A5029197411- Context-Aware Activity Recognition Systems
- Indoor and Outdoor Localization Technologies
- Digital Marketing and Social Media
- Gait Recognition and Analysis
- Recommender Systems and Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Data Management and Algorithms
- Mobile Agent-Based Network Management
- Inertial Sensor and Navigation
- Robotics and Automated Systems
- Sharing Economy and Platforms
- Human Mobility and Location-Based Analysis
- Video Analysis and Summarization
- Video Surveillance and Tracking Methods
- Robotics and Sensor-Based Localization
- Service-Oriented Architecture and Web Services
- Energy Efficient Wireless Sensor Networks
- IoT and Edge/Fog Computing
- Mobile Learning in Education
- Gaze Tracking and Assistive Technology
- Energy Efficiency in Computing
- Distributed systems and fault tolerance
- Underwater Vehicles and Communication Systems
- Augmented Reality Applications
- Data Mining Algorithms and Applications
Polytechnic Institute of Porto
2010-2015
University of Minho
2015
Institute on Taxation and Economic Policy
2012
This paper presents a step count algorithm designed to work in real-time using low computational power. proposal is our first for the development of an indoor navigation system, based on Pedestrian Dead Reckoning (PDR). We present two approaches solve this problem and compare them their error counting, as well as, capability use real time system.
This paper presents an ankle mounted Inertial Navigation System (INS) used to estimate the traveled distance.The number of steps is travelled propose method based on force sensors enhance results obtained from INS.Experimental have shown that, depending step frequency, distance error varies between 2.7% and 5.6%.
In this paper, we present the tours planning system entitled TOURSPLAN, along with a new lightweight user modelling (UM) process intended to work as tourism recommendation in commercial environment. The tackles issues like cold start, grey sheep and over-specialisation through rich model application of gradual forgetting function collected action history. Also, significant performance improvements were achieved regarding previously proposed UM process.
A pedestrian inertial navigation system is typically used to suppress the Global Navigation Satellite System limitation track persons in indoor or dense environments.However, lowcost systems provide huge location estimation errors due sensors and dead reckoning inherent characteristics.To some of these we propose a that uses two measurement units spread person's body, which measurements are aggregated using learning algorithms learn gait behaviors.In this work present our results on...
Emergence of the social web has brought new powerful applications that connect people in a global scale and allow them to reap benefits life from online virtual environments. Taking into account strengths weaknesses networks tourism information systems, we propose an evolved version Toursplan system, backed up by network. This way, can exploit data generate collective intelligence travel domains, improve quality its recommendation planning services.
Nowadays, due to the incredible grow of mobile devices market, when we want implement a client-server applications must consider limitations. In this paper discuss which can be more reliable and fast way exchange information between server an Android application. This is important issue because with responsive application user experience enjoyable. present study that test evaluate two data transfer protocols, socket HTTP, three serialization formats (XML, JSON Protocol Buffers) using...
Pedestrian inertial navigation systems are an alternative to that based on structured environments. However, due low-cost sensors and pedestrian dead reckoning inherent char- acteristics, these provide huge location estimation errors. Thus, we propose a system uses two measurement units spread in person's body, which measurements used by neural network learn the human gait behavior. In this work demonstrate how is characterize step according type of terrain, can be at ascending or descending...
Most of pedestrian inertial navigation system estimates displacement based on the integration sensors measurements. However, due to low-cost and dead reckoning inherent characteristics these systems provide huge location estimation errors. To suppress some limitations we propose a information fusion learning techniques. The proposed introduces step characterization module that characterizes according activity is performing. This performs three characterizations: terrain, direction length....