The PASCAL Visual Object Classes Challenge

https://scholarlypublications.universiteitleiden.nl/access/item%3A2943283/view

Deep learning for visual understanding

This study aimed to review the literature describing and quantifying time lags in the health research translation process. Papers were included in the review if they quantified time lags in the development of health interventions. The study identified 23 papers. Few were comparable as different studies use different measures, of different things, at different time points. We concluded that the current state of knowledge of time lags is of limited use to those responsible for R&D and knowledge transfer who face difficulties in knowing what they should or can do to reduce time lags. This effectively ‘blindfolds’ investment decisions and risks wasting effort. The study concludes that understanding lags first requires agreeing models, definitions and measures, which can be applied in practice. A second task would be to develop a process by which to gather these data.

The Answer Is 17 Years, What Is the Question

Learning Deconvolution Network for Semantic Segmentation

We introduce hand movement, orientation, and grasp (HMOG), a set of behavioral features to continuously authenticate smartphone users. HMOG features unobtrusively capture subtle micro-movement and orientation dynamics resulting from how a user grasps, holds, and taps on the smartphone. We evaluated authentication and biometric key generation (BKG) performance of HMOG features on data collected from 100 subjects typing on a virtual keyboard. Data were collected under two conditions: 1) sitting and 2) walking. We achieved authentication equal error rates (EERs) as low as 7.16% (walking) and 10.05% (sitting) when we combined HMOG, tap, and keystroke features. We performed experiments to investigate why HMOG features perform well during walking. Our results suggest that this is due to the ability of HMOG features to capture distinctive body movements caused by walking, in addition to the hand-movement dynamics from taps. With BKG, we achieved the EERs of 15.1% using HMOG combined with taps. In comparison, BKG using tap, key hold, and swipe features had EERs between 25.7% and 34.2%. We also analyzed the energy consumption of HMOG feature extraction and computation. Our analysis shows that HMOG features extracted at a 16-Hz sensor sampling rate incurred a minor overhead of 7.9% without sacrificing authentication accuracy. Two points distinguish our work from current literature: 1) we present the results of a comprehensive evaluation of three types of features (HMOG, keystroke, and tap) and their combinations under the same experimental conditions and 2) we analyze the features from three perspectives (authentication, BKG, and energy consumption on smartphones).

/pdf/hmog-new-behavioral-biometric-features-for-continuous-wxqxi7t4mv.pdf

HMOG: New Behavioral Biometric Features for Continuous Authentication of Smartphone Users

Purpose: With the patient care experience being a healthcare priority, it is concerning that patients with stroke reported boredom and a desire for greater fostering of autonomy, when evaluating their rehabilitation experience. Technology has the potential to reduce these shortcomings by engaging patients through entertainment and objective feedback. Providing objective feedback has resulted in improved outcomes and may assist the patient in learning how to self-manage rehabilitation. Our goal was to examine the extent to which physical and occupational therapists use technology in clinical stroke rehabilitation home exercise programs.Materials and methods: Surveys were sent via mail, email and online postings to over 500 therapists, 107 responded.Results: Conventional equipment such as stopwatches are more frequently used compared to newer technology like Wii and Kinect games. Still, less than 25% of therapists’ report using a stopwatch five or more times per week. Notably, feedback to patients i...

Reported use of technology in stroke rehabilitation by physical and occupational therapists.

We present language-motivated approaches to detecting, localizing and classifying activities and gestures in videos. In order to obtain statistical insight into the underlying patterns of motions in activities, we develop a dynamic, hierarchical Bayesian model which connects low-level visual features in videos with poses, motion patterns and classes of activities. This process is somewhat analogous to the method of detecting topics or categories from documents based on the word content of the documents, except that our documents are dynamic. The proposed generative model harnesses both the temporal ordering power of dynamic Bayesian networks such as hidden Markov models (HMMs) and the automatic clustering power of hierarchical Bayesian models such as the latent Dirichlet allocation (LDA) model. We also introduce a probabilistic framework for detecting and localizing pre-specified activities (or gestures) in a video sequence, analogous to the use of filler models for keyword detection in speech processing. We demonstrate the robustness of our classification model and our spotting framework by recognizing activities in unconstrained real-life video sequences and by spotting gestures via a one-shot-learning approach.

/pdf/language-motivated-approaches-to-action-recognition-s604rgblrk.pdf

Language-motivated approaches to action recognition

Inspired by the the behavioral scientific discoveries of Dr. Paul Ekman in relation to deceit detection, along with the television drama series Lie to Me, also based on Dr. Ekman's work, we use machine learning techniques to study the underlying phenomena expressed when a person tells a lie. We build an automated framework which detects deceit by measuring the deviation from normal behavior, at a critical point in the course of an investigative interrogation. Behavioral psychologists have shown that the eyes (via either gaze aversion or gaze extension) can be good “reflectors” of the inner emotions, when a person tells a high-stake lie. Hence we develop our deceit detection framework around eye movement changes. A dynamic bayesian model of eye movements is trained during a normal course of conversation for each subject, to represent normal behavior. The remaining conversation is broken into sequences and each sequence is tested against the parameters of the model of normal behavior. At the critical points in the interrogations, the deviations from normalcy are observed and used to deduce verity/deceit. An analysis on 40 subjects gave an accuracy of 82.5% which strongly suggests that the latent parameters of eye movements successfully capture behavioral changes and could be viable for use in automated deceit detection.

Lie to Me: Deceit detection via online behavioral learning

Traditionally, when generative models of data are developed via deep architectures, greedy layer-wise pre-training is employed. In a well-trained model, the lower layer of the architecture models the data distribution conditional upon the hidden variables, while the higher layers model the hidden distribution prior. But due to the greedy scheme of the layerwise training technique, the parameters of lower layers are fixed when training higher layers. This makes it extremely challenging for the model to learn the hidden distribution prior, which in turn leads to a suboptimal model for the data distribution. We therefore investigate joint training of deep autoencoders, where the architecture is viewed as one stack of two or more single-layer autoencoders. A single global reconstruction objective is jointly optimized, such that the objective for the single autoencoders at each layer acts as a local, layer-level regularizer. We empirically evaluate the performance of this joint training scheme and observe that it not only learns a better data model, but also learns better higher layer representations, which highlights its potential for unsupervised feature learning. In addition, we find that the usage of regularizations in the joint training scheme is crucial in achieving good performance. In the supervised setting, joint training also shows superior performance when training deeper models. The joint training framework can thus provide a platform for investigating more efficient usage of different types of regularizers, especially in light of the growing volumes of available unlabeled data.

Is Joint Training Better for Deep Auto-Encoders?

Dissemination of malicious code, also known as malware, poses severe challenges to cyber security Malware authors embed software in seemingly innocuous executables, unknown to a user The malware subsequently interacts with security-critical OS resources on the host system or network, in order to destroy their information or to gather sensitive information such as passwords and credit card numbers Malware authors typically use Application Programming Interface (API) calls to perpetrate these crimes We present a model that uses text mining and topic modeling to detect malware, based on the types of API call sequences We evaluated our technique on two publicly available datasets We observed that Decision Tree and Support Vector Machine yielded significant results We performed t-test with respect to sensitivity for the two models and found that statistically there is no significant difference between these models We recommend Decision Tree as it yields ‘if-then’ rules, which could be used as an early warning expert system

Ifeoma Nwogu

Papers

Reported use of technology in stroke rehabilitation by physical and occupational therapists.

Language-motivated approaches to action recognition

Lie to Me: Deceit detection via online behavioral learning

Is Joint Training Better for Deep Auto-Encoders?

Malware detection via API calls, topic models and machine learning