Pub Date : 2022-12-27DOI: 10.1109/ICCSPA55860.2022.10019107
Eiman ElGhanam, Mohamed S. Hassan, A. Osman
Optimal prediction and coordination of the energy demand of electric vehicles (EVs) is essential to address the energy availability and range anxiety concerns of current and potential EV users. As a result, different EV demand predictors are developed in the literature based on traffic simulators and/or locally-generated EV charging datasets, to provide the required inputs for EV demand management programs. These predictors, however, may not reliably scale to model the EV energy requirements in different regions, particularly with the scarcity of real-world data on EV driving patterns. This work proposes a data-driven, machine learning (ML)-based EV demand predictor based on vehicular traffic flow data between different origin-destination (OD) pairs. The proposed model incorporates the driving patterns in the regions under consideration to determine the corresponding EV energy consumption and hence, the minimum EV energy requirements per trip. The data used in this work is obtained from TomTom Move O/D Analysis portal for the cities of Dubai and Sharjah, UAE. Different ML models are trained on the dataset to develop the EV demand predictor, namely random forests (RF), extreme gradient boosting (XGBoost), multilayer perceptron (MLP) and linear regression models. Results reveal that the MLP offers a superior performance to all other models, with an $R^{2} > 0.8$ and a symmetric mean absolute percentage error of ≈ 20% on both the training and testing data subsets, and a significantly lower training time compared to RF and XGBoost. This makes it suitable for EV demand predictions to incorporate regular updates in vehicular traffic flow data for further model tuning.
{"title":"Machine Learning-Based Electric Vehicle Charging Demand Prediction Using Origin-Destination Data: A UAE Case Study","authors":"Eiman ElGhanam, Mohamed S. Hassan, A. Osman","doi":"10.1109/ICCSPA55860.2022.10019107","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019107","url":null,"abstract":"Optimal prediction and coordination of the energy demand of electric vehicles (EVs) is essential to address the energy availability and range anxiety concerns of current and potential EV users. As a result, different EV demand predictors are developed in the literature based on traffic simulators and/or locally-generated EV charging datasets, to provide the required inputs for EV demand management programs. These predictors, however, may not reliably scale to model the EV energy requirements in different regions, particularly with the scarcity of real-world data on EV driving patterns. This work proposes a data-driven, machine learning (ML)-based EV demand predictor based on vehicular traffic flow data between different origin-destination (OD) pairs. The proposed model incorporates the driving patterns in the regions under consideration to determine the corresponding EV energy consumption and hence, the minimum EV energy requirements per trip. The data used in this work is obtained from TomTom Move O/D Analysis portal for the cities of Dubai and Sharjah, UAE. Different ML models are trained on the dataset to develop the EV demand predictor, namely random forests (RF), extreme gradient boosting (XGBoost), multilayer perceptron (MLP) and linear regression models. Results reveal that the MLP offers a superior performance to all other models, with an $R^{2} > 0.8$ and a symmetric mean absolute percentage error of ≈ 20% on both the training and testing data subsets, and a significantly lower training time compared to RF and XGBoost. This makes it suitable for EV demand predictions to incorporate regular updates in vehicular traffic flow data for further model tuning.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125269233","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/ICCSPA55860.2022.10019056
Hebatalla Ouda, Hossam S. Hassanein, Khalid Elgazzar
The computer-aided interpretation of ECG signals has become a pivotal tool for physicians in the clinical assessment of cardiovascular diseases during the last decade. Therefore, computerized diagnosis systems depend heavily on machine learning and deep learning models to guarantee high classification accuracy. However, a large amount of power is consumed due to the need for heavy computations to handle the classification tasks which act as a barrier to maintain continuous ECG monitoring. Hence, this work targets energy saving in the constrained embedded environment on a Texas Instruments CC2650 Micro-controller Unit (MCU). We provide a new approach to support energy-efficient ECG monitoring in real-time through the adaptive selection of ECG leads after applying multi-class classification on the raw ECG signals. We deploy two different CNN model scenarios on MIT-BIH and CODE-test datasets, and adjust the number of ECG streamed channels to 1,4, and 8, based on the detected cardiac abnormalities, such as arrhythmias and heart blocks. The adaptive selection of ECG channels achieves 77.7% power saving in the normal cardiac condition and up to 55.5% for the heart blocks, sinus bradycardia, and sinus tachycardia.
{"title":"Adaptive ECG Leads Selection for Low-Power ECG Monitoring Systems Using Multi-class Classification","authors":"Hebatalla Ouda, Hossam S. Hassanein, Khalid Elgazzar","doi":"10.1109/ICCSPA55860.2022.10019056","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019056","url":null,"abstract":"The computer-aided interpretation of ECG signals has become a pivotal tool for physicians in the clinical assessment of cardiovascular diseases during the last decade. Therefore, computerized diagnosis systems depend heavily on machine learning and deep learning models to guarantee high classification accuracy. However, a large amount of power is consumed due to the need for heavy computations to handle the classification tasks which act as a barrier to maintain continuous ECG monitoring. Hence, this work targets energy saving in the constrained embedded environment on a Texas Instruments CC2650 Micro-controller Unit (MCU). We provide a new approach to support energy-efficient ECG monitoring in real-time through the adaptive selection of ECG leads after applying multi-class classification on the raw ECG signals. We deploy two different CNN model scenarios on MIT-BIH and CODE-test datasets, and adjust the number of ECG streamed channels to 1,4, and 8, based on the detected cardiac abnormalities, such as arrhythmias and heart blocks. The adaptive selection of ECG channels achieves 77.7% power saving in the normal cardiac condition and up to 55.5% for the heart blocks, sinus bradycardia, and sinus tachycardia.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131106582","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/ICCSPA55860.2022.10019177
U. Iqbal, A. Abosekeen, M. Elsheikh, A. Noureldin, M. Korenberg
GNSS navigation requires an unobstructed line-of-sight view of four or more satellites with suitable geometry to compute latitude, longitude, altitude, and time. GNSS signal weakens in degraded environments such as Urban Canyons, Tunnels, Under Passes, and Green Tunnels. Therefore, GNSS alone cannot provide reliable navigation support in challenging environments. To address this limitation, GNSS can be augmented with multiple other navigation sensors to provide an integrated solution, including inertial measurement units, magnetometers, and radars. Low-cost, small size and lightweight MEMS sensors are used for a wide range of navigation applications. However, adding each sensor increases the complexity of the systems as each sensor independently measures a particular parameter. Multi-sensor data fusion techniques, such as Kalman Filter (KF), play a vital role in improving the navigation accuracy of the system. This paper reviews multiple sensor schemes for integrating two accelerometers, a gyroscope, a magnetometer, and Adaptive Cruise Control Radar augmented with GNSS to provide an integrated multisensor navigation system. These multiple sensor schemes were tested in an actual road trajectory in Kingston. In addition, GNSS outages were intentionally introduced on this road trajectory to examine the performance of different Schemes for various motion dynamics.
{"title":"A Review of Sensor System Schemes for Integrated Navigation","authors":"U. Iqbal, A. Abosekeen, M. Elsheikh, A. Noureldin, M. Korenberg","doi":"10.1109/ICCSPA55860.2022.10019177","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019177","url":null,"abstract":"GNSS navigation requires an unobstructed line-of-sight view of four or more satellites with suitable geometry to compute latitude, longitude, altitude, and time. GNSS signal weakens in degraded environments such as Urban Canyons, Tunnels, Under Passes, and Green Tunnels. Therefore, GNSS alone cannot provide reliable navigation support in challenging environments. To address this limitation, GNSS can be augmented with multiple other navigation sensors to provide an integrated solution, including inertial measurement units, magnetometers, and radars. Low-cost, small size and lightweight MEMS sensors are used for a wide range of navigation applications. However, adding each sensor increases the complexity of the systems as each sensor independently measures a particular parameter. Multi-sensor data fusion techniques, such as Kalman Filter (KF), play a vital role in improving the navigation accuracy of the system. This paper reviews multiple sensor schemes for integrating two accelerometers, a gyroscope, a magnetometer, and Adaptive Cruise Control Radar augmented with GNSS to provide an integrated multisensor navigation system. These multiple sensor schemes were tested in an actual road trajectory in Kingston. In addition, GNSS outages were intentionally introduced on this road trajectory to examine the performance of different Schemes for various motion dynamics.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134093800","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/ICCSPA55860.2022.10019159
Dipkumar Patel, Khalid Elgazzar
Road boundary detection has been an active research area for autonomous driving to support full autonomy in all weather conditions. It also helps human drivers to drive safely in bad weather conditions when vehicles ahead and road boundaries are obscured. For example, knowing the road boundaries enables snow plow vehicles to clean the road more precisely, thereby increasing the amount of drivable area available during the winter. The majority of current road boundary detection techniques use camera and lidar sensors. The camera excels in clear daylight conditions but struggles in low visibility light. While lidar sensors perform well in low light, they struggle in inclement weather conditions such as rain or fog. The high attenuation power of automotive radar makes it extremely effective in all types of weather conditions. However, due to the low resolution of the radar, it is currently limited to object detection for cruise control applications. This paper proposes a method for detecting road boundaries in all weather conditions by combining a camera and mmwave radar. We present radar sensor filters that will aid researchers in making more efficient use of millimeter-wave radars. We demonstrate that our approach performs 20% better than the pure vision-based approach. We showcase that in inclement weather conditions when a camera can barely see our approach can precisely detect road boundaries. The proposed method has been validated by mounting an experimental setup on a test vehicle and driving it in a variety of different conditions and on a variety of different types of roads.
{"title":"Road Boundary Detection using Camera and mmwave Radar","authors":"Dipkumar Patel, Khalid Elgazzar","doi":"10.1109/ICCSPA55860.2022.10019159","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019159","url":null,"abstract":"Road boundary detection has been an active research area for autonomous driving to support full autonomy in all weather conditions. It also helps human drivers to drive safely in bad weather conditions when vehicles ahead and road boundaries are obscured. For example, knowing the road boundaries enables snow plow vehicles to clean the road more precisely, thereby increasing the amount of drivable area available during the winter. The majority of current road boundary detection techniques use camera and lidar sensors. The camera excels in clear daylight conditions but struggles in low visibility light. While lidar sensors perform well in low light, they struggle in inclement weather conditions such as rain or fog. The high attenuation power of automotive radar makes it extremely effective in all types of weather conditions. However, due to the low resolution of the radar, it is currently limited to object detection for cruise control applications. This paper proposes a method for detecting road boundaries in all weather conditions by combining a camera and mmwave radar. We present radar sensor filters that will aid researchers in making more efficient use of millimeter-wave radars. We demonstrate that our approach performs 20% better than the pure vision-based approach. We showcase that in inclement weather conditions when a camera can barely see our approach can precisely detect road boundaries. The proposed method has been validated by mounting an experimental setup on a test vehicle and driving it in a variety of different conditions and on a variety of different types of roads.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133640226","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/ICCSPA55860.2022.10019082
Philip Wickberg, A. Fattouh, S. Afshar, Johan Sjöberg, M. Bohlin
Construction sites are a special kind of off-road environment that needs dedicated dynamic maps to enable autonomous navigation in such terrains. In this paper, challenges for autonomous navigation on construction sites are first identified. Later, requirements for dynamic maps for autonomous navigation on construction sites are proposed based on the identified challenges.
{"title":"Dynamic Maps Requirements for Autonomous Navigation on Construction Sites","authors":"Philip Wickberg, A. Fattouh, S. Afshar, Johan Sjöberg, M. Bohlin","doi":"10.1109/ICCSPA55860.2022.10019082","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019082","url":null,"abstract":"Construction sites are a special kind of off-road environment that needs dedicated dynamic maps to enable autonomous navigation in such terrains. In this paper, challenges for autonomous navigation on construction sites are first identified. Later, requirements for dynamic maps for autonomous navigation on construction sites are proposed based on the identified challenges.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125927738","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/ICCSPA55860.2022.10019022
Yue Li, Fei Wang
We develop a secure communication scheme for an active intelligent reflecting surface (IRS) aided wireless network to maximize the mobile users' (MUs') transmission rate, where a multiple antenna base station (BS) transmits confidential information to MUs with the assistance of an active IRS. First, we formulate a rate maximization problem by jointly optimizing the transmission beamforming vectors, the IRS's phase-shifts and amplification-coefficients, and the system channel bandwidth allocation coefficients. Since the formulated optimization problem is non-convex with multiple coupled variables, we first adopt the block coordinate descending (BCD) method to decompose the formulated non-convex optimization problem into several subproblems, and then use the sequential convex approximation (SCA) method to transform the non-convex subproblems into the convex problems. Then, we can use CVX to solve them. Finally, the proposed scheme is verified by numerical analysis, which show that compared with the baseline scheme with passive IRS, when the noise power at the active IRS is much smaller than that at the MUs, our proposed scheme can achieve much larger transmission rates by using the active IRS even with a small number of reflecting elements.
{"title":"Rate Maximization for Active-IRS-Aided Secure Communication Networks","authors":"Yue Li, Fei Wang","doi":"10.1109/ICCSPA55860.2022.10019022","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019022","url":null,"abstract":"We develop a secure communication scheme for an active intelligent reflecting surface (IRS) aided wireless network to maximize the mobile users' (MUs') transmission rate, where a multiple antenna base station (BS) transmits confidential information to MUs with the assistance of an active IRS. First, we formulate a rate maximization problem by jointly optimizing the transmission beamforming vectors, the IRS's phase-shifts and amplification-coefficients, and the system channel bandwidth allocation coefficients. Since the formulated optimization problem is non-convex with multiple coupled variables, we first adopt the block coordinate descending (BCD) method to decompose the formulated non-convex optimization problem into several subproblems, and then use the sequential convex approximation (SCA) method to transform the non-convex subproblems into the convex problems. Then, we can use CVX to solve them. Finally, the proposed scheme is verified by numerical analysis, which show that compared with the baseline scheme with passive IRS, when the noise power at the active IRS is much smaller than that at the MUs, our proposed scheme can achieve much larger transmission rates by using the active IRS even with a small number of reflecting elements.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130367156","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/ICCSPA55860.2022.10019038
Ahmed Eldemiry, Abdelazim A. Abdelsalam, H. Abdel-Atty, A. Azouz, A. Gaafar, Walid A. Raslan
Known as a new promising waveform modulation technique, the orthogonal time-frequency space (OTFS) technique is considered a very important waveform modulation technique that modulates data in the delay-Doppler (DD) domain. The key difference between OTFS and the traditional multiplexing techniques is that it is two-dimensional modulation that converts between the time-frequency (TF) domain and delay-Doppler domain, these features enable dealing with the Doppler shift generated from high mobility objects which were ignored in the traditional modulation techniques such as orthogonal frequency division multiplexing (OFDM). The main objective of this survey is to provide an overview of this novel subject indicating its system model. Also, we review the main topics related to OTFS modulation as data detection techniques, channel estimation, MIMO, and multiuser systems. Then, the main research direction of OTFS on future wireless generation systems is given.
{"title":"Overview of the Orthogonal Time-Frequency Space for High Mobility Communication Systems","authors":"Ahmed Eldemiry, Abdelazim A. Abdelsalam, H. Abdel-Atty, A. Azouz, A. Gaafar, Walid A. Raslan","doi":"10.1109/ICCSPA55860.2022.10019038","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019038","url":null,"abstract":"Known as a new promising waveform modulation technique, the orthogonal time-frequency space (OTFS) technique is considered a very important waveform modulation technique that modulates data in the delay-Doppler (DD) domain. The key difference between OTFS and the traditional multiplexing techniques is that it is two-dimensional modulation that converts between the time-frequency (TF) domain and delay-Doppler domain, these features enable dealing with the Doppler shift generated from high mobility objects which were ignored in the traditional modulation techniques such as orthogonal frequency division multiplexing (OFDM). The main objective of this survey is to provide an overview of this novel subject indicating its system model. Also, we review the main topics related to OTFS modulation as data detection techniques, channel estimation, MIMO, and multiuser systems. Then, the main research direction of OTFS on future wireless generation systems is given.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114835206","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/ICCSPA55860.2022.10019226
H. Ignatious, H. El-Sayed, M. A. Khan, P. Kulkarni
The goal of fifth-generation (5G) communication technol-ogy is to provide increased data throughput, excellent user exposure, reduced power consumption, and exceptionally low latency. To provide clients with the quality of service they desire, these cellular networks will employ a diverse multi-layer approach that includes device-to-device networks, macrocells, and several types of small cells (QoS). With the extensive need for these cellular technologies for increased data transfer and advanced analytics, appropriate resource allocation and management is essential. Since 5G networks operate on high bandwidth, high frequency, and short-range transmission, multiple devices can enjoy the service within the stipulated range. Hence a versatile and efficient resource allocation schema is required. Still, researches are in progress to instantly handle the resource allocation and management in 5G networks. Keeping this problem as a primary goal, this research has proposed a versatile software-defined network (SDN) based resource allocation and management model for 5G networks. Adequate experiments are performed using NetSim simulator, to prove the efficiency of the proposed models.
{"title":"Flexibly Controlled 5G Network Slicing","authors":"H. Ignatious, H. El-Sayed, M. A. Khan, P. Kulkarni","doi":"10.1109/ICCSPA55860.2022.10019226","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019226","url":null,"abstract":"The goal of fifth-generation (5G) communication technol-ogy is to provide increased data throughput, excellent user exposure, reduced power consumption, and exceptionally low latency. To provide clients with the quality of service they desire, these cellular networks will employ a diverse multi-layer approach that includes device-to-device networks, macrocells, and several types of small cells (QoS). With the extensive need for these cellular technologies for increased data transfer and advanced analytics, appropriate resource allocation and management is essential. Since 5G networks operate on high bandwidth, high frequency, and short-range transmission, multiple devices can enjoy the service within the stipulated range. Hence a versatile and efficient resource allocation schema is required. Still, researches are in progress to instantly handle the resource allocation and management in 5G networks. Keeping this problem as a primary goal, this research has proposed a versatile software-defined network (SDN) based resource allocation and management model for 5G networks. Adequate experiments are performed using NetSim simulator, to prove the efficiency of the proposed models.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128799142","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/ICCSPA55860.2022.10019194
Razan S. Youssef, S. Youssef, N. Ghatwary
The paper introduces an ensemble model combined with CNN and data augmentation to predict respiratory diseases. Respiratory diseases are one of the top causes of death around the world, according to WHO there are about three million people die each year from respiratory diseases, an estimated 6% of all deaths worldwide. The goal of the paper is to be able to diagnose the respiratory disease from lung sound using ensemble model and applying data augmentation. This technique may help healthcare professionals to save people's life. The aim was to classify two classes from a dataset of respiratory sounds. The model used in this paper was a combination between CNN and Random Forest to classify the respiratory disease with accuracy of 93%.
{"title":"Predicting Respiratory Diseases from Lung Sounds using Ensemble Model","authors":"Razan S. Youssef, S. Youssef, N. Ghatwary","doi":"10.1109/ICCSPA55860.2022.10019194","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019194","url":null,"abstract":"The paper introduces an ensemble model combined with CNN and data augmentation to predict respiratory diseases. Respiratory diseases are one of the top causes of death around the world, according to WHO there are about three million people die each year from respiratory diseases, an estimated 6% of all deaths worldwide. The goal of the paper is to be able to diagnose the respiratory disease from lung sound using ensemble model and applying data augmentation. This technique may help healthcare professionals to save people's life. The aim was to classify two classes from a dataset of respiratory sounds. The model used in this paper was a combination between CNN and Random Forest to classify the respiratory disease with accuracy of 93%.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115784566","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/ICCSPA55860.2022.10019121
Sulaiman A. Aburakhia, Tareq Tayeh, Ryan Myers, Abdallah Shami
Within smart manufacturing, data driven techniques are commonly adopted for condition monitoring and fault diagnosis of rotating machinery. Classical approaches use supervised learning where a classifier is trained on labeled data to predict or classify different operational states of the machine. However, in most industrial applications, labeled data is limited in terms of its size and type. Hence, it cannot serve the training purpose. In this paper, this problem is tackled by addressing the classification task as a similarity measure to a reference sample rather than a supervised classification task. Similarity-based approaches require a limited amount of labeled data and hence, meet the requirements of real-world industrial applications. Accordingly, the paper introduces a similarity-based framework for predictive maintenance (PdM) of rotating machinery. For each operational state of the machine, a reference vibration signal is generated and labeled according to the machine's operational condition. Consequentially, statistical time analysis, fast Fourier transform (FFT), and short-time Fourier transform (STFT) are used to extract features from the captured vibration signals. For each feature type, three similarity metrics, namely structural similarity measure (SSM), cosine similarity, and Euclidean distance are used to measure the similarity between test signals and reference signals in the feature space. Hence, nine settings in terms of feature type-similarity measure combinations are evaluated. Experimental results confirm the effectiveness of similarity-based approaches in achieving very high accuracy with moderate computational requirements compared to machine learning (ML)-based methods. Further, the results indicate that using FFT features with cosine similarity would lead to better performance compared to the other settings.
{"title":"Similarity-Based Predictive Maintenance Framework for Rotating Machinery","authors":"Sulaiman A. Aburakhia, Tareq Tayeh, Ryan Myers, Abdallah Shami","doi":"10.1109/ICCSPA55860.2022.10019121","DOIUrl":"https://doi.org/10.1109/ICCSPA55860.2022.10019121","url":null,"abstract":"Within smart manufacturing, data driven techniques are commonly adopted for condition monitoring and fault diagnosis of rotating machinery. Classical approaches use supervised learning where a classifier is trained on labeled data to predict or classify different operational states of the machine. However, in most industrial applications, labeled data is limited in terms of its size and type. Hence, it cannot serve the training purpose. In this paper, this problem is tackled by addressing the classification task as a similarity measure to a reference sample rather than a supervised classification task. Similarity-based approaches require a limited amount of labeled data and hence, meet the requirements of real-world industrial applications. Accordingly, the paper introduces a similarity-based framework for predictive maintenance (PdM) of rotating machinery. For each operational state of the machine, a reference vibration signal is generated and labeled according to the machine's operational condition. Consequentially, statistical time analysis, fast Fourier transform (FFT), and short-time Fourier transform (STFT) are used to extract features from the captured vibration signals. For each feature type, three similarity metrics, namely structural similarity measure (SSM), cosine similarity, and Euclidean distance are used to measure the similarity between test signals and reference signals in the feature space. Hence, nine settings in terms of feature type-similarity measure combinations are evaluated. Experimental results confirm the effectiveness of similarity-based approaches in achieving very high accuracy with moderate computational requirements compared to machine learning (ML)-based methods. Further, the results indicate that using FFT features with cosine similarity would lead to better performance compared to the other settings.","PeriodicalId":106639,"journal":{"name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130702787","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：