Faculty of Maritime Techology and Operations

The importance of the road infrastructure for the society could be compared with importance of blood vessels for humans. To ensure road surface quality it should be monitored continuously and repaired as necessary. The optimal distribution of resources for road repairs is possible providing the availability of comprehensive and objective real time data about the state of the roads. Participatory sensing is a promising approach for such data collection. The paper is describing a mobile sensing system for road irregularity detection using Android OS based smart-phones. Selected data processing algorithms are discussed and their evaluation presented with true positive rate as high as 90% using real world data. The optimal parameters for the algorithms are determined as well as recommendations for their application.

Monitoring wild animals, especially those that are becoming endangered (for example, lynxes and wolves) is important for biology researchers. Solutions for the monitoring already exist; however, they all have drawbacks, such as limited range or lifetime, sensing modality, reporting delays, unreliability of operation. In this work we describe our experiences in designing an improved animal monitoring sensor system and low-level software for sensor node control and communication. The target animals for this particular research are wild lynxes or canines, however it can be extended to other animal species. The LynxNet system is based on tracking collars, built around TMote Mini sensor nodes, sensors, GPS and 433MHz radio, and stationary base stations, placed at the locations that are frequented by the animals. We present preliminary field results of our radio communication range tests.

Road surface analysis including pothole reports is an important problem for road maintainers and drivers. In this paper we propose a methodology for pothole detection using mobile vehicles equipped with off the shelf microphone and global positioning devices attached to an on-board computer. The approach is generic enough to be extended for other kind of event detection using different sensors as well. The vehicles are driving on public streets and measuring pothole induced sound signals. Our approach was tested and evaluated by real world experiments in a road segment for which we had established the ground truth beforehand. The results show pothole detection with high accuracy despite the background noise and other audio events.

Often software for wireless sensor networks (WSNs) is developed using a specific event based operating system (OS) such as TinyOS. However, this requires steep learning curve for the new developers. Other operating systems for embedded devices have limited support for new hardware platforms. Our goal is to provide an operating system for resource constrained devices that is easy to use for the wide range of researchers and developers familiar with C programming language and Unix operating system concepts. In addition, we provide a framework for agile portability to new hardware platforms, due to the nature of WSN systems that require specific hardware or features for the sensing tasks at hand. We propose Multiple agent netted sensor Operating System (MansOS), that demonstrates ability to execute the same application on different platforms including x86 CPU based computers for easy simulation and debugging of a single node or a whole network. The new platforms are easily added to MansOS thanks to the well defined abstraction layers. MansOS is being successfully used in real world applications, such as wild animal tracking and environmental monitoring in a fruit care research garden. It has also been used in academic environment for teaching wireless sensor networks.

Road surface quality monitoring is an important requirement for efficient, safe and comfortable transportation. However, the data collection is made difficult by the scope of the data source. Therefore, participatory sensing is a promising approach for road damage assessment. We are developing a vehicular participatory sensing application using Android smart-phones for pothole detection. This paper describes lessons learned from our field tests, which have exposed the deficiencies in terms of collected data quality. Nevertheless, the tests provide invaluable experience for planing future field tests and improvements to the test execution procedure for vehicular sensing researchers. Based on empirical and analytical results, we conclude, that semi-automated ground-truth reference point recording by a human observer in a moving vehicle while doing the actual data collection is imprecise as a consequence of multiple technical and human factors. We also discuss the motivation, why careful pothole position marking and categorization by walking along the test track is capable of providing highly accurate ground-truth.

Road surface monitoring, including automated pothole and bump detection, is essential for both drivers and road maintainers. This paper presents preliminary results from an ongoing experimental study with the central question: is a smartphone with Android operating system capable of performing road surface monitoring using participatory sensing approach? The test results with 3 Android models and several tracks are presented and demonstrate feasibility of the approach.

Maritime operations involve complex tasks that must be taught through practical training. Using modern technologies offshore simulators can serve as realistic environment for training. The degree of immersiveness can be increased by replacing conventional input devices (keyboards, joysticks) with natural user interface (NUI) devices. This paper surveys different NUI technologies and advocates that vision-based systems, such as Microsoft Kinect, can provide gesture recognition with high fidelity. The unobtrusiveness of vision-based technologies is highly important to avoid user resistance and preserve realism of the simulation.

Safety is an important aspect of transportation systems for both, the drivers and pedestrians. Significant part of road accidents are related to driver inability to react in time on sudden hazardous situations, such as pedestrians or wild animals on the road, a car stopped in case of emergency, or a slippery pavement segment. In this paper we propose an embedded system for driver visual notification in case of a hazard. The system can be unobtrusively added to existing road infrastructure, it is solar-powered and can function autonomously without human intervention. The evaluation shows, that proposed solution is able to detect several types of hazardous situations and report them to drivers.

Wireless sensor networks (WSNs) have been a widely researched field since the beginning of the 21st century. The field is already maturing, and TinyOS has established itself as the de facto standard WSN Operating System (OS). However, the WSN researcher community is still active in building more flexible, efficient and user-friendly WSN operating systems. Often, WSN OS design is based either on practical requirements of a particular research project or research group's needs or on theoretical assumptions spread in the WSN community. The goal of this paper is to propose WSN OS design rules that are based on a thorough survey of 40 WSN deployments. The survey unveils trends of WSN applications and provides empirical substantiation to support widely usable and flexible WSN operating system design.

Wireless sensor networks and other battery powered embed-ded systems often require long lifetime. To assess application efficiency, accurate energy estimation tools are required. Although software energy profiling provides scalable network simulation opportunities, it lacks ac-curacy. In this paper we propose a hardware-based energy measurement approach using EdiMote prototyping platform. Evaluation shows, that it is more accurate compared to software profiling while providing ex-tra information about energy consumption of separate system modules: MCU and radio chip.

Alarms are an important part of automation systems that raise user awareness in emergency situations. However, research shows that existing audible and visual alarms are ineffective. Failure to deliver alarm signals leads to lack of awareness that results in accidents. This paper presents a work in progress on a wearable tactile device application for smart alarm systems. We describe our hypotheses that tactile alarms can decrease user resistance and deliver more focused awareness with directional hints. In this paper, the prototype of a wearable tactile belt is described and its future improvements are analysed.

Wireless sensor networks (WSN) consist of a number of low-power spatially distributed autonomous nodes equipped with means of communication. Developing software for WSN is challenging; operating system (OS) support is required. In this paper we present MansOS, a portable and easy-to-use WSN operating system that has a smooth learn-ing curve for users with C and UNIX programming experience. The OS features a configuration model that allows to reduce application binary code size and build time. In contrast to other WSN OS, MansOS by default provides both event-based and threaded user application support, including a complete although lightweight implementation of preemptive threads.

Data-related businesses is an emerging trend in the recent decade. However, the availability and amount of information make it difficult to ensure quality in terms of data fusion and version control. Completely automated data aggregation systems fail to provide reliable and consistent data. In this paper we summarise existing knowledge on relation databases and augment it with description of business requirements for data version control. We propose an architecture that addresses the requirements, and discuss possible future work to improve and evaluate the approach.

Complexity and specificity of monitoring sensor data from marine operations brought a majority of challenges of how to evaluate the visualizations of such sensor data. It's urgently needed to develop and implement new evaluation methods to assess the visualization of maritime data. In this paper, we explore both quantitative and qualitative evaluation approaches to define evaluative metrics of our interactive visualization techniques, and present a case study carrying out by domain researches in real setting. This work is an important part to complement the visual analytics for maritime operations.