Continuous Conditional Random Fields Research Articles

Analysis of EEG Signals and Facial Expressions for Continuous Emotion Detection

Emotions are time varying affective phenomena that are elicited as a result of stimuli. Videos and movies in particular are made to elicit emotions in their audiences. Detecting the viewers’ emotions instantaneously can be used to find the emotional traces of videos. In this paper, we present our approach in instantaneously detecting the emotions of video viewers’ emotions from electroencephalogram (EEG) signals and facial expressions. A set of emotion inducing videos were shown to participants while their facial expressions and physiological responses were recorded. The expressed valence (negative to positive emotions) in the videos of participants’ faces were annotated by five annotators. The stimuli videos were also continuously annotated on valence and arousal dimensions. Long-short-term-memory recurrent neural networks (LSTM-RNN) and continuous conditional random fields (CCRF) were utilized in detecting emotions automatically and continuously. We found the results from facial expressions to be superior to the results from EEG signals. We analyzed the effect of the contamination of facial muscle activities on EEG signals and found that most of the emotionally valuable content in EEG features are as a result of this contamination. However, our statistical analysis showed that EEG signals still carry complementary information in presence of facial expressions.

Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields.

In this article, we tackle the problem of depth estimation from single monocular images. Compared with depth estimation using multiple images such as stereo depth perception, depth from monocular images is much more challenging. Prior work typically focuses on exploiting geometric priors or additional sources of information, most using hand-crafted features. Recently, there is mounting evidence that features from deep convolutional neural networks (CNN) set new records for various vision applications. On the other hand, considering the continuous characteristic of the depth values, depth estimation can be naturally formulated as a continuous conditional random field (CRF) learning problem. Therefore, here we present a deep convolutional neural field model for estimating depths from single monocular images, aiming to jointly explore the capacity of deep CNN and continuous CRF. In particular, we propose a deep structured learning scheme which learns the unary and pairwise potentials of continuous CRF in a unified deep CNN framework. We then further propose an equally effective model based on fully convolutional networks and a novel superpixel pooling method, which is about 10 times faster, to speedup the patch-wise convolutions in the deep model. With this more efficient model, we are able to design deeper networks to pursue better performance. Our proposed method can be used for depth estimation of general scenes with no geometric priors nor any extra information injected. In our case, the integral of the partition function can be calculated in a closed form such that we can exactly solve the log-likelihood maximization. Moreover, solving the inference problem for predicting depths of a test image is highly efficient as closed-form solutions exist. Experiments on both indoor and outdoor scene datasets demonstrate that the proposed method outperforms state-of-the-art depth estimation approaches.

회귀나무 분석을 이용한 C-CRF의 특징함수 구성 방법

We suggest a method to configure feature functions of continuous conditional random field (C-CRF). Regression tree and similarity analysis are introduced to construct the first and second feature functions of C-CRF, respectively. Rules from the regression tree are transformed to logic functions. If a logic in the set of rules is true for a data then it returns the corresponding value of leaf node and zero, otherwise. We build an Euclidean similarity matrix to define neighborhood, which constitute the second feature function. Using two feature functions, we make a C-CRF model and an illustrate example is provided.

Accelerated Continuous Conditional Random Fields For Load Forecasting

Increasingly, aiming to contain their rapidly growing energy expenditures, commercial buildings are equipped to respond to utility’s demand and price signals. Such smart energy consumption, however, heavily relies on accurate short-term energy load forecasting, such as hourly predictions for the next $n$ $(n\ge 2)$ hours. To attain sufficient accuracy for these predictions, it is important to exploit the relationships among the $n$ estimated outputs. This paper treats such multi-steps ahead regression task as a sequence labeling (regression) problem, and adopts the continuous conditional random fields (CCRF) to explicitly model these interconnected outputs. In particular, we improve the CCRF’s computation complexity and predictive accuracy with two novel strategies. First, we employ two tridiagonal matrix computation techniques to significantly speed up the CCRF’s training and inference. These techniques tackle the cubic computational cost required by the matrix inversion calculations in the training and inference of the CCRF, resulting in linear complexity for these matrix operations. Second, we address the CCRF’s weak feature constraint problem with a novel multi-target edge function, thus boosting the CCRF’s predictive performance. The proposed multi-target feature is able to convert the relationship of related outputs with continuous values into a set of “sub-relationships”, each providing more specific feature constraints for the interplays of the related outputs. We applied the proposed approach to two real-world energy load prediction systems: one for electricity demand and another for gas usage. Our experimental results show that the proposed strategy can meaningfully reduce the predictive error for the two systems, in terms of mean absolute percentage error and root mean square error, when compared with three benchmarking methods. Promisingly, the relative error reduction achieved by our CCRF model was up to 50 percent.

Continuous Conditional Random Fields for Efficient Regression in Large Fully Connected Graphs

When used for structured regression, powerful Conditional Random Fields (CRFs) are typically restricted to modeling effects of interactions among examples in local neighborhoods. Using more expressive representation would result in dense graphs, making these methods impractical for large-scale applications. To address this issue, we propose an effective CRF model with linear scale-up properties regarding approximate learning and inference for structured regression on large, fully connected graphs. The proposed method is validated on real-world large-scale problems of image de-noising and remote sensing. In conducted experiments, we demonstrated that dense connectivity provides an improvement in prediction accuracy. Inference time of less than ten seconds on graphs with millions of nodes and trillions of edges makes the proposed model an attractive tool for large-scale, structured regression problems.

Travel Speed Forecasting by Means of Continuous Conditional Random Fields

This paper explores the application of the recently proposed continuous conditional random fields (CCRF) to travel forecasting. CCRF is a flexible, probabilistic framework that can seamlessly incorporate multiple traffic predictors and exploit spatial and temporal correlations inherently present in traffic data. In addition to improving prediction accuracy, the probabilistic approach provides information about prediction uncertainty. Moreover, information about the relative importance of particular predictor and spatial–temporal correlations can be easily extracted from the model. CCRF is fault-tolerant and can provide predictions even when some observations are missing. Several CCRF models were applied to the problem of travel speed prediction in a range from 10 to 60 min ahead and evaluated on loop detector data from a 5.71-mi section of I-35W in Minneapolis, Minnesota. Several CCRF models, with increasing levels of complexity, are proposed to assess performance of the method better. When these CCRF models were compared with the linear regression model, they reduced the mean absolute error by around 4%. The results imply that modeling spatial and temporal neighborhoods in traffic data and combining various baseline predictors under the CCRF framework can be beneficial.

Infant responding compared under conjugate- and continuous-reinforcement schedules.

The peiformance of six human infants (aged 16 to 20 weeks) was compared under a conjugateversus a continuousreinforcement schedule. The contingent visual stimulus, a sequence of 5 colored lights, their intensity varying in proportion to response amplitude under the conjugate but not under the continuous schedule, was presented alone and together with a constant auditory contingent stimulus-ehimes placed behind the lights-under both schedules. The target operant response-a foot press of a vertical panel-produced the lights with/without the tinkling chimes. A reversal design counterbalanced with alternating treatments was implemented for each half of the participants. Visual inspection of the graphedoperant frequencies for all six infants, and one-tail binomial tests, showed at p < 0.008 that: (a) the two contingent-stimulus complexes, visual alone and visual-plus auditory, functioned as reinforcers of leg thrusts under both reinforcement schedules; the visual-pIus-auditory consequence was a more effective reinforcer for leg-thrust operants than was the visual consequence alone; and, (c) compared to the continuous CRF schedule, the conjugate-reinforcement schedule generated higher peak responding.

Behavioral thermoregulation with microwave radiation of albino rats.

The objective of this exploratory study was to investigate the extent to which microwave radiation would reinforce operant behavior in a cold environment. A reversal-design with the single subject serving as its own control was used for testing the reinforcing properties of microwaves. Six albino rats were conditioned to produce 6-sec. pulses of microwave radiation within a refrigerated environment. The schedule of reinforcement was continuous (crf). Each lever press produced a 6-sec. output of microwave radiation. The intensity of radiation was varied across blocks of sessions in the reversal design. Microwave values used were as follows: 62.5 W, 125 W, 250 W, and 437.5 W. Sessions lasted from 8 to 9 hr. over an approximate 7-mo. period. Results showed that rates of operant responding varied as a direct function of microwave intensity. Relatively high mean rates were associated with moderate microwave intensity (250 W), whereas lower mean rates of responding were associated with extreme microwave intensities (62.5 W and 437.5 W) in the reversal design. These data are explained in terms of satiation and deprivation of the reinforcing value of microwave radiation.