Research Interests:
Body posture is one of many visual cues used by sighted persons to determine if someone would be open to initiate a conversation. These cues are inaccessible for individuals with blindness leading to difficulties when deciding whom to... more
Body posture is one of many visual cues used by sighted persons to determine if someone would be open to initiate a conversation. These cues are inaccessible for individuals with blindness leading to difficulties when deciding whom to approach for eventual assistance. Current camera technologies, such as depth cameras, enable to automatically scan the environment to assess the approachability of nearby persons. We present Whom-I-Approach, a system that translates postures of bystanders into a measure of approachability and communicates this information using auditory and tactile cues. The system scans the environment and determines the approachability based on body posture for the persons in the vicinity of the user. Efficiency as well as perceived system usability and psychosocial attitudes are measured in a user study showing the potential to improve competence for users with blindness prior to engagement in social interactions.
Research Interests:
Deep learning pervades heavy data-driven disciplines in research and development. The Internet of Things and sensor systems, which enable smart environments and services, are settings where deep learning can provide invaluable utility.... more
Deep learning pervades heavy data-driven disciplines in research and development. The Internet of Things and sensor systems, which enable smart environments and services, are settings where deep learning can provide invaluable utility. However, the data in these systems are very often directly or indirectly related to people, which raises privacy concerns. Federated learning (FL) mitigates some of these concerns and empowers deep learning in sensor-driven environments by enabling multiple entities to collaboratively train a machine learning model without sharing their data. Nevertheless, a number of works in the literature propose attacks that can manipulate the model and disclose information about the training data in FL. As a result, there has been a growing belief that FL is highly vulnerable to severe attacks. Although these attacks do indeed highlight security and privacy risks in FL, some of them may not be as effective in production deployment because they are feasible only g...
Research Interests:
Research Interests:
Internet-based communication systems have become an increasing tool for spreading misinformation and propaganda. Even though there exist mechanisms that are able to track unwarranted information and messages, users made up different ways... more
Internet-based communication systems have become an increasing tool for spreading misinformation and propaganda. Even though there exist mechanisms that are able to track unwarranted information and messages, users made up different ways to avoid their scrutiny and detection. An example is represented by the mixed-code language, that is text written in an unconventional form by combining different languages, symbols, scripts and shapes. It aims to make more difficult the detection of specific content, due to its custom and ever changing appearance, by using special characters to substitute for alphabet letters. Indeed, such substitute combinations of symbols, which tries to resemble the shape of the intended alphabet’s letter, makes it still intuitively readable to humans, however nonsensical to machines. In this context, the paper explores the possibility of identifying propaganda in such mixed-code texts over the Internet, centred on a machine learning based approach. In particula...
Research Interests:
Research Interests:
Criminals and related illegal activities represent problems that are neither trivial to predict nor easy to handle once they are identified. The Police Forces (PFs) typically base their strategies solely on their intra-communication, by... more
Criminals and related illegal activities represent problems that are neither trivial to predict nor easy to handle once they are identified. The Police Forces (PFs) typically base their strategies solely on their intra-communication, by neglecting the involvement of third parties, such as the citizens, in the investigation chain which results in a lack of timeliness among the occurrence of the criminal event, its identification, and intervention. In this regard, a system based on IoT social devices, for supporting the detection and tracking of criminals in the real world, is proposed. It aims to enable the communication and collaboration between citizens and PFs in the criminal investigation process by combining app-based technologies and embracing the advantages of an Edge-based architecture in terms of responsiveness, energy saving, local data computation, and distribution, along with information sharing. The proposed model as well as the algorithms, defined on the top of it, have...
Research Interests:
Online social networks (OSNs) represent powerful digital tools to communicate and quickly disseminate information in a non-official way. As they are freely accessible and easy to use, criminals abuse of them for achieving their purposes,... more
Online social networks (OSNs) represent powerful digital tools to communicate and quickly disseminate information in a non-official way. As they are freely accessible and easy to use, criminals abuse of them for achieving their purposes, for example, by spreading propaganda and radicalising people. Unfortunately, due to their vast usage, it is not always trivial to identify criminals using them unlawfully. Machine learning techniques have shown benefits in problem solving belonging to different application domains, when, due to the huge dimension in terms of data and variables to consider, it is not feasible their manual assessment. However, since the OSNs domain is relatively young, a variety of issues related to data availability makes it difficult to apply and immediately benefit from such techniques, in supporting the detection of criminals on OSNs. In this perspective, this paper wants to share the experience conducted in using a public dataset containing information related to...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
These are the Proceedings of the 4th IUI Workshop on Interacting with Smart Objects. Objects that we use in our everyday life are expanding their restricted interaction capabilities and provide functionalities that go far beyond their... more
These are the Proceedings of the 4th IUI Workshop on Interacting with Smart Objects. Objects that we use in our everyday life are expanding their restricted interaction capabilities and provide functionalities that go far beyond their original functionality. They feature computing capabilities and are thus able to capture information, process and store it and interact with their environments, turning them into smart objects.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
In this paper we investigate the influence of external noise on the inference of network structures. The purpose of our simulations is to gain insights in the experimental design of microarray experiments to infer, e.g., transcription... more
In this paper we investigate the influence of external noise on the inference of network structures. The purpose of our simulations is to gain insights in the experimental design of microarray experiments to infer, e.g., transcription regulatory networks from microarray experiments. Here external noise means, that the dynamics of the system under investigation, e.g., temporal changes of mRNA concentration, is affected by measurement errors. Additionally to external noise another problem occurs in the context of microarray experiments. Practically, it is not possible to monitor the mRNA concentration over an arbitrary long time period as demanded by the statistical methods used to learn the underlying network structure. For this reason, we use only short time series to make our simulations more biologically plausible.
Research Interests: Geography, Computer Science, Time Series, Inference, Experimental Design, and 14 moreMarkov Chain Monte Carlo, Gene networks, Measurement Error, Gene Network, Structure learning, Bayesian Network, dynamic Bayesian network, Network structure, Graphical Model, Bayesian Probability, Microarray Data, Temporal Change, Statistical Method, and Transcriptional regulatory network
An increasing demand for supporting users in diverse contexts of use, e.g., depending on interaction device and primary task, results in new challenges for User Interface (UI) development. Two key challenges are: how to create these... more
An increasing demand for supporting users in diverse contexts of use, e.g., depending on interaction device and primary task, results in new challenges for User Interface (UI) development. Two key challenges are: how to create these multiple UIs for one application (creation challenge), and how to consistently modify them (modification challenge). The creation challenge has been addressed in various works utilizing automatic UI generation. We present our approach (Dialogue Refinement) and its tool-support to address the modification challenge by allowing one modification to be applied to multiple UIs at once.
Research Interests:
Designing mobile and wearable applications is a challenge. The context of use is more important than ever and tradi- tional methodologies for elicitation and specification reach their limits. This paper investigates the challenge of cre-... more
Designing mobile and wearable applications is a challenge. The context of use is more important than ever and tradi- tional methodologies for elicitation and specification reach their limits. This paper investigates the challenge of cre- ating and communicating information about the user's pri- mary task with regards to its fine grained temporal struc- ture. TaskObserver is a TabletPC software that allows real- time logging of events during observations of complex mo- bile scenarios. The results are communicated to other team members using task trace graphs of the events observed. A user study was performed to estimate the accuracy of the real-time annotations and the amount of time that can be saved by using the system. Additionally the usability of the existing tool was evaluated.
Research Interests:
ABSTRACT Designing wearable application interfaces that integrate well into real-world processes like aircraft maintenance or medical examinations is challenging. One of the main success criteria is how well the multimodal interaction... more
ABSTRACT Designing wearable application interfaces that integrate well into real-world processes like aircraft maintenance or medical examinations is challenging. One of the main success criteria is how well the multimodal interaction with the computer system fits an already existing real-world task. Therefore, the interface design needs to take the real-world task flow into account from the beginning. We propose a
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Enterprises are constantly struggling to optimize their business processes in order to gain competitive advantage and to survive in the fast evolving global market. Often, the only ones to understand the matter and complexity of these... more
Enterprises are constantly struggling to optimize their business processes in order to gain competitive advantage and to survive in the fast evolving global market. Often, the only ones to understand the matter and complexity of these processes are the people, who actually execute them. This raises the need for novel business process management approaches, which can enable business users to proactively express process knowledge and to participate in the business process management and design according to their actual expertise and problem solving strategies. The presented paper describes an architecture, which supports a framework for end user-driven composition and management of underspecified, human-centric business processes. The solution builds up on email-integrated task management and enables dynamic generation of decentralized-emerging process structures through web service-based activity tracking. The captured process execution examples are shared in central enterprise repos...
Research Interests:
User input on television typically requires a mediator device such as a handheld remote control. While being a well-established interaction paradigm, a handheld device has serious drawbacks: it can be easily misplaced due to its mobility... more
User input on television typically requires a mediator device such as a handheld remote control. While being a well-established interaction paradigm, a handheld device has serious drawbacks: it can be easily misplaced due to its mobility and in case of a touch screen interface, it also requires additional visual attention. Emerging interaction paradigms like 3D mid-air gestures using novel depth
Research Interests:
The dependency of our society on networked computers has become frightening: In the economy, all-digital networks have turned from facilitators to drivers; as cyber-physical systems are coming of age, computer networks are now becoming... more
The dependency of our society on networked computers has become frightening: In the economy, all-digital networks have turned from facilitators to drivers; as cyber-physical systems are coming of age, computer networks are now becoming the central nervous systems of our physical world—even of highly critical infrastructures such as the power grid. At the same time, the 24/7 availability and correct functioning of networked computers has become much more threatened: The number of sophisticated and highly tailored attacks on IT systems has significantly increased. Intrusion Detection Systems (IDSs) are a key component of the corresponding defense measures; they have been extensively studied and utilized in the past. Since conventional IDSs are not scalable to big company networks and beyond, nor to massively parallel attacks, Collaborative IDSs (CIDSs) have emerged. They consist of several monitoring components that collect and exchange data. Depending on the specific CIDS architectur...
Research Interests:
Research Interests:
... An IR Local Positioning System for Smart Items and Devices ... Therefore, the encoded signal should contain as few '0'-bits as possible. ... Furthermore, the image compression algorithm... more
... An IR Local Positioning System for Smart Items and Devices ... Therefore, the encoded signal should contain as few '0'-bits as possible. ... Furthermore, the image compression algorithm employed by the camera seems to degrade image quality and therefore lowers the accuracy of ...
Research Interests:
In this chapter, we will consider the language support of VoiceXML 2.1 to express flexible dialogs in pervasive environments. Missing information about the environment and the inability to react to external events lead to rigid and... more
In this chapter, we will consider the language support of VoiceXML 2.1 to express flexible dialogs in pervasive environments. Missing information about the environment and the inability to react to external events lead to rigid and verbose dialogs. But building upon the recently defined W3C MMI architecture we present an approach where dialog authors can adapt their dialogs' behavior with regard to the users' surroundings and incorporate available information and devices from the pervasive environment. Adding these features extends the expressiveness of VoiceXML 2.1, and allows for an integration into a multimodal and mobile interaction as anticipated in the, as of now, dormant VoiceXML 3.0 standard.