiFi Device in an Undersea Environment","authors":"Y. Taniguchi","doi":"10.1109/AIMS.2015.70","DOIUrl":"https://doi.org/10.1109/AIMS.2015.70","url":null,"abstract":"In undersea environment, development of low-cost communication module is highly important for dissemination of undersea wireless sensor networks. Some undersea wireless sensor network applications do not require high performance communication capability such as transmission distance. If the terrestrial low-cost communication module can be used in the undersea environment, it is possible to use the module in some undersea wireless sensor networks. In this paper, we evaluate the communication capability of a commercially available WiFi device in an undersea environment. In the experiment, we use a mobile access point as a sender node and an Android tablet as a receiver node. Through evaluations, we show that the transmission distance of WiFi device is around 0.1 m in an undersea environment. In addition, we evaluate a fish farm monitoring system based on WiFi modules through simulations.","PeriodicalId":121874,"journal":{"name":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129216621","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}
Launcelot C. De Guzman, Ryan Paolo C. Maglaque, Vianca May B. Torres, Simon Philippe A. Zapido, M. Cordel
There are several current systems developed to identify common skin lesions such as eczema that utilize image processing and most of these apply feature extraction techniques and machine learning algorithms. These systems extract the features from pre-processed images and use them for identifying the skin lesions through machine learning as the core. This paper presents the design and evaluation of a system that implements a multi-model, multi-level system using the Artificial Neural Network (ANN) architecture for eczema detection. In this work, multi-model system is defined as architecture with different models depending on the input characteristic. The outputs of these models are integrated by a decision layer, thus multi-level, which computes the probability of an eczema case. The resulting system has 68.37% average confidence level as opposed to the 63.01% of the single level, i.e. Single model, system in the actual testing of eczema versus non-eczema cases. Furthermore, the multi-model, multi-level design produces more stable models in the training phase wherein over fitting was reduced.
{"title":"Design and Evaluation of a Multi-model, Multi-level Artificial Neural Network for Eczema Skin Lesion Detection","authors":"Launcelot C. De Guzman, Ryan Paolo C. Maglaque, Vianca May B. Torres, Simon Philippe A. Zapido, M. Cordel","doi":"10.1109/AIMS.2015.17","DOIUrl":"https://doi.org/10.1109/AIMS.2015.17","url":null,"abstract":"There are several current systems developed to identify common skin lesions such as eczema that utilize image processing and most of these apply feature extraction techniques and machine learning algorithms. These systems extract the features from pre-processed images and use them for identifying the skin lesions through machine learning as the core. This paper presents the design and evaluation of a system that implements a multi-model, multi-level system using the Artificial Neural Network (ANN) architecture for eczema detection. In this work, multi-model system is defined as architecture with different models depending on the input characteristic. The outputs of these models are integrated by a decision layer, thus multi-level, which computes the probability of an eczema case. The resulting system has 68.37% average confidence level as opposed to the 63.01% of the single level, i.e. Single model, system in the actual testing of eczema versus non-eczema cases. Furthermore, the multi-model, multi-level design produces more stable models in the training phase wherein over fitting was reduced.","PeriodicalId":121874,"journal":{"name":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","volume":"319 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116230887","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}
I. Saad, Nur Husna Bais, C. Bun Seng, H. M. Zuhir, N. Bolong
Analysis of electromyogram (EMG) signal processing and its application to identify human muscle strength of rehabilitation purpose has been successfully carried out in this paper. Single channel EMG signal was obtained from human muscle using non-invasive electrodes and further process by signal acquisition circuit to get a suitable signal to be process. In the first part of signal acquisition, the amplification circuit for the small EMG signal has been design successfully. After amplification stage EMG signal was digitized through analogue and digital converter (ADC) then further process in microcontroller (ATmega328) for getting accurate EMG signal. Finally, the processed EMG signal was classified into 6 different levels in order to display the muscle strength level of the user. This EMG device can be used to help the weak person or an elderly to identity their strength level of muscle for clinical rehabilitation purpose.
{"title":"Electromyogram (EMG) Signal Processing Analysis for Clinical Rehabilitation Application","authors":"I. Saad, Nur Husna Bais, C. Bun Seng, H. M. Zuhir, N. Bolong","doi":"10.1109/AIMS.2015.76","DOIUrl":"https://doi.org/10.1109/AIMS.2015.76","url":null,"abstract":"Analysis of electromyogram (EMG) signal processing and its application to identify human muscle strength of rehabilitation purpose has been successfully carried out in this paper. Single channel EMG signal was obtained from human muscle using non-invasive electrodes and further process by signal acquisition circuit to get a suitable signal to be process. In the first part of signal acquisition, the amplification circuit for the small EMG signal has been design successfully. After amplification stage EMG signal was digitized through analogue and digital converter (ADC) then further process in microcontroller (ATmega328) for getting accurate EMG signal. Finally, the processed EMG signal was classified into 6 different levels in order to display the muscle strength level of the user. This EMG device can be used to help the weak person or an elderly to identity their strength level of muscle for clinical rehabilitation purpose.","PeriodicalId":121874,"journal":{"name":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","volume":"205 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123055401","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}
This study describes and demonstrates a new Model Recovery Anti-Windup scheme with a proportional-integral-derivative (PID) controller. PID control has been widely used in the industrial processes. However, if a control system has an integral element, the windup effect causes control system performance deterioration. To solve this problem, it is necessary to add an anti-windup (AW) compensator to the control system. In the proposed method, PID controller gain and feedback gain of an AW filter are obtained simultaneously using a linear matrix inequality method. Simulation results prove the proposed method to be robust against external disturbances and to provide better performance than previous AW strategy.
{"title":"Approach to New Model Recovery Anti-windup Scheme with PID Controller","authors":"Kazushi Kawamura, Y. Ishida","doi":"10.1109/AIMS.2015.41","DOIUrl":"https://doi.org/10.1109/AIMS.2015.41","url":null,"abstract":"This study describes and demonstrates a new Model Recovery Anti-Windup scheme with a proportional-integral-derivative (PID) controller. PID control has been widely used in the industrial processes. However, if a control system has an integral element, the windup effect causes control system performance deterioration. To solve this problem, it is necessary to add an anti-windup (AW) compensator to the control system. In the proposed method, PID controller gain and feedback gain of an AW filter are obtained simultaneously using a linear matrix inequality method. Simulation results prove the proposed method to be robust against external disturbances and to provide better performance than previous AW strategy.","PeriodicalId":121874,"journal":{"name":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122186420","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}
In this paper, we propose a method for online controller adjustment by a fictitious reference iterative tuning (FRIT) of a frequency domain using sliding discrete Fourier transform (DFT). We have extended the FRIT to correspond time delay and characteristic variation of a control object. A sliding DFT was used to correspond to the time delay of the controlled object. In addition, we have optimized the method using a recursive least-squares algorithm to determine the controller gains online. In this study, we utilized an algorithm that was designed in a two-degree-of-freedom (2DOF) control system. We have experimentally verified the effectiveness of the proposed method. The proposed method can correspond to the time delay of a controlled object. In addition, it can also correspond to characteristic variations of a control object.
{"title":"Controller Design by Frequency-Domain Fictitious Reference Iterative Tuning Using Sliding DFT","authors":"Nobutoshi Suwa, Y. Ishida","doi":"10.1109/AIMS.2015.42","DOIUrl":"https://doi.org/10.1109/AIMS.2015.42","url":null,"abstract":"In this paper, we propose a method for online controller adjustment by a fictitious reference iterative tuning (FRIT) of a frequency domain using sliding discrete Fourier transform (DFT). We have extended the FRIT to correspond time delay and characteristic variation of a control object. A sliding DFT was used to correspond to the time delay of the controlled object. In addition, we have optimized the method using a recursive least-squares algorithm to determine the controller gains online. In this study, we utilized an algorithm that was designed in a two-degree-of-freedom (2DOF) control system. We have experimentally verified the effectiveness of the proposed method. The proposed method can correspond to the time delay of a controlled object. In addition, it can also correspond to characteristic variations of a control object.","PeriodicalId":121874,"journal":{"name":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131926095","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}
This article describes our approach to designing a model matching controller based on a discrete-time active disturbance rejection control (ADRC). The ADRC is an effective control technique to achieve a high performance of the disturbance estimation or its compensation. In a conventional ADRC, the extended state observer (ESO) is used in order to estimate the plant state variables and the generalized perturbation which is composed of the plant with modeling error and a plant output-side disturbance. However, when the input-side disturbance is added to the plant, the steady-state error may occur in the control system. To solve this problem, the design method of the observer that simultaneously estimates the plant state variables, the generalized perturbation of the plant and the plant input-side disturbance is proposed. Furthermore, our proposed method is applied to the model matching control. In simulation studies, it is shown that the proposed method is effective for some plants. Furthermore, by applying the proposed method to a DC motor, the effectiveness of the method is confirmed.
{"title":"Model Matching Control Based on Discrete-Time Improved ADRC Considering Plant Input-Side Disturbance","authors":"R. Tanaka, T. Murakami, Y. Ishida","doi":"10.1109/AIMS.2015.40","DOIUrl":"https://doi.org/10.1109/AIMS.2015.40","url":null,"abstract":"This article describes our approach to designing a model matching controller based on a discrete-time active disturbance rejection control (ADRC). The ADRC is an effective control technique to achieve a high performance of the disturbance estimation or its compensation. In a conventional ADRC, the extended state observer (ESO) is used in order to estimate the plant state variables and the generalized perturbation which is composed of the plant with modeling error and a plant output-side disturbance. However, when the input-side disturbance is added to the plant, the steady-state error may occur in the control system. To solve this problem, the design method of the observer that simultaneously estimates the plant state variables, the generalized perturbation of the plant and the plant input-side disturbance is proposed. Furthermore, our proposed method is applied to the model matching control. In simulation studies, it is shown that the proposed method is effective for some plants. Furthermore, by applying the proposed method to a DC motor, the effectiveness of the method is confirmed.","PeriodicalId":121874,"journal":{"name":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","volume":"38 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121343154","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}
Vehicular Ad Hoc Networks (VANETs) are special class of Mobile Ad Hoc Networks (MANETs) formed by vehicles equipped with wireless gadgets. The communication in VANET occurs between Vehicle 2 Vehicle mode and Vehicle to road side unit forming an intelligent transport system. Routing plays an important role in forwarding the required data to the nodes or vehicles. In this paper we investigate the performance evaluation of reactive routing protocols such as AODV and DSR and proactive routing protocols such as OLSR in urban city traffic scenario using SUMO and network performance using NS3 to find an appropriate protocol by using network parameters such as packet delivery ratio, throughput and delay. From the simulations we observed that AODV fared well over other routing protocols in VANET scenarios.
车辆自组织网络(vanet)是一种特殊的移动自组织网络(manet)，由配备无线设备的车辆组成。VANET中的通信发生在Vehicle - 2 Vehicle模式和Vehicle - to - road side unit之间，形成一个智能交通系统。路由在将所需数据转发到节点或车辆方面起着重要作用。本文研究了在城市交通场景下，使用SUMO对AODV、DSR等被动路由协议和OLSR等主动路由协议进行性能评估，使用NS3对网络性能进行评估，通过使用分组传送率、吞吐量和延迟等网络参数找到合适的协议。从模拟中我们观察到，在VANET场景中，AODV比其他路由协议表现良好。
{"title":"A Study on Vehicular Ad Hoc Networks","authors":"V. D. Viswacheda, A. Chekima, F. Wong, J. Dargham","doi":"10.1109/AIMS.2015.73","DOIUrl":"https://doi.org/10.1109/AIMS.2015.73","url":null,"abstract":"Vehicular Ad Hoc Networks (VANETs) are special class of Mobile Ad Hoc Networks (MANETs) formed by vehicles equipped with wireless gadgets. The communication in VANET occurs between Vehicle 2 Vehicle mode and Vehicle to road side unit forming an intelligent transport system. Routing plays an important role in forwarding the required data to the nodes or vehicles. In this paper we investigate the performance evaluation of reactive routing protocols such as AODV and DSR and proactive routing protocols such as OLSR in urban city traffic scenario using SUMO and network performance using NS3 to find an appropriate protocol by using network parameters such as packet delivery ratio, throughput and delay. From the simulations we observed that AODV fared well over other routing protocols in VANET scenarios.","PeriodicalId":121874,"journal":{"name":"2015 3rd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134121285","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：