Anna Gruebler

Design of a Wearable Device for Reading Positive Expressions from Facial EMG Signals

In this paper we present the design of a wearable device that reads positive facial expressions using physiological signals. We first analyze facial morphology in 3 dimensions and facial electromyographic signals on different facial locations and show that we can detect electromyographic signals with high amplitude on areas of low facial mobility on the side of the face, which are correlated to ones obtained from electrodes on traditional surface electromyographic capturing positions on top of facial muscles on the front of the face. We use a multi-attribute decision-making method to find adequate electrode positions on the side of face to capture these signals. Based on this analysis, we design and implement an ergonomic wearable device with high reliability. Because the signals are recorded distally, the proposed device uses independent component analysis and an artificial neural network to analyze them and achieve a high facial expression recognition rate on the side of the face. The recognized emotional facial expressions through the wearable interface device can be recorded during therapeutic interventions and for long-term facial expression recognition to quantify and infer the users affective state in order to support medical professionals.

Measurement of distal EMG signals using a wearable device for reading facial expressions

In this paper we present a quantitative analysis of electrode positions on the side of the face for facial expression recognition using facial bioelectrical signals. We show that distal electrode locations on areas of low facial mobility have a strong amplitude and are correlated to signals captured in the traditional positions on top of the facial muscles. We report on electrode position choice as well successful facial expression identification using computational methods. We also propose a wearable interface device that can detect facial bioelectrical signals distally in a continuous manner while being unobtrusive to the user. The proposed device can be worn on the side of the face and capture signals that are considered to be a mixture of facial electromyographic signals and other bioelectrical signals. Finally we show the design of an interface that can be comfortably worn by the user and makes facial expression recognition possible.

An intrusion detection system against malicious attacks on the communication network of driverless cars

Vehicular ad hoc networking (VANET) have become a significant technology in the current years because of the emerging generation of self-driving cars such as Google driverless cars. VANET have more vulnerabilities compared to other networks such as wired networks, because these networks are an autonomous collection of mobile vehicles and there is no fixed security infrastructure, no high dynamic topology and the open wireless medium makes them more vulnerable to attacks. It is important to design new approaches and mechanisms to rise the security these networks and protect them from attacks. In this paper, we design an intrusion detection mechanism for the VANETs using Artificial Neural Networks (ANNs) to detect Denial of Service (DoS) attacks. The main role of IDS is to detect the attack using a data generated from the network behavior such as a trace file. The IDSs use the features extracted from the trace file as auditable data. In this paper, we propose anomaly and misuse detection to detect the malicious attack.

An Intrusion Detection System against Black Hole Attacks on the Communication Network of Self-Driving Cars

The emergence of self-driving and semi self-driving vehicles which form vehicular ad hoc networks (VANETs) has attracted much interest in recent years. However, VANETs have some characteristics that make them more vulnerable to potential attacks when compared to other networks such as wired networks. The characteristics of VANETs are: an open medium, no traditional security infrastructure, high mobility and dynamic topology. In this paper, we build an intelligent intrusion detection system (IDS) for VANETs that uses a Proportional Overlapping Scores (POS) method to reduce the number of features that are extracted from the trace file of VANET behavior and used for classification. These are relevant features that describe the normal or abnormal behavior of vehicles. The IDS uses Artificial Neural Networks (ANNs) and fuzzified data to detect black hole attacks. The IDSs use the features extracted from the trace file as auditable data to detect the attack. In this paper, we propose hybrid detection (misuse and anomaly) to detect black holes.

Coaching robot behavior using continuous physiological affective feedback

In this work we present a new way for human-robot interaction, where a robot is able to receive physiological affective feedback for its actions from a human trainer and learn from it. We capture the human trainers facial expressions using a wearable device that records distal electromyographic signals and uses computational methods of signal processing and pattern recognition in real time. We show how a robot can be coached to perform a certain action when confronted with an object by using the continuous physiological affective feedback from the human trainer. We also show that the robot is able to quickly learn the appropriate actions for different situations from the trainer in a manner modeled after the way children learn from their parents encouragement or reproach. This work shows an effective way to coach a robot using affective feedback and has the advantage of working in multiple lighting conditions and camera angles as well as not increasing the cognitive load of the trainer. Our method has applications in the area of social robotics because it shows that interaction between humans and robots is possible using continuous non-verbal social cues, which are characteristic for human-human interaction.

Emotionally Assisted Human–Robot Interaction Using a Wearable Device for Reading Facial Expressions

Abstract In this paper, we introduce a novel paradigm of emotionally assisted interaction between humans and robots. We present a personal wearable device that can be worn on the side of the face to unobtrusively and continuously detect physiological signals that are a mixture of facial electromyographic signals. Through real-time pattern classification, facial expressions can be identified from them and interpreted as positive and negative responses from a human. We report on successful facial expression identification using Independent Component Analysis and an Artificial Neural Network, and show the design of the interface device that can be used for coaching a real robot.

On the detection of grey hole and rushing attacks in self-driving vehicular networks

Vehicular ad hoc networks play an important role in the success of a new class of vehicles, i.e. self-driving and semi self-driving vehicles. These networks provide safety and comfort to passengers, drivers and vehicles themselves. These vehicles depend heavily on external communication to predicate the surrounding environment through the exchange of cooperative awareness messages (CAMs) and control data. VANETs are exposed to many types of attacks such as black hole, grey hole and rushing attacks. In this paper, we present an intelligent Intrusion Detection System (IDS) which relies on anomaly detection to protect external communications from grey hole and rushing attacks. Many researchers agree that grey hole attacks in VANETs are a substantial challenge due to them having their distinct types of behaviour: normal and abnormal. These attacks try to prevent transmission between vehicles and roadside units and have a direct and negative impact on the wide acceptance of this new class of vehicles. The proposed IDS is based on features that have been extracted from a trace file generated in a network simulator. In our paper, we used a feed-forward neural network and a support vector machine for the design of the intelligent IDS. The proposed system uses only significant features extracted from the trace file. Our research, concludes that a reduction in the number of features leads to a higher detection rate and a decrease in false alarms.

Intelligent Intrusion Detection of Grey Hole and Rushing Attacks in Self-Driving Vehicular Networks

Vehicular ad hoc networks (VANETs) play a vital role in the success of self-driving and semi self-driving vehicles, where they improve safety and comfort. Such vehicles depend heavily on external communication with the surrounding environment via data control and Cooperative Awareness Messages (CAMs) exchanges. VANETs are potentially exposed to a number of attacks, such as grey hole, black hole, wormhole and rushing attacks. This work presents an intelligent Intrusion Detection System (IDS) that relies on anomaly detection to protect the external communication system from grey hole and rushing attacks. These attacks aim to disrupt the transmission between vehicles and roadside units. The IDS uses features obtained from a trace file generated in a network simulator and consists of a feed-forward neural network and a support vector machine. Additionally, the paper studies the use of a novel systematic response, employed to protect the vehicle when it encounters malicious behaviour. Our simulations of the proposed detection system show that the proposed schemes possess outstanding detection rates with a reduction in false alarms. This safe mode response system has been evaluated using four performance metrics, namely, received packets, packet delivery ratio, dropped packets and the average end to end delay, under both normal and abnormal conditions.

Prediction of DoS attacks in external communication for self-driving vehicles using a fuzzy petri net model

In this paper we propose a security system to protect external communications for self-driving and semi self-driving cars. The proposed system can detect malicious vehicles in an urban mobility scenario. The anomaly detection system is based on fuzzy petri nets (FPN) to detect packet dropping attacks in vehicular ad hoc networks. The experimental results show the proposed FPN-IDS can successfully detect DoS attacks in external communication of self-driving vehicles.

An Analysis of Facial Morphology for the Robot Assisted Smile Recovery

Expression based non verbal communication accounts for a significant amount of the information exchange in human communication. In order to recreate facial expressions artificially for conveying an exact message it is necessary to make them as natural as possible since human beings posses a remarkable ability to recognize the emotion from an expression. In this paper we try to analyze facial expressions in terms of facial skin displacements from an anatomical point of view. We have been developing a wearable device, robot mask, to support and recreate human facial expressions by using artificial muscles. We conducted several experiments involving a comparison of the skin displacement along the facial muscles for natural expressions and artificially generated expressions. The experimental results contribute significantly to design criteria of robot mask. This paper also explains how shape memory alloy based artificial muscles can be used to generate facial expressions artificially.