Pub Date : 2022-09-02DOI: 10.1109/ICCE-Berlin56473.2022.9937121
Walmir A. Silva, M. N. Rylo, Guido Soprano Machado, R. L. Medeiros, V. Lucena
Maintenance aims to keep the vehicle in good working order and avoid unpleasant surprises, such as mechanical breakdown and component breakage due to damaged parts, increasing losses. Currently, to detect these problems, the On-Board Diagnostic II (OBD-II) is used to diagnose issues in the Electronic Control Unit (ECU). Data are obtained from it by employing adapters, and such data are used in various applications. Ambient intelligence (AmI) is an environment with several devices connected in a wired or wireless network to obtain data from users without knowing it to aid and automate routine tasks. In this way, we consider that can access the information a home AmI can offer through these devices. In this context, would it be possible to connect the car to the AmI to provide information that will help us avoid significant vehicle problems? This paper presents a system capable of sending vehicle information to the user's smartphone via the messaging app alerting that the vehicle is above average temperature.
{"title":"Continuous Supervision and Diagnostics System for Legacy Vehicles Integrated to Ambient Intelligence","authors":"Walmir A. Silva, M. N. Rylo, Guido Soprano Machado, R. L. Medeiros, V. Lucena","doi":"10.1109/ICCE-Berlin56473.2022.9937121","DOIUrl":"https://doi.org/10.1109/ICCE-Berlin56473.2022.9937121","url":null,"abstract":"Maintenance aims to keep the vehicle in good working order and avoid unpleasant surprises, such as mechanical breakdown and component breakage due to damaged parts, increasing losses. Currently, to detect these problems, the On-Board Diagnostic II (OBD-II) is used to diagnose issues in the Electronic Control Unit (ECU). Data are obtained from it by employing adapters, and such data are used in various applications. Ambient intelligence (AmI) is an environment with several devices connected in a wired or wireless network to obtain data from users without knowing it to aid and automate routine tasks. In this way, we consider that can access the information a home AmI can offer through these devices. In this context, would it be possible to connect the car to the AmI to provide information that will help us avoid significant vehicle problems? This paper presents a system capable of sending vehicle information to the user's smartphone via the messaging app alerting that the vehicle is above average temperature.","PeriodicalId":138931,"journal":{"name":"2022 IEEE 12th International Conference on Consumer Electronics (ICCE-Berlin)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115051860","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 : 2022-09-02DOI: 10.1109/ICCE-Berlin56473.2022.10021310
N. Anagnostopoulos, Yufan Fan, Muhammad Umair Saleem, Nico Mexis, Emiliia Geloczi, Felix Klement, Florian Frank, André Schaller, T. Arul, S. Katzenbeisser
In this work, we present a Physical Unclonable Function (PUF) implemented on a Commercial Off-The-Shelf (COTS) NAND Flash memory module using programming disturbances, and examine the robustness of its responses to environmental variations. In particular, we test a removable Flash memory module serving as a PUF, under nominal conditions, as well as under temperature and voltage variations. To determine its resilience to environmental variations, we utilise well-known PUF metrics, such as the Hamming weight and the intra-device Hamming distance. Our results prove that, in general, the tested Samsung K9F1G08U0E NAND Flash memory can be used to realise a lightweight, scalable, and flexible hardware security primitive, namely a PUF, that can be utilised in the context of smart homes, smart vehicles, and other smart applications, as well as to protect commercial devices and networks in general. However, voltage variations seem to pose a substantial threat to the adoption of this PUF in practice. This threat may be addressed by small-scale design improvements that should be implemented and tested in practice as part of future works.
{"title":"Testing Physical Unclonable Functions Implemented on Commercial Off-the-Shelf NAND Flash Memories Using Programming Disturbances","authors":"N. Anagnostopoulos, Yufan Fan, Muhammad Umair Saleem, Nico Mexis, Emiliia Geloczi, Felix Klement, Florian Frank, André Schaller, T. Arul, S. Katzenbeisser","doi":"10.1109/ICCE-Berlin56473.2022.10021310","DOIUrl":"https://doi.org/10.1109/ICCE-Berlin56473.2022.10021310","url":null,"abstract":"In this work, we present a Physical Unclonable Function (PUF) implemented on a Commercial Off-The-Shelf (COTS) NAND Flash memory module using programming disturbances, and examine the robustness of its responses to environmental variations. In particular, we test a removable Flash memory module serving as a PUF, under nominal conditions, as well as under temperature and voltage variations. To determine its resilience to environmental variations, we utilise well-known PUF metrics, such as the Hamming weight and the intra-device Hamming distance. Our results prove that, in general, the tested Samsung K9F1G08U0E NAND Flash memory can be used to realise a lightweight, scalable, and flexible hardware security primitive, namely a PUF, that can be utilised in the context of smart homes, smart vehicles, and other smart applications, as well as to protect commercial devices and networks in general. However, voltage variations seem to pose a substantial threat to the adoption of this PUF in practice. This threat may be addressed by small-scale design improvements that should be implemented and tested in practice as part of future works.","PeriodicalId":138931,"journal":{"name":"2022 IEEE 12th International Conference on Consumer Electronics (ICCE-Berlin)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116443871","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 : 2022-09-02DOI: 10.1109/ICCE-Berlin56473.2022.9937136
Daniel Nicolas Bailon, S. Shavgulidze, J. Freudenberger
Automotive computing applications like AI databases, ADAS, and advanced infotainment systems have a huge need for persistent memory. This trend requires NAND flash memories designed for extreme automotive environments. However, the error probability of NAND flash memories has increased in recent years due to higher memory density and production tolerances. Hence, strong error correction coding is needed to meet automotive storage requirements. Many errors can be corrected by soft decoding algorithms. However, soft decoding is very resource-intensive and should be avoided when possible. NAND flash memories are organized in pages, and the error correction codes are usually encoded page-wise to reduce the latency of random reads. This page-wise encoding does not reach the maximum achievable capacity. Reading soft information increases the channel capacity but at the cost of higher latency and power consumption. In this work, we consider cell-wise encoding, which also increases the capacity compared to page-wise encoding. We analyze the cell-wise processing of data in triple-level cell (TLC) NAND flash and show the performance gain when using Low-Density Parity-Check (LDPC) codes. In addition, we investigate a coding approach with page-wise encoding and cell-wise reading.
{"title":"Cell-wise encoding and decoding for TLC flash memories","authors":"Daniel Nicolas Bailon, S. Shavgulidze, J. Freudenberger","doi":"10.1109/ICCE-Berlin56473.2022.9937136","DOIUrl":"https://doi.org/10.1109/ICCE-Berlin56473.2022.9937136","url":null,"abstract":"Automotive computing applications like AI databases, ADAS, and advanced infotainment systems have a huge need for persistent memory. This trend requires NAND flash memories designed for extreme automotive environments. However, the error probability of NAND flash memories has increased in recent years due to higher memory density and production tolerances. Hence, strong error correction coding is needed to meet automotive storage requirements. Many errors can be corrected by soft decoding algorithms. However, soft decoding is very resource-intensive and should be avoided when possible. NAND flash memories are organized in pages, and the error correction codes are usually encoded page-wise to reduce the latency of random reads. This page-wise encoding does not reach the maximum achievable capacity. Reading soft information increases the channel capacity but at the cost of higher latency and power consumption. In this work, we consider cell-wise encoding, which also increases the capacity compared to page-wise encoding. We analyze the cell-wise processing of data in triple-level cell (TLC) NAND flash and show the performance gain when using Low-Density Parity-Check (LDPC) codes. In addition, we investigate a coding approach with page-wise encoding and cell-wise reading.","PeriodicalId":138931,"journal":{"name":"2022 IEEE 12th International Conference on Consumer Electronics (ICCE-Berlin)","volume":"31 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116848968","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 : 2022-09-02DOI: 10.1109/ICCE-Berlin56473.2022.9937135
M. N. Rylo, Walmir A. Silva, R. L. P. Medeiros, V. Lucena
This paper evaluated two machine learning techniques using low-frequency photoplethysmography and motion sensor data from wearable devices in gesture segmentation and classification. SVM and random forests were the classifiers selected for testing. Preliminary evaluations show that frequencies of 25 Hz are suitable for the recognition process, achieving an F1-score of 0.819 for seven gesture sets.
{"title":"Gesture recognition of wrist motion using low-frequency PPG","authors":"M. N. Rylo, Walmir A. Silva, R. L. P. Medeiros, V. Lucena","doi":"10.1109/ICCE-Berlin56473.2022.9937135","DOIUrl":"https://doi.org/10.1109/ICCE-Berlin56473.2022.9937135","url":null,"abstract":"This paper evaluated two machine learning techniques using low-frequency photoplethysmography and motion sensor data from wearable devices in gesture segmentation and classification. SVM and random forests were the classifiers selected for testing. Preliminary evaluations show that frequencies of 25 Hz are suitable for the recognition process, achieving an F1-score of 0.819 for seven gesture sets.","PeriodicalId":138931,"journal":{"name":"2022 IEEE 12th International Conference on Consumer Electronics (ICCE-Berlin)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130832520","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 : 2022-09-02DOI: 10.1109/ICCE-Berlin56473.2022.9937118
Daniel Nicolas Bailon, G. Taburet, S. Shavgulidze, J. Freudenberger
Large persistent memory is crucial for many applications in embedded systems and automotive computing like AI databases, ADAS, and cutting-edge infotainment systems. Such applications require reliable NAND flash memories made for harsh automotive conditions. However, due to high memory densities and production tolerances, the error probability of NAND flash memories has risen. As the number of program/erase cycles and the data retention times increase, non-volatile NAND flash memories' performance and dependability suffer. The read reference voltages of the flash cells vary due to these aging processes. In this work, we consider the issue of reference voltage adaption. The considered estimation procedure uses shallow neural networks to estimate the read reference voltages for different life-cycle conditions with the help of histogram measurements. We demonstrate that the training data for the neural networks can be enhanced by using shifted histograms, i.e., a training of the neural networks is possible based on a few measurements of some extreme points used as training data. The trained neural networks generalize well for other life-cycle conditions.
{"title":"Neural network aided reference voltage adaptation for NAND flash memory","authors":"Daniel Nicolas Bailon, G. Taburet, S. Shavgulidze, J. Freudenberger","doi":"10.1109/ICCE-Berlin56473.2022.9937118","DOIUrl":"https://doi.org/10.1109/ICCE-Berlin56473.2022.9937118","url":null,"abstract":"Large persistent memory is crucial for many applications in embedded systems and automotive computing like AI databases, ADAS, and cutting-edge infotainment systems. Such applications require reliable NAND flash memories made for harsh automotive conditions. However, due to high memory densities and production tolerances, the error probability of NAND flash memories has risen. As the number of program/erase cycles and the data retention times increase, non-volatile NAND flash memories' performance and dependability suffer. The read reference voltages of the flash cells vary due to these aging processes. In this work, we consider the issue of reference voltage adaption. The considered estimation procedure uses shallow neural networks to estimate the read reference voltages for different life-cycle conditions with the help of histogram measurements. We demonstrate that the training data for the neural networks can be enhanced by using shifted histograms, i.e., a training of the neural networks is possible based on a few measurements of some extreme points used as training data. The trained neural networks generalize well for other life-cycle conditions.","PeriodicalId":138931,"journal":{"name":"2022 IEEE 12th International Conference on Consumer Electronics (ICCE-Berlin)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131382309","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 : 2022-09-02DOI: 10.1109/ICCE-Berlin56473.2022.9937111
Loujaina Hatim Backar, Meriam A. Khalifa, Mohammed Abdel-Megeed Salem
Driving drowsiness detection through videos/images is one of the most important issues for driver safety in today's world. Because of the great advancements in technology in the last few decades, deep learning techniques applied to computer vision applications such as sleep detection have shown promising results. Drowsiness is characterised by closed eyes, yawning, and micro-sleeps. Moreover, one of the biggest tragedies in the news lately, is toddlers or pets dying from heat built up in cars. In this work, a real-time deep learning algorithm is designed to monitor driver drowsiness, driver distraction, as well as an alert system for forgetting children and pets, and a seat belt usage system. The approach taken was to recognise and localise the face, eyes, and mouth, using the Dlib library, Histogram of Oriented Gradients, and a facial landmark predictor. The eye aspect ratio and the mouth aspect ratio are then calculated and evaluated for yawning detection and micro-sleep detection. The information on the driver's state was saved using a Firebase real-time database. This information is used by the children and pets detection algorithm, which sends an automatic email to the driver if a child or pet is discovered in the backseat when the driver is not in the car. When a driver uses a cell phone, eats, or drinks while driving, this is considered as a distraction. Canny edge detection is used to monitor the seat belt. Furthermore, the proposed method was subjected to several rounds of testing, that proved its viability and reliability.
{"title":"In-Vehicle Monitoring for Passengers' Safety","authors":"Loujaina Hatim Backar, Meriam A. Khalifa, Mohammed Abdel-Megeed Salem","doi":"10.1109/ICCE-Berlin56473.2022.9937111","DOIUrl":"https://doi.org/10.1109/ICCE-Berlin56473.2022.9937111","url":null,"abstract":"Driving drowsiness detection through videos/images is one of the most important issues for driver safety in today's world. Because of the great advancements in technology in the last few decades, deep learning techniques applied to computer vision applications such as sleep detection have shown promising results. Drowsiness is characterised by closed eyes, yawning, and micro-sleeps. Moreover, one of the biggest tragedies in the news lately, is toddlers or pets dying from heat built up in cars. In this work, a real-time deep learning algorithm is designed to monitor driver drowsiness, driver distraction, as well as an alert system for forgetting children and pets, and a seat belt usage system. The approach taken was to recognise and localise the face, eyes, and mouth, using the Dlib library, Histogram of Oriented Gradients, and a facial landmark predictor. The eye aspect ratio and the mouth aspect ratio are then calculated and evaluated for yawning detection and micro-sleep detection. The information on the driver's state was saved using a Firebase real-time database. This information is used by the children and pets detection algorithm, which sends an automatic email to the driver if a child or pet is discovered in the backseat when the driver is not in the car. When a driver uses a cell phone, eats, or drinks while driving, this is considered as a distraction. Canny edge detection is used to monitor the seat belt. Furthermore, the proposed method was subjected to several rounds of testing, that proved its viability and reliability.","PeriodicalId":138931,"journal":{"name":"2022 IEEE 12th International Conference on Consumer Electronics (ICCE-Berlin)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131618045","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 : 2022-09-02DOI: 10.1109/ICCE-Berlin56473.2022.9937098
S. Bianco, Gabriele Ferrario, Paolo Napoletano
Large-scale pre-trained language models, which have learned cross-modal representations on image-text pairs, are becoming popular for vision-language tasks because the fine-tuning to a specific task enables state-of-the-art results. Existing methods require features of image regions as input, but these regions are extracted with an object detection model that does not handle overlapping, noisy and ambiguous regions; this inevitably results in less meaningful features. In this paper we propose a new way to extract region features based on image segmentation, with the goal of reducing overlapping and noise. Our method is motivated by the observation that image segmentation can remove useless pixels using the binary mask to extract only the object of interest.
{"title":"Image Captioning using Pretrained Language Models and Image Segmentation","authors":"S. Bianco, Gabriele Ferrario, Paolo Napoletano","doi":"10.1109/ICCE-Berlin56473.2022.9937098","DOIUrl":"https://doi.org/10.1109/ICCE-Berlin56473.2022.9937098","url":null,"abstract":"Large-scale pre-trained language models, which have learned cross-modal representations on image-text pairs, are becoming popular for vision-language tasks because the fine-tuning to a specific task enables state-of-the-art results. Existing methods require features of image regions as input, but these regions are extracted with an object detection model that does not handle overlapping, noisy and ambiguous regions; this inevitably results in less meaningful features. In this paper we propose a new way to extract region features based on image segmentation, with the goal of reducing overlapping and noise. Our method is motivated by the observation that image segmentation can remove useless pixels using the binary mask to extract only the object of interest.","PeriodicalId":138931,"journal":{"name":"2022 IEEE 12th International Conference on Consumer Electronics (ICCE-Berlin)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125676792","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 : 2022-09-02DOI: 10.1109/ICCE-Berlin56473.2022.9937087
Javier Usón, J. Cabrera, Daniel Corregidor, Narciso García
Volumetric video acquisition systems enable realistic virtual experiences such as Free-Viewpoint Video (FVV). Stereo matching is a well known way of obtaining this volumetric information as depth images, calculating the disparity be-tween two stereo color images. On these applications, the background of the scene captured is static and does not change, so foreground information is much more valuable. We propose adding foreground segmentation to help learning based algorithms, such as deep learning models, improve results previously obtained. We utilized the framework De-tectron2 to model foreground segmentation by detecting people. Additionally, we built a large stereo dataset focused on FVV systems. Finally, we modified a successful deep learning model from the state-of-the-art, CREStereo, to add foreground segmentation and performed supervised training on it to estimate disparity, obtaining promising results.
{"title":"Analysing Foreground Segmentation in Deep Learning Based Depth Estimation on Free-Viewpoint Video Systems","authors":"Javier Usón, J. Cabrera, Daniel Corregidor, Narciso García","doi":"10.1109/ICCE-Berlin56473.2022.9937087","DOIUrl":"https://doi.org/10.1109/ICCE-Berlin56473.2022.9937087","url":null,"abstract":"Volumetric video acquisition systems enable realistic virtual experiences such as Free-Viewpoint Video (FVV). Stereo matching is a well known way of obtaining this volumetric information as depth images, calculating the disparity be-tween two stereo color images. On these applications, the background of the scene captured is static and does not change, so foreground information is much more valuable. We propose adding foreground segmentation to help learning based algorithms, such as deep learning models, improve results previously obtained. We utilized the framework De-tectron2 to model foreground segmentation by detecting people. Additionally, we built a large stereo dataset focused on FVV systems. Finally, we modified a successful deep learning model from the state-of-the-art, CREStereo, to add foreground segmentation and performed supervised training on it to estimate disparity, obtaining promising results.","PeriodicalId":138931,"journal":{"name":"2022 IEEE 12th International Conference on Consumer Electronics (ICCE-Berlin)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116586501","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 : 2022-09-02DOI: 10.1109/ICCE-Berlin56473.2022.9937102
S. Bianco, M. Buzzelli, Gianluca Giudice
The recognition of logos can be useful in developing autonomous checkout systems, or monitoring brand presence and advertisement in shopping malls. The continuous generation and update of new brand logos imposes the definition of a flexible solution to the problem. We therefore define a two-stage logo recognition system composed of an agnostic logo detector, to locate image regions that possess generic logo-like characteristics, and an incremental logo classifier, to progressively update the set of known logo classes. We investigate our solution's sensitivity to regularization and availability of training samples, and we develop two alternative techniques for model compression. Results are presented and compared with state of the art solutions, showing promising results. Our code is made available for public download.
{"title":"Incremental Two-Stage Logo Recognition with Knowledge Distillation","authors":"S. Bianco, M. Buzzelli, Gianluca Giudice","doi":"10.1109/ICCE-Berlin56473.2022.9937102","DOIUrl":"https://doi.org/10.1109/ICCE-Berlin56473.2022.9937102","url":null,"abstract":"The recognition of logos can be useful in developing autonomous checkout systems, or monitoring brand presence and advertisement in shopping malls. The continuous generation and update of new brand logos imposes the definition of a flexible solution to the problem. We therefore define a two-stage logo recognition system composed of an agnostic logo detector, to locate image regions that possess generic logo-like characteristics, and an incremental logo classifier, to progressively update the set of known logo classes. We investigate our solution's sensitivity to regularization and availability of training samples, and we develop two alternative techniques for model compression. Results are presented and compared with state of the art solutions, showing promising results. Our code is made available for public download.","PeriodicalId":138931,"journal":{"name":"2022 IEEE 12th International Conference on Consumer Electronics (ICCE-Berlin)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120987699","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 : 2022-09-02DOI: 10.1109/ICCE-Berlin56473.2022.9937124
M. Shawki, Ziad Ayman, Kareem Mahmoud, T. Elshabrawy
Nowadays, the internet of things and its application have rapid growth in the industry and research committee. Many of those applications require long battery life. Such applications have motivated the recent developments in LoRa technology. LoRa has a simple modulation scheme that allows the transmission with low power consumption, low bit rates, and extensive coverage area through an loT network. As a result, the capacity estimation of LoRa networks has paramount importance in the design phase. This paper aims to develop a LoRa network emulator that can represent the LoRa traffic received from thousands of loT devices at a given LoRa gateway. The proposed emulator utilizes a software defined radio (SDR) device and LoRa commercial transceiver to design a realistic network capacity estimation. The proposed network emulator incorporates different wireless channel conditions within the network under study. Furthermore, the transmitted signals from the SDR consider interference scenarios in terms of relative time over lap as well as SIR between interfering signals. The capacity of LoRa networks can be evaluated by the proposed emulator. The presented emulator for capacity evaluation has the advantage that it derives the cumulative distribution that could be supported from the cell-edge towards the cell-center of an individual LoRa gateway. The experimental result shows that the emulator can generate a representative SIR/SNR profile by comparing target emulated traffic signal level cumulative distribution with that measured by a commercial LoRa transceiver. The emulator adopts a calibration process such that the confidence interval for estimated data extraction rate performance is within the scale of ±2 %.
{"title":"A LoRa Network Emulator Using Software Defined Radio","authors":"M. Shawki, Ziad Ayman, Kareem Mahmoud, T. Elshabrawy","doi":"10.1109/ICCE-Berlin56473.2022.9937124","DOIUrl":"https://doi.org/10.1109/ICCE-Berlin56473.2022.9937124","url":null,"abstract":"Nowadays, the internet of things and its application have rapid growth in the industry and research committee. Many of those applications require long battery life. Such applications have motivated the recent developments in LoRa technology. LoRa has a simple modulation scheme that allows the transmission with low power consumption, low bit rates, and extensive coverage area through an loT network. As a result, the capacity estimation of LoRa networks has paramount importance in the design phase. This paper aims to develop a LoRa network emulator that can represent the LoRa traffic received from thousands of loT devices at a given LoRa gateway. The proposed emulator utilizes a software defined radio (SDR) device and LoRa commercial transceiver to design a realistic network capacity estimation. The proposed network emulator incorporates different wireless channel conditions within the network under study. Furthermore, the transmitted signals from the SDR consider interference scenarios in terms of relative time over lap as well as SIR between interfering signals. The capacity of LoRa networks can be evaluated by the proposed emulator. The presented emulator for capacity evaluation has the advantage that it derives the cumulative distribution that could be supported from the cell-edge towards the cell-center of an individual LoRa gateway. The experimental result shows that the emulator can generate a representative SIR/SNR profile by comparing target emulated traffic signal level cumulative distribution with that measured by a commercial LoRa transceiver. The emulator adopts a calibration process such that the confidence interval for estimated data extraction rate performance is within the scale of ±2 %.","PeriodicalId":138931,"journal":{"name":"2022 IEEE 12th International Conference on Consumer Electronics (ICCE-Berlin)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128882751","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：