Pub Date : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019171
Mahshid Behravan, N. Zhang, A. Jaekel, Marc Kneppers
Vehicular ad-hoc network (VANET) will play an important role in improving driving safety and efficiency in transport systems. As various attacks arise in VANET, it is essential to design mechanisms that can detect these attacks and then mitigate them. In this paper, we make an effort to detect five different position falsification attacks in VANET, including constant attack, constant offset attack, random attack, random offset attack, and eventual stop attack. Two detection systems based on ensemble machine learning algorithms, including stacking ensemble learning algorithms for classification and stacking ensemble learning for neural network, are proposed. We extracted the most important features by performing feature importance techniques. Then, we train the proposed learning algorithms on VeReMi dataset which includes five different position falsification attacks with three traffic densities and three attacker densities. Extensive experimental results are provided to evaluate the proposed solutions' effectiveness. Based on our results, stacking ensemble learning for classification algorithm can achieve the best performance in terms of accuracy and recall. In low density traffic, accuracy and recall of stacking ensemble learning for classification algorithms are 1 for the constant attack, constant offset attack, and random attack. Accuracy and recall for the random offset attack are 0.999 and 0.996, respectively. For the eventual stop attack, accuracy and recall are 0.995 and 0.985, respectively. In medium density, accuracy and recall of stacking ensemble learning also achieve the best performance.
{"title":"Intrusion Detection Systems Based on Stacking Ensemble Learning in VANET","authors":"Mahshid Behravan, N. Zhang, A. Jaekel, Marc Kneppers","doi":"10.1109/ICCSPA55860.2022.10019171","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019171","url":null,"abstract":"Vehicular ad-hoc network (VANET) will play an important role in improving driving safety and efficiency in transport systems. As various attacks arise in VANET, it is essential to design mechanisms that can detect these attacks and then mitigate them. In this paper, we make an effort to detect five different position falsification attacks in VANET, including constant attack, constant offset attack, random attack, random offset attack, and eventual stop attack. Two detection systems based on ensemble machine learning algorithms, including stacking ensemble learning algorithms for classification and stacking ensemble learning for neural network, are proposed. We extracted the most important features by performing feature importance techniques. Then, we train the proposed learning algorithms on VeReMi dataset which includes five different position falsification attacks with three traffic densities and three attacker densities. Extensive experimental results are provided to evaluate the proposed solutions' effectiveness. Based on our results, stacking ensemble learning for classification algorithm can achieve the best performance in terms of accuracy and recall. In low density traffic, accuracy and recall of stacking ensemble learning for classification algorithms are 1 for the constant attack, constant offset attack, and random attack. Accuracy and recall for the random offset attack are 0.999 and 0.996, respectively. For the eventual stop attack, accuracy and recall are 0.995 and 0.985, respectively. In medium density, accuracy and recall of stacking ensemble learning also achieve the best performance.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121716647","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 : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019125
M. Sanad, N. Hassan
A foldable/deployable multi-beam antenna has been developed for Low-Earth Orbit (LEO) satellites and ground stations. It consists of dual parabolic cylindrical reflectors with multiple resonant feeds. It can generate an arbitrary number of beams with arbitrary vertical and horizontal beam-tilt for each beam. It can be remotely controlled to cover any arbitrary area having any shape/size. It has a very wide frequency band-width. It can even, simultaneously, work at multi wide frequency bands such as 5G-sub-6GHz band (3.3-6.0 GHz), Ku-band (10–16 GHz) and Ka-band (18–31 GHz). A very simple beam tracking technique has been developed without using any adaptive methods. For any specific satellite orbit, the orientation of the ground station (terminal) antenna will always be adjusted such that its generated beams are parallel to the satellite's beams and directed toward them. This automatic orientation of the ground station (terminal) antenna, completely, depends on its location, orientation and elevation with no need for any adaptive beam steering/tracking or any adaptive beam-shaping. Furthermore, the terminal antenna can simultaneously communicate with multiple satellites in different orbits. For example, a penta beam terminal antenna can, simultaneously, communicate with five satellites in five different orbits.
{"title":"A Multibeam Antenna for Multi-Orbit LEO Satellites and Terminals with a Very Simple Tracking Technique","authors":"M. Sanad, N. Hassan","doi":"10.1109/ICCSPA55860.2022.10019125","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019125","url":null,"abstract":"A foldable/deployable multi-beam antenna has been developed for Low-Earth Orbit (LEO) satellites and ground stations. It consists of dual parabolic cylindrical reflectors with multiple resonant feeds. It can generate an arbitrary number of beams with arbitrary vertical and horizontal beam-tilt for each beam. It can be remotely controlled to cover any arbitrary area having any shape/size. It has a very wide frequency band-width. It can even, simultaneously, work at multi wide frequency bands such as 5G-sub-6GHz band (3.3-6.0 GHz), Ku-band (10–16 GHz) and Ka-band (18–31 GHz). A very simple beam tracking technique has been developed without using any adaptive methods. For any specific satellite orbit, the orientation of the ground station (terminal) antenna will always be adjusted such that its generated beams are parallel to the satellite's beams and directed toward them. This automatic orientation of the ground station (terminal) antenna, completely, depends on its location, orientation and elevation with no need for any adaptive beam steering/tracking or any adaptive beam-shaping. Furthermore, the terminal antenna can simultaneously communicate with multiple satellites in different orbits. For example, a penta beam terminal antenna can, simultaneously, communicate with five satellites in five different orbits.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126071951","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 : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10018969
Uzma Ahmed Din, S. Mukhopadhyay, Usman Tariq
Plastics have become a cornerstone of modern life, but they are also hazardous for the environment. Manually collecting and sorting such recyclable plastic from a mix of other refuse is tedious work, and has accompanying health hazards. This work develops a prototype autonomous robot that can navigate via a combination of GPS and image based techniques to reach known locations where recyclable trash is expected, then identify and collect plastic bottles from among other waste. For a first prototype, the focus is on recognition and picking up of a particular type of plastic bottle commonly used for packaging drinking water.
{"title":"A Robotic System for Automatic Identification and Collection of Recyclable Plastic Bottles","authors":"Uzma Ahmed Din, S. Mukhopadhyay, Usman Tariq","doi":"10.1109/ICCSPA55860.2022.10018969","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10018969","url":null,"abstract":"Plastics have become a cornerstone of modern life, but they are also hazardous for the environment. Manually collecting and sorting such recyclable plastic from a mix of other refuse is tedious work, and has accompanying health hazards. This work develops a prototype autonomous robot that can navigate via a combination of GPS and image based techniques to reach known locations where recyclable trash is expected, then identify and collect plastic bottles from among other waste. For a first prototype, the focus is on recognition and picking up of a particular type of plastic bottle commonly used for packaging drinking water.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115347197","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 : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019102
Abdulla Lutfi, Ayman H. El-Hag
Outdoor insulators are crucial components to the integrity of overhead lines. There are two main types of outdoor insulators: ceramic and non-ceramic insulators. Both types suffer from different types of defects in the field and hence they need to be inspected regularly to avoid any possible sudden failure of these insulators. In this paper, the different types of defects of outdoor insulators are summarized. Moreover, the different pros and cons of sensors are highlighted and compared. Furthermore, the application of machine learning to enhance the inspection process is introduced.
{"title":"Smart Monitoring of Outdoor Insulators","authors":"Abdulla Lutfi, Ayman H. El-Hag","doi":"10.1109/ICCSPA55860.2022.10019102","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019102","url":null,"abstract":"Outdoor insulators are crucial components to the integrity of overhead lines. There are two main types of outdoor insulators: ceramic and non-ceramic insulators. Both types suffer from different types of defects in the field and hence they need to be inspected regularly to avoid any possible sudden failure of these insulators. In this paper, the different types of defects of outdoor insulators are summarized. Moreover, the different pros and cons of sensors are highlighted and compared. Furthermore, the application of machine learning to enhance the inspection process is introduced.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129463363","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 : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019198
Amal Samir, B. ElDiwany, Ahmad Elmoslimany, M. Nafie, Sherif ElAzzouni, T. Elbatt
In this paper, we propose a novel design for a high-speed underwater acoustic (UWA) receiver chain. Towards this objective, we introduce a novel closed-loop, adaptive, single-rate Doppler scale estimation and compensation algorithm and a novel dual-domain channel estimation and equalization technique. We validate our results and evaluate the proposed schemes using extensive simulations based on channel models generated from the analysis of the Kauai Acomms MURI 2011 (KAM11) UWA communications experiment's recording. The extensive simulations show that the proposed algorithms exhibit superior performance compared to the state-of-the-art.
{"title":"On the Design of a High Data Rate Underwater Acoustic Receiver","authors":"Amal Samir, B. ElDiwany, Ahmad Elmoslimany, M. Nafie, Sherif ElAzzouni, T. Elbatt","doi":"10.1109/ICCSPA55860.2022.10019198","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019198","url":null,"abstract":"In this paper, we propose a novel design for a high-speed underwater acoustic (UWA) receiver chain. Towards this objective, we introduce a novel closed-loop, adaptive, single-rate Doppler scale estimation and compensation algorithm and a novel dual-domain channel estimation and equalization technique. We validate our results and evaluate the proposed schemes using extensive simulations based on channel models generated from the analysis of the Kauai Acomms MURI 2011 (KAM11) UWA communications experiment's recording. The extensive simulations show that the proposed algorithms exhibit superior performance compared to the state-of-the-art.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130127775","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 : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019100
Ali J. Almasadeh, Khawla A. Alnajjar, M. Albreem
Massive multiple-input multiple-output (MIMO) is a crucial technology in fifth-generation (5G) and beyond 5G (B5G). However, the huge number of antennas used in massive MIMO systems causes a high computational complexity during signal detection. In this paper, we propose an efficient massive MIMO detection technique which is based on approximate matrix inversion methods and deep learning to enhance the system performance while keeping computational complexity low. Three approximate methods which are Gauss–Seidel (GS), successive over-relaxation (SOR), and conjugate gradient (CG) are exploited for the initialization of a modified version of the MM network (MMNet) algorithm. The performance of the proposed technique is validated under both Gaussian and realistic channel scenarios, i.e., Quadriga channels models. Simulation results show that the proposed technique outperforms MMNet, minimum mean square estimation (MMSE), detection network (DetNet), and orthogonal approximate message passing deep net (OAMP-Net) in terms of symbol error rate (SER) during offline training. It also provides a significant SER improvement of up to 87% when compared to MMNet in the online training scenario.
{"title":"Enhanced Deep Learning for Massive MIMO Detection Using Approximate Matrix Inversion","authors":"Ali J. Almasadeh, Khawla A. Alnajjar, M. Albreem","doi":"10.1109/ICCSPA55860.2022.10019100","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019100","url":null,"abstract":"Massive multiple-input multiple-output (MIMO) is a crucial technology in fifth-generation (5G) and beyond 5G (B5G). However, the huge number of antennas used in massive MIMO systems causes a high computational complexity during signal detection. In this paper, we propose an efficient massive MIMO detection technique which is based on approximate matrix inversion methods and deep learning to enhance the system performance while keeping computational complexity low. Three approximate methods which are Gauss–Seidel (GS), successive over-relaxation (SOR), and conjugate gradient (CG) are exploited for the initialization of a modified version of the MM network (MMNet) algorithm. The performance of the proposed technique is validated under both Gaussian and realistic channel scenarios, i.e., Quadriga channels models. Simulation results show that the proposed technique outperforms MMNet, minimum mean square estimation (MMSE), detection network (DetNet), and orthogonal approximate message passing deep net (OAMP-Net) in terms of symbol error rate (SER) during offline training. It also provides a significant SER improvement of up to 87% when compared to MMNet in the online training scenario.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125644468","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 : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019241
Youssef M. Eldokmak, M. H. Ismail, Mohamed S. Hassan
In this paper, we analyze the secrecy performance assuming correlated generalized gamma fading for the legitimate and eavesdropper channels. Specifically, we derive expressions for the probability of non-zero secrecy capacity, a lower bound on the secrecy outage probability and the average secrecy capacity in case of high signal-to-noise ratio (SNR). Monte Carlo simulations were then run verifying the accuracy of our analysis.
{"title":"Secrecy Analysis Over Correlated Generalized Gamma Fading Channels","authors":"Youssef M. Eldokmak, M. H. Ismail, Mohamed S. Hassan","doi":"10.1109/ICCSPA55860.2022.10019241","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019241","url":null,"abstract":"In this paper, we analyze the secrecy performance assuming correlated generalized gamma fading for the legitimate and eavesdropper channels. Specifically, we derive expressions for the probability of non-zero secrecy capacity, a lower bound on the secrecy outage probability and the average secrecy capacity in case of high signal-to-noise ratio (SNR). Monte Carlo simulations were then run verifying the accuracy of our analysis.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114858488","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 : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019068
Mohamed Mostafa, M. H. Ismail
In this paper, we study the capacity of the recently proposed Beaulieu-Xie fading channel under different trans-mission strategies. This fading distribution is used to model wireless channels characterized by multiple line-of-sight (LOS) components with some indirect rays due to multiple scatterers. Novel expressions for the channel capacity under optimum power and rate adaptation (OPRA), optimum rate adaption (ORA), channel inversion with fixed rate (CIFR) and truncated channel inversion with fixed rate (TIFR) are derived in semi-closed form. The derived expressions are verified through special cases that are already well-documented in the literature and through Monte-Carlo simulations where perfect agreement is observed thus confirming the validity of the derived expressions.
{"title":"Capacity of the Beaulieu-Xie Fading Channel under Adaptive Transmission Strategies","authors":"Mohamed Mostafa, M. H. Ismail","doi":"10.1109/ICCSPA55860.2022.10019068","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019068","url":null,"abstract":"In this paper, we study the capacity of the recently proposed Beaulieu-Xie fading channel under different trans-mission strategies. This fading distribution is used to model wireless channels characterized by multiple line-of-sight (LOS) components with some indirect rays due to multiple scatterers. Novel expressions for the channel capacity under optimum power and rate adaptation (OPRA), optimum rate adaption (ORA), channel inversion with fixed rate (CIFR) and truncated channel inversion with fixed rate (TIFR) are derived in semi-closed form. The derived expressions are verified through special cases that are already well-documented in the literature and through Monte-Carlo simulations where perfect agreement is observed thus confirming the validity of the derived expressions.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125302401","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 : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10018972
Esmail Elsaidy, Tamer Rakia
Free space optical (FSO) uplink from a service provider to a Low Earth Orbit (LEO) satellite has emerged as a promising solution to transfer large amount of data to the satellite to be relayed to huge number of users over wide geographical areas. In this paper, we present a new unified model for the FSO uplink from an optical ground station (OGS) to a LEO satellite, while considering subcarrirer intensity mod-ulation/direct detection (SIM/DD) and coherent FSO detection techniques. We take into account the various channel fading effects of atmospheric turbulence, beam wander and OGS - Satellite misalignment errors. We then make use of this model to present new expressions for the outage probability and the ergodic capacity of the FSO uplink and the average symbol error rate over the FSO uplink for different digital modulation schemes in exact closed-forms. Numerical examples show that coherent FSO systems give better performance over the FSO uplink than SIM/DD FSO systems which improves more with small zenith angles and less misalignment errors.
{"title":"A Unified Performance Analysis of OGS-to-Satellite FSO UpLink under Turbulence and Beam Wander","authors":"Esmail Elsaidy, Tamer Rakia","doi":"10.1109/ICCSPA55860.2022.10018972","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10018972","url":null,"abstract":"Free space optical (FSO) uplink from a service provider to a Low Earth Orbit (LEO) satellite has emerged as a promising solution to transfer large amount of data to the satellite to be relayed to huge number of users over wide geographical areas. In this paper, we present a new unified model for the FSO uplink from an optical ground station (OGS) to a LEO satellite, while considering subcarrirer intensity mod-ulation/direct detection (SIM/DD) and coherent FSO detection techniques. We take into account the various channel fading effects of atmospheric turbulence, beam wander and OGS - Satellite misalignment errors. We then make use of this model to present new expressions for the outage probability and the ergodic capacity of the FSO uplink and the average symbol error rate over the FSO uplink for different digital modulation schemes in exact closed-forms. Numerical examples show that coherent FSO systems give better performance over the FSO uplink than SIM/DD FSO systems which improves more with small zenith angles and less misalignment errors.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126287072","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 : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019168
Yasir Kadhim, A. Khalifeh
Sound source localization (SSL) is technique that is used to process where the source and determine its direction using several SSL algorithms. Having an accurate, fast and computational efficient SSL algorithm, is extremely useful especially when designing hearing aid devices, that can guide the deaf person to the sound source direction, which is very important especially when encountering dangerous sound sources such as car horn. In this paper, a performance comparison of several SSL algorithms are conducted, bearing in mind the algorithms' accuracy, execution time and suitability for hearing aid devices. The conducted tests show that both the The MUltiple Signal Classification (MUSIC) and the steered response power (SRP) algorithms performed the nearly best in terms of accuracy especially under low signal-to-noise (SNR) conditions, the capability of identifying multiple audio sources, and the low processing delay, which make them best candidates to be deployed on hearing aid devices when compared with other SSL algorithms.
{"title":"Performance Evaluation and Comparative Analysis for Widely Used Sound Source Localization Algorithms","authors":"Yasir Kadhim, A. Khalifeh","doi":"10.1109/ICCSPA55860.2022.10019168","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019168","url":null,"abstract":"Sound source localization (SSL) is technique that is used to process where the source and determine its direction using several SSL algorithms. Having an accurate, fast and computational efficient SSL algorithm, is extremely useful especially when designing hearing aid devices, that can guide the deaf person to the sound source direction, which is very important especially when encountering dangerous sound sources such as car horn. In this paper, a performance comparison of several SSL algorithms are conducted, bearing in mind the algorithms' accuracy, execution time and suitability for hearing aid devices. The conducted tests show that both the The MUltiple Signal Classification (MUSIC) and the steered response power (SRP) algorithms performed the nearly best in terms of accuracy especially under low signal-to-noise (SNR) conditions, the capability of identifying multiple audio sources, and the low processing delay, which make them best candidates to be deployed on hearing aid devices when compared with other SSL algorithms.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128426923","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：