IoT has become tremendously popular. It provides information access, processing and connectivity for a huge number of devices or sensors. IoT systems, however, often do not process the information locally, rather send the information to remote locations in the Cloud. As a result, it adds huge amount of data traffic to the network and additional delay to data processing. The later feature might have significant impact on applications that require fast response times, such as sophisticated artificial intelligence (AI) applications including Augmented reality, face recognition, and object detection. Consequently, edge computing paradigm that enables computation of data near the source has gained a significant importance in achieving a fast response time in the recent years. IoT devices can be employed to provide computational resources at the edge of the network near the sensors and actuators. The aim of this thesis work is to design and implement a kind of edge computing concept that brings AI models to a small embedded IoT device by the use of virtualization concepts. The use of virtualization technology enables the easy packing and shipping of applications to different hardware platforms. Additionally, this enable the mobility of AI models between edge devices and the Cloud. We will implement an AI model inside a Docker container, which will be deployed on a FireflyRK3399 single-board computer (SBC). Furthermore, we will conduct CPU and memory performance evaluations of Docker on Firefly-RK3399. The methodology adopted to reach to our goal is experimental research. First, different literatures have been studied to demonstrate by implementation the feasibility of our concept. Then we setup an experiment that covers measurement of performance metrics by applying synthetic load in multiple scenarios. Results are validated by repeating the experiment and statistical analysis. Results of this study shows that, an AI model can successfully be deployed and executed inside a Docker container on Arm-Cortex-based single-board computer. A Docker image of OpenFace face recognition model is built for ARM architecture of the Firefly SBC. On the other hand, the performance evaluation reveals that the performance overhead of Docker in terms of CPU and Memory is negligible. The research work comprises the mechanisms how AI application can be containerized in ARM architecture. We conclude that the methods can be applied to containerize software application in ARM based IoT devices. Furthermore, the insignificant overhead brought by Docker facilitates for deployment of applications inside a container with less performance overhead. The functionality of IoT device i.e. Firefly-RK3399 is exploited in this thesis. It is shown that the device is capable and powerful and gives an insight for further studies.

The goal of this diploma thesis is to create the functional prototype of intelligent peephole (video doorman) on Raspberry Pi 3B+ platform. It will support face recognition of the people, alternatively authorization by QR code and the record of the situations in form of picture, video, and text. Furthermore, it will allow remote control from Android application with possibility to see live stream of Raspberry Pi’s video in this application. Creation of the project is preceded by brief introduction of Raspberry Pi platform, its alternatives and process of face recognition. Python programming language was primarily used for software development on Raspberry Pi platform. Two approaches were used for image processing, direct processing on Raspberry Pi and on more powerful computer. This work describes use of various modern libraries, platforms, and frameworks, used during the creation of the project, with goal to provide beginners in this field insight into this technology, way of its use, and offer starting point for further work.

Single-board computers as hardware for container orchestration have been a growing subject. Previous studies have investigated their potential of running production-grade technologies in various environments where low-resource, cheap, and flexible clusters may be of use. This report investigates the appliance of methods and processes prevalent in cluster, container orchestration, and cloud-native environments. The motivation being that if single-board computers are able to run clusters to a satisfactory degree, they should also be able to fulfill the methods and processes which permeate the same cloud-native technologies. Investigation of the subject will be conducted through the creation of different criteria for each method and process. They will then act as an evaluation basis for an experiment in which a single-board computer cluster will be built, provisioned, configured, and monitored. As a summary, the investigation has been successful, instilling more confidence in single-board computer clusters and their ability to implement cluster related methodologies and processes.

This research paper focuses on analog computers and creating a modular low-cost analog computer system in a single board computer form factor. The single-board analog computer will have the capacity to solve second-order differential equations. The capabilities and possibilities of the single board Analog computer will be explored as well as analog computing in general. The paper follows design science research methodology (DSRM) with the goal of creating and evaluating a working artifact. The artifacts' functionality is evaluated based on a demonstration of its ability to solve Mathieu’s differential equation as well as simulate a spring-mass dampening system. This paper proves that it is possible to create a low-cost analog computer in a modern form factor. The artifact is also placed in a larger contextual setting based on the empirical material provided where its value of it in a digital society is presented. For the world to continue its progression in computational power, but still, limit the already high energy usage, a drastic change is needed. This paper suggests adapting to analog/hybrid technology. To further the progression of analog/hybrid technology it must be made accessible to a wider group of people compared to today. The artifact in this paper offers a solution to this.

The purpose of this thesis is to determine the feasibility of using blockchain to implement proof of location. There has been an increasing demand for a way to create a validated proof of location that is economical, and easy to deploy as well as portable. There are several reasons for an increased demand in this technology including the ever-increasing number of mobile gamers that have been able to spoof their location successfully, the increasing number of on demand package shipments from companies such as Amazon, and the desire to reduce the occurrence of medical errors as well as holding hospitals accountable for their errors. Additional reasons that this technology is gaining popularity and increasing in demand is due the continually increasing number of lost baggage claims that airlines are receiving, as well as insurance companies desire to reduce the number of fraud cases that are related to high-value goods as well as increasing the probability of their recovery. Within the past year, there has been an extensive amount of research as well as work that has been completed to create an irrefutable method of location verification, which will permit a user to be able to create time-stamped documentation validating that they were at a particular location at a certain day and time. Additionally, the user is then permitted to release the information at a later date and time that is convenient for them. This research was completed using a Raspberry Pi 3B, a Raspberry Pi 3B+, two virtual Raspberry Pi’s as well as two virtual servers in which the goal was to download, and setup either Ethereum and/or Tendermint Blockchain on each piece of equipment. After completely synchronizing the blockchain it be used to store the verified location data that been time-stamped. There was a variety of issues that were encountered during the setup and installation of the blockchains on the equipment including overclocking processors, which negatively affected the computational abilities of the devices as well as causing overheating and surges in voltage as well as a variety of software and hardware incompatibilities. These issues when looked at individually appear to not have much of an impact on the results of this research but when combined together it is obvious that they reduced the results that could be obtained. In conclusion, the combination of hardware and software issues when combined with the temperature and voltage issues that were due to the overheating of the processor resulted in several insurmountable issues that could not be overcome. There are several recommendations for continuing this work including presyncing the blockchain using a computer, using a device that has more functionality and computational abilities, connecting a cooling device such as a fan or adding a heat sink, increasing the available power supply, utilizing an externally power hard drive for data storage, recreate this research with the goal in mind of determining what process or application was causing the high processor usage, or creating a distributed system that utilizes both physical and virtual equipment to reduce the amount of work on one type of device.

Saab använder sig i nuläget av ett utdaterat system för att utföra tester av deras produkter. Systemet filmar ur olika vinklar och sammanfogar videoströmmarna till en slutgiltig video, där de sedan kan analysera resultatet av produkten. Enkortsdatorer är något som på senare år har blivit mer och mer populärt, Saab vill därför undersöka om det går att ersätta det äldre systemet med enkortsdatorer och kameror.Det ska undersökas om enkortsdatorn BeagleBoard klarar av att köra objektidentifiering samtidigt som den filmar och utför operationer som videosynkning, videokodning samt sparar den synkade filmen.Undersökningen visade att BeagleBoardens processor inte är tillräckligt kraftfull för att klara av objektidentifieringen utan hårdvarustöd. Istället behöver det utföras av en dator som bearbetar filmen i efterhand och plockar ut objekt. Det har förslagits en bättre metod för att göra objektidentifieringen smartare och lärande som kommer fungera bättre i Saabs fall. / Saab is currently using an old and complex system to perform tests of their products. The system is based on filming from different angles which will be merged to one film from which Saab can analyze the results of their products. Single-board computers is something that have become increasingly popular in the recent years, therefore, we are to investigate whether it is possible or not to replace the older systems with SBCs and cameras.We will also investigate whether the BeagleBoard is capable of detecting objects while filming, synchronizing, encoding and saving the video for later use.The result showed that the processor isn’t powerful enough to handle object identification without full hardware support. Instead, it needs to be performed afterwards by a computer which will identify objects in the video. A better method has been proposed to make object identification smarter and learning, which will work better in Saab’s case and their future work.

The use of Intrusion Detection Systems is a normal thing today in bigger companies, butthe solutions that are to be found in market is often too expensive for the smallercompany. Therefore, we saw the need in investigating if there is a more affordablesolution. In this report, we will show that it is possible to use low cost single boardcomputers as part of a bigger centralized Intrusion Detection System. To investigate this,we set up a test system including 2 Raspberry Pi 3 Model B, a cloud server and the use oftwo home networks, one with port mirroring implemented in firmware and the other withdedicated span port. The report will show how we set up the environment and the testingwe have done to prove that this is a working solution.

Master thesis deals with analysis of single board PC which use Linux as operation system. Analysis of individual NIDS systems and examined their properties for choosing right candidate for single board computer which shall be used as network probe for analysis, filtering and logging of network traffic. Part of the work is aimed on development of a interface which is used for configuration of network probe through the web browser. Web interface allows perform basic operations over network probe which influence network traffic or specify, which information shall be logged. Subsequently network parsers were implemented for network protocols using the Scappy library. The conclusion of the thesis contains the design of the security cover for the device according to the IP54 requirements.

As the Automotive industry is heavily regulated from a quality point of view, excellence in pro-duction is obligatory. Due to the fact that removing human error from humans is impossible, new solutions must be found. The transition to more data driven production strategies enables the implantation of automated vision systems for replacing humans in simple classification tasks. As research in the field of artificial intelligence advances, the hardware required to run the algorithms decreases. Concurrently small computing platforms break new performance records and the innovation space converges. This work harnesses state-of-the-art from both domains by implementing a plug-on vision system, driven by a resource-constrained edge device in a production line. The implemented CNN-model based on the MobileNetV2 architecture achieved 97.80, 99.93, and 95.67% in accuracy, precision, and recall respectively. The model was trained using only 100 physical samples, which were expanded by a ratio of 1:15 through innovative real world and digital augmentations. The core of the vision system was a commodity device, the Raspberry Pi 4. The solution fulfilled all the requirements while sparking new development ideas for future work.

The declining population of black rhinoceroses in Tsavo West national park, Kenya, has served as the driving force behind Project Ngulia, with Ngulia serving as an enclosed area within the park. As of now, the area is equipped with multiple cameras connected to a system that automatically classify animals and humans. This thesis aims to investigate the suitability of the Insta360 One X2 camera acting as a virtual watch tower for capturing and streaming 360° images. This will work in real-time, providing a remote surveillance experience for the park rangers thereby optimizing their work. A system was implemented to create a efficient workflow, which includes stitching of the 360° images, file transfer protocol for image transmission and storage, as well as socket programming to facilitate port monitoring and communication. Additionally, the compat- ibility of two single board computers, LattePanda and Rock 4 SE, with the implemented system was evaluated. User experience methods as field studies, workshops and a user interview were also performed. The work has been developed in Sweden, resulting in limited availability for testing at the target location during the initial months. The outcome was a both locally and remotely working system, together with LattePanda, capturing images of the waterhole in Ngulia. However, because of the conclusions drawn regarding the power supply and the lack of essential functions in the 360° camera, the system was taken home for further research. Propositions is presented regarding future work, some being that the projects within Ngulia team may collaborate to enhance hardware efficiency and explore the utilization of 360° images in educational and entertainment contexts.