A5071144214- Evolutionary Algorithms and Applications
- Reinforcement Learning in Robotics
- Music Technology and Sound Studies
- Embedded Systems Design Techniques
- Metaheuristic Optimization Algorithms Research
- Music and Audio Processing
- Social Robot Interaction and HRI
- Neural Networks and Applications
- Robot Manipulation and Learning
- Mental Health Research Topics
- Context-Aware Activity Recognition Systems
- Human Pose and Action Recognition
- Human Motion and Animation
- Robotics and Sensor-Based Localization
- Modular Robots and Swarm Intelligence
- Interconnection Networks and Systems
- Advanced Manufacturing and Logistics Optimization
- Robotic Path Planning Algorithms
- Neuroscience and Music Perception
- Optimization and Packing Problems
- VLSI and FPGA Design Techniques
- VLSI and Analog Circuit Testing
- AI in Service Interactions
- Parallel Computing and Optimization Techniques
- Video Surveillance and Tracking Methods
University of Oslo
2016-2025
Universidade Federal do Rio Grande do Sul
2024
The Research Council of Norway
2022
Oslo University Hospital
2019
Conference Board
2019
Natural Selection (United States)
2019
European Space Agency
2018
Kyoto University
1995-2002
Norwegian University of Science and Technology
1997-2002
Personal and ubiquitous sensing technologies such as smartphones have allowed the continuous collection of data in an unobtrusive manner. Machine learning methods been applied to sensor predict user contextual information location, mood, physical activity, etc. Recently, there has a growing interest leveraging for mental health care applications, thus, allowing automatic monitoring different conditions depression, anxiety, stress, so on. This paper surveys recent research works systems...
This paper analyses different hardware sorting architectures in order to implement a highly scaleable sorter for solving huge problems at high performance up the GB range linear time complexity. It will be proven that combination of FIFO-based merge and tree-based results best low cost. Moreover, we demonstrate how partial run-time reconfiguration can used saving almost half FPGA resources or alternatively improving speed. Experiments show sustainable throughput 2GB/s fitting into on-chip...
Exploiting the benefits of partial run-time reconfiguration requires efficient tools. In this paper, we introduce tool Go Ahead that is able to implement reconfigurable systems for all recent Xilinx FPGAs. This includes in particular support low cost and power Spartan-6 assists during floor planning automates constraint generation. It interacts with vendor tools triggers physical implementation phases way down final configuration bit streams. enables building flexible integrating many...
Novel computing systems are increasingly being composed of large numbers heterogeneous components, each with potentially different goals or local perspectives, and connected in networks which change over time. Management such quickly becomes infeasible for humans. As such, future should be able to achieve advanced levels autonomous behaviour. In this context, the system's ability self-aware self-express important. This paper surveys definitions current understanding self-awareness...
Wearable sensors measuring different parts of people's activity are a common technology nowadays. In research, data collected using these devices also draws attention. Nevertheless, datasets containing sensor in the field medicine rare. Often, is non-public and only results published. This makes it hard for other researchers to reproduce compare or even collaborate. this paper we present unique dataset from patients suffering depression. The contains motor recordings 23 unipolar bipolar...
A depth camera-based novel method is proposed here for efficient facial expression recognition. For each pixel in a image, eight local directional strengths are obtained and ranked. Once the rank of all pixels obtained, histograms developed surrounding directions. The then concatenated to represent features image face. This approach named histogram pattern (LDRHP). To combine with LDRHP features, one more robust feature extraction technique strength (LDSP) proposed. Typical (LDP) considers...
Current practice of assessing mood episodes in affective disorders largely depends on subjective observations combined with semi-structured clinical rating scales. Motor activity is an objective observation the inner physiological state expressed behavior patterns. Alterations motor are essential features bipolar and unipolar depression. The aim was to investigate if measures can aid existing diagnostic practice, by applying machine-learning techniques analyze patterns depressed patients...
With the emergence of ubiquitous sensing technologies, it is now possible to continuously monitor users during their everyday activities in order provide personalized feedback and interventions. For example, fitness trackers can count steps motivate keep active. rich set sensors, smartphones are also capable monitoring user behavior such as physical activity location. Smartphones' inertial sensors have been used recognize different types activities. Usually, statistical sets features from...
An automatic traffic sign detection system is important in a driver assistance system. approach for detecting Norwegian speed limit signs proposed. It consists of three major steps: color-based filtering, locating sign(s) an image and numbers on the sign. About 91% correct recognition achieved selection 198 images.
With the Xilinx Design Language (XDL), FPGA vendor offers a very powerful interface that provides access to virtually all features of their devices. This includes on one side generation complete device descriptions containing information about primitives and routing fabric. On other side, XDL can be used constrain systems or directly implement modules macros for FPGAs. In this paper, we will provide documentation language reveal several use cases language.
Achieving high speed run-time reconfiguration is important for the adaptation of partial in many applications. The that currently available today somehow artificially limited by FPGA vendors, while fabrication process technologies used building latest devices are capable achieving much higher speed. In this paper we will present a new design and implementation method exceeds specified today's FPGAs. By adding custom logic around Internal Configuration Access Port (ICAP) to implement an...
Work on human self-awareness is the basis for a framework to develop computational systems that can adaptively manage complex dynamic tradeoffs at runtime. An architectural case study in cloud computing illustrates framework's potential benefits.
For robots to handle the numerous factors that can affect them in real world, they must adapt changes and unexpected events. Evolutionary robotics tries solve some of these issues by automatically optimizing a robot for specific environment. Most research this field, however, uses simplified representations robotic system software simulations. The large gap between performance simulation world makes it challenging transfer resulting world. In paper, we apply multi-objective evolutionary...
With the emerging interest in ubiquitous sensing field, it has become possible to build assistive technologies for persons during their daily life activities provide personalized feedback and services. For instance, is detect an individual’s behavioral pattern (e.g., physical activity, location, mood) by using sensors embedded smart-watches smartphones. The multi-sensor environments also come with some challenges, such as how fuse combine different sources of data. In this article, we...
Artificial Intelligence (AI) has the potential to greatly improve delivery of healthcare and other services that advance population health wellbeing. However, use AI in also brings risks may cause unintended harm. To guide future developments AI, High-Level Expert Group on set up by European Commission (EC), recently published ethics guidelines for what it terms “trustworthy” AI. These are aimed at a variety stakeholders, especially guiding practitioners toward more ethical robust...
With recent advances in the field of sensing, it has become possible to build better assistive technologies. This enables strengthening eldercare with regard daily routines and provision personalised care users. For instance, is detect a person's behaviour based on wearable or ambient sensors; however, difficult for users wear devices 24/7, as they would have be recharged regularly because their energy consumption. Similarly, although cameras been widely used sensors, carry risk breaching...