Search

The current technological revolution driven by advances in machine learning has motivated a wide range of applications aiming to improve our quality of life. Representative of such applications are autonomous and semiautonomous Powered Wheelchairs (PWs), where the focus is on providing a degree of autonomy to the wheelchair user as a matter of guidance and interaction with the environment. Based on these perspectives, the focus of the current research has been on the design of lightweight systems that provide the necessary accuracy in the navigation system while enabling an embedded implementation. This motivated us to develop a real-time measurement methodology that relies on a monocular RGB camera to detect the caregiver’s feet based on a deep learning method, followed by the distance measurement of the caregiver from the PW. An important contribution of this article is the metrological characterization of the proposed methodology in comparison with measurements made with dedicated depth cameras. Our results show that despite shifting from 3D imaging to 2D imaging, we can still obtain comparable metrological performances in distance estimation as compared with Light Detection and Ranging (LiDAR) or even improved compared with stereo cameras. In particular, we obtained comparable instrument classes with LiDAR and stereo cameras, with measurement uncertainties within a magnitude of 10 cm. This is further complemented by the significant reduction in data volume and object detection complexity, thus facilitating its deployment, primarily due to the reduced complexity of initial calibration, positioning, and deployment compared with three-dimensional segmentation algorithms.

Efficient management of agricultural resources de-mands a profound comprehension of plant growth dynamics, focusing on sustainable methodologies. This study delves into the forestry sector in Sweden, explicitly addressing the critical early phases of pine tree development within controlled en-vironments, predominantly nurseries and specialised facilities. To tackle the complexities of temporal classification in pine tree growth, we propose a novel measurement system that uses image data to leverage the power of different deep transfer learning-based convolutional neural networks. To classify pine trees over time, our approach integrates different state-of-the-art transfer learning models based on the features extracted by SqueezeNet, MobileNetV2, GoogLeNet, ShuffieNet, and ResNetXt into our measurement system. The primary challenge in tem-porally sorting plant growth is that instances within the same class exhibit variations, whereas instances belonging to different classes may share similarities. We also addressed a pivotal question: whether focusing on the region of interest (ROI) as the input improves the final results. To explore this, we defined two distinct scenarios and conducted a comparative analysis to elucidate the impact of varied input images on the efficacy of our measurement systems. Our experimental results highlight the superior performance of deep SqueezeNet transfer learning over other models, with an error reduction of 15% compared to the second-best approach. Additionally, we provide a sensitivity analysis of the hyperparameters.

Prediction and early estimation of earthquake hazards have always been a subject of research. Indeed, the ability to promptly understand the energy released by a given earthquake event is of utmost importance for rapidly estimating the extent of damage to property and people. Estimating the Magnitude of an earthquake event, and thus the energy released by it, is, however, a slow process, requiring knowledge of the location of the epicenter and, therefore, necessitating the analysis of measurements from several seismic stations. The goal of this work has, hence, been to develop a model that succeeds in providing a coarse estimate, through the use of Artificial Neural Networks, of the Magnitude of a seismic event from the measurements of a single station, with the aim then of refining the estimate in a network of stations. The focus was directed toward estimating the classification uncertainty of the results based on the input measurements' uncertainty to assess the results' reliability.

We are experiencing a prolific growth of Artificial Intelligence (AI) that is enabling its ubiquitous diffusion. As part of it, generative AI models have gained particular attention due to their promising capabilities in solving complex tasks previously associated solely to human cognitive capabilities. In this article we focus on a specific AI tool, ChatGPT, which has been developed with the vision of behaving as an educational tool tailored to everyone's learning needs. This case study analyses the capabilities of such a tool in solving a predefined set of tasks in the subject area of Digital Systems Design, with the scope of designing robust assignments for students that cannot be solved and plagiarised with this tool. The results observed across different categories of cognitive depth show that ChatGPT has extensive conceptual knowledge in the area. However, this tool has important limitations when it comes to optimisation tasks, device specific configurations and overlaying of concepts, putting an emphasis on the importance of using such aspects in the design of robust tasks., Higher Education and Digitalisation (HEaD)

Industrial condition monitoring has benefited significantly from developments in machine learning and deep learning. However, textile machines, to a large extent, still use simple sensor systems, requiring additional manual quality inspections. This paper focuses on applying deep neural networks (DNNs) in image-based condition monitoring of air-spinning machines. It specifically focuses on the spinning pressure parameter, which is strongly related to the quality of the produced yarn. The study aims to develop a method to detect structural defects in yarns and assign them to specific machine conditions. DNNs are used to analyze images of yarns generated at different spinning pressures within the spinning box to create a rich dataset for training deep learning models. The study then evaluates the effectiveness of the DNN-based approach in detecting and classifying structural defects in yarns and determining the corresponding machine conditions. The results demonstrate that the developed model can distinguish good yarn from bad yarn, which is used to analyze the proportion of good yarn segments in a longer yarn section. A decreasing proportion with decreasing spinning pressure can thus be used to identify trends in degrading machine conditions. The outcomes of the presented research could potentially help textile enterprises improve the quality and efficiency of their yarn manufacturing processes.

The efficient management of agricultural resources requires a deep understanding of plant growth dynamics. This research focuses on Sweden's forestry sector and explicitly addresses the crucial early stages of pine tree development. The main difficulty in categorising plant growth over time is that instances within a given category are not identical, while instances from different categories may have similarities. In this context, we present a novel measurement system that integrates the capa-bilities of evolutionary computation and deep transfer learning using image data. The image acquisition system includes a tray of plates that moves through a nursery, generating a dataset captured over 44 days of plant growth. Our newly proposed algorithm, EvoSqueezeNet, employs various search strategies for SqueezeNet deep transfer learning to find proper hyper-parameters. We opted for SqueezeNet based on our preliminary studies, revealing its superior performance compared to other pre-trained models in our case study. Given that our approach is independent of any specific evolutionary algorithm, we utilised five distinct search strategies. These include Differential Evolution (DE), Particle Swarm Optimisation (PSO), Covariance Ma-trix Adaptation Evolution Strategy (CMA-ES), Comprehensive Learning PSO (CLPSO), and Linear Population Size Reduction Success-History Adaptation DE (LSHADE). Consequently, we proposed five EvoSqueezeNet schemes for temporal plant growth categorisation. One characteristic of our proposed model is that it uses a limited computation budget for search strategies, en-hancing its applicability in real-world applications. The proposed EvoSqueezeNet methodology demonstrates an error reduction of more than 40%, showcasing its superior performance compared to competing methods.

Eliminating Multi-Path Interference (MPI) stands as a significant unresolved challenge in the domain of depth estimation using Time-of-Flight (ToF) cameras. ToF data is typically influenced by significant noise and artifacts stemming from MPI. Although a variety of conventional methods have been suggested to enhance ToF data quality, the application of machine learning techniques has been infrequent, primarily due to the scarcity of authentic training data with accurate depth information. This paper introduces an approach that eliminates the dependency on labeled real-world data within the learning framework. We employ a U-Net trained on the data with ground truth in a supervised manner, enabling it to leverage multi-frequency ToF data for MPI correction. Concurrently, we compare three channels as input with one channel and two channels. Our experimental results convincingly showcase the effectiveness of this approach in reducing noise in real-world data.

Snow accumulations, especially if of great intensity, as is the case in northern countries, for example, can be very damaging, especially if they occur in urban environments. The damage provoked by snow is not only related to the weight of the accumulations, causing damage to structures but also to the pollution retained by the structure of the snowflakes. However, snow weight monitoring is a complex task, both because of the placement of the sensors and the specific operating ranges they must have in terms of operating temperature. These complications can be overcome by the design and use of a soft sensor, that is, a sensor capable of making indirect measurements from other parameters related to the measurement under consideration. This paper presents the design and metrological validation of a soft sensor for indirect weight measurement of snow accumulations. The designed soft sensor has been based on Artificial Neural Network and achieved, as a result, a Root-Mean-Square Error (RMSE) of 114g and a maximum extended uncertainty, evaluated by Monte Carlo simulation, of 300g in a measurement range from 150g to 5200g.

The development of machine learning has resulted in data gaining a pivotal role in the technological advancement, especially data where the ground truth of targeted parameters can be efficiently captured. This requires the development of methods that facilitate accurate data collection with ground truth. Under this perspective, Time of Flight sensors pose a high complexity due to the multifaceted nature of noise in the captured data. To enable the use of such sensors in a wide range of applications including Artificial Intelligence, we need to provide also accurate ground truth data. In this article, we present a method for automated data capturing from a LiDAR sensor together with ground truth data generation. This method will facilitate generating big datasets from LiDAR sensors with high accuracy ground truth data. In addition, we provide a dataset that aside from depth sensor data contains also RGB, confidence and infrared data captured from the LiDAR sensor. As a result, the proposed method not only facilitates data capturing but it enables to generate accurate ground truth data, with RMSE of only 0.04 m at 1.3 m distance.

QC 20240926 ; Part of ISBN [9798350363340]

Implementing Convolutional Neural Networks (CNN) based computer vision algorithms in Internet of Things (IoT) sensor nodes can be difficult due to strict computational, memory, and latency constraints. To address these challenges, researchers have utilized techniques such as quantization, pruning, and model partitioning. Partitioning the CNN reduces the computational burden on an individual node, but the overall system computational load remains constant. Additionally, communication energy is also incurred. To understand the effect of partitioning and pruning on energy and latency, we conducted a case study using a feet detection application realized with Tiny Yolo-v3 on a 12th Gen Intel CPU with NVIDIA GeForce RTX 3090 GPU. After partitioning the CNN between the sequential layers, we apply quantization, pruning, and compression and study the effects on energy and latency. We analyze the extent to which computational tasks, data, and latency can be reduced while maintaining a high level of accuracy. After achieving this reduction, we offloaded the remaining partitioned model to the edge node. We found that over 90% computation reduction and over 99% data transmission reduction are possible while maintaining mean average precision above 95%. This results in up to 17x energy savings and up to 5.2x performance speed-up.

Computer vision systems in sensor nodes of the Internet of Things (IoT) based on Deep Learning (DL) are demanding because the DL models are memory and computation hungry while the nodes often come with tight constraints on energy, latency, and memory. Consequently, work has been done to reduce the model size or distribute part of the work to other nodes. However, then the question arises how these approaches impact the energy consumption at the node and the inference time of the system. In this work, we perform a case study to explore the impact of partitioning a Convolutional Neural Network (CNN) such that one part is implemented on the IoT node, while the rest is implemented on an edge device. The goal is to explore how the choice of partition point, quantization method and communication technology affects the IoT system. We identify possible partitioning points between layers, where we transform the feature maps passed between layers by applying quantization and compression to reduce the data sent over the communication channel between the two partitions in Tiny YOLOv3. The results show that a reduction of transmitted data by 99.8% reduces the network accuracy by 3 percentage points. Furthermore, the evaluation of various IoT communication protocols shows that the quantization of data facilitates CNN network partitioning with significant reduction of overall latency and node energy consumption.

In a time when Artificial Intelligence (AI) technologies are nearly ubiquitous, railway construction and maintenance systems have not fully grasped the capabilities of such technologies. Traditional railway inspection methods rely on inspection from experienced workers, making such tasks costly from both, the monetary and the time perspective. From an overview of the state-of-the-art research in this area regarding AI-based systems, we observed that their main focus was solely on detection accuracy of different railway components. However, if we consider the critical importance of railway fastening in the overall safety of the railway, there is a need for a thorough analysis of these AI-based methodologies, to define their uncertainty also from a metrological perspective. In this article we address this issue, proposing an image-based system that detects the rotational displacement of the fastened railway clips. Furthermore, we provide an uncertainty analysis of the measurement system, where the resulting uncertainty is of 0.42°, within the 3° error margin defined by the clip manufacturer.

To produce flawless glass containers, continuous monitoring of the glass gob is required. It is essential to ensure production of molten glass gobs with the right shape, temperature, viscosity and weight. At present, manual monitoring is common practice in the glass container industry, which heavily depends on previous experience, operator knowledge and trial and error. This results in inconsistent measurements and consequently loss of production. In this article, a multi-camera based setup is used as a non-invasive real-time monitoring system. We have shown that under certain conditions, such as keeping the glass composition constant, it is possible to do in-line measurement of viscosity using sensor fusion to correlate the rate of geometrical change in the gob and its temperature. The correlation models presented in this article show that there is a strong correlation, i.e., 0.65, between our measurements and the projected viscosity.

Railway fastening clips dataset wth fastclip This record contains a dataset with the railway fastening clip called fastclip and the installation datasheet for the same clip provided by the clip manufacturer, Pandrol AB. The railway_dataset folder contains three subfolders:- The calibration folder, where are the images taken at angles from 0 - 30 with a step of 3 degrees.- The test and the validation folder, where are the images and their respective labels based on the YOLO Oriented Bounding Box method. The fastclip datasheet document is an installation sheet provided from the manufacturer of the fastclip, Pandrol AB.

The sophistication and high accuracy of Deep Neural Networks have gotten significant attention in recent years, with a wide range of applications making use of their capabilities. However, the deployment of such networks still faces limitations due to the high volume of data to be processed and the high computational requirements. In this article we focus on the effects that data volume reduction, due to image compression and scaling down the image resolution, will have on the detection accuracy for the design case of a powered wheelchair guidance system. Throughout our analysis we show that the reduction in image resolution to a factor of 16× in image area alongside with JPEG compression provides a detection accuracy of over 0.93 in mAP, while the additional error in the position estimation of the caregiver is less than 0.5 cm. By reducing the data volume we inherently reduce the communication energy consumption, which is reduced by more than one order of magnitude. These results prove that we can overcome the complexity of high data volume for the deployment of DNNs in resource constrained IoT applications by interlacing the effects of image compression and resolution reduction, maintaining the accuracy and reducing the node energy consumption.

The study aims to explore the fuel consumption of city buses with data fusion using a dataset with multiple parameters such as travelled distance, weekday, hour of the day, drivers, buses, and routes, that influence the trip fuel consumption. In this study, manipulated parameters such as modified driver, bus and route identification numbers are used together with original parameters to identify the optimal combination of parameters that can be used to enhance the accuracy of the prediction model. Two regression methods, i.e. cubic SVM and artificial neural networks (ANN), are used to demonstrate the performance of the proposed approach. Results shows that a combination of original parameters and processed parameters increases the performance.

Optimising the energy consumption of IoT nodes can be tedious due to the due to complex trade-offs involved between processing and communication. In this article, we investigate the partitioning of processing between the sensor node and a server and study the energy trade-offs involved. We propose a method that provides a trade-off analysis for a given set of constraints and allows for exploring several intelligence partitioning configurations. Furthermore, we demonstrate how this method can be used for the analysis of four design examples with traditional and CNN-based image processing systems, and we also provide an implementation of it on Matlab. CCBY

Image processing systems exploit image information for a purpose determined by the application at hand. The implementation of image processing systems in an Internet of Things (IoT) context is a challenge due to the amount of data in an image processing system, which affects the three main node constraints: memory, latency and energy. One method to address these challenges is the partitioning of tasks between the IoT node and a server. In this work, we present an in-depth analysis of how the input image size and its content within the conventional image processing systems affect the decision on where tasks should be implemented, with respect to node energy and latency. We focus on explaining how the characteristics of the image are transferred through the system until finally influencing partition decisions. Our results show that the image size affects significantly the efficiency of the node offloading configurations. This is mainly due to the dominant cost of communication over processing as the image size increases. Furthermore, we observed that image content has limited effects in the node offloading analysis.

This zip folder contains the MatLab code that can be used during design space exploration to identify optimisation areas for a given design case. Based on a preliminary set of data such as an estimate of the number of operations, an energy constraint, and the intermediate data volume between the processing stages, we can use this tool to identify areas where optimisation efforts would provide the highest impact on the node energy efficiency.

The Internet of Things has grown quickly in the last few years, with a variety of sensing, processing and storage devices interconnected, resulting in high data traffic. While some sensors such as temperature, or humidity sensors produce a few bits of data periodically, imaging sensors output data in the range of megabytes every second. This raises a complexity for battery operated smart cameras, as they would be required to perform intensive image processing operations on large volumes of data, within energy consumption constraints. By using intelligence partitioning we analyse the effects of different partitioning scenarios for the processing tasks between the smart camera node, the fog computing layer and cloud computing, in the node energy consumption as well as the real time performance of the WVSN (Wireless Vision Sensor Node). The results obtained show that traditional design space exploration approaches are inefficient for WVSN, while intelligence partitioning enhances the energy consumption performance of the smart camera node and meets the timing constraints.

Due to the limited energy budget for sensor nodes in the Internet of Things (IoT), it is crucial to develop energy efficient communications amongst others. This need leads to the development of various energy-efficient protocols that consider different aspects of the energy status of a node. However, a single protocol covers only one part of the whole stack and savings on one level might not be as efficient for the overall system, if other levels are considered as well. In this paper, we analyze the energy required for an end device to maintain connectivity to the network as well as perform application specific tasks. By integrating the complete stack perspective, we build a more holistic view on the energy consumption and overhead for a wireless sensor node. For better understanding, we compare three different stack variants in a base scenario and add an extended study to evaluate the impact of retransmissions as a robustness mechanism. Our results show, that the overhead introduced by the complete stack has an significant impact on the nodes energy consumption especially if retransmissions are required., SMART (Smarta system och tjänster för ett effektivt och innovativt samhälle)

The Internet of Things (IoT) is becoming a tangible reality, with a variety of sensors, devices and data centres interconnected to support scenarios such as Smart City with information about traffic, city administration, health-care services and entertainment. Decomposing these systems into smaller components, results in a variety of requirements for processing and communication resources for each subsystem. Wireless Vision Sensor Network (WVSN) is one of the subsystems, relying on visual sensors that produce several megabytes of data every second, unlike temperature or pressure sensors producing several bytes of data every hour. In addition, to facilitate the deployment of the nodes for different environments, we consider themas battery-operated devices. The high data rates from the imaging sensor have extensive computational and communication requirements, which in the meantime should meet the constraints regarding the energy efficiency of the device, to ensure a satisfactory battery lifetime. In this thesis we analyse the energy efficiency of the smart camera, including the smart camera architecture, the distribution of the image processing tasks between several processing elements, and the inter-effects of processing and communication. Sensor selection and algorithmic implementation of the image processing tasks affects the processing energy consumption of the node, alongside to the hardware and software implementation of the tasks. Furthermore, considerations of different intelligence partitioning configurations are included in the analysis of communication related elements, such as communication delays and channel utilisation. The inter-effects resulting from the variety of configurations in image processing allocation and communication technologies with different characteristics provide an insight into the overall variations of the smart camera node energy consumption. The aim of thesis is to facilitate the design of energy efficient smart cameras, while prov, Vid tidpunkten för framläggningen av avhandlingen var följande delarbete opublicerat: delarbete 3 (manuskript).At the time of the defence the following paper was unpublished: paper 3 (manuscript)., SMART (Smarta system och tjänster för ett effektivt och innovativt samhälle)

The Internet of Things has changed the range of applications for cameras requiring them to be easily deployed for a variety of scenarios indoor and outdoor, while achieving high performance in processing. As a result, future projections emphasise the need for battery operated smart cameras, capable of complex image processing tasks that also communicate within one another, and the server. Based on these considerations, we evaluate in-node and node – server configurations of image processing tasks to provide an insight of how tasks partitioning affects the overall energy consumption. The two main energy components taken in consideration for their influence in the total energy consumption are processing and communication energy. The results from the people counting scenario proved that processing background modelling, subtraction and segmentation in-node while transferring the remaining tasks to the server results in the most energy efficient configuration, optimising both processing and communication energy. In addition, the inclusion of data reduction techniques such as data aggregation and compression not always resulted in lower energy consumption as generally assumed, and the final optimal partition did not include data reduction., SMART (Smarta system och tjänster för ett effektivt och innovativt samhälle)

Smart camera systems integrating multi-model image sensors provide better spectral sensitivity and hence better pass-fail decisions. In a given vision system, pre-processing tasks have a ripple effect on output data and pass-fail decision of high level tasks such as feature extraction, classification and recognition. In this work, we investigated four pre-processing pipelines and evaluated the effect on classification accuracy and output transmission data. The pre-processing pipelines processed four types of images, thermal grayscale, thermal binary, visual and visual binary. The results show that the pre-processing pipeline, which transmits visual compressed Region of Interest (ROI) images, offers 13 to 64 percent better classification accuracy as compared to thermal grayscale, thermal binary and visual binary. The results show that visual raw and visual compressed ROI with suitable quantization matrix offers similar classification accuracy but visual compressed ROI offers up to 99 percent reduced communication data as compared to visual ROI., SMART (Smarta system och tjänster för ett effektivt och innovativt samhälle)

Background subtraction is one of the fundamental steps in the image-processing pipeline for distinguishing foreground from background. Most of the methods have been investigated with respect to visual images, in which case challenges are different compared to thermal images. Thermal sensors are invariant to light changes and have reduced privacy concerns. We propose the use of a low-pass IIR filter for background modelling in thermographic imagery due to its better performance compared to algorithms such as Mixture of Gaussians and K-nearest neighbour, while reducing memory requirements for implementation in embedded architectures. Based on the analysis of four different image datasets both indoor and outdoor, with and without people presence, the learning rate for the filter is set to 3×10-3 Hz and the proposed model is implemented on an Artix-7 FPGA., City Movements, SMART (Smarta system och tjänster för ett effektivt och innovativt samhälle)