Category: Archive

Luister

Duration: 01/2006 – 01/2007  Funding: Kenniswijk Project SenterNovum

Luister

Almende has developed ASK, a communication platform based on the principles of self-organization.

In order to help people to articulate their preferences and to handle the accompanying challenges, Almende has developed ASK, a communication platform based on the principles of self-organization. ASK makes the best connections between people that most of the time do not know each other and uses feedback from previous connections to arrange a better match next time. The system estimates the quantity of the demand and supply during the day and takes initiatives to ensure that contact can always be made. Every participant can up-date his/ her own availability and reachability information on the internet.

 

 

Contribution

For the fist time ASK is being implemented in an elderly home at Humanitas Rotterdam Zuid. Elderly people pushing their alarm button are connected to a server that classifies their question by means of speech recognition. ASK matches them instantly with the best and available volunteer or professional and calls them on their PDA/ mobile phone. The PDA can also register the start and end time of the care session and can communicate this with an existing planning tool.

Results

The project resulted in a communication system, namely ASK. Both parties are requested to give feedback in order to investigate whether or not this match should take place in the future. This way, complex last minute planning has become streamlined and simplified.

More info?

Need specific information regarding the project? Please contact our senior consultant for more information.

Jan Kraaijeveld

Senior consultant

+31 (0)10 404 9444

jan@almende.com

Read More

Intelligent Trading Agents

Intelligent Trading Agents that Facilitate Decision Making in Multi-Agent Marketplaces using Preference Modeling

Duration: 11/2008 – 04/2013  

Intelligent Trading Agents

Modern business networks and markets are highly dynamic and exhibit a high degree of uncertainty. Business managers thus often have to make complex strategic, tactical, and operational decisions; ranging from the macroscopic (i.e. which markets should we enter and when?) to the microscopic (i.e. which products should be packed on which pallet?).

This project aims to design, build and assess an intelligent multi-agent system that is able to support people in making such complex business decisions. The software agents must mimic human decision making behaviour in an electronic market or auction environment.

Learning agents are defined as software entities that carry out some set of operations on behalf of a user or another program with some degree of independence or autonomy. Agents improve their performance by learning from experience and in so doing employ some knowledge or representation of the user’s goals or needs. The application will be aimed at the logistics domain, specifically supply chain management.

Contribution

Results

More info?

Need specific information regarding the project? Please contact our senior consultant for more information.

Jan Kraaijeveld

Senior consultant

+31 (0)10 404 9444

jan@almende.com

Read More

ICIS

Interactive Collaborative Information Systems

Duration: 01/2005 – 12/2009 
Funding: BSIK SenterNovum

ICIS

The ICIS partners believe that the search for techniques and methods that help to build information systems with intelligent behaviour is one of the most critical areas in future information systems research. Among the requirements for these systems are capabilities to help the human actors to (pre)process ever increasing amounts of digital and digitized information and search for relevance, meaning and importance, support a chain of activities (rather than a single function) that is focused on reaching a set of goals by acting on both the system and the environment in which the system operates, be able to auto-detect and cope with changes both in the environment, the system and in the goals, and support reasoning with uncertainty, reasoning with risks and reasoning under a lack of knowledge, necessary because of the chaotic nature of the real world.

As an overall architecture for ICIS-type systems, the project will use a new paradigm.
In particular, ICIS systems will use Actor-Agent Communities, a particular type of complex system, involving the collaboration of multiple human and artificial agents for the realization of a common mission.

The ICIS project will use a focus on one particular application domain to ensure that with a relatively limited amount of effort over a restricted period of time, a noticeable and recognizable impact of ICIS technology on society can be realized. These results however, can be used in other domains of application. In particular ICIS application domains are characterized by real-time decision making in complex, dynamic and chaotic environments.

Contribution

Results

More info?

Need specific information regarding the project? Please contact our senior consultant for more information.

Jan Kraaijeveld

Senior consultant

+31 (0)10 404 9444

jan@almende.com

Read More

Hybrid Human-Agent Networks

Duration: 04/2005 – 03/2009  Funding: Casimir programme of SenterNovum

Hybrid Human-Agent Networks

The goal of the research programme is to increase the mobility of researchers and enhance information exchange between companies and public knowledge institutes. Core of the programme is to give beta and technical researchers employees of knowledge institutes a chance to work temporarily for companies and vice versa.

Mobility and the possibility to continue a career as researcher at a different setting makes a job as researcher more challenging and versatile. The project increases the attraction of a research career and improves the labour market for researchers. 

Contribution

Results

More info?

Need specific information regarding the project? Please contact our senior consultant for more information.

Jan Kraaijeveld

Senior consultant

+31 (0)10 404 9444

jan@almende.com

Read More

Fit4Green

Federated IT for a sustainable environmental impact

Duration: 01/2010 – 06/2012  Funding:  FP7 – ICT for Energy Efficiency

FIT4Green

FIT4Green contributes to ICT energy reducing efforts by creating an energy-aware layer of plug-ins for data center automation frameworks. 

The FIT4Green platform gives users insights into their energy consumption. The plug-ins enhance IT solutions deployment strategies with respect to energy consumption, for example by moving computation and services around a federation of data centers, and switching of idle machines. FIT4Green implements these energy-saving measures without having to compromise for Quality of Service or compliance with Service Level Agreements. Being a generic solution, the plug-in may easily be adapted to different systems in both single site and federated data centers. 

FIT4Green is expected to reduce energy consumption by at least 20% in direct server and network devices. An additional 30% savings in cooling needs is expected. 

Contribution

Almende has been involved in all phases of the FIT4Green project but was mainly responsible for the energy control plug-ins; from design to implementation, testing and validation. The research has taken different perspectives into account, namely, the business and functional requirements of the FIT4Green platform, the reference architecture and design of the plug-ins, the data centre and energy models, the energy aware optimization policies, and exploitation and dissemination activities of the project. 

Results

More info?

Need specific information regarding the project? Please contact our senior consultant for more information.

Jan Kraaijeveld

Senior consultant

+31 (0)10 404 9444

jan@almende.com

Read More

Dynamic Contracting

Duration: 01/2010 – 01/2014  

Dynamic Contracting

Tendering is the main method in the public sector for attracting contractors to execute infrastructural projects, such as road construction.

The problem is that such tenders result in long-term contracts, while circumstances may change during the building process, leading to new risks and opportunities for both parties. Also, contracts may be based on lacking or false information. A method for creating more dynamic contracts is thus called for, allowing for renegotiation of details during execution of the project.

Dynamic Contracting in Infrastructures claimed to find a better way for setting up rules for tendering. Among others, the project looked for a way to give contractors incentives to provide more information beforehand, and to support contractors and managers in dealing with changes. Furthermore, contractors are challenged to take into account so-called “social costs”: the costs of serious traffic queues due to maintenance activities.

Contribution

From the beginning, Almende has focused on multi-agent modeling for Dynamic Contracting. Both mechanism design and game theory have been used to attempt optimization in problems where agents are self-interested and (partial) information is only privately known to each agent.

Results

The project has resulted in in the serious game, constructed for the maintenance process. Another outcome of the project interesting to Almende consists of techniques for agent-based traffic simulation. An application of these techniques is foreseen in the Deal platform of daughter company Deal Services.

More info?

Need specific information regarding the project? Please contact our senior consultant for more information.

Jan Kraaijeveld

Senior consultant

+31 (0)10 404 9444

jan@almende.com

Read More

DEAL

Distributed Engine for Advanced Logistics

Duration: 04/2002 – 04/2006  Funding: Programme E.E.T. of Senter Novum

DEAL

The aim of DEAL has been to speed up negotiations between different parties by using representation through software agents, increasing the number of examined alternatives as a result. The use of software agents also allow for an unlimited number of stakeholders to take part in negotiations, generating an overall optimal solution. With a higher level of detail of the information used in negotiations, such as specific location and remaining driving time, a better deal can be offered.

Reducing the percentage of empty trucks has a significant effect on the environment as well. The amount of goods being moved remains the same, but the necessary mileage is strongly reduced. This leads to less CO2 emission, which contributes to the realization of the Kyoto treaty commitments. A side effect of the reduction in transportation movements is the improvement of mobility as a whole.

DEAL is a research project depending on the collaboration between commercial and research parties. Within the present consortium, wide experience is present on both the technological aspects and the market in focus. The ambition of the consortium is to apply the attained knowledge on a broad scale in products destined for the national and international logistic services.

Contribution

In the DEAL project, Almende focused on the development of a new agent platform, and the design of the individual agents. This platform emphasized distributed representational agents: all actors (trucks, containers etc.) are represented by software agents and distributed locally among these actors. In this way, people or organizations are able to create, programme and interact with their own agents locally, increasing trust and acceptance of the introduced system. Communication between agents is done through internet. A next step was to integrate the agent-platform in existing logistic settings (e.g. DLG). Almende developed methods to generate and initialize an agent-platform from a single XML file. On their turn agents can use this same XML file to send messages to. This allows for agents to migrate to other platform, without losing their settings. Implementation in real logistic settings allowed for extensive research into (computer) resource management and agent behavior (e.g. re-scheduling if internal or external circumstances change).  

Zooming in on agent behaviour, Almende specifically looked into Dynamic Vehicle Routing Problems. Different algorithms were tested to optimize dynamic planning in case of real-time job arrivals, truck-load pick-ups and deliveries with incidents (e.g. route specific constraints or driver / customer preferences).

Results

More info?

Need specific information regarding the project? Please contact our senior consultant for more information.

Jan Kraaijeveld

Senior consultant

+31 (0)10 404 9444

jan@almende.com

Read More

Credo

Modelling and analysis of evolutionary structures for distributed services

Duration: 09/2006 – 08/2009  Funding: CORDIS FP6

CREDO

The CREDO project developed a compositional modeling and validation framework for dynamically evolving software systems, in which computation, coordination and scheduling are clearly separated from each other. A uniform modeling language is developed in which object-orientated components are combined with flexible communication and timing models. 

The interface composition enables end-to-end reasoning about evolving systems. These interfaces specify services and formalize the context awareness needed for run-time coordination and reconfiguration. The framework helps developers design and maintain systems by validating reconfigurations. The focus of the project is on automatable and compositional validation techniques, including abstract simulations, synthesis, model checking, test-generation, and verification of interface compatibility. 

Contribution

The usefulness of the framework is assessed through two case studies, one of these being carried out by Almende. The focus of Almende is on applying these tools and techniques to the ASK-system, an intelligent communication platform developed by Almende and marketed by spin-off company ASK Community Systems. 

Results

More info?

Need specific information regarding the project? Please contact our senior consultant for more information.

Jan Kraaijeveld

Senior consultant

+31 (0)10 404 9444

jan@almende.com

Read More

Containers in a network

Almende logo

Duration: 01/2006 – 07/2007  Funding: Subsidie Electronische Communicatie of Senter Novum

Containers in a network

In the Containers in a Network (CAN) project, Almende, Chess and Salland Electronics researched how sensors can be applied in bulk container management in a Klok Containers garbage processing plant. Self-learning ad-hoc communication networks predict when containers have to be emptied.

CAN proposed several new techniques to aid an operator at Klok Containers in container management. There are several garbage containers at Klok Containers that are each filled at different rates with different materials. The current, not so elaborate, way to know when a container has to be emptied, is by kicking to its exterior and inferring its fill grade by the sound.

The project’s solution exists out of sensor nodes that measure the amount of dirt in the containers, a wireless sensor network to store that information temporarily in a redundant distributed way, and a PC as network drain and graphical user interface to the Klok operator. The Klok operator receives a signal when a container is full, and he can subsequently inform the drivers of the shovels which container to empty.

Salland Electronics developed an ultrasonic sensor to measure the amount of dirt in the garbage containers at Klok Containers. In cooperation with other parties like the VU in Amsterdam, Chess developed a wireless network mote with an energy-saving information dissemination (gossip) protocol. Those motes are called MyriaNed nodes.

Contribution

Almende developed higher level software on the nodes and on the operator's computer. This level of software adapts to and learns from the environment and is implemented in an agent-oriented way. The system needs to be able to learn and adapt. In the first place, it has to relieve the system installer in fine tuning parameters at installation. Those are parameters like calibration levels when a container is full, and when it is empty. Its second purpose is to implement the forecasting functionality needed on an application level. 

Results

More info?

Need specific information regarding the project? Please contact our senior consultant for more information.

Jan Kraaijeveld

Senior consultant

+31 (0)10 404 9444

jan@almende.com

Read More

CIM

Cybernetic Incident Management

Duration: 01/2003 – 12/2007  Funding: TSIT program of Senter Novum

CIM

Human interaction plays a key role in calamity suppression and can be seen as a dynamic system. Humans can experience some events during a real life disaster as completely unexpected. The current problem of an emergency plan is the fact that it has never been tested.

The main goal of the CIM project is to shape the plan on paper into an active structure. The specific challenges are that a calamity might take place but nobody knows when and how. Furthermore, no scenario can completely cover what happens during a calamity. Lastly, it is very  expensive and complex to invest in all operating municipal care services, thus help has to be provided from national care services, which brings extra logistics and coordinating problems. 

The CIM project aimed at generating sufficient knowledge to allow the industrial partners of the project to build the first generation of an intelligent and adaptive agent-based ICT-infrastructure for incident management within 5 years from the start of the project. The used agent technology should allow simulation of the dynamic and often non-hierarchical nature of emergency management by the various involved organizations. 

Contribution

Almende introduced the use of software agents to support people in responding quickly and in establishing communication. The interaction between people and software agents is also used for training (real-life or simulated), which resulted in an increased effectiveness of protocols and efficiency of communication in case of a real incident.

The system contains knowledge in the communication structures. The supporting software are distributed agents that are able to obtain and weigh information dynamically. The maintenance and evolution of the system is achieved by performing simulations and training sessions, both virtually as well as real-life. Measuring the effectiveness of a response and using this as feedback can improve the quality of the protocols and the system itself. 

Results

More info?

Need specific information regarding the project? Please contact our senior consultant for more information.

Jan Kraaijeveld

Senior consultant

+31 (0)10 404 9444

jan@almende.com

Read More