Machine learning techniques for implicit interaction using mobile sensors

Interactions in mobile devices normally happen in an explicit manner, which means that they are initiated by the users. Yet, users are typically unaware that they also interact implicitly with their devices. For instance, our hand pose changes naturally when we type text messages. Whilst the touchscreen captures finger touches, hand movements during this interaction however are unused. If this implicit hand movement is observed, it can be used as additional information to support or to enhance the users’ text entry experience. This thesis investigates how implicit sensing can be used to improve existing, standard interaction technique qualities. In particular, this thesis looks into enhancing front-of-device interaction through back-of-device and hand movement implicit sensing. We propose the investigation through machine learning techniques. We look into problems on how sensor data via implicit sensing can be used to predict a certain aspect of an interaction. For instance, one of the questions that this thesis attempts to answer is whether hand movement during a touch targeting task correlates with the touch position. This is a complex relationship to understand but can be best explained through machine learning. Using machine learning as a tool, such correlation can be measured, quantified, understood and used to make predictions on future touch position. Furthermore, this thesis also evaluates the predictive power of the sensor data. We show this through a number of studies. In Chapter 5 we show that probabilistic modelling of sensor inputs and recorded touch locations can be used to predict the general area of future touches on touchscreen. In Chapter 7, using SVM classifiers, we show that data from implicit sensing from general mobile interactions is user-specific. This can be used to identify users implicitly. In Chapter 6, we also show that touch interaction errors can be detected from sensor data. In our experiment, we show that there are sufficient distinguishable patterns between normal interaction signals and signals that are strongly correlated with interaction error. In all studies, we show that performance gain can be achieved by combining sensor inputs.

Addressing challenges in heterogeneous embedded systems programming: security and performance

Embedded systems are increasingly integral to daily life, improving and facilitating the efficiency of modern Cyber-Physical Systems which provide access to sensor data, and actuators. As modern architectures become increasingly complex and heterogeneous, their optimization becomes a challenging task. Additionally, ensuring platform security is important to avoid harm to individuals and assets. This study primarily addresses challenges in contemporary Embedded Systems, focusing on platform optimization and security enforcement. The initial section of this study delves into the application of machine learning methods to efficiently determine the optimal number of cores for a parallel RISC-V cluster to minimize energy consumption using static source code analysis. Results demonstrate that automated platform configuration is not only viable but also that there is a moderate performance trade-off when relying solely on static features. The second part focuses on addressing the problem of heterogeneous device mapping, which involves assigning tasks to the most suitable computational device in a heterogeneous platform for optimal runtime. The contribution of this section lies in the introduction of novel pre-processing techniques, along with a training framework called Siamese Networks, that enhances the classification performance of DeepLLVM, an advanced approach for task mapping. Importantly, these proposed approaches are independent from the specific deep-learning model used. Finally, this research work focuses on addressing issues concerning the binary exploitation of software running in modern Embedded Systems. It proposes an architecture to implement Control-Flow Integrity in embedded platforms with a Root-of-Trust, aiming to enhance security guarantees with limited hardware modifications. The approach involves enhancing the architecture of a modern RISC-V platform for autonomous vehicles by implementing a side-channel communication mechanism that relays control-flow changes executed by the process running on the host core to the Root-of-Trust. This approach has limited impact on performance and it is effective in enhancing the security of embedded platforms.

Entity localization and tracking: a sensor fusion-based mechanism in WSNs

Knowing exactly where a mobile entity is and monitoring its trajectory in real-time has recently attracted a lot of interests from both academia and industrial communities, due to the large number of applications it enables, nevertheless, it is nowadays one of the most challenging problems from scientific and technological standpoints. In this work we propose a tracking system based on the fusion of position estimations provided by different sources, that are combined together to get a final estimation that aims at providing improved accuracy with respect to those generated by each system individually. In particular, exploiting the availability of a Wireless Sensor Network as an infrastructure, a mobile entity equipped with an inertial system first gets the position estimation using both a Kalman Filter and a fully distributed positioning algorithm (the Enhanced Steepest Descent, we recently proposed), then combines the results using the Simple Convex Combination algorithm. Simulation results clearly show good performance in terms of the final accuracy achieved. Finally, the proposed technique is validated against real data taken from an inertial sensor provided by THALES ITALIA.

Localization system for pedestrians based on sensor and information fusion

Nowadays there is an increase of location-aware mobile applications. However, these applications only retrieve location with a mobile device's GPS chip. This means that in indoor or in more dense environments these applications don't work properly. To provide location information everywhere a pedestrian Inertial Navigation System (INS) is typically used, but these systems can have a large estimation error since, in order to turn the system wearable, they use low-cost and low-power sensors. In this work a pedestrian INS is proposed, where force sensors were included to combine with the accelerometer data in order to have a better detection of the stance phase of the human gait cycle, which leads to improvements in location estimation. Besides sensor fusion an information fusion architecture is proposed, based on the information from GPS and several inertial units placed on the pedestrian body, that will be used to learn the pedestrian gait behavior to correct, in real-time, the inertial sensors errors, thus improving location estimation.

Land cover classification of Lago Grande de Curuai floodplain (Amazon, Brazil) using multi-sensor and image fusion techniques

Given the limitations of different types of remote sensing images, automated land-cover classifications of the Amazon várzea may yield poor accuracy indexes. One way to improve accuracy is through the combination of images from different sensors, by either image fusion or multi-sensor classifications. Therefore, the objective of this study was to determine which classification method is more efficient in improving land cover classification accuracies for the Amazon várzea and similar wetland environments - (a) synthetically fused optical and SAR images or (b) multi-sensor classification of paired SAR and optical images. Land cover classifications based on images from a single sensor (Landsat TM or Radarsat-2) are compared with multi-sensor and image fusion classifications. Object-based image analyses (OBIA) and the J.48 data-mining algorithm were used for automated classification, and classification accuracies were assessed using the kappa index of agreement and the recently proposed allocation and quantity disagreement measures. Overall, optical-based classifications had better accuracy than SAR-based classifications. Once both datasets were combined using the multi-sensor approach, there was a 2% decrease in allocation disagreement, as the method was able to overcome part of the limitations present in both images. Accuracy decreased when image fusion methods were used, however. We therefore concluded that the multi-sensor classification method is more appropriate for classifying land cover in the Amazon várzea.

Visual sensor fusion for active security in robotic industrial environments

This work presents a method of information fusion involving data captured by both a standard CCD camera and a ToF camera to be used in the detection of the proximity between a manipulator robot and a human. Both cameras are assumed to be located above the work area of an industrial robot. The fusion of colour images and time of light information makes it possible to know the 3D localization of objects with respect to a world coordinate system. At the same time this allows to know their colour information. Considering that ToF information given by the range camera contains innacuracies including distance error, border error, and pixel saturation, some corrections over the ToF information are proposed and developed to improve the results. The proposed fusion method uses the calibration parameters of both cameras to reproject 3D ToF points, expressed in a common coordinate system for both cameras and a robot arm, in 2D colour images. In addition to this, using the 3D information, the motion detection in a robot industrial environment is achieved, and the fusion of information is applied to the foreground objects previously detected. This combination of information results in a matrix that links colour and 3D information, giving the possibility of characterising the object by its colour in addition to its 3D localization. Further development of these methods will make it possible to identify objects and their position in the real world, and to use this information to prevent possible collisions between the robot and such objects.

Visual sensor fusion for active security in robotic industrial environments

This work presents a method of information fusion involving data captured by both a standard charge-coupled device (CCD) camera and a time-of-flight (ToF) camera to be used in the detection of the proximity between a manipulator robot and a human. Both cameras are assumed to be located above the work area of an industrial robot. The fusion of colour images and time-of-flight information makes it possible to know the 3D localization of objects with respect to a world coordinate system. At the same time, this allows to know their colour information. Considering that ToF information given by the range camera contains innacuracies including distance error, border error, and pixel saturation, some corrections over the ToF information are proposed and developed to improve the results. The proposed fusion method uses the calibration parameters of both cameras to reproject 3D ToF points, expressed in a common coordinate system for both cameras and a robot arm, in 2D colour images. In addition to this, using the 3D information, the motion detection in a robot industrial environment is achieved, and the fusion of information is applied to the foreground objects previously detected. This combination of information results in a matrix that links colour and 3D information, giving the possibility of characterising the object by its colour in addition to its 3D localisation. Further development of these methods will make it possible to identify objects and their position in the real world and to use this information to prevent possible collisions between the robot and such objects.

Land cover classification of Lago Grande de Curuai floodplain (Amazon, Brazil) using multi-sensor and image fusion techniques

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Sistemi riconfigurabili a basso consumo per applicazioni di monitoraggio distribuito

The term Ambient Intelligence (AmI) refers to a vision on the future of the information society where smart, electronic environment are sensitive and responsive to the presence of people and their activities (Context awareness). In an ambient intelligence world, devices work in concert to support people in carrying out their everyday life activities, tasks and rituals in an easy, natural way using information and intelligence that is hidden in the network connecting these devices. This promotes the creation of pervasive environments improving the quality of life of the occupants and enhancing the human experience. AmI stems from the convergence of three key technologies: ubiquitous computing, ubiquitous communication and natural interfaces. Ambient intelligent systems are heterogeneous and require an excellent cooperation between several hardware/software technologies and disciplines, including signal processing, networking and protocols, embedded systems, information management, and distributed algorithms. Since a large amount of fixed and mobile sensors embedded is deployed into the environment, the Wireless Sensor Networks is one of the most relevant enabling technologies for AmI. WSN are complex systems made up of a number of sensor nodes which can be deployed in a target area to sense physical phenomena and communicate with other nodes and base stations. These simple devices typically embed a low power computational unit (microcontrollers, FPGAs etc.), a wireless communication unit, one or more sensors and a some form of energy supply (either batteries or energy scavenger modules). WNS promises of revolutionizing the interactions between the real physical worlds and human beings. Low-cost, low-computational power, low energy consumption and small size are characteristics that must be taken into consideration when designing and dealing with WSNs. To fully exploit the potential of distributed sensing approaches, a set of challengesmust be addressed. Sensor nodes are inherently resource-constrained systems with very low power consumption and small size requirements which enables than to reduce the interference on the physical phenomena sensed and to allow easy and low-cost deployment. They have limited processing speed,storage capacity and communication bandwidth that must be efficiently used to increase the degree of local ”understanding” of the observed phenomena. A particular case of sensor nodes are video sensors. This topic holds strong interest for a wide range of contexts such as military, security, robotics and most recently consumer applications. Vision sensors are extremely effective for medium to long-range sensing because vision provides rich information to human operators. However, image sensors generate a huge amount of data, whichmust be heavily processed before it is transmitted due to the scarce bandwidth capability of radio interfaces. In particular, in video-surveillance, it has been shown that source-side compression is mandatory due to limited bandwidth and delay constraints. Moreover, there is an ample opportunity for performing higher-level processing functions, such as object recognition that has the potential to drastically reduce the required bandwidth (e.g. by transmitting compressed images only when something ‘interesting‘ is detected). The energy cost of image processing must however be carefully minimized. Imaging could play and plays an important role in sensing devices for ambient intelligence. Computer vision can for instance be used for recognising persons and objects and recognising behaviour such as illness and rioting. Having a wireless camera as a camera mote opens the way for distributed scene analysis. More eyes see more than one and a camera system that can observe a scene from multiple directions would be able to overcome occlusion problems and could describe objects in their true 3D appearance. In real-time, these approaches are a recently opened field of research. In this thesis we pay attention to the realities of hardware/software technologies and the design needed to realize systems for distributed monitoring, attempting to propose solutions on open issues and filling the gap between AmI scenarios and hardware reality. The physical implementation of an individual wireless node is constrained by three important metrics which are outlined below. Despite that the design of the sensor network and its sensor nodes is strictly application dependent, a number of constraints should almost always be considered. Among them: • Small form factor to reduce nodes intrusiveness. • Low power consumption to reduce battery size and to extend nodes lifetime. • Low cost for a widespread diffusion. These limitations typically result in the adoption of low power, low cost devices such as low powermicrocontrollers with few kilobytes of RAMand tenth of kilobytes of program memory with whomonly simple data processing algorithms can be implemented. However the overall computational power of the WNS can be very large since the network presents a high degree of parallelism that can be exploited through the adoption of ad-hoc techniques. Furthermore through the fusion of information from the dense mesh of sensors even complex phenomena can be monitored. In this dissertation we present our results in building several AmI applications suitable for a WSN implementation. The work can be divided into two main areas:Low Power Video Sensor Node and Video Processing Alghoritm and Multimodal Surveillance . Low Power Video Sensor Nodes and Video Processing Alghoritms In comparison to scalar sensors, such as temperature, pressure, humidity, velocity, and acceleration sensors, vision sensors generate much higher bandwidth data due to the two-dimensional nature of their pixel array. We have tackled all the constraints listed above and have proposed solutions to overcome the current WSNlimits for Video sensor node. We have designed and developed wireless video sensor nodes focusing on the small size and the flexibility of reuse in different applications. The video nodes target a different design point: the portability (on-board power supply, wireless communication), a scanty power budget (500mW),while still providing a prominent level of intelligence, namely sophisticated classification algorithmand high level of reconfigurability. We developed two different video sensor node: The device architecture of the first one is based on a low-cost low-power FPGA+microcontroller system-on-chip. The second one is based on ARM9 processor. Both systems designed within the above mentioned power envelope could operate in a continuous fashion with Li-Polymer battery pack and solar panel. Novel low power low cost video sensor nodes which, in contrast to sensors that just watch the world, are capable of comprehending the perceived information in order to interpret it locally, are presented. Featuring such intelligence, these nodes would be able to cope with such tasks as recognition of unattended bags in airports, persons carrying potentially dangerous objects, etc.,which normally require a human operator. Vision algorithms for object detection, acquisition like human detection with Support Vector Machine (SVM) classification and abandoned/removed object detection are implemented, described and illustrated on real world data. Multimodal surveillance: In several setup the use of wired video cameras may not be possible. For this reason building an energy efficient wireless vision network for monitoring and surveillance is one of the major efforts in the sensor network community. Energy efficiency for wireless smart camera networks is one of the major efforts in distributed monitoring and surveillance community. For this reason, building an energy efficient wireless vision network for monitoring and surveillance is one of the major efforts in the sensor network community. The Pyroelectric Infra-Red (PIR) sensors have been used to extend the lifetime of a solar-powered video sensor node by providing an energy level dependent trigger to the video camera and the wireless module. Such approach has shown to be able to extend node lifetime and possibly result in continuous operation of the node.Being low-cost, passive (thus low-power) and presenting a limited form factor, PIR sensors are well suited for WSN applications. Moreover techniques to have aggressive power management policies are essential for achieving long-termoperating on standalone distributed cameras needed to improve the power consumption. We have used an adaptive controller like Model Predictive Control (MPC) to help the system to improve the performances outperforming naive power management policies.

POSE ESTIMATION AND 3D RECONSTRUCTION USING SENSOR FUSION

A camera maps 3-dimensional (3D) world space to a 2-dimensional (2D) image space. In the process it loses the depth information, i.e., the distance from the camera focal point to the imaged objects. It is impossible to recover this information from a single image. However, by using two or more images from different viewing angles this information can be recovered, which in turn can be used to obtain the pose (position and orientation) of the camera. Using this pose, a 3D reconstruction of imaged objects in the world can be computed. Numerous algorithms have been proposed and implemented to solve the above problem; these algorithms are commonly called Structure from Motion (SfM). State-of-the-art SfM techniques have been shown to give promising results. However, unlike a Global Positioning System (GPS) or an Inertial Measurement Unit (IMU) which directly give the position and orientation respectively, the camera system estimates it after implementing SfM as mentioned above. This makes the pose obtained from a camera highly sensitive to the images captured and other effects, such as low lighting conditions, poor focus or improper viewing angles. In some applications, for example, an Unmanned Aerial Vehicle (UAV) inspecting a bridge or a robot mapping an environment using Simultaneous Localization and Mapping (SLAM), it is often difficult to capture images with ideal conditions. This report examines the use of SfM methods in such applications and the role of combining multiple sensors, viz., sensor fusion, to achieve more accurate and usable position and reconstruction information. This project investigates the role of sensor fusion in accurately estimating the pose of a camera for the application of 3D reconstruction of a scene. The first set of experiments is conducted in a motion capture room. These results are assumed as ground truth in order to evaluate the strengths and weaknesses of each sensor and to map their coordinate systems. Then a number of scenarios are targeted where SfM fails. The pose estimates obtained from SfM are replaced by those obtained from other sensors and the 3D reconstruction is completed. Quantitative and qualitative comparisons are made between the 3D reconstruction obtained by using only a camera versus that obtained by using the camera along with a LIDAR and/or an IMU. Additionally, the project also works towards the performance issue faced while handling large data sets of high-resolution images by implementing the system on the Superior high performance computing cluster at Michigan Technological University.

Inertial and magnetic sensors for upper limb kinematics: modeling, calibration, sensor fusion and clinical applications

The primary aim of the research activity presented in this PhD thesis was the development of an innovative hardware and software solution for creating a unique tool for kinematics and electromyographic analysis of the human body in an ecological setting. For this purpose, innovative algorithms have been proposed regarding different aspects of inertial and magnetic data elaboration: magnetometer calibration and magnetic field mapping (Chapter 2), data calibration (Chapter 3) and sensor-fusion algorithm. Topics that may conflict with the confidentiality agreement between University of Bologna and NCS Lab will not be covered in this thesis. After developing and testing the wireless platform, research activities were focused on its clinical validation. The first clinical study aimed to evaluate the intra and interobserver reproducibility in order to evaluate three-dimensional humero-scapulo-thoracic kinematics in an outpatient setting (Chapter 4). A second study aimed to evaluate the effect of Latissimus Dorsi Tendon Transfer on shoulder kinematics and Latissimus Dorsi activation in humerus intra - extra rotations (Chapter 5). Results from both clinical studies have demonstrated the ability of the developed platform to enter into daily clinical practice, providing useful information for patients' rehabilitation.

Data gathering approach in dense sensor networks

Sensor/actuator networks promised to extend automated monitoring and control into industrial processes. Avionic system is one of the prominent technologies that can highly gain from dense sensor/actuator deployments. An aircraft with smart sensing skin would fulfill the vision of affordability and environmental friendliness properties by reducing the fuel consumption. Achieving these properties is possible by providing an approximate representation of the air flow across the body of the aircraft and suppressing the detected aerodynamic drags. To the best of our knowledge, getting an accurate representation of the physical entity is one of the most significant challenges that still exists with dense sensor/actuator network. This paper offers an efficient way to acquire sensor readings from very large sensor/actuator network that are located in a small area (dense network). It presents LIA algorithm, a Linear Interpolation Algorithm that provides two important contributions. First, it demonstrates the effectiveness of employing a transformation matrix to mimic the environmental behavior. Second, it renders a smart solution for updating the previously defined matrix through a procedure called learning phase. Simulation results reveal that the average relative error in LIA algorithm can be reduced by as much as 60% by exploiting transformation matrix.

Energy efficient scheduling for cluster-tree wireless sensor networks with time-bounded data flows: application to IEEE 802.15.4/ZigBee

Cluster scheduling and collision avoidance are crucial issues in large-scale cluster-tree Wireless Sensor Networks (WSNs). The paper presents a methodology that provides a Time Division Cluster Scheduling (TDCS) mechanism based on the cyclic extension of RCPS/TC (Resource Constrained Project Scheduling with Temporal Constraints) problem for a cluster-tree WSN, assuming bounded communication errors. The objective is to meet all end-to-end deadlines of a predefined set of time-bounded data flows while minimizing the energy consumption of the nodes by setting the TDCS period as long as possible. Sinceeach cluster is active only once during the period, the end-to-end delay of a given flow may span over several periods when there are the flows with opposite direction. The scheduling tool enables system designers to efficiently configure all required parameters of the IEEE 802.15.4/ZigBee beaconenabled cluster-tree WSNs in the network design time. The performance evaluation of thescheduling tool shows that the problems with dozens of nodes can be solved while using optimal solvers.

Simulation study of energy efficient scheduling for IEEE 802.15.4/ZigBee cluster-treeWireless Sensor Networks with time-bounded data flows

The simulation analysis is important approach to developing and evaluating the systems in terms of development time and cost. This paper demonstrates the application of Time Division Cluster Scheduling (TDCS) tool for the configuration of IEEE 802.15.4/ZigBee beaconenabled cluster-tree WSNs using the simulation analysis, as an illustrative example that confirms the practical applicability of the tool. The simulation study analyses how the number of retransmissions impacts the reliability of data transmission, the energy consumption of the nodes and the end-to-end communication delay, based on the simulation model that was implemented in the Opnet Modeler. The configuration parameters of the network are obtained directly from the TDCS tool. The simulation results show that the number of retransmissions impacts the reliability, the energy consumption and the end-to-end delay, in a way that improving the one may degrade the others.

Enhanced PCA-based localization using depth maps with missing data

In this paper a new method for self-localization of mobile robots, based on a PCA positioning sensor to operate in unstructured environments, is proposed and experimentally validated. The proposed PCA extension is able to perform the eigenvectors computation from a set of signals corrupted by missing data. The sensor package considered in this work contains a 2D depth sensor pointed upwards to the ceiling, providing depth images with missing data. The positioning sensor obtained is then integrated in a Linear Parameter Varying mobile robot model to obtain a self-localization system, based on linear Kalman filters, with globally stable position error estimates. A study consisting in adding synthetic random corrupted data to the captured depth images revealed that this extended PCA technique is able to reconstruct the signals, with improved accuracy. The self-localization system obtained is assessed in unstructured environments and the methodologies are validated even in the case of varying illumination conditions.