Yasser Mohammad

Yasser Mohammad
NEC Corporation | Nippon Electric Company, Limited · Data Science Research Laboratories

PhD

About

125
Publications
11,506
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
924
Citations
Introduction
My main interest is building intelligent agents (robots or otherwise) that can communicate with people and other intelligent agents, learning from and teaching them in the process.
Additional affiliations
November 2017 - present
National Institute of Advanced Industrial Science and Technology
Position
  • Researcher
November 2016 - November 2017
KDDI R&D Laboratories Inc.
Position
  • Engineer
July 2016 - present
Assiut University
Position
  • Professor (Associate)

Publications

Publications (125)
Article
Full-text available
Recent years are showing increased adoption of AI technology to automate business and production processes thanks to the recent successes of machine learning techniques. This leads to increased interest in automated negotiation as a method for achieving win-win agreements among self-interested agents. Research in automated negotiation can be traced...
Conference Paper
With the availability of domain specific historical negotiation data, the practical applications of machine learning techniques can prove to be increasingly effective in the field of automated negotiation. Yet a large portion of the literature focuses on domain independent negotiation and thus passes the possibility of leveraging any domain specifi...
Chapter
In the current study, a novel approach for speech emotion recognition is proposed and evaluated. The proposed method is based on multiple pairwise classifiers for each emotion pair resulting in dimensionality and emotion ambiguity reduction. The method was evaluated using the state-of-the-art English IEMOCAP corpus and showed significantly higher a...
Article
Full-text available
Automated Negotiation is a growing area of research in recent years as it provides a mechanism for intelligent agents representing people and institutions to coordinate their behavior in a complex environment under rational selfish assumptions. Most research in this area assumes either a single negotiation thread with a well-defined utility functio...
Chapter
Most research in automated negotiation focuses on strategy development in preset scenarios where decisions about what to negotiate about, whom to negotiate with, and on which issues are given to the agents. Moreover, in many cases, the agents’ utility functions are predefined, static, and independent of other negotiations. NegMAS (Negotiations Mana...
Chapter
Automated negotiation is gaining more attention as a possible mechanism for organizing self-interested intelligent agents in a distributed environment. The problem of designing effective negotiation strategies in such environments was studied extensively by researchers from economics, computer science, multiagent systems, and AI. This paper focuses...
Preprint
Full-text available
Despite abundant negotiation strategies in literature, the complexity of automated negotiation forbids a single strategy from being dominant against all others in different negotiation scenarios. To overcome this, one approach is to use mixture of experts, but at the same time, one problem of this method is the selection of experts, as this approac...
Chapter
Alongside the widespread adoption of AI technology throughout the business world, automated negotiation is similarly gaining more interest within the multiagent system (MAS) research community. This interest has prompted the development of research-oriented automated negotiation platforms like GENIUS. This paper introduces NegMAS, Negotiations Mana...
Chapter
The current empirical study focuses on speech emotion recognition using speech data extracted from video clips. Although many studies reported speech emotion recognition, the majority of the studies presented were based on using acted and clean speech. A more challenging and realistic task would be using spontaneous noisy speech from video clips. I...
Chapter
The current study focuses on multilingual speech emotion recognition using realistic emotional speech extracted from English, Italian, and Spanish films. Two novel methods are proposed, which exploit language information and emotion information. In the first method, features specific to the three languages are concatenated with emotion-specific fea...
Chapter
The Automated Negotiating Agents Competition (ANAC) is a yearly-organized international contest in which participants from all over the world develop intelligent negotiating agents for a variety of negotiation problems. To facilitate the research on agent-based negotiation, the organizers introduce new research challenges every year. ANAC 2019 pose...
Chapter
Full-text available
In the very near future, we anticipate that more and more artificially intelligent agents will be deployed to represent individuals and institutions. Automated negotiation environments are a mechanism by which to coordinate the behavior of such agents. Most existing work on automated negotiation assumes a context that is predefined, and hence, stat...
Chapter
Speech emotion recognition is a task designed to automatically identify human emotions in spoken utterances. The current study focuses on speech emotion recognition based on deep convolutional neural networks (DCNNs) and extremely randomized trees. Specifically, we propose a method based on DCNN, which extracts informative features from the speech...
Article
Activity recognition from sensors is a classification problem over time-series data. Some research in the area utilize time and frequency domain handcrafted features that differ between datasets. Another categorically different approach is to use deep learning methods for feature learning. This paper explores a middle ground in which an off-the-she...
Chapter
Full-text available
Constrained motif discovery was proposed as an unsupervised method for efficiently discovering interesting recurrent patterns in time-series. The de-facto standard way to calculate the required constraint on motif occurrence locations is change point discovery. This paper proposes the use of time-series complexity for finding the constraint and sho...
Chapter
Full-text available
Autonomous Negotiation is a promising technology that allows individuals and institutions to reduce the burden and cost of negotiating win-win agreements. A common challenge in practical applications is the inability or high cost of finding the utility value for each possible outcome of the negotiation before it even starts. Earlier work on utility...
Article
Full-text available
Activity recognition from mobile device sensors and wearables is attracting more attention from the research community due to the widespread adoption of these devices and the unique opportunity they provide for understanding user’s behavior leading to novel services and improvements in the delivery of existing ones. Approaches to tackle this proble...
Conference Paper
Spoken language identification is the process by which the language in a spoken utterance is recognized automatically. Spoken language identification is commonly used in speech translation systems, in multilingual speech recognition, and in speaker diarization. In the current paper, spoken language identification based on deep learning (DL) and the...
Conference Paper
Human physical activity recognition from sensor data is a growing area of research due to the widespread adoption of sensor-rich wearable and smart devices. The growing interest resulted in several formulations with multiple proposals for each of them. This paper is interested in activity recognition from short sequences of sensor readings. Traditi...
Conference Paper
Activity recognition from smart devices and wearable sensors is an active area of research due to the widespread adoption of smart devices and the benefits it provide for supporting people in their daily lives. Many of the available datasets for fine-grained primitive activity recognition focus on locomotion or sports activities with less emphasis...
Chapter
Appearance of service and social robots provides new challenges and new opportunities for HCI leading to the field of Human Robot Interaction (HRI). HRI is a vast multidisciplinary field of research that encompasses engineering the human-robot-interface, evaluating such interfaces and understanding the psychological and social aspects of the intera...
Conference Paper
Time series are being generated continuously from all kinds of human endeavors. The ubiquity of time-series data generates a need for data mining and pattern discovery algorithms targeting this data format which is becoming of ever increasing importance. Three basic problems in mining time-series data are change point discovery, causality discovery...
Conference Paper
Cultural differences have been documented in different aspects of perception of robots as well as understanding of their behavior. A different line of research in developmental psychology has established a major role for imitation in skill transfer and emergence of culture. This study is a preliminary cross–cultural exploration of the effect of imi...
Article
How we perceive robots affects how we interact with them and vice versa. This leads us to hypothesize that imitating a robot (back imitation) would affect human’s perception of this robot. More specifically, we suggest that it would lead to the attribution to a higher imitative skill to the robot when it subsequently imitates the human. Given that...
Article
Discovering approximately recurrent motifs (ARMs) in timeseries is an active area of research in data mining. Exact motif discovery is defined as the problem of efficiently finding the most similar pairs of timeseries subsequences and can be used as a basis for discovering ARMs. The most efficient algorithm for solving this problem is the MK algori...
Conference Paper
Learning from demonstration (LFD) is an active area of research in robotics. There are many approaches to LFD. One of the most widely used approaches is the combination of Gaussian Mixture Model learning for modeling and Gaussian Mixture Regression for behavior generation (GMM/GMR) due to its advantages including easy learning using Expectation Max...
Conference Paper
Full-text available
Synthetic evidential study (SES) is a novel approach to understanding and augmenting collective thought process through substantiation by interactive media. It consists of a role-play game by participants, projecting the resulting play into a shared virtual space, critical discussions with mediated role-play, and componentization for reuse. We pres...
Conference Paper
Full-text available
Synthetic evidential study (SES for short) is a novel technology-enhanced methodology for combining theatrical role play and group discussion to help people spin stories by bringing together partial thoughts and evidences. SES not only serves as a methodology for authoring stories and games but also exploits the framework of game framework to help...
Conference Paper
Full-text available
Learning from Demonstration is an important technology for the new wave of robots that are envisioned to work side-by-side with workers in factories as well as social robots. Most available techniques for learning from demonstration rely on the existence of a training set of demonstrations that is assumed to be pre-segmented and is usually processe...
Chapter
Chapter 13 will review several algorithms for learning from demonstration ranging from inverse optimal control to symbolic modeling. What all of these algorithms share is the assumption that demonstrations are segmented from the continuous behavioral stream of the model (i.e. the demonstrator).
Chapter
Social robotics is an exciting field with too many research threads within which interesting new developments appear every year. It is very hard to summarize what a field as varied and interdisciplinary as social robotics is targeting but we can distinguish two main research directions within the field.
Chapter
Change point discovery (CPD) is one of the most relied upon technologies in this book.
Chapter
Imitation is one of the most utilized modes of learning in human infants and adults. We consciously imitate others when we want to learn new skills and unconsciously imitate them during interaction.
Chapter
The previous chapter introduced the behavioral platform of EICA upon which we built our approach to social robotics. This chapter provides the details of this architecture in light of the theoretical foundations presented in Chap. 8 and shows how different parts of the architecture fit together to provide human-like interaction capabilities for the...
Chapter
Data is being generated in an ever increasing rate by all kinds of human endeavors. A sizable fraction of this data appears in the form of time-series or can be converted to this form.
Chapter
A recurring problem in the second part of this book is the problem of discovering recurrent patterns in long multidimensional time-series. This chapter introduces some of the algorithms that can be employed in solving this kind of problems for both discrete and continuous time-series.
Chapter
In Chap. 10 we presented an overview of proposed architecture and detailed how can it generate behavior given that the intentions and processes involved are already available.
Chapter
The study of causality can be traced back to Aristotle who defined four types of causal relations (material, formal, efficient and final causes).
Chapter
In the previous chapter, we pointed out the main theoretical foundations of EICA and its guiding principles: intention through interaction and historical social embodiment. EICA has two components: a general behavioral robotic architecture with a flexible action integration mechanism upon which interaction protocol learning to support autonomous so...
Chapter
This book provided a systematic introduction to the engineering of autonomous sociality in robots using techniques from time-series analysis and data mining.
Chapter
Creating robots that can easily learn new skills as effectively as humans (or dogs or ants) is the holly grail of intelligent robotics. Several approaches to achieve this goal have appeared over the years.
Chapter
Research in HRI focuses on the social aspect of the robot while intelligent robotics research strives to achieve the smartest possible autonomous robot. We argue in this chapter that realizing sociability and realizing autonomy are not two independent directions of research but are interrelated aspects of the robot design.
Book
This book explores an approach to social robotics based solely on autonomous unsupervised techniques and positions it within a structured exposition of related research in psychology, neuroscience, HRI, and data mining. The authors present an autonomous and developmental approach that allows the robot to learn interactive behavior by imitating huma...
Article
Full-text available
Our goal is to make a system to detect the times at which one almost laughed but he or she did not show their laughter on his/her face. We define this kind of laughter as hidden laughter. To accomplish this goal, we first tried making decision trees to detect one's amusement, the input data of which were physiological indices. We used 10-fold cross...
Article
Understanding human interactive behavior is a key technology required for future robots. To achieve this goal, the robot should be able to recognize key patterns in human–human interactions. Moreover, the robot should be able to generate similar behaviors during its interaction with human partners. In this paper, an unsupervised system is proposed...
Article
A promising technology for teaching robots new skills is learning from demonstrations (LfD) or imitation learning. Even though there is currently large literature in imitation learning, smaller attention was given to studying social aspects of the imitation situation. Back imitation is the situation when the demonstrator (human) imitates the learne...
Conference Paper
Learning from demonstrations (LfD) is gaining more popularity in robotics due to its promise of providing a human-friendly technique for teaching robots new skills by robotics-naive users. The two main approaches to LfD are dynamic motor primitives (DMP) which models demonstrated motions as dynamical systems with the advantage flexibility in changi...
Chapter
Conversation is complex. It is amazing how easily participants coordinate their actions to establish a discourse and make points often with little conscious effort in daily conversation save for a few special cases. To date, numerous authors have investigated conversations from a wide variety of angles. In this chapter, we overview major theories t...
Chapter
Conversational system development dates back to the early days of computer science when pioneering researchers started to take up serious projects aimed at having computers interact with people using natural language. Their endeavors have produced a broad range of theories, techniques, and systems, ranging from basic research to applications, from...
Chapter
Conversation quantization is a conceptual framework used for capturing and reusing shared meanings and expressions in a conversation. As a generic framework, it encompasses different implementations ranging in granularity, depth and breadth of annotation, representational fidelity, and generality. In this chapter, we discuss the scope and requireme...
Chapter
This book is the first systematic presentation of conversational informatics. It not only compiled the major outcomes resulting from research and development activities of our group, it also identified the foundations on which we have been relying so far as well as potential directions of future research on this subject. Topics are laid from the fu...
Chapter
In this chapter, we will describe a framework of learning by mimicking for converting observation into proficient conversational behaviors. Individuals of some species can utilize the learning capacities of other individuals by mimicking their behavior. When this happens, biologists speak about culture. Humans are arguably the most sophisticated cu...
Chapter
In this chapter, we discuss some high-level issues left beyond the scope of this book but deemed critical for future research. We first place conversational intelligence and conversational informatics in a larger picture of conversational knowledge circulation and social intelligence design to discuss issues from a wider perspective. We then single...
Chapter
Conversation is not only a joint activity in itself, but also a means for joint activity. Discussions can benefit from augmented conversation in stimulating, editing, disseminating, and reusing conversations. Conversational intelligence empowered by conversational agents allows wisdom exchanged in conversation to be shared and evolved in a communit...
Chapter
Better understanding of conversation paves the way towards better conversational systems. In this chapter we shed light on the practical aspects of multi-modal interaction analysis towards a better understanding of conversation as a phenomenon. On the one hand, investigators need to take great care of methodological issues, since conversation invol...
Chapter
In this chapter, we focus on the computer vision, image understanding and image synthesis approaches related to develop the conversation systems, namely, finding human faces, recognizing facial expressions and gestures, and synthesizing facial expressions and body gestures. In Chaps. 2–4, we introduce the theory, history and techniques for organizi...
Chapter
When we build a conversational system, it is necessary to understand that a full-fledged system may become fairly complex if we are to address all the issues related to uncertainty and noise, coherency and consistency in strong time constraints, and a wide spectrum of phenomena across multiple levels of hierarchies. A strong methodological approach...
Chapter
In this chapter, we will describe two case studies that utilized the architecture presented in Chap. 9 which utilizes ideas from the simulation theory of mind for behavior generation during interaction and imitation learning as a technique to develop the required computational processes needed. The first case study will be concerned with gaze behav...
Chapter
The spatial environment surrounding participants in conversation has a critical, if not conclusive, influence on the qualitative and quantitative aspects of conversation conducted therein. Imagine how awful the conversation would be if one had to converse with a stranger in a vacuum with only the two of you present. A contrastive situation would be...
Conference Paper
Discovering approximately recurrent motifs (ARMs) in timeseries is an active area of research in data mining. Exact motif discovery was later defined as the problem of efficiently finding the most similar pairs of timeseries subsequences and can be used as a basis for discovering ARMs. The most efficient algorithm for solving this problem is the MK...
Conference Paper
Humanoid robots have - by definition - some level of human-likeness in body form. According to previous research in HRI, this leads to a higher expectation of human-like behavior. Nevertheless, human-likeness is not an easy notion to define for motion even in a task as straight forward as real-time motion copying (the shadowing task) as this paper...
Conference Paper
Motif discovery is the problem of finding unknown patterns that appear frequently in real valued timeseries. Several approaches have been proposed to solve this problem with no a-priori knowledge of the timeseries or motif characteristics. MK algorithm is the de facto standard exact motif discovery algorithm but it can discover a single motif of a...
Article
Conversation is indispensable in our intellectual life. People may make conversation either to achieve a social goal, to create a joint story, or to just enjoy a language game. Although a conversation has a fairly sophisticated structure and dynamism, people are sufficiently proficient in expressing their thoughts and interpreting utterances of the...
Article
Approximately Recurring Motif (ARM) discovery is the problem of finding unknown patterns that appear frequently in real valued timeseries. In this paper, we propose a novel algorithm for solving this problem that can achieve performance comparable with the most accurate algorithms with a speed comparable to the fastest ones. The main idea behind th...
Article
Previous research in HRI have shown that human's subjective evaluation of robot's abilities affect the way people interact with robots. Given that one of the major challenges in learning from demonstration in robotics is the limited number of training examples that the demonstrator is usually willing to provide, it would be beneficial to design the...
Book
This book covers an approach to conversational informatics which encompasses science and technology for understanding and augmenting conversation in the network age. A major challenge in engineering is to develop a technology for conveying not just messages but also underlying wisdom. Relevant theories and practices in cognitive linguistics and com...
Article
Autonomous development of gaze behavior for natural human-robot interaction
Conference Paper
Learning by imitation is becoming increasingly important for teaching humanoid robots new skills. The simplest form of imitation is behavior copying in which the robot is minimizing the difference between its perceived motion and that of the imitated agent. One problem that must be solved even in this simplest of all imitation tasks is calculating...
Conference Paper
Learning from demonstrations (LfD) is receiving more attention recently as an important modality for teaching robots and other agents new skills by untrained users. A successful LfD system must tackle several problems including the decision about what and whom to imitate but, ultimately, it needs to reproduce the skill it learned solving the how to...
Article
Full-text available
Agents engaged in lifelong learning can benefit from the ability to acquire new concepts from continuous interaction with objects in their environments which is a ubiquitous ability in humans. This paper advocates the use of sensorimotor concepts that combine perceptual and actuation patterns. Related representations to sensorimotor conceptsare Pre...
Conference Paper
Human Behavior Understanding (HBU) is a major challenge facing intelligent agents. Most approaches to solve this problem assume a recognition/detection context in which the agent/robot tries to match the perceived behavior to one or more predefined motion patterns (e.g. walking, running etc). A more challenging problem is discovering these motion p...
Article
Research in learning from demonstrations has focused primarily on the question of how to utilize demonstrations to learn new behavior assuming that the demonstrator (teacher) explicitly teaches the learner. In this paper, we focus our attention on learning from unplanned demonstrations. In such cases, the learner has to take the initiative and deci...
Conference Paper
Most available motif discovery algorithms in real-valued time series find approximately recurring patterns of a known length without any prior information about their locations or shapes. In this paper, a new motif discovery algorithm is proposed that has the advantage of requiring no upper limit on the motif length. The proposed algorithm can disc...
Conference Paper
Full-text available
Change Point Discovery (CPD) and Constrained Motif Discovery (CMD) are two essential problems in data mining with applications in many fields including robotics, economics, neuroscience and other fields. In this paper, we show that these two problems are related and report the development of a MATLAB Toolbox (CPMD) that encapsulates several useful...
Conference Paper
Internal representation is an important design decision in any imitation learning system. Actions and perceptual spaces were separate in classical AI due to the standard sense-process-act loop. Recently another representation that combines the two spaces into what we call a common sensorimotor space was inspired by the discovery of mirror neurons i...
Conference Paper
Imitation learning is an important area in robotics and agents research because it provides an easy way for robot programming and also a bootstrapping technique for social learning. Available learning by imitation systems implicitly or explicitly assume that the boundaries of the actions to be imitated are set by the demonstrator and that the robot...
Article
Full-text available
Complex systems involve the interaction between many processes that may or may not have causal relations to each other. In such systems, discovering causal relations can provide significant insights into the internals of the system and facilitate fault discovery and recovery procedures. In this paper, we provide a novel causality detection algorith...
Article
Full-text available
Change point discovery is an important problem in data mining and industrial systems. Different approaches have been proposed and some of the most promising approaches are based on singular spectrum analysis (SSA). These algorithms have the advantages of requiring no ad-hoc tuning for different types of signals and having a built-in noise attenuati...
Article
Full-text available
In this paper, we present our efforts toward building interactive robots that can learn how to interact naturally with human partners in different environments and contexts. The main feature of our approach is that it relies completely on unsupervised learning and time series analysis techniques that al-low the robot to build its own interaction pr...
Conference Paper
Full-text available
Human Robot Interaction using natural interactive modalities like gesture and verbal communication channels is becoming an important research direction because of the increase in social applications of robotics. Nevertheless, the naturalness of the interaction is usually restricted by the fact that in most cases the set of gestures or verbal comman...
Conference Paper
Full-text available
Research in robot navigation usually concentrates on implementing navigation algorithms that allow the robot to navigate without human aid. In many real world situations, it is desirable that the robot is able to understand natural gestures from its user or partner and use this understanding to guide its navigation. Some algorithms already exist fo...