Sahin Albayrak

Distributed Artificial Intelligence Laboratory

Data science has been the foundation of recommender systems for a long time. Over the past few decades, various recommender systems have been developed using different data science and machine learning methodologies and techniques. However, no existing work systematically discusses the significant relationships between data science and recommender...

Multi-access Edge Computing (MEC) is an imperative for next-generation Machine-Type Communications (MTC) to alleviate the shortcomings of Cloud Computing (CC) infrastructures in terms of service delays and network loads. Intelligent Transportation System (ITS) is an application area of MTC that utilizes edge network nodes and Vehicle-to-Everything...

Digital Twin (DT) is a promising technology for executing real-time monitoring and diagnostic operations in Intelligent Transportation Systems (ITSs). Guaranteeing safety and functionality in DT-enabled ITS domain requires reliable data streams among vehicular edge and cloud network resources. Therefore, in this paper, we propose Graph Neural Netwo...

A limitation for collaborative robots (cobots) is their lack of ability to adapt to human partners, who typically exhibit an immense diversity of behaviors. We present an autonomous framework as a cobot’s real-time decision-making mechanism to anticipate a variety of human characteristics and behaviors, including human errors, toward a personalized...

In this paper, we propose and analyse algorithms for zeroth-order optimisation of non-convex composite objectives, focusing on reducing the complexity dependence on dimensionality. This is achieved by exploiting the low dimensional structure of the decision set using the stochastic mirror descent method with an entropy alike function, which perform...

The application of containerization technology has seen a significant increase in popularity in recent years, both in the business and scientific sectors. In particular, the ability to create portable applications that can be deployed on different machines has become a valuable asset. Autonomous driving has embraced this technology, as it offers a...

To take unit commitment (UC) decisions under uncertain net load, most studies utilize a stochastic UC (SUC) model that adopts a one-size-fits-all representation of uncertainty. Disregarding contextual information such as weather forecasts and temporal information, these models are typically plagued by a poor out-of-sample performance. To effectivel...

In this paper, we propose and analyse a family of generalised stochastic composite mirror descent algorithms. With adaptive step sizes, the proposed algorithms converge without requiring prior knowledge of the problem. Combined with an entropy-like update-generating function, these algorithms perform gradient descent in the space equipped with the...

This paper proposes a new family of algorithms for the online optimisation of composite objectives. The algorithms can be interpreted as the combination of the exponentiated gradient and p -norm algorithm. Combined with algorithmic ideas of adaptivity and optimism, the proposed algorithms achieve a sequence-dependent regret upper bound, matching th...

In this paper, we propose and analyze algorithms for zeroth-order optimization of non-convex composite objectives, focusing on reducing the complexity dependence on dimensionality. This is achieved by exploiting the low dimensional structure of the decision set using the stochastic mirror descent method with an entropy alike function, which perform...

This article puts forward a methodology for procuring flexible ramping products ({FRP}s) in the day-ahead market ({DAM}). The proposed methodology comprises two market passes, the first of which employs a stochastic unit commitment ({SUC}) model that explicitly evaluates the uncertainty and the intra-hourly and inter-hourly variability of net load...

Intelligent Transportation Systems (ITSs) are expected to have a profound impact on the quality of experience in future smart cities. Anomaly detection is an imperative for urban ITS applications to alleviate vulnerabilities that may cause accidents and fatal causalities. Previously proposed anomaly detection methods mostly require prior knowledge...

Multicast communication over wireless networks has many potential applications, such as real-time audiovisual content distribution or digital signage systems with multiple remote terminals. However, today’s common 802.11 networks cannot fully support such applications at the link layer due to the technical challenges in achieving both high transmis...

This paper proposes a new family of algorithms for online optimisation of composite objectives. The algorithms can be interpreted as the combination of exponentiated gradient and $p$-norm algorithm. Combined with algorithmic ideas of adaptivity and optimism, the proposed algorithms achieve a sequence dependent regret upper bound, matching the best...

Radio Access Network (RAN) slicing is getting increasing attention as a resource allocation technique for satisfying diverse Quality-of-Service (QoS) requirements in 5G vehicular networks. Hierarchical Reinforcement Learning (HRL), such as hierarchical-DQN (h-DQN), is a promising slice management approach that decomposes performance constraints int...

The mobility and transportation domain is constantly undergoing a comprehensive transformation due to increasing digitalization, which is already permeating into fundamental components of public and private infrastructures. At the same time, connected and automated driving (CAD) functionalities are being further elaborated. However, most of the sys...

This paper addresses the problem of predicting time series data using the autoregressive integrated moving average (ARIMA) model in an online manner. Existing algorithms require model selection, which is time consuming and unsuitable for the setting of online learning. Using adaptive online learning techniques, we develop algorithms for fitting ARI...

We study the problem of predicting time series data using the autoregressive integrated moving average (ARIMA) model in an online manner. Existing algorithms require model selection, which is time consuming and inapt for the setting of online learning. Using adaptive online learning techniques, we develop algorithms for fitting ARIMA models with fe...

A limitation for collaborative robots (cobots) is their lack of ability to adapt to human partners, who typically exhibit an immense diversity of behaviors. We present an autonomous framework as a cobot's real-time decision-making mechanism to anticipate a variety of human characteristics and behaviors, including human errors, toward a personalized...

This study focuses on the question of how humans can be inherently integrated into cyber-physical systems (CPS) to reinforce their involvement in the increasingly automated industrial processes. After a use-case oriented review of the related research literature, a human-integration framework and associated data models are presented as part of a mu...

The deepening penetration of variable energy resources creates unprecedented challenges for system operators (SOs). An issue that merits special attention is the precipitous net load ramps, which require SOs to have flexible capacity at their disposal so as to maintain the supply-demand balance at all times. In the judicious procurement and deploym...

The deepening penetration of renewable resources into power systems entails great difficulties that have not been surmounted satisfactorily. An issue that merits special attention is the short-term planning of power systems under net load uncertainty. To this end, we work out a distributionally robust unit commitment methodology that expressly asse...

The global climate change creates a dire need to mitigate greenhouse gas (GHG) emissions from thermal generation resources (TGRs). While microgrids are instrumental in enabling the deeper penetration of renewable resources, the short-term planning of microgrids needs to explicitly assess the full range of impact of GHG emissions. To this end, we pr...

This paper proposes a distributionally robust unit commitment approach for microgrids under net load and electricity market price uncertainty. The key thrust of the proposed approach is to leverage the Kullback-Leibler divergence to construct an ambiguity set of probability distributions and formulate an optimization problem that minimizes the expe...

This paper proposes a combined day-ahead forecasting and scheduling energy management system (EMS) with multiple complimentary objectives on household level. Our comparative case study, analyses, economical, ecological and grid independence aspects of our model include the utilization of renewable energy source (RES) with a controllable diesel gene...

Power system frequency plays a pivotal role in ensuring the security, adequacy, and integrity of a power system. While some frequency response services are automatically delivered to maintain the frequency within the stipulated limits, certain cases may require that system operators ( SO s) manually intervene—against the clock—to take the necessar...

Rings are widely accepted wearables for gesture interaction. However, most rings can sense only the motion of one finger or the whole hand. We present PeriSense, a ring-shaped interaction device enabling multi-finger gesture interaction. Gestures of the finger wearing ring and its adjacent fingers are sensed by measuring capacitive proximity betwee...

In this demo paper, we present a demonstrator for a ring-based finger tracking approach. The demonstrator consists of a ring-shaped interaction device, called PeriSense, utilizing capacitive sensing in order to enable finger tracking. The motion of the finger wearing the ring and the adjacent fingers is sensed by measuring the ca-pacitive proximity...

We present a ring-shaped interaction device, called PeriSense, utilizing capacitive sensing in order to enable finger tracking. The finger angles and its adjacent fingers are sensed by measuring capacitive proximity between electrodes and human skin. To map the capac-itive measurements to the finger angles, we use long short-term memory (LSTM). By...

Special Operations Forces (SOF) are facing extreme risks when prosecuting crimes in uncharted environments like buildings. Autonomous drones could potentially save officers' lives by assisting in those exploration tasks, but an intuitive and reliable way of communicating with autonomous systems is yet to be established. This paper proposes a set of...

Recommender systems have strongly attracted the attention of the machine learning research community with prosperous real-life deployments in the last few decades. The performance and success of most applications developed in this domain highly depend on an elaborate selection of models and configuration of their hyperparameters. The international...

Recent advances in the Internet of Things (IoT) provides rich opportunities to future mobility services for the development of more flexible solutions. Instead of using a fixed set of data sources or services, applications can benefit from those flexible mechanisms by adapting to change in the sensing environment such as sensor disappearance/degrad...

While developing context-aware applications, there may be uncertainty with respect to the available data sources. Applications that are developed to a fixed set of data sources may not be flexible enough, to adapt to change in the sensing environment such as sensor disappearance or degradation. Opportunistic sensing tackles this problem by enabling...

The sample mean is one of the most fundamental concepts in statistics with far-reaching implications for data mining and pattern recognition. Household load profiles are compared to the aggregated levels more intermittent and a specific error measure based on local permutations has been proposed to cope with this when comparing profiles. We formall...

Lowly aggregated load profiles such as of individual households or buildings are more fluctuating and relative forecast errors are comparatively high. Therefore, the prevalent point forecasts are not sufficiently capable of optimally capturing uncertainty and hence lead to non-optimal decisions in different operational tasks. We propose an approach...

As a key component of collaborative robots (cobots) working with humans, existing decision-making approaches try to model the uncertainty in human behaviors as latent variables. However, as more possible contingencies are covered by such intention-aware models , they face slow convergence times and less accurate responses. For this purpose, we pres...

The number of unmanned aerial system (UAS) applications for supporting rescue forces is growing in recent years. Nevertheless, the analysis of sensed information and control of unmanned aerial vehicle (UAV) creates an enormous psychological and emotional load for the involved humans especially in critical and hectic situations. The introduced resea...

Increasing user participation or changing behavior are key goals when applying gamification. Existing studies in domains such as education, health, and enterprise show that gamification can have a positive impact on meeting these goals. However, there is still a lack of detailed insights into how certain game design elements affect user behavior an...

The development of complex systems ensembles that operate in uncertain environments is a major challenge. The reason for this is that system designers are not able to fully specify the system during specification and development and before it is being deployed. Natural swarm systems enjoy similar characteristics, yet, being self-adaptive and being...

In the Multi-Agent Programming Contest 2017 the TUBDAI team of the Technische Universität Berlin is using the complex multi-agent scenario to evaluate the application of two frameworks from the field (multi-)robot systems. In particular the task-level decision-making and planning framework ROS Hybrid Behaviour Planner (RHBP) is used to implement th...

The number of unmanned aerial system (UAS) applications for supporting rescue forces is growing in recent years. The analysis of sensed information and control of the UAV creates an enormous psychological and emotional load for the involved humans especially in critical and hectic situations. To enable a mission-guided application of drones and red...

The development¹ of self-adaptive systems can greatly benefit from reference frameworks to structure the development process. Current reference frameworks abstract from the adaptation decision - the selection of a specific adaptation based on the goals and options available. This decision is usually based on the three adaptation policies: rule-base...

We propose an architecture as a robot's decision-making mechanism to anticipate a human's state of mind, and so plan accordingly during a human-robot collaboration task. At the core of the architecture lies a novel stochastic decision-making mechanism that implements a partially observable Markov decision process anticipating a human's state of min...

Coordination of mobile multi-robot systems in a self-organised manner is in the first place beneficial for simple robots in common swarm robotics scenarios. Moreover, sophisticated robot systems as for instance in disaster rescue teams, service robotics and robot soccer can also benefit from a decentralised coordination while performing complex tas...

News organizations employ personalized recommenders to target news articles to specific readers and thus foster engagement. Existing approaches rely on extensive user profiles. However frequently possible, readers rarely authenticate themselves on news publishers' websites. This paper proposes an approach for such cases. It provides a basic degree...

In our fast changing world, data streams move into the focus. In this paper, we study recommender systems for news portals. Compared with traditional recommender scenarios based on static data sets, the short life cycle of news items and the dynamics in users' preferences are major challenges when developing news recommender systems. This motivates...

This work approaches the question whether or not agents are able to learn the personality of a human during interaction. We develop two agent-models to learn about the personality of humans during repeatedly played rounds in the Colored Trails Game. Human personality is described using a psychological theory of personality traits known as the Five-...

The work on hand targets the missing capabilities for data access and service clearing in connected mobility service solutions. Interviewed experts pointed out that current solutions of the mobility domain lack appropriate clearing capabilities as well as access on internally processed data. We approach both limitations and elaborate a message prot...

Online news readers exhibit a very dynamic behavior. News publishers have been investigating ways to predict such changes in order to adjust their recommendation strategies and better engage the readers. Existing research focuses on analyzing the evolution of reading interests associated with news categories. Compared to these, we study also how re...

Model synchronization is one of the core activities in model driven engineering. One of the challenges is non-determinism when multiple valid solutions exist. This is exasperated in triple graph based approaches, where additional non-determinism may arise from the alignment of the synchronized changes and the grammar. Non-determinism is often the r...

Context-awareness has become a critical factor in improving the predictions of user interest in modern online TV recommendation systems. In addition to individual user preferences, existing context-aware approaches such as tensor factorization incorporate system-level contextual bias to increase predicting accuracy. We analyzed a user interaction d...

The fully automated sentiment analysis on large text collections is an important task in many applications scenarios. The sentiment analysis is a challenging task due to the domain-specific language style and the variety of sentiment indicators. The basis for learning powerful sentiment classifiers are annotated datasets, but for many domains and e...

In today’s society where audio-visual content such as professionally edited and user-generated videos is ubiquitous, automatic analysis of this content is a decisive functionality. Within this context, there is an extensive ongoing research about understanding the semantics (i.e., facts) such as objects or events in videos. However, little research...

In this use case chapter, we summarize our experience during the development of an autonomous UAV for the German DLR Spacebot Cup robot competition. The autarkic UAV is designed as a companion robot for a ground robot supporting it with fast environment exploration and object localisation. On the basis of ROS Indigo we employed, extended and develo...

We propose an architecture that integrates Theory of Mind into a robot's decision-making to infer a human's intention and adapt to it. The architecture implements human-robot collaborative decision-making for a robot incorporating human variability in their emotional and intentional states. This research first implements a mechanism for stochastica...

Connecting a massive number of sensors and actuators with energy and transmission constraints is only possible by providing a reliable connection despite the increase in data traffic due to the Internet of Things, and by guaranteeing a maximum end-to-end delay for applications with real-time constraints. Next generation network architectures need t...

Recent studies show that robots are still far from being long-term companions in our daily lives. With an interdisciplinary approach, this position paper structures around coping with this problem and suggests guidelines on how to develop a cognitive architecture for social robots assuring their long-term personal assistance at home. Following the...

Urbanization increases the problem of density. More people live on less space and all demand mobility. However, due to geographical constraints, the expansion of the mobility infrastructure is limited. Therefore, intelligent mobility services are considered to be key to support citizens and commuters in their daily lives in future smart city. These...

When the situation involves artificial and natural agents in the same environment that work together to achieve joint goals we talk about cooperative activities, human-agent teamwork, joint activities, or joint human-agent activities. Although, teamwork has become a widely accepted metaphor for multi-robot/multi-agent cooperation there are several...

Personality is one of the central elements determining the behaviour of humans. It influences other cognitive mechanisms such as emotions and moods and thus effects attention and actions. However, in the literature about cognitive agents, work that investigates the effects of personality is rare and somewhat disconnected. Bridging this gap represen...

With the move to ubiquitous computing, user interfaces (UI) are no longer bound to specific devices. While this problem can be tackled using the model-based UI development (MBUID) process, the usability of the device-specific interfaces is still an open question. We are presenting a combined system that integrates MBUID with a cognitive modeling fr...

Information and communication technologies (ICTs) have a profound impact on the current state and envisioned future of automobiles. This paper presents an overview of research on ICT-based support and assistance services for the safety of future connected vehicles. A general classification and a brief description of the focus areas for research and...

It is observed that the number of service platform solutions in the context of Smart City and respective Smart Mobility is increasing. Such platforms enable the exchange of mobility data between interested parties. Some service platform solutions are developed as cloud applications or make use of the benefits which the cloud computing paradigm offe...