Filter

edge-ml is a browser based, end-to-end machine learning framework for time-series data on microcontrollers. Data can be ingested using various methods, including live collection. Labeling is supported in a user-friendly manner with a graphical user interface. Based on the datasets and labels, users can train machine learning models which are deployable onto microcontrollers.

EUHubs4Data Most of Europe’s SMEs lag behind in data-driven innovation. To tackle this problem, the EU-funded EUHubs4Data project will build a European federation of Data Innovation Hubs based on existing key players in this area and connecting with data incubators and platforms, SME networks, AI communities, skills and training organisations and open data repositories. A more…

DroneCAS The target is to capture digital data in the medium voltage grid, which supplies energy to European rural areas through over 4 million kilometers of power lines. On-foot inspections are cost-effective but do not capture digital data, limiting the implementation of AI analysis. Drones can provide high-quality data at a lower cost but require more…

FreshIndex in EUHub4Data is a project that focuses on enhancing the safety and sustainability of the food sector by utilizing AI and IoT technologies. The project aims to develop a comprehensive monitoring system that tracks food quality and safety from farm to table, while reducing waste and promoting sustainability throughout the food supply more…

In the ARCTUS project we develop machine learning (ML) models to monitor refrigerator condensing units (RCU). Such ML models can bring significant value since they provide information on upcoming malfunctions that could stop the operation of an RCU and also predict future energy consumption. For this project we use public datasets as well as data more…

Coronazähler.de is the most up to date counter of Corona Cases for Germany. It uses unique Web-Crawling technology and intelligent information recognition and AI to keep the information up to date and to prognose future development. 

AI-Platform for automated training of object detection models based on cad data The manual assembly of devices consisting of many individual parts is a time-consuming, tedious and error-prone industrial process, which could in principle be supported by automated recognition technologies. As a typical example, Gabler is a manufacturer of production machines for packaging goods, each more…

In the Fit2Ear project we are applying smartphone depth cameras to generate customized otoplastics for earable computing. Contact – Tobias Röddiger – Haibin Zhao

HelioPas AI is a startup spin-off which monitors agricultural fields on parameters like crop health and soil moisture. The latest research in data science enables HelioPas AI to produce unparalleled in spatial resolution and prediction accuracy. The data is used by farmers to monitor fields further away to better plan their field work and to more…

Within the BMBF-funded project “Lehre hoch Forschung”, several measures to establish research-oriented teaching at a much earlier stage than in traditional university teaching are implemented at KIT – both in individual institutes as well as in the central institutions. TECO / the Chair for Pervasive Computing Systems is involved in the more…

Environmental sensors must be calibrated regularly in order to correctly take into account construction-related and external influences in the interpretation of the raw data and to correct them accordingly. Only then can any meaning be ascribed to the measurement data. Low-cost sensors are preferably used in Citizen Science applications, whereby a lengthy calibration with an more…

Germany has a leading position in the development of mechatronic systems. However, manufacturers often face the following contradiction: on the one hand they themselves manufacture high-tech for the production of tomorrow and on the other hand due to the high diversity in their own production they become fragmented with to manual processes. The lack of more…

Ambient assisted living (AAL) technologies have great potential to guarantee a self-dependent life for people with disabilities like visually impaired people or the elderly. However, many AAL research projects fail to deliver market-ready products. The explicit application of Universal Design (UD) on smart home products could facilitate marketing them. Also,  technologies, which are usable ─ more…

The world is increasingly being “technified”, yet many people can’t use modern ICT  due to Disability, (Digital) Illiteracy,  or Aging: We don’t have solutions for all. It’s too expensive for many. People don’t know what exists that would help them. Access to ONE device is no longer sufficient: access to all encountered devices is needed… more…

When visualizing big data streams, overwhelming the user with a large amount of information can quickly become an issue. This psychological phenomenon is called Information Overload and is usually caused by badly designed user interfaces, especially when too much information is shown on the screen at the same time. The key for overcoming these problems more…

The increasing complexity of processes leads to an enormous amount of data which needs to be processed and understood by people. This is true for a great variability of processes, such as a production process in a factory or a more abstract procedure settled in an office environment. Finding a suitable way to visualize the more…

Over several years, the KIT-FM (Facility Management) has collected data with immense value for the operational management, but also for the planning and implementation of future infrastructure developments. This data has been collected in a widely closed real system and is available for nearly all buildings on the Campus North (former research center) containing a more…

Lowering the energy consumption has become a prime goal for most, if not all, system developers and engineers working nowadays in building smart environments, consorting that way with the today’s world’s climate and energy policy. A smart environment like a smart home should therefore be able to provide energy efficient solutions and services. This should more…

The ubiquity of mobile networks and smartphones in principle offers an excellent infrastructure for participatory environmental measurements, e.g. in Smart City scenarios. Modern smartphones are already equipped with a variety of internal sensors. In some current models, even environmental sensors for measuring temperature, humidity and air pressure can be found. However, phenomena such as the more…

Particulate Matter has a serious impact on health, well-being and the life expectancy of people. Today, only few stationary or mobile sensing stations are available for the monitoring of large areas, e.g. a city. This project aims to develop mobile particulate matter dosimeters that can be used for distributed Fine Dust Monitoring, e.g. through Participatory more…

In the Smart Air Purifier project, a prototypical microelectronic IoT-platform was developed and integrated into an air purifier unit for the use in cars. This Smart Air Purifier is outfitted with various environmental sensors, a microcontroller, and a Bluetooth Low Energy module. The system can determine the temperature, humidity, and concentration of various gases and particulate more…

ProximityHat is a wearable sensory substitution system, which uses pressure actuators around the head to convey spatial information. It was already shown that the sense of touch can be used to augment our perception of reality. Existing systems focus on vibration signals for information transfer, but this is unsuitable for constant stimulation in everyday use. Our system more…

In order to meet the increasing demands for high resolution and high quality environmental data, e.g. in Smart City scenarios, new approaches for sensing systems have to be considered. One alternative for using few professional measuring stations consists in crowdsourcing the data collection – Participatory Sensing. Data is collected highly distributed with mobile and inexpensive more…

In Germany, the majority of people already owns a smartphone or another mobile device – and carries, unconsciously, a well-equipped sensor system with them. Just a few of these sensors are sufficient to draw conclusions about current and future activities or the context of the owner. Even non-physical data sources may provide relevant information for more…

The enormous amount of data created by people using every day mobile devices with increasingly sensing capabilities, such as image, location and other data, has led to the establishment of a new crowdsourcing concept called Participatory Sensing. It describes people voluntarily sensing their local environment and sharing this data using mobile phones and the web, more…

The bPart is a sensor node with Bluetooth Low Energy (BT LE) radio and several off the shelf MEMS sensors, all highly integrated in a volume of less than 1cm³. Aside from the BT transceiver, the bPart features a light sensor, 3-axis accelerometer, temperature sensor, humidity sensor, battery, processing unit and a multicolor RGB-led for more…

The project Towards a Mobile Hybrid Cloud is an activity in the Computing in the Cloud action line of EIT ICT Labs. It is a continuation of the 2012 project Towards a Mobile Cloud and has the goal to deliver concepts and tools for managing specific aspects of hybrid cloud environments, including the optimization of quality of more…

Servicing the factory of the future raises challenges for the service teams and organizations. The industrial plant environment is changing rapidly due to the impact of the market and new autonomously operating information technologies such as on site information and communication services, an Internet of Things (IoT), smart sensors and intelligent automation devices as well more…

In this project, we develop a tool chain based on In-Memory Data Management and Parallel Data Processing in GPU using CUDA for large and intensive Smart Meter analytics.

The Software Campus project InstaGuide tackles the problem of document generation in high variability intelligent industrial environments. The goal is to create a software prototype which can facilitate the dynamic generation of product documentation based not only on the current software configuration but also on the context at hand. At the core, it enables association, more…

Human activity recognition, i.e. the recognition of a users’ current physical activity (e.g. walking, eating, sleeping) by monitoring and analyzing her/his behavior and the environment, can improve quality of living. However, current sensors for activity recognition have a number of drawbacks such as installation/attachment effort, battery runtime or privacy concerns. In AKTIFUNK, TECO is researching more…

The Software Campus project PreTIGA is about optimizing player experience in game environments based on a generalizable model. The objectives are to build a game model generalizable to diverse game environments as a foundation to predict situations of interest like a decrease in fun or the drop-out of players and to proactively prevent such situation. more…

The Software Campus project FRAGMENTS is about interacting with intelligent environments. The goal is to create a software framework which can facilitate the design and development of efficient and intuitive user interfaces by the use of appropriate design guidelines. The editor at the core of the framework enables short iteration cycles by providing basic interface more…

Description The Software Campus integrates higher education and research projects in an innovative dual concept. It embeds students in a partnership with leading German IT companies, offering them relevant workshops and career mentoring by top managers. The goal of the Software Campus is to establish a top-ranked qualification program more…

The Software Campus UHUS project is about updating the software components of distributed systems at runtime. It’s goals are to provide mechanisms to implement hot updates on individual devices, and provide planning strategies to coordinate update plans on many systems. We are working on identifying dependencies between software components, such as communicating devices in smart more…

Koordinator is the follow up project to the sucessful BMBF project landmarke in which research was directed towards the creation of an ad hoc wireless sensor network to improve firefighter navigation. In Koordinator it is now investigated how this navigation support network may be extended using novel pervasive technologies to improve mission control in more…

Description Science Bridge Asia: Urban Sensing of City Dynamics and Energy Use in the Beijing Metropolitan Area The “Science Bridge: Asia” program of the Robert Bosch Stiftung supports scientists working in Germany who would like to strengthen and rekindle exchange and cooperation with researchers in China, Indonesia, India, Japan, Singapore, South Korea or Vietnam. more…

The project Towards a Mobile Cloud is an activity in the Computing in the Cloud action line of EIT ICT Labs. It conducts research in order to support next-generation elastic mobile clouds, where mobile scenarios are consistently supported by cloud environments. Benchmarking and Evaluation Tools for assessing more…

  The TECO Envboard is an environmental sensing platform for research and development purposes. It carries a variety of commercial off-the-shelf (COTS) sensors, ranging from accelerometers over weather sensors like temperature, humidity and barometric pressure to sensors for gas concentrations and particulate matter. The Envboard is intended to be generically suitable for various application scenarios. more…

Digital Preservation (DP) is traditionally understood as the management of digital information over time. The digital preservation problem is well-understood for query-centric information scenarios but has been less explored for scenarios where the important digital information to be preserved is the execution context within which data is processed, analysed, transformed and rendered. A primary motivation more…

The objective of the research project Polytos is to develop printed organic circuits with integrated sensors capable of recording data such as temperature, humidity or light exposure. The deployment of these types of printed organic circuits for item-level-tagging in logistics or supply chain scenarios could be used as organic printed smart labels in the future. more…

The DiagnOptiMesh project will conduct original research on the possibilities to diagnose and optimize the status of commercial wireless networks based on the WirelessHART standard. This will be the first attempt to establish network diagnosis and management for wireless field bus systems used in industrial automation that will collect diagnostic information and optimize the system more…

Aletheia was a leading innovation project, sponsored by the Federal Ministry of Education and Research, that aims at obtaining comprehensive access to product information through the use of semantic technologies. TECO researches in federating information from heterogeneous device such as sensor nodes and RFID tags. Together with ABB we work on platform independent solutions for more…

Chosen: Cooperative Hybrid Objects Sensor Networks. Chosen researches, develops and applies a ultra-low power standard chipset for wireless sensor nodes that will be SOA/Web2.0 enabled. The sensor node will have features as wake-up-on-radio pattern and will integrate directly into Web 2.0 applications. Applications areas cover automotive and avionics. TU Braunschweig leads the middleware and system/integration more…

Classical approaches of computer science do not scale well for today’s large and complex software-intensive systems. Software systems cannot be considered in isolation, since they are connected among each other and interact massively. Instead they are to be designed as parts of a larger IT Ecosystem. In analogy to biological ecosystems, IT Ecosystems are based more…

In the landmarke BMBF project TECO researches how a mobile ad hoc wireless sensor network can improve firefighter navigation in harsh indoor environments. The landmarke vision describes a system which does not focus on precise locationing but on providing navigational support which builds on the existing skills of firefighters. During the mission the firefighters themselves more…

In sensor networks, different types of sensors are used to capture events, recognize contexts, derive states of objects or monitor processes within application scenarios. The processes themselves are often very complex (e.g. in industrial applications) and a combination of sensor data from different sensor nodes is used to derive information regarding their states or properties. more…

With the progress of wireless sensor network (WSN), this emerging technique is soon applied in many industrial projects. However, a standard to describe the security level in WSN is still lacking, which becomes very needful today. In MoSe Project we try to build a formal model to describe the security level of sensor network and more…

Wireless sensor networks are well suited for supervising conditions in various environments. When used in rail cargo for continuous monitoring of freight wagons, the results can provide many benefits for the operator, such as train sequence monitoring, monitoring of unusual events that may lead to accidents or estimation of optimal service points. The main challenges more…

Topic Development and utilisation of methods of context prediction for the optimisation of data generation in wireless sensor networks Research area and field of work Computer Science / Electrical Engineering: Algorithms, Optimisation, Sensor Networks Summary The aim of the project is to develop new methods for context prediction in wireless sensor networks (WSN) and to more…

The dinam concept is a novel approach to simplified rapid development of wireless sensor network applications as well as an according WSN platform. As opposed to the traditional mote- based development archetype, dinam proposes combining the development steps into a single continuous, fluid process that is completely integrated into the node. The dinam concept sensor more…

Low Cost Smart-Labels for Logistic Processes in Retail Sponsor: Bundesministerium für Bildung und Forschung (BMBF) Projektdauer: 01.04.2006 bis 30.09.2008 (30 Monate) Ziel des Projektes Das Ziel des Projektes besteht darin das Inventurproblem im Einzelhandel zu lösen. Dazu sollen billige RFID-Tags mit gedruckten Antennen an jedem einzelnen Produkt angebracht werden. Durch Optimierungen der Kommunikationsprotokolle und mobile more…

P2P4Ubicomp researches how to interconnect various distributed sensor networks, what performance measures are important, what and how information are replicated among involved remote locations etc. The project researches this issues regarding integrating into Internet and Telco environments and builds up large, world-spanning environments. Many industrial applications rely on sensors and sensor networks residing on machinery, more…

The goal of RELATE is to research in spatial relationships between tangible objects that together form an interface both in P2P location hardware, software (recognition, protocols, applications) and user applications. One goal of the project is to develop generic building blocks for a lightweight short range (room size) location system that does NOT require infrastructure, more…

The goal of this project is to create practical approaches to human activity recognition (HAR). HAR is the process of allowing IT devices, processes and infrastructures to be aware of the situations and activities of the human beings interacting with these systems. Awareness is typically enabled by applying data processing and machine learning techniques to more…

This project proposes a file system as an abstraction layer for a uniform way of accessing any system resource on wireless sensor nodes. Even functions and libraries can be represented and accessed in this uniform way allowing developers a novel way to design and implement applications. Tiny, Ressource poor sensor nodes require novel operating systems more…

Superimposing codes can be used for a variety of applications in sensor network communication. One of the earliest applications was precise time synchronization of sensor nodes and channel access negotiation in AwareCon. More advances applications are using superimposed codes for ultra-fast ultra power-saving transmission of information – up to 1000 times faster than with traditional more…

OSOITE: Overlay-network Search Oriented for Information about Town Events. OSOITE researches collaboration mechanisms of independent large scale sensor networks and how to improve user interaction with sensor data. Generally speaking people are likely to search things related to their daily lives in the real world ranging from straight-forward queries to complex ones. In order to more…

Cooperative and collaborative strategies for transmission in wireless sensor networks enable transmission range restricted nodes to reach distant receivers by superimposing transmission signals. This addresses an important practical problem of wireless sensor networks. In this proposal we extend this strategy by emergent properties: We establish a method to adapt the collaborative emergent optimisation process by more…

SmartSurroundingsThe Smart Surroundings research program is investigating a new paradigm for bringing the flexibility of information technology to bear in every aspect of daily life. It foresees that people will be surrounded by deeply embedded and flexibly networked systems that provide easily accessible yet unobtrusive support for an open-ended range of activities, to enrich daily more…

CoBIs develops a radically new approach to business processes that concerns physical entities in enterprise environments (goods, tools, etc). This approach embraces advances in networked embedded systems to embed business logic in the physical entities, thereby creating Collaborative Business Items (CoBIs). These items bring closer together the state of an enterprise as represented in a more…

AwareOffice The AwareOffice is an technology equipped office environment like a meeting room supporting various actions like scheduling, presentation, annotation and providing different services concerning these actions. Goal The goal of the AwareOffice initiative is to provide a real world test bed setting for ubiquitous computing (UbiComp) applications. Therefore we trace two directions opening up more…

This project seeks to gather basic understanding in how far context aware camera systems are able to support human memory. The project seeks to develop a small wearable context aware camera device, gains insight into what activities are contributing to events we like to keep in memory, how to recognize these activities using a minimal more…

uParts are tiny little sensor network nodes that are very easy to deploy and run a 0-administration and low configuration (or 0-configuration when used with default) approach. The projects researches how to reach minimum deployment and maintenance costs of a sensor network and includes research on long lifetime hardware, 0-maintanance communication protocols, lower production costs more…

ContextAsAKey is an approach to reach ad-hoc security and privacy in a Ubiquitous Computing environment without any user involvement – management, configuration nor administration. The basic principle is the use of the common context that exist when computing devices are located close to each other in the same physical environment. Technically the system bases on more…

Particle Computer is an enabling platform for various scenarios related to Ubicomp. Particles are tiny wireless nodes where a huge variety of sensors can be attached. Further, the fully programmable micro controller accompanied by powerful libraries let novices as well as professionals implement applications in the fields of sensor networks, human-computer interaction, supply-chain management and more…

The MediaCup is an ordinary coffee cup augmented with sensing, processing and communication capabilities (integrated in the cup’s bottom), to collect and communicate general context information in a given environment. It is an example how to equip everyday objects with computing and communication capabilities. With the MediaCup setup (consisting of several cups and other equipment) more…

The eSeal concept researches how to extend the concept of seals to general objects using Ubiquitous Computing technology. It identifies which additional threads can be detected using an electronic seal an implements several prototype seals. A major implementation path of eSeal was the DigiClip. The DigiClip system allows the tracking, synchronization and and integrity control more…

ParticleBasic is an attempt to simplify the programming model of the Particle Computer and enable rapid prototyping of applications. It therefore consists of two major components: A small scale VM on the Particle Computer and an interpreter running on top of it. A compiler for the development platform (written in JAVA) that generates byte code more…

The In/Out Board is an ambient display showing the presence of persons in an office environment based on their activity. It integrates recognition of persons using RFID technology and PC based background services with an ambient display.   Start/End: 2004 Partners: SAP AG Research Topics: RFID system, Integration of information infrastructure Application and economic dissemination: more…

Rather than using a hierachical approach to resolve RFIDs indentification code to database information this project researches in using Peer-to-Peer technology. The project showed that privacy of information can be better ensured and higher reliability can be gained using such an approach. A query, which consists of an identification string, is sent to the network more…

The Smart-Its project is interested in a far-reaching vision of computation embedded in the world. In this vision, mundane everyday artefacts become augmented as soft media, able to enter into dynamic digital relationships. In our project, we approach this vision with development of “Smart-Its” – small-scale embedded devices that can be attached to everyday objects more…

AwareCon is an approach for communicating in context aware environments and the network stack for the Particle Computers. AwareCon goes beyond traditional network approaches by using sensed context information from the environment to adjust parameters inside the network stack and by optimising the transfer of context information inside Ubiquitous Computing environments. It is therefore both more…

The SmartShelf is an RFID reader enabled shelf. The project goal was to research various strategies to understand and influence the customers’ decision behavior during the process of buying items in a retail store. The SmartShelf is a technology to reveal customers’ interactions with a product item in an unobtrusive way. Features: The SmartShelf is more…

RAUM is a communication principle for spontaneous communication between small devices in Ubiquitous Computing environments. Its central idea is to use location information to assign producers and consumers of communication events in such environment and provide location aware and location dependent routing to distribute information within Ubiquitous Computing environments. The centre of the RAUM system more…

AmbientTelepresence researched the possibility to build up a ambient presence of remote people using a Ubiquitous Computing environment instrumented with embedded devices rather than with video or audio transmission. “Ambient Telepresence is a method to give someone the feeling that someone else is present while they are not co-located”. The project showed that transfer of more…

Several projects reserched the use of ambient, non-obtrusive human-computer interaction. For wearable computers, we developed an interface that is able to observe users behaviour and conclude on the behaviour (implicit Human Computer Interaction). In contrast to traditional HCI concepts, users have not to be trained for the application nor have do they need to be more…

Point&click researches on ways to control devices in the environment using a single handheld device and interface. It concludes that a split in two phases (point and click) is most appropriate also for controlling (embedded) electronic devices in a physical environment. It also found that there is less chance to find a general interface for more…

UbicompBrowser researches how electronic consumer devices embedded into the environment can be connected to the information network using Internet technologies. It results in a prototype that is able to bridge the gap between physical devices and information space by utilizing a handheld device equipped with a Barcode scanner – the UbicompBrowser. Using the UbicompBrowser software more…

As computing devices and sensors get smaller, the interface with their user becomes more and more boring and irritating. The user has to explicitly input everything in detail in order to get some decent service from his device. Part of the solution to this problem is known as CONTEXT AWARENESS: thanks to hardware sensors and more…