Search results for "500"
showing 10 items of 3244 documents
An Encoder-Decoder based Deep Learning Approach for Anonymization of Visual Surveillance Media with Preservation of Utility
2020
Master's thesis in Information- and communication technology (IKT590) The field of computer vision has seen significant progress recently fol-lowing innovations in deep learning neural networks. Activity can be identified from surveillance cameras. Automatic detection of unwanted incidents would enable police to act quickly with appropriate resources. Activity detecting machine learning algorithms need many examples in its learning phase. However, videos from surveillance cameras may contain privacy-sensitive information. The videos are not allowed to be used outside of the police unless anonymized. However, traditional anonymization techniques remove visual information, reducing utility as…
Expanding on the end-to-end memory network for goal-oriented dialogue
2019
Master's thesis Information- and communication technology IKT590 - University of Agder 2019 A series of end-to-end models have been proposed in order to satisfy therequirements of the Dialog System Technology Challenge: building an end-to-end dialog system for goal-oriented applications. While these modelshave proven to be a good solution for such tasks, they perform worse whendealing with out-of-vocabulary tasks and none-synthetic data. Additionally,they rely heavily on the use of an underlying knowledge base to achieve goodresults.We propose two new models that build on the end-to-end memory net-work architecture. The goal of these two models is to better handle out-of-vocabulary tasks an…
A Machine Learning Approach for Intrusion Detection
2020
Master's thesis in Information- and communication technology (IKT590) Securing networks and their confidentiality from intrusions is crucial, and for this rea-son, Intrusion Detection Systems have to be employed. The main goal of this thesis is to achieve a proper detection performance of a Network Intrusion Detection System (NIDS). In this thesis, we have examined the detection efficiency of machine learning algorithms such as Neural Network, Convolutional Neural Network, Random Forestand Long Short-Term Memory. We have constructed our models so that they can detect different types of attacks utilizing the CICIDS2017 dataset. We have worked on identifying 15 various attacks present in CICI…
Computer Vision based Auxiliary System for Computer Assembly: System Design and implementation
2019
Master's thesis Information- and communication technology IKT590 - University of Agder 2019 This thesis proposes a solution that employs AI in assisting a human withlittle or no technical background for computer assembly in real-time with-out any form of other assistance. To achieve this goal, a state-of-the-artobject detection, namely Lighthead R-CNN is adopted as foundation. Al-terations and modifications of the algorithm are carried out to achieve theoptimal trade-o↵between accuracy loss and speed gain. In more details,it is expected to reduce the complexity of the algorithm in order to makethe solution applicable in a computer with limited computational capacity.Numerical results show t…
Blockchain-based Smart Contracts for Consent Management in eHealth
2021
Master's thesis in Information- and communication technology (IKT590) Since the introduction of Bitcoin by Satoshi Nakamoto in a white paper in 2008, Blockchain has gathered considerable attention because of its ability to be decentralized and immutable. Blockchain is still considered as a new and experimental technology, and the state-of-the-art literature review was conducted to identify various use cases for the Blockchain technology for the healthcare industry. Consent management is one of the most critical components in healthcare because of the constantly evolving eHealth services requiring access to personal data, and of corresponding privacy laws, such as the European General Data P…
Combination of automatic and manual testing for web accessibility
2018
Master's thesis Information- and communication technology IKT590 - University of Agder 2018 Web accessibility is an indispensable medium for online communication and digital inclusion nowadays. With the recent adoption of the Web Accessibility Directive making the Internet resources accessible has become a legal obligation and strikes a need for more detailed and reliable ways of web accessibility evaluation of the websites. Throughout the years, many tools have been developed for testing web accessibility as well as a plethora of metrics that are expected to convey the results. Unfortunately, in most cases the findings appear to be incomplete since the studies rely only on one testing meth…
E-Health : A smartphone-based e-health application for enhancing rural healthcare with the integration of medical sensor devices
2019
Master's thesis Information- and communication technology IKT590 - University of Agder 2019 The purpose of this research is to develop a smartphone or tablet based eHealth applica-tion to assist health workers in remote regions of different parts of the world with record-ing medical information and with the provision of basic health services to the patients.Health applications are becoming more popular day by day, and the use of technologyalong with these applications helps to improve the healthcare system. In this project,”mTeleHealth-UiA”, a smartphone-based application, was developed to address this chal-lenge. The application was implemented for the Android platform in the Android studi…
A Deep Learning Approach for Recognizing Daily Movement Patterns through Accelerometer Data
2018
Master's thesis Information- and communication technology IKT590 - University of Agder 2018 Physical activity is a key factor in the treatment of chronic diseases such asdiabetes, cardiovascular disease, and depression. Doctors and personal trainershave limited methods to accurately monitor and classify a patients actual activi-ties based on training diaries and logs that are commonly used today. In this thesis,we apply a tri-axial accelerometer carried by a patient to collect data associated todifferent activities of daily life (ADL) and utilize deep learning (DL) algorithmsfor classifying distinct activities based on the data obtained from the accelerome-ter. Among various DL methods and …
Hierarchical Fish Species Detection in Real-Time Video Using YOLO
2020
Master's thesis in Information- and communication technology (IKT590) Information gathering of aquatic life is often based on time consuming methods with a foundation in video feeds. It would be beneficial to capture more information in a cost effective manner from video feeds, and video object detection has an opportunity to achieve this. Recent research has shown promising results with the use of YOLO for object detection of fish. As under-water conditions can be difficult and fish species hard to discriminate, we propose the use of a hierarchical structures in both the classification and the dataset to gain valuable information. With the use of hierarchical classification and other techn…
A Generative Adversarial Network approach using Latent Space Manipulation for Clothing Display on Synthetic Images Using the latent space of an non-p…
2020
Master's thesis in Information- and communication technology (IKT590) The Fashion industry is continuously inventing new clothing. A significant bottleneck when introducing newly designed clothing to the market is advertisements. This thesis looks into the possibility of streamlining this bottleneck through the automated manipulation of clothing onto generated humans. A common problem in Generative Adversarial Networks (GAN) is the black-box nature of the generated re-sults. Meaning a user has no direct input on the traits of images produced. GANs are capable of exceptional levels of "creativity" when utilizing its generator to create novel results. For instance, it is possible to project a…