The modern technological development in the field of communications and electronic systems has contributed to reducing the complexity of the application systems. This paper introduces an advanced face recognition technology, using multiresolution wavelet transform and principal component analysis (PCA). In this method, five levels of discrete wavelet transform (DWT) are used, where each level is subjected to one type of wavelet family. Then, all images are projected to the principal component domain to produce the training features array with further reduction in the processing data. The classifier of this method is the Euclidean distance, such that the minimum distance guides to know the index of anonymous person. The proposed method achieves 99.5% and 98.89% using the ORL and Yale datasets, respectively. Experimental results show that the proposed method outperforms other approaches that used the DWT-PCA technique.
{"title":"Combining multi-resolution wavelets with principal component analysis for face recognition","authors":"Hameed R. Farhan, Hawraa Abbas, H. Shahadi","doi":"10.1145/3321289.3321325","DOIUrl":"https://doi.org/10.1145/3321289.3321325","url":null,"abstract":"The modern technological development in the field of communications and electronic systems has contributed to reducing the complexity of the application systems. This paper introduces an advanced face recognition technology, using multiresolution wavelet transform and principal component analysis (PCA). In this method, five levels of discrete wavelet transform (DWT) are used, where each level is subjected to one type of wavelet family. Then, all images are projected to the principal component domain to produce the training features array with further reduction in the processing data. The classifier of this method is the Euclidean distance, such that the minimum distance guides to know the index of anonymous person. The proposed method achieves 99.5% and 98.89% using the ORL and Yale datasets, respectively. Experimental results show that the proposed method outperforms other approaches that used the DWT-PCA technique.","PeriodicalId":375095,"journal":{"name":"Proceedings of the International Conference on Information and Communication Technology - ICICT '19","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116983605","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 vibration analysis using Fast Fourier Transform FFT is a common and widely used method, because of the similarity between faults signatures in this analysis a question is raised to what is the most effective ways to distinguish between different faults. In order to overcome this difficulty other method combined with the FFT was used. In this paper, a new combination will be present to overcome this situation. Independent Component Analysis (ICA) is used in combination with FFT to identify faults in rotating machines. The vibration is measured through multichannel vibration data acquisition system. The signals are then analyzed using ICA and finally, FFT is applied on ICA components. The extraction features give the best signature to identify each fault from others. This method is used for detecting more general faults occur in rotating machine (bearing fault, misalignment, unbalance, shaft fatigue), and can identify the similarity between faults. The interaction between different types of faults can be solved effectively by using ICA.
{"title":"Combination of FFT & ICA methods for faults analysis of rotating machine","authors":"Abdulbasir Shari, A. Ali, Mujtaba Almudhaffer","doi":"10.1145/3321289.3321307","DOIUrl":"https://doi.org/10.1145/3321289.3321307","url":null,"abstract":"The vibration analysis using Fast Fourier Transform FFT is a common and widely used method, because of the similarity between faults signatures in this analysis a question is raised to what is the most effective ways to distinguish between different faults. In order to overcome this difficulty other method combined with the FFT was used. In this paper, a new combination will be present to overcome this situation. Independent Component Analysis (ICA) is used in combination with FFT to identify faults in rotating machines. The vibration is measured through multichannel vibration data acquisition system. The signals are then analyzed using ICA and finally, FFT is applied on ICA components. The extraction features give the best signature to identify each fault from others. This method is used for detecting more general faults occur in rotating machine (bearing fault, misalignment, unbalance, shaft fatigue), and can identify the similarity between faults. The interaction between different types of faults can be solved effectively by using ICA.","PeriodicalId":375095,"journal":{"name":"Proceedings of the International Conference on Information and Communication Technology - ICICT '19","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130812928","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}
Indoor propagation models are considered as a mathematical expression to describe the wave propagation as a function of frequency, distance, and other conditions. Choosing the appropriate propagation model for a specific environment requires extensive analyses. The ray tracing 3D shoot-and-bounce ray (SBR) technique employed by Wireless InSite software is adopted in this work to simulate the signal propagation and evaluate its strength. Three indoor scenarios with two cases each; Line of sight (LOS) and non-line of sight (NLOS) are being simulated and tested. The test bed was conducted based on Net Spot software. The Basic objective is to compare the measured and simulated received power in order to introduce the potentials and limitations of using ray tracing to characterize the indoor wireless channel at 2.4 and 5 GHz. The comparison results show an acceptable correlation between experimental and simulation results. The effects of distance, frequency, and obstacles materialized by different furniture features have been investigated. The nodes that are located in LOS at room B outperforms the NLOS nodes which are located at room A by (3 dBm) in terms of mean received power for both frequencies. Long distance contributes significantly in signal strength reduction, where minimum received power equals to (-77 dBm) at 5 GHz is noticed at the corridor due to long distance. In addition, 2.4 GHz case verifies better signal quality due to less path loss, and the corridor scenario gains less difference between both frequencies. The office scenario achieves the minimum Mean Absolute Error (MAE) between experimental and simulation results at both 2.4 and 5 GHz.
{"title":"A comparative study of indoor propagation models for IEEE 802.11n network","authors":"Rawaa Akram M., Aseel H. Al-Nakkash, O. Salim","doi":"10.1145/3321289.3321296","DOIUrl":"https://doi.org/10.1145/3321289.3321296","url":null,"abstract":"Indoor propagation models are considered as a mathematical expression to describe the wave propagation as a function of frequency, distance, and other conditions. Choosing the appropriate propagation model for a specific environment requires extensive analyses. The ray tracing 3D shoot-and-bounce ray (SBR) technique employed by Wireless InSite software is adopted in this work to simulate the signal propagation and evaluate its strength. Three indoor scenarios with two cases each; Line of sight (LOS) and non-line of sight (NLOS) are being simulated and tested. The test bed was conducted based on Net Spot software. The Basic objective is to compare the measured and simulated received power in order to introduce the potentials and limitations of using ray tracing to characterize the indoor wireless channel at 2.4 and 5 GHz. The comparison results show an acceptable correlation between experimental and simulation results. The effects of distance, frequency, and obstacles materialized by different furniture features have been investigated. The nodes that are located in LOS at room B outperforms the NLOS nodes which are located at room A by (3 dBm) in terms of mean received power for both frequencies. Long distance contributes significantly in signal strength reduction, where minimum received power equals to (-77 dBm) at 5 GHz is noticed at the corridor due to long distance. In addition, 2.4 GHz case verifies better signal quality due to less path loss, and the corridor scenario gains less difference between both frequencies. The office scenario achieves the minimum Mean Absolute Error (MAE) between experimental and simulation results at both 2.4 and 5 GHz.","PeriodicalId":375095,"journal":{"name":"Proceedings of the International Conference on Information and Communication Technology - ICICT '19","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122562288","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 Brain Computer Interface (BCI), the brain signals are used to perform some commands or actions in a computer. Brain signals are recorded using many methods. Electroencephalogram (EEG) is one of the non-invasive methods. EEG signals are recorded using multiple channels. Selection methods are used to choose the most relevant and powerful signals. Usually Meta-heuristic algorithms are used for selection. Meta-heuristic algorithms depends on random generated population of solutions for the objective function. Because of the randomness, there is always a chance to select zero as a solution. Zero in EEG channels selection means no channel is chosen to extract its signal features. This situation is not practical, the selection process should be repeated whenever a zero solution appears. The repetition will reduce the algorithm speed. This paper introduces a fast channel selection algorithm using Crow Search Algorithm (CSA). CSA is used to select the best channels offline. Using no-zero channel condition to fasten the algorithm. Our results show that CSA with no-zero channels condition is better than Genetic algorithm (GA). Although CSA and GA results are almost have the same accuracy, but CSA with no-zero condition is faster.
{"title":"Fast channel selection method using crow search algorithm","authors":"Zaineb M. Alhakeem, R. Ali","doi":"10.1145/3321289.3321309","DOIUrl":"https://doi.org/10.1145/3321289.3321309","url":null,"abstract":"In Brain Computer Interface (BCI), the brain signals are used to perform some commands or actions in a computer. Brain signals are recorded using many methods. Electroencephalogram (EEG) is one of the non-invasive methods. EEG signals are recorded using multiple channels. Selection methods are used to choose the most relevant and powerful signals. Usually Meta-heuristic algorithms are used for selection. Meta-heuristic algorithms depends on random generated population of solutions for the objective function. Because of the randomness, there is always a chance to select zero as a solution. Zero in EEG channels selection means no channel is chosen to extract its signal features. This situation is not practical, the selection process should be repeated whenever a zero solution appears. The repetition will reduce the algorithm speed. This paper introduces a fast channel selection algorithm using Crow Search Algorithm (CSA). CSA is used to select the best channels offline. Using no-zero channel condition to fasten the algorithm. Our results show that CSA with no-zero channels condition is better than Genetic algorithm (GA). Although CSA and GA results are almost have the same accuracy, but CSA with no-zero condition is faster.","PeriodicalId":375095,"journal":{"name":"Proceedings of the International Conference on Information and Communication Technology - ICICT '19","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122984064","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}
Muhammad Ali Khan, M. Qureshi, I. Raza, S. Hussain
Wireless Sensor Network is comprised of sensor nodes with a limited energy supply in the form of built-in batteries. Efficient utilization of limited energy supply of sensor nodes is one of the key design issues in wireless sensor networks. Hence, energy efficiency needs to be enhanced to prolong the stability and lifetime of WSN. In this paper, we propose Energy-Efficient Clustering Protocol based on Energy Intervals (EECP-EI) for multi-level WSN. EECP-EI associates sensor nodes to clusters based on energy intervals. The cluster heads are selected based on average energy of certain energy interval and the total estimated energy of network at a particular round. The role of cluster head is rotated within the cluster to evenly distribute the energy among sensor nodes inside the cluster. The sensed data is aggregated at the cluster head to reduce the amount of data that needs to be communicated to the base station. The sensed data is communicated to the base station using hierarchy of cluster heads that are in ten-meter distance to the sending cluster head. When the cluster formation no longer remains optimal, every sensor node in the network transmits data directly to the base station. Simulations show that EECP-EI shows the improved stability period of 37.08%, 36.37%, and 19.39%, and the improved network lifetime of 6.58%, 13.13%, and 32.15% as compared to LEACH, DEEC, and DDEEC respectively.
{"title":"EECP-EI: energy-efficient clustering protocol based on energy intervals for wireless sensor networks","authors":"Muhammad Ali Khan, M. Qureshi, I. Raza, S. Hussain","doi":"10.1145/3321289.3321316","DOIUrl":"https://doi.org/10.1145/3321289.3321316","url":null,"abstract":"Wireless Sensor Network is comprised of sensor nodes with a limited energy supply in the form of built-in batteries. Efficient utilization of limited energy supply of sensor nodes is one of the key design issues in wireless sensor networks. Hence, energy efficiency needs to be enhanced to prolong the stability and lifetime of WSN. In this paper, we propose Energy-Efficient Clustering Protocol based on Energy Intervals (EECP-EI) for multi-level WSN. EECP-EI associates sensor nodes to clusters based on energy intervals. The cluster heads are selected based on average energy of certain energy interval and the total estimated energy of network at a particular round. The role of cluster head is rotated within the cluster to evenly distribute the energy among sensor nodes inside the cluster. The sensed data is aggregated at the cluster head to reduce the amount of data that needs to be communicated to the base station. The sensed data is communicated to the base station using hierarchy of cluster heads that are in ten-meter distance to the sending cluster head. When the cluster formation no longer remains optimal, every sensor node in the network transmits data directly to the base station. Simulations show that EECP-EI shows the improved stability period of 37.08%, 36.37%, and 19.39%, and the improved network lifetime of 6.58%, 13.13%, and 32.15% as compared to LEACH, DEEC, and DDEEC respectively.","PeriodicalId":375095,"journal":{"name":"Proceedings of the International Conference on Information and Communication Technology - ICICT '19","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129106303","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}
Day by day the frequency spectrum became unable to provide the service that user needs. The frequency spectrum became more crowded due to increasing the number of users. One of the solutions to minimize this problem is the cognitive radio (CR). This paper includes design and FPGA implementation of a new CR based on feature selection to increase the probability of detection (Pd) for different modulation systems. This design is based on statistical features that used to distinguish between signal and the noise. The system shows an excellent performance of a detection probability as compared with the traditional detection methods. Both AWGN and fading channels are tested in order to proof the performance of the proposed system. The obtained simulation results provide Pd equals to 100% at SNR is -18dB for 6000 sample. Also there are high similarity between the simulation and practical implementation. Xilinx Spartan-3A DSP 3400A is used to implement the proposed detection systems.
{"title":"Design and implementation of a new detection system based on statistical features for different noisy channels","authors":"A. Thabit, H. Ziboon","doi":"10.1145/3321289.3321294","DOIUrl":"https://doi.org/10.1145/3321289.3321294","url":null,"abstract":"Day by day the frequency spectrum became unable to provide the service that user needs. The frequency spectrum became more crowded due to increasing the number of users. One of the solutions to minimize this problem is the cognitive radio (CR). This paper includes design and FPGA implementation of a new CR based on feature selection to increase the probability of detection (Pd) for different modulation systems. This design is based on statistical features that used to distinguish between signal and the noise. The system shows an excellent performance of a detection probability as compared with the traditional detection methods. Both AWGN and fading channels are tested in order to proof the performance of the proposed system. The obtained simulation results provide Pd equals to 100% at SNR is -18dB for 6000 sample. Also there are high similarity between the simulation and practical implementation. Xilinx Spartan-3A DSP 3400A is used to implement the proposed detection systems.","PeriodicalId":375095,"journal":{"name":"Proceedings of the International Conference on Information and Communication Technology - ICICT '19","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132155227","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}
Panoramic Musculoskeletal Ultrasound Images (PMUI) is a developed version of ultrasound images. However, low contrast is a concrete problem which impact negatively on the interpretation of important details of PMUI. Therefore, in this paper a new automated contrast enhancement method was presented and examined on the PMUI. A fuzzy technique is the main tool underpinning this method, and it consists of three steps: fuzzification, modification of membership equation and defuzzification. Maximum fuzzy entropy of PMUI was used to optimize parameters of the membership function. The quality of results was examined using quantitative metrics. Based on these assessment metrics, the performance of the fuzzy technique outperforms the performance of other method with 21%. The results achieved are very effective and could be used for preprocessing in computer vision applications.
{"title":"Enhancement of panoramic musculoskeletal ultrasound image based on fuzzy technique","authors":"S. I. Jabbar, C. Day, E. Chadwick","doi":"10.1145/3321289.3321312","DOIUrl":"https://doi.org/10.1145/3321289.3321312","url":null,"abstract":"Panoramic Musculoskeletal Ultrasound Images (PMUI) is a developed version of ultrasound images. However, low contrast is a concrete problem which impact negatively on the interpretation of important details of PMUI. Therefore, in this paper a new automated contrast enhancement method was presented and examined on the PMUI. A fuzzy technique is the main tool underpinning this method, and it consists of three steps: fuzzification, modification of membership equation and defuzzification. Maximum fuzzy entropy of PMUI was used to optimize parameters of the membership function. The quality of results was examined using quantitative metrics. Based on these assessment metrics, the performance of the fuzzy technique outperforms the performance of other method with 21%. The results achieved are very effective and could be used for preprocessing in computer vision applications.","PeriodicalId":375095,"journal":{"name":"Proceedings of the International Conference on Information and Communication Technology - ICICT '19","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123659161","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}
Software Defined Networking (SDN), often referred to as a revolutionary rather than an evolutionary new idea in networking, promises to dramatically simplify network control, management, and enable innovation through network programmability. SDN has shown great potential to simplify the existing complex, inflexible, and costly network architecture and infrastructure through the reshaping of conventional network functions and design of the protocols. To achieve this goal, OpenFlow protocol has been proposed and is considered the most widely deployed protocol in the field of SDN technology. Mininet emulator provides an efficient virtualization method to design and study the SDN concepts with different types of software switches and controllers. In this research, an extensive study about the effects of changing the size and type of network topology that is constructed in Mininet's virtualization environment presented, in addition to the effects of the types of SDN switches and controllers used to build the network on the amount of resources that must be provided by the operating system. The results showed that there are differences in performance for the controllers and switches, where the OVS controller utilized the higher processing power for Open vSwitch than that of User-Space switches. The later type of switches consumed vast amount of system memory during the construction of large size topologies. The use of Open vSwitch also, resulted in more setupteardown time, which was almost twice that of User-Space switches in large size topologies.
{"title":"Network parameters effects on system resources in software defined networks","authors":"E. B. Yahya, M. Al-Somaidai","doi":"10.1145/3321289.3321317","DOIUrl":"https://doi.org/10.1145/3321289.3321317","url":null,"abstract":"Software Defined Networking (SDN), often referred to as a revolutionary rather than an evolutionary new idea in networking, promises to dramatically simplify network control, management, and enable innovation through network programmability. SDN has shown great potential to simplify the existing complex, inflexible, and costly network architecture and infrastructure through the reshaping of conventional network functions and design of the protocols. To achieve this goal, OpenFlow protocol has been proposed and is considered the most widely deployed protocol in the field of SDN technology. Mininet emulator provides an efficient virtualization method to design and study the SDN concepts with different types of software switches and controllers. In this research, an extensive study about the effects of changing the size and type of network topology that is constructed in Mininet's virtualization environment presented, in addition to the effects of the types of SDN switches and controllers used to build the network on the amount of resources that must be provided by the operating system. The results showed that there are differences in performance for the controllers and switches, where the OVS controller utilized the higher processing power for Open vSwitch than that of User-Space switches. The later type of switches consumed vast amount of system memory during the construction of large size topologies. The use of Open vSwitch also, resulted in more setupteardown time, which was almost twice that of User-Space switches in large size topologies.","PeriodicalId":375095,"journal":{"name":"Proceedings of the International Conference on Information and Communication Technology - ICICT '19","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127395136","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：