Individuals generate tremendous amount of personal data each day, with a wide variety of uses. This datum often contains sensitive information about individuals, which can be disclosed by “adversaries”. Even when direct identifiers such as social security numbers are masked, an adversary may be able to recognize an individual’s identity for a data record by looking at the values of quasi-identifiers (QIDs), known as identity disclosure, or can uncover sensitive attributes (SAs) about an individual through attribute disclosure. In data privacy field, multiple disclosure risk measures have been proposed. These share two drawbacks: they do not consider identity and attribute disclosure concurrently, and they consider a restrictive attack model by assuming certain attributes, namely QIDs and SAs. In this paper, we present a flexible adversary disclosure risk measure that addresses these limitations, by presenting a single combined metric of identity and attribute disclosure, and generalizing attack models by considering all scenarios for an adversary’s knowledge and disclosure targets while providing the flexibility to model a specific disclosure preference. We have developed an efficient algorithm for computing our proposed risk measure and evaluated the performance of our approach on a benchmark dataset from 1994 Census database.

The ability to rapidly program robots for complex tasks is an important precursor to wider adoption of robotics in industry. Robot programming is often time consuming and brittle to unanticipated variations in processing. Automated robot task learning is a solution to this problem. Reinforcement Learning (RL) is a commonly used approach for a robot to autonomously learn simple tasks. In RL, rewards are used to guide the robot towards learning an optimal plan or control policy. RL, however, has proven to be of limited value for problems with large-state spaces and considerable environmental variability. In this paper, we investigate formulation of the RL approach for inspect/correct types of tasks, specifically a misplaced block in a simple grid-world environment (requiring searching the gird world to identify a missing block and returning the missing block back to the target). We use a hybrid method, combining the SARSA algorithm and a model of the environment. The model of the environment is used as a reference model to reduce the state space, avoiding unnecessary exploration of the environment. A main focus of this research is the impact of task variability on RL performance.

In Privacy Preserving Data Publishing, various privacy models have been developed for employing anonymization operations on sensitive individual level datasets, in order to publish the data for public access while preserving the privacy of individuals in the dataset. However, there is always a trade-off between preserving privacy and data utility; the more changes we make on the confidential dataset to reduce disclosure risk, the more information the data loses and the less data utility it preserves. The optimum privacy technique is the one that results in a dataset with minimum disclosure risk and maximum data utility. In this paper, we propose an improved suppression method, which reduces the disclosure risk and enhances the data utility by targeting the highest risk records and keeping other records intact. We have shown the effectiveness of our approach through an experiment on a real-world confidential dataset.

A tremendous amount of individual-level data is generated each day, of use to marketing, decision makers, and machine learning applications. This data often contain private and sensitive information about individuals, which can be disclosed by adversaries. An adversary can recognize the underlying individual's identity for a data record by looking at the values of quasi-identifier attributes, known as identity disclosure, or can uncover sensitive information about an individual through attribute disclosure. In Statistical Disclosure Control, multiple disclosure risk measures have been proposed. These share two drawbacks: they do not consider identity and attribute disclosure concurrently in the risk measure, and they make restrictive assumptions on an adversary's knowledge by assuming certain attributes are quasi-identifiers and there is a clear boundary between quasi-identifiers and sensitive information. In this paper, we present a novel disclosure risk measure that addresses these limitations, by presenting a single combined metric of identity and attribute disclosure risk, and providing flexibility in modeling adversary's knowledge. We have developed an efficient algorithm for computing the proposed risk measure and evaluated the feasibility and performance of our approach on a real-world data set from the domain of social work.

Consumers often react expressively to products such as food samples, perfume, jewelry, sunglasses, and clothing accessories. This research discusses a multimodal affect recognition system developed to classify whether a consumer likes or dislikes a product tested at a counter or kiosk, by analyzing the consumer's facial expression, body posture, hand gestures, and voice after testing the product. A depth-capable camera and microphone system - Kinect for Windows - is utilized. An emotion identification engine has been developed to analyze the images and voice to determine affective state of the customer. The image is segmented using skin color and adaptive threshold. Face, body and hands are detected using the Haar cascade classifier. Canny edges are identified and the lip, body and hand contours are extracted using spatial filtering. Edge count and orientation around the mouth, cheeks, eyes, shoulders, fingers and the location of the edges are used as features. Classification is done by an emotion template mapping algorithm and training a classifier using support vector machines. The real-time performance, accuracy and feasibility for multimodal affect recognition in feedback assessment are evaluated.

In this work, fire inhibition performance of four flame retardant formulations of brominated flame retardant (BFR: GreenArmor (R)), antimony(III) oxide (Sb2O3) and high impact polystyrene (HIPS) is reported. The standard Underwriters Laboratory (UL 94) vertical burn test was applied for assessing the flame retardancy of a variety of polymer blends. A formulation having 13.3 wt% GreenArmor (R), 4 wt% Sb2O3 and 82.7 wt% HIPS, named sample D, successfully passed the flame test and was rated V-0. The other formulations with deficient composition exhibited low flame retardancy, as expected. The X-ray grating interferometry method is introduced for probing the 3D internal structures across the burnt UL 94 flame retarded polymer blend formulations to present the detailed mechanisms of flame retardancy. The X-ray images revealed several features for the formulation (sample D) that passed the UL 94 test: heat-induced dissolution of BFR and Sb2O3 residual particles, formation of gas bubbles inside the burnt polymer test bar, deflation of gas bubbles in a char layer through a microcrack, and thick char layer development, defined by the Br and Sb concentration profile to a depth of 100-220 mu m. Also, the X-ray images show clear differences between formulations that pass and fail the UL 94 test. X-ray grating interferometry imaging is proposed as a novel technique for assessment of new generation flame retardants. (C) 2017 Elsevier Ltd. All rights reserved.

The aim of this research is development of rule based decision model for emotion recognition. This research also proposes using the rules for augmenting inter-corporal recognition accuracy in multimodal systems that use supervised learning techniques. The classifiers for such learning based recognition systems are susceptible to over fitting and only perform well on intra-corporal data. To overcome the limitation this research proposes using rule based model as an additional modality. The rules were developed using raw feature data from visual channel, based on human annotator agreement and existing studies that have attributed movement and postures to emotions. The outcome of the rule evaluations was combined during the decision phase of emotion recognition system. The results indicate rule based emotion recognition augment recognition accuracy of learning based systems and also provide better recognition rate across inter corpus emotion test data.

Affect (emotion) recognition has gained significant attention from researchers in the past decade. Emotion-aware computer systems and devices have many applications ranging from interactive robots, intelligent online tutor to emotion based navigation assistant. In this research data from multiple modalities such as face, head, hand, body and speech was utilized for affect recognition. The research used color and depth sensing device such as Kinect for facial feature extraction and tracking human body joints. Temporal features across multiple frames were used for affect recognition. Event driven decision level fusion was used to combine the results from each individual modality using majority voting to recognize the emotions. The study also implemented affect recognition by matching the features to the rule based emotion templates per modality. Experiments showed that multimodal affect recognition rates using combination of emotion templates and supervised learning were better compared to recognition rates based on supervised learning alone. Recognition rates obtained using temporal feature were higher compared to recognition rates obtained using position based features only.

Anaphora resolution is the problem of resolving references of pronouns to antecedents (previously mentioned noun phrases) in text documents. It is a fundamental preprocessing step in text understanding (semantic) applications, including dialogue and story understanding, document summarization, information extraction, machine translation, and recognizing entailment relations in text. We propose a set of computational and linguistic features to resolve the pronominal anaphora in text documents for a machine learning approach. The system was evaluated on the BBN Pronoun Coreference and Entity Type Corpus, and an F-measure of 89% was obtained. The system was also tested on different genre of document and the performance is compared with the result of the annotated corpus. Leili Javadpour et al. / IJAMML 5:1 (2016) 81-98 82

Emotional and physical well-being at workplace is important for a positive work environment and higher productivity. Jobs such as software programming lead to a sedentary lifestyle and require high interaction with computers. Working at the same job for years can cause a feeling of intellectual stagnation and lack of drive. Many employees experience lack of motivation, mild to extreme depression due to reasons such as aversion towards job responsibilities and incompatibility with coworkers or boss. This research proposed an affect monitoring system EmoFit that would play the role of psychological and physical health trainer. The day to day computer activity and body language was analyzed to detect the physical and emotional well-being of the user. Keystrokes, activity interruptions, eye tracking, facial expressions, body posture and speech were monitored to gauge the users health. The system also provided activities such as at-desk exercise and stress relief game and motivational quotes in an attempt to promote users well-being. The experimental results and positive feedback from test subjects showed that EmoFit would help improve emotional and physical well-being at jobs that involve significant computer usage.

Prison facilities, mental correctional institutions, sports bars and places of public protest are prone to sudden violence and conflicts. Surveillance systems play an important role in mitigation of hostile behavior and improvement of security by detecting such provocative and aggressive activities. This research proposed using automatic aggressive behavior and anger detection to improve the effectiveness of the surveillance systems. An emotion and aggression aware component will make the surveillance system highly responsive and capable of alerting the security guards in real time. This research proposed facial expression, head, hand and body movement and speech tracking for detecting anger and aggressive actions. Recognition was achieved using support vector machines and rule based features. The multimodal affect recognition precision rate for anger improved by 15.2% and recall rate improved by 11.7% when behavioral rule based features were used in aggressive action detection.

Background: There has been growing research interest in automated answering of questions or generation of summary of free form text such as news article. In order to implement this task, the computer should be able to identify the sequence of events, duration of events, time at which event occurred and the relationship type between event pairs, time pairs or event-time pairs. Specific Problem: It is important to accurately identify the relationship type between combinations of event and time before the temporal ordering of events can be defined. The machine learning approach taken in Mani et. al (2006) provides an accuracy of only 62.5 on the baseline data from TimeBank. The researchers used maximum entropy classifier in their methodology. TimeML uses the TLINK annotation to tag a relationship type between events and time. The time complexity is quadratic when it comes to tagging documents with TLINK using human annotation. This research proposes using decision tree and parsing to improve the relationship type tagging. This research attempts to solve the gaps in human annotation by automating the task of relationship type tagging in an attempt to improve the accuracy of event and time relationship in annotated documents. Scope information: The documents from the domain of news will be used. The tagging will be performed within the same document and not across documents. The relationship types will be identified only for a pair of event and time and not a chain of events. The research focuses on documents tagged using the TimeML specification which contains tags such as EVENT, TLINK, and TIMEX. Each tag has attributes such as identifier, relation, POS, time etc.

One of the challenges in affect recognition is accurate estimation of the emotion intensity level. This research proposes development of an affect intensity estimation model based on a weighted sum of classification confidence levels, displacement of feature points and speed of feature point motion. The parameters of the model were calculated from data captured using multiple modalities such as face, body posture, hand movement and speech. A preliminary study was conducted to compare the accuracy of the model with the annotated intensity levels. An emotion intensity scale ranging from 0 to 1 along the arousal dimension in the emotion space was used. Results indicated speech and hand modality significantly contributed in improving accuracy in emotion intensity estimation using the proposed model.

The digital universe is expanding at very high rates. New ways of retrieving and enriching text and audio content are required. In this work, a methodology for actor level emotion magnitude prediction in text and speech is proposed. A model is trained to predict emotion magnitudes per actor at any point in a story using previous emotion magnitudes plus current text and speech features which act on the actor’s emotional state. The methodology compares linear and non-linear regression techniques to determine the optimal model that fits the data. Results of the analysis show that non-linear regression models based on Support Vector Regression (SVR) using a Radial Basis Function (RBF) kernel provide the most accurate prediction model. An analysis of the contribution of the features for emotion magnitude prediction is performed.

The freshwater fish, Danio rerio (zebrafish), have become widely used as a model organism for vertebrate development, DNA mutation, and human disease studies [1]. Maintaining live colonies of the numerous developed strains of zebrafish under investigation can be prohibitively costly. As such, there is a growing need to catalog their reproductive cells and have them available on demand [2]. Thus cryopreservation of model strain gametes has become an important endeavor, where evaluation of freezing and thawing techniques is currently a bottleneck to these procedures.

Introduction to the papers presented at the 2013 FLAIRS Conference Special Track on Artificial Intelligence and Cyber Security.

Objective: The goal of this work is to develop and test an automated system methodology that can detect emotion from text and speech features. Background: Affective human–computer interaction will be critical for the success of new systems that will be prevalent in the 21st century. Such systems will need to properly deduce human emotional state before they can determine how to best interact with people. Method: Corpora and machine learning classification models are used to train and test a methodology for emotion detection. The methodology uses a stepwise approach to detect sentiment in sentences by first filtering out neutral sentences, then distinguishing among positive, negative, and five emotion classes. Results: Results of the classification between emotion and neutral sentences achieved recall accuracies as high as 77% in the University of Illinois at Urbana-Champaign (UIUC) corpus and 61% in the Louisiana State University medical drama (LSU-MD) corpus for emotion samples. Once neutral sentences were filtered out, the methodology achieved accuracy scores for detecting negative sentences as high as 92.3%. Conclusion: Results of the feature analysis indicate that speech spectral features are better than speech prosodic features for emotion detection. Accumulated sentiment composition text features appear to be very important as well. This work contributes to the study of human communication by providing a better understanding of how language factors help to best convey human emotion and how to best automate this process. Application: Results of this study can be used to develop better automated assistive systems that interpret human language and respond to emotions through 3-D computer graphics.

In recent years there has been a rapid increase in the size of video and image databases. Effective searching and retrieving of images from these databases is a significant current research area. In particular, there is a growing interest in query capabilities based on semantic image features such as objects, locations, and materials, known as content-based image retrieval. This study investigated mechanisms for identifying materials present in an image. These capabilities provide additional information impacting conditional probabilities about images (e.g. objects made of steel are more likely to be buildings). These capabilities are useful in Building Information Modeling (BIM) and in automatic enrichment of images. I2T methodologies are a way to enrich an image by generating text descriptions based on image analysis. In this work, a learning model is trained to detect certain materials in images. To train the model, an image dataset was constructed containing single material images of bricks, cloth, grass, sand, stones, and wood. For generalization purposes, an additional set of 50 images containing multiple materials (some not used in training) was constructed. Two different supervised learning classification models were investigated: a single multi-class SVM classifier, and multiple binary SVM classifiers (one per material). Image features included Gabor filter parameters for texture, and color histogram data for RGB components. All classification accuracy scores using the SVM-based method were above 85%. The second model helped in gathering more information from the images since it assigned multiple classes to the images. A framework for the I2T methodology is presented.

This paper presents an analysis of the audio section of the SEMAINE database for affect detection. Chi-square and principal component analysis techniques are used to reduce the dimensionality of the audio datasets. After dimensionality reduction, different classification techniques are used to perform emotion classification at the word level. Additionally, for unbalanced training sets, class re-sampling is performed to improve the model's classification results. Overall, the final results indicate that Support Vector Machines (SVM) performed best for all data sets. Results show promise for the SEMAINE database as an interesting corpus to study affect detection.