New Trends in Image Analysis and Processing – ICIAP 2019, 2019
IoT end-user devices are attractive and sometime easy targets for attackers, because they are oft... more IoT end-user devices are attractive and sometime easy targets for attackers, because they are often vulnerable in different aspects. Cyberattacks, started from those devices, can easily disrupt the availability of services offered by major internet companies. People that commonly get access to them across the world may experience abrupt interruption of services they use. In that context, this paper describes an embedded prototype to classify intrusions, affecting TCP packets. The proposed solution adopts an Artificial Neural Network (ANN) executed on resource-constrained and low-cost embedded micro controllers. The prototype operates without the need of remote intelligence assist. The adoption of an on-the-edge artificial intelligence architecture brings advantages such as responsiveness, promptness and low power consumption. The embedded intelligence is trained by using the well-known KDD Cup 1999 dataset, properly balanced on 5 types of labelled intrusions patterns. A pre-trained ANN classifies features extracted from TCP packets. The results achieved in this paper refer to the application running on the low cost widely available Nucleo STM32 micro controller boards from STMicroelectronics, featuring a F3 chip running at 72 MHz and a F4 chip running at 84 MHz with small embedded RAM and Flash memory.
The focus of this work is to design a deeply quantized anomaly detector of oil leaks that may hap... more The focus of this work is to design a deeply quantized anomaly detector of oil leaks that may happen at the junction between the wind turbine high-speed shaft and the external bracket of the power generator. We propose a block-based binary shallow echo state network (BBS-ESN) architecture belonging to the reservoir computing (RC) category and, as we believe, it also extends the extreme learning machines (ELM) domain. Furthermore, BBS-ESN performs binary block-based online training using fixed and minimal computational complexity to achieve low power consumption and deployability on an off-the-shelf micro-controller (MCU). This has been achieved through binarization of the images and 1-bit quantization of the network weights and activations. 3D rendering has been used to generate a novel publicly available dataset of photo-realistic images similar to those potentially acquired by image sensors on the field while monitoring the junction, without and with oil leaks. Extensive experimen...
This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived a... more This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived as a starting point for developing and validating DoA algorithms for real-life scenarios. Unlike other datasets, it contains Bluetooth signals with not only varying intensity of additive white Gaussian noise, but also coherent interfering signals with random DoA coordinates. The dataset is divided into two branches, one consisting of pure sinusoidal tones and the second comprised of baseband Bluetooth signals. The Python code which generated this dataset is included. Therefore, the dataset can be expanded and also modified to suit other types of signals and simulate other types of antenna arrays. Please note that this is only the first part of the dataset. The dataset is comprised of four parts, and you need to download all of them in order to recreate the entire directory structure. Part 1: http://dx.doi.org/10.17632/zjn2zxcgyz.1 Part 2: http://dx.doi.org/10.17632/gysjfpvxpm.1 Part 3: ht...
Accurate pedestrian detection has a primary role in automotive safety: for example, by issuing wa... more Accurate pedestrian detection has a primary role in automotive safety: for example, by issuing warnings to the driver or acting actively on car's brakes, it helps decreasing the probability of injuries and human fatalities. In order to achieve very high accuracy, recent pedestrian detectors have been based on Convolutional Neural Networks (CNN). Unfortunately, such approaches require vast amounts of computational power and memory, preventing efficient implementations on embedded systems. This work proposes a CNN-based detector, adapting a general-purpose convolutional network to the task at hand. By thoroughly analyzing and optimizing each step of the detection pipeline, we develop an architecture that outperforms methods based on traditional image features and achieves an accuracy close to the state-of-the-art while having low computational complexity. Furthermore, the model is compressed in order to fit the tight constrains of low power devices with a limited amount of embedde...
Echo State Networks (ESN) are a class of Recurrent Neural Networks (RNN) that has gained substant... more Echo State Networks (ESN) are a class of Recurrent Neural Networks (RNN) that has gained substantial popularity due to their effectiveness, ease of use and potential for compact hardware implementation. An ESN contains the three network layers input, reservoir and readout where the reservoir is the truly recurrent network. The input and reservoir layers of an ESN are initialized at random and never trained afterwards and the training of the ESN is applied to the readout layer only. The alternative of Recursive Neural Gas (RNG) is one of the many proposals of fully-trainable reservoirs that can be found in the literature. Although some improvements in performance have been reported with RNG, to the best of authors' knowledge, no experimental comparative results are known with benchmarks for which ESN is known to yield excellent results. This work describes an accurate model of RNG together with some extensions to the models presented in the literature and shows comparative result...
This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived a... more This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived as a starting point for developing and validating DoA algorithms for real-life scenarios. Unlike other datasets, it contains Bluetooth signals with not only varying intensity of additive white Gaussian noise, but also coherent interfering signals with random DoA coordinates. The dataset is divided into two branches, one consisting of pure sinusoidal tones and the second comprised of baseband Bluetooth signals. The Python code which generated this dataset is included. Therefore, the dataset can be expanded and also modified to suit other types of signals and simulate other types of antenna arrays. Please note that this is only the first part of the dataset. The dataset is comprised of four parts, and you need to download all of them in order to recreate the entire directory structure. Part 1: http://dx.doi.org/10.17632/zjn2zxcgyz.1 Part 2: http://dx.doi.org/10.17632/gysjfpvxpm.1 Part 3: ht...
This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived a... more This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived as a starting point for developing and validating DoA algorithms for real-life scenarios. Unlike other datasets, it contains Bluetooth signals with not only varying intensity of additive white Gaussian noise, but also coherent interfering signals with random DoA coordinates. The dataset is divided into two branches, one consisting of pure sinusoidal tones and the second comprised of baseband Bluetooth signals. The Python code which generated this dataset is included. Therefore, the dataset can be expanded and also modified to suit other types of signals and simulate other types of antenna arrays. Please note that this is only the first part of the dataset. The dataset is comprised of four parts, and you need to download all of them in order to recreate the entire directory structure. Part 1: http://dx.doi.org/10.17632/zjn2zxcgyz.1 Part 2: http://dx.doi.org/10.17632/gysjfpvxpm.1 Part 3: ht...
This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived a... more This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived as a starting point for developing and validating DoA algorithms for real-life scenarios. Unlike other datasets, it contains Bluetooth signals with not only varying intensity of additive white Gaussian noise, but also coherent interfering signals with random DoA coordinates. The dataset is divided into two branches, one consisting of pure sinusoidal tones and the second comprised of baseband Bluetooth signals. The Python code which generated this dataset is included. Therefore, the dataset can be expanded and also modified to suit other types of signals and simulate other types of antenna arrays. Please note that this is only the first part of the dataset. The dataset is comprised of four parts, and you need to download all of them in order to recreate the entire directory structure. Part 1: http://dx.doi.org/10.17632/zjn2zxcgyz.1 Part 2: http://dx.doi.org/10.17632/gysjfpvxpm.1 Part 3: ht...
This paper presents the state-of-the-art review of the different approaches for Neural Architectu... more This paper presents the state-of-the-art review of the different approaches for Neural Architecture Search targeting resource constrained devices such as microcontrollers. As well as the implementations of On-Device learning techniques for those devices.
2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN), 2018
In this demo, we present COSSIM, an open-source simulation framework for cloud applications. Our ... more In this demo, we present COSSIM, an open-source simulation framework for cloud applications. Our solution models the client and server computing devices as well as the network that comprise the overall system and thus provides cycle accurate results, realistic communications and power/energy consumption estimates based on the actual dynamic usage scenarios. The simulator provides the necessary hooks to security testing software and can be extended through an IEEE standardized interface to include additional tools, such as simulators of physical models. The application that will be used to demonstrate COSSIM is mobile visual search, where mobile nodes capture images, extract their compressed representation and dispatch a query to the cloud. A server compares the received query to a local database and sends back some of the corresponding results.
Medical assessment of bone health often uses quantitative computed tomography (QCT) scans and req... more Medical assessment of bone health often uses quantitative computed tomography (QCT) scans and requires a reliable segmentation of bone geometry from surrounding tissues for a quick determination of bone mineral mass. Because of its shape and position in the body, the femur is one of the most challenging bones to investigate. In the current study, we developed a new automated way to accurately evaluate both the shape and the mineral mass of cadaveric femur. The results were achieved through a series of steps including the segmentation of bone tissue from sets of QCT images, the estimation of the bone’s outer surface, the calculation of the volume enclosed, and finally the evaluation of bone mineral mass in a user-defined region. We compared our algorithms outputs to results obtained by expert manual segmentation and those obtained using other published methods. Key Words Image based meshing, deformable models, femur shape QCT, mineral mass, finite element analysis, osteoporosis 1.
2021 International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET), 2021
The High Accuracy Asset Tracking (HAAT) of Bluetooth 5.1 Low Energy needs tiny antenna arrays to ... more The High Accuracy Asset Tracking (HAAT) of Bluetooth 5.1 Low Energy needs tiny antenna arrays to achieve efficient and very compact solutions. Rectangular Antenna Arrays guarantee good performances, both in azimuth and elevation in the Direction of arrival (DoA) estimation. This paper studies the eight antenna rectangular array topology, called URA8. Historically, MUSIC has been the most used algorithm on this type of array. Unfortunately in HAAT real-time applications, where it is essential to have a fast response from the DoA Locator, MUSIC, due to its high computational complexity in the peak searching over the pseudo-spectrum, may be inadequate for the scope. This paper proposes an innovative approach to reduce the complexity of this peak-searching phase: instead of only one peak-search over the complete azimuth-elevation hemisphere, we propose a two step search, the first with a reduced resolution and the latter with a fine resolution inside a proper confidence region, found in the first step. The proposed method ensures a good trade-off between computational complexity and detection performances: it turns out to approximately 6 times faster than the classic MUSIC, maintaining the same precision.
Neural networks and Machine Learning in general, represent today one of the greatest expectations... more Neural networks and Machine Learning in general, represent today one of the greatest expectations for the realization of models that can serve to determine the behavior and operation of different physical systems. Undoubtedly the calculation resources necessary for the training and the realization of the model are great especially if linked to the amount of data needed to detect the salient parameters of the model. At the same time, the models so obtained can be integrated on embedded systems, thanks to TinyML technologies, allowing to work exactly where the physical phenomena to analyze happen. In the consumer and industrial world these technologies have taken hold, and are also watched with interest by other sectors such as the automotive world. In this article we present a framework for the implementation of models based on neural networks on automotive family microprocessors, demonstrating their efficiency in two typical applications of the vehicle world: intrusion detection on ...
New Trends in Image Analysis and Processing – ICIAP 2019, 2019
IoT end-user devices are attractive and sometime easy targets for attackers, because they are oft... more IoT end-user devices are attractive and sometime easy targets for attackers, because they are often vulnerable in different aspects. Cyberattacks, started from those devices, can easily disrupt the availability of services offered by major internet companies. People that commonly get access to them across the world may experience abrupt interruption of services they use. In that context, this paper describes an embedded prototype to classify intrusions, affecting TCP packets. The proposed solution adopts an Artificial Neural Network (ANN) executed on resource-constrained and low-cost embedded micro controllers. The prototype operates without the need of remote intelligence assist. The adoption of an on-the-edge artificial intelligence architecture brings advantages such as responsiveness, promptness and low power consumption. The embedded intelligence is trained by using the well-known KDD Cup 1999 dataset, properly balanced on 5 types of labelled intrusions patterns. A pre-trained ANN classifies features extracted from TCP packets. The results achieved in this paper refer to the application running on the low cost widely available Nucleo STM32 micro controller boards from STMicroelectronics, featuring a F3 chip running at 72 MHz and a F4 chip running at 84 MHz with small embedded RAM and Flash memory.
The focus of this work is to design a deeply quantized anomaly detector of oil leaks that may hap... more The focus of this work is to design a deeply quantized anomaly detector of oil leaks that may happen at the junction between the wind turbine high-speed shaft and the external bracket of the power generator. We propose a block-based binary shallow echo state network (BBS-ESN) architecture belonging to the reservoir computing (RC) category and, as we believe, it also extends the extreme learning machines (ELM) domain. Furthermore, BBS-ESN performs binary block-based online training using fixed and minimal computational complexity to achieve low power consumption and deployability on an off-the-shelf micro-controller (MCU). This has been achieved through binarization of the images and 1-bit quantization of the network weights and activations. 3D rendering has been used to generate a novel publicly available dataset of photo-realistic images similar to those potentially acquired by image sensors on the field while monitoring the junction, without and with oil leaks. Extensive experimen...
This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived a... more This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived as a starting point for developing and validating DoA algorithms for real-life scenarios. Unlike other datasets, it contains Bluetooth signals with not only varying intensity of additive white Gaussian noise, but also coherent interfering signals with random DoA coordinates. The dataset is divided into two branches, one consisting of pure sinusoidal tones and the second comprised of baseband Bluetooth signals. The Python code which generated this dataset is included. Therefore, the dataset can be expanded and also modified to suit other types of signals and simulate other types of antenna arrays. Please note that this is only the first part of the dataset. The dataset is comprised of four parts, and you need to download all of them in order to recreate the entire directory structure. Part 1: http://dx.doi.org/10.17632/zjn2zxcgyz.1 Part 2: http://dx.doi.org/10.17632/gysjfpvxpm.1 Part 3: ht...
Accurate pedestrian detection has a primary role in automotive safety: for example, by issuing wa... more Accurate pedestrian detection has a primary role in automotive safety: for example, by issuing warnings to the driver or acting actively on car's brakes, it helps decreasing the probability of injuries and human fatalities. In order to achieve very high accuracy, recent pedestrian detectors have been based on Convolutional Neural Networks (CNN). Unfortunately, such approaches require vast amounts of computational power and memory, preventing efficient implementations on embedded systems. This work proposes a CNN-based detector, adapting a general-purpose convolutional network to the task at hand. By thoroughly analyzing and optimizing each step of the detection pipeline, we develop an architecture that outperforms methods based on traditional image features and achieves an accuracy close to the state-of-the-art while having low computational complexity. Furthermore, the model is compressed in order to fit the tight constrains of low power devices with a limited amount of embedde...
Echo State Networks (ESN) are a class of Recurrent Neural Networks (RNN) that has gained substant... more Echo State Networks (ESN) are a class of Recurrent Neural Networks (RNN) that has gained substantial popularity due to their effectiveness, ease of use and potential for compact hardware implementation. An ESN contains the three network layers input, reservoir and readout where the reservoir is the truly recurrent network. The input and reservoir layers of an ESN are initialized at random and never trained afterwards and the training of the ESN is applied to the readout layer only. The alternative of Recursive Neural Gas (RNG) is one of the many proposals of fully-trainable reservoirs that can be found in the literature. Although some improvements in performance have been reported with RNG, to the best of authors' knowledge, no experimental comparative results are known with benchmarks for which ESN is known to yield excellent results. This work describes an accurate model of RNG together with some extensions to the models presented in the literature and shows comparative result...
This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived a... more This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived as a starting point for developing and validating DoA algorithms for real-life scenarios. Unlike other datasets, it contains Bluetooth signals with not only varying intensity of additive white Gaussian noise, but also coherent interfering signals with random DoA coordinates. The dataset is divided into two branches, one consisting of pure sinusoidal tones and the second comprised of baseband Bluetooth signals. The Python code which generated this dataset is included. Therefore, the dataset can be expanded and also modified to suit other types of signals and simulate other types of antenna arrays. Please note that this is only the first part of the dataset. The dataset is comprised of four parts, and you need to download all of them in order to recreate the entire directory structure. Part 1: http://dx.doi.org/10.17632/zjn2zxcgyz.1 Part 2: http://dx.doi.org/10.17632/gysjfpvxpm.1 Part 3: ht...
This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived a... more This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived as a starting point for developing and validating DoA algorithms for real-life scenarios. Unlike other datasets, it contains Bluetooth signals with not only varying intensity of additive white Gaussian noise, but also coherent interfering signals with random DoA coordinates. The dataset is divided into two branches, one consisting of pure sinusoidal tones and the second comprised of baseband Bluetooth signals. The Python code which generated this dataset is included. Therefore, the dataset can be expanded and also modified to suit other types of signals and simulate other types of antenna arrays. Please note that this is only the first part of the dataset. The dataset is comprised of four parts, and you need to download all of them in order to recreate the entire directory structure. Part 1: http://dx.doi.org/10.17632/zjn2zxcgyz.1 Part 2: http://dx.doi.org/10.17632/gysjfpvxpm.1 Part 3: ht...
This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived a... more This is a dataset for Bluetooth 5.1 DoA applications with URA8 antenna arrays. It was conceived as a starting point for developing and validating DoA algorithms for real-life scenarios. Unlike other datasets, it contains Bluetooth signals with not only varying intensity of additive white Gaussian noise, but also coherent interfering signals with random DoA coordinates. The dataset is divided into two branches, one consisting of pure sinusoidal tones and the second comprised of baseband Bluetooth signals. The Python code which generated this dataset is included. Therefore, the dataset can be expanded and also modified to suit other types of signals and simulate other types of antenna arrays. Please note that this is only the first part of the dataset. The dataset is comprised of four parts, and you need to download all of them in order to recreate the entire directory structure. Part 1: http://dx.doi.org/10.17632/zjn2zxcgyz.1 Part 2: http://dx.doi.org/10.17632/gysjfpvxpm.1 Part 3: ht...
This paper presents the state-of-the-art review of the different approaches for Neural Architectu... more This paper presents the state-of-the-art review of the different approaches for Neural Architecture Search targeting resource constrained devices such as microcontrollers. As well as the implementations of On-Device learning techniques for those devices.
2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN), 2018
In this demo, we present COSSIM, an open-source simulation framework for cloud applications. Our ... more In this demo, we present COSSIM, an open-source simulation framework for cloud applications. Our solution models the client and server computing devices as well as the network that comprise the overall system and thus provides cycle accurate results, realistic communications and power/energy consumption estimates based on the actual dynamic usage scenarios. The simulator provides the necessary hooks to security testing software and can be extended through an IEEE standardized interface to include additional tools, such as simulators of physical models. The application that will be used to demonstrate COSSIM is mobile visual search, where mobile nodes capture images, extract their compressed representation and dispatch a query to the cloud. A server compares the received query to a local database and sends back some of the corresponding results.
Medical assessment of bone health often uses quantitative computed tomography (QCT) scans and req... more Medical assessment of bone health often uses quantitative computed tomography (QCT) scans and requires a reliable segmentation of bone geometry from surrounding tissues for a quick determination of bone mineral mass. Because of its shape and position in the body, the femur is one of the most challenging bones to investigate. In the current study, we developed a new automated way to accurately evaluate both the shape and the mineral mass of cadaveric femur. The results were achieved through a series of steps including the segmentation of bone tissue from sets of QCT images, the estimation of the bone’s outer surface, the calculation of the volume enclosed, and finally the evaluation of bone mineral mass in a user-defined region. We compared our algorithms outputs to results obtained by expert manual segmentation and those obtained using other published methods. Key Words Image based meshing, deformable models, femur shape QCT, mineral mass, finite element analysis, osteoporosis 1.
2021 International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET), 2021
The High Accuracy Asset Tracking (HAAT) of Bluetooth 5.1 Low Energy needs tiny antenna arrays to ... more The High Accuracy Asset Tracking (HAAT) of Bluetooth 5.1 Low Energy needs tiny antenna arrays to achieve efficient and very compact solutions. Rectangular Antenna Arrays guarantee good performances, both in azimuth and elevation in the Direction of arrival (DoA) estimation. This paper studies the eight antenna rectangular array topology, called URA8. Historically, MUSIC has been the most used algorithm on this type of array. Unfortunately in HAAT real-time applications, where it is essential to have a fast response from the DoA Locator, MUSIC, due to its high computational complexity in the peak searching over the pseudo-spectrum, may be inadequate for the scope. This paper proposes an innovative approach to reduce the complexity of this peak-searching phase: instead of only one peak-search over the complete azimuth-elevation hemisphere, we propose a two step search, the first with a reduced resolution and the latter with a fine resolution inside a proper confidence region, found in the first step. The proposed method ensures a good trade-off between computational complexity and detection performances: it turns out to approximately 6 times faster than the classic MUSIC, maintaining the same precision.
Neural networks and Machine Learning in general, represent today one of the greatest expectations... more Neural networks and Machine Learning in general, represent today one of the greatest expectations for the realization of models that can serve to determine the behavior and operation of different physical systems. Undoubtedly the calculation resources necessary for the training and the realization of the model are great especially if linked to the amount of data needed to detect the salient parameters of the model. At the same time, the models so obtained can be integrated on embedded systems, thanks to TinyML technologies, allowing to work exactly where the physical phenomena to analyze happen. In the consumer and industrial world these technologies have taken hold, and are also watched with interest by other sectors such as the automotive world. In this article we present a framework for the implementation of models based on neural networks on automotive family microprocessors, demonstrating their efficiency in two typical applications of the vehicle world: intrusion detection on ...
Uploads