PRATIT: a CNN-based emotion recognition system using histogram equalization and data augmentation

Multimedia Tools and Applications - Emotions are spontaneous feelings that are accompanied by fluctuations in facial muscles, which leads to facial expressions. Categorization of these facial...     

Handling Movement Epenthesis and Hand Segmentation Ambiguities in Continuous Sign Language Recognition Using Nested Dynamic Programming

We consider two crucial problems in continuous sign language recognition from unaided video sequences. At the sentence level, we consider the movement epenthesis (me) problem and at the feature level, we consider the problem of hand segmentation and grouping. We construct a framework that can handle both of these problems based on an enhanced, nested version of the dynamic programming approach. To address movement epenthesis, a dynamic programming (DP) process employs a virtual me option that does not need explicit models. We call this the enhanced level building (eLB) algorithm. This formulation also allows the incorporation of grammar models. Nested within this eLB is another DP that handles the problem of selecting among multiple hand candidates. We demonstrate our ideas on four American Sign Language data sets with simple background, with the signer wearing short sleeves, with complex background, and across signers. We compared the performance with Conditional Random Fields (CRF) and Latent Dynamic-CRF-based approaches. The experiments show more than 40 percent improvement over CRF or LDCRF approaches in terms of the frame labeling rate. We show the flexibility of our approach when handling a changing context. We also find a 70 percent improvement in sign recognition rate over the unenhanced DP matching algorithm that does not accommodate the me effect.     

Improved gait recognition by gait dynamics normalization

Potential sources for gait biometrics can be seen to derive from two aspects: gait shape and gait dynamics. We show that improved gait recognition can be achieved after normalization of dynamics and focusing on the shape information. We normalize for gait dynamics using a generic walking model, as captured by a population Hidden Markov Model (pHMM) defined for a set of individuals. The states of this pHMM represent gait stances over one gait cycle and the observations are the silhouettes of the corresponding gait stances. For each sequence, we first use Viterbi decoding of the gait dynamics to arrive at one dynamics-normalized, averaged, gait cycle of fixed length. The distance between two sequences is the distance between the two corresponding dynamics-normalized gait cycles, which we quantify by the sum of the distances between the corresponding gait stances. Distances between two silhouettes from the same generic gait stance are computed in the linear discriminant analysis space so as to maximize the discrimination between persons, while minimizing the variations of the same subject under different conditions. The distance computation is constructed so that it is invariant to dilations and erosions of the silhouettes. This helps us handle variations in silhouette shape that can occur with changing imaging conditions. We present results on three different, publicly available, data sets. First, we consider the HumanlD Gait Challenge data set, which is the largest gait benchmarking data set that is available (122 subjects), exercising five different factors, i.e., viewpoint, shoe, surface, carrying condition, and time. We significantly improve the performance across the hard experiments involving surface change and briefcase carrying conditions. Second, we also show improved performance on the UMD gait data set that exercises time variations for 55 subjects. Third, on the CMU Mobo data set, we show results for matching across different walking speeds. It is worth noting that there was no separate training for the UMD and CMU data sets.     

Effect of beam limiting aperture and collector potential on multi-element focused ion beams

A compact microwave driven plasma based multi-element focused ion beam system has been developed. In the present work, the effect of reduced beam limiter (BL) aperture on the focused ion beam parameters, such as current and spot size, and a method of controlling beam energy independently by introducing a biased collector at focal point (FP) are investigated. It is found that the location of FP does not change due to the reduction of BL aperture. The location of FP and beam size are found to be weakly dependent on the collector potential in the range from -8 kV to -18 kV.     

In-Place Stabilization of Pond Ash Deposits by Hydrated Lime Columns

Abandoned coal ash ponds cover up vast stretches of precious land and cause environmental problems. Application of suitable in situ stabilization methods may bring about improvement in the geotechnical properties of the ash deposit as a whole, converting it to a usable site. In this study, a technique of in-place stabilization by hydrated lime columns was applied to large-scale laboratory models of ash ponds. Samples collected from different radial distances and different depths of the ash deposit were tested to study the improvements in the water content, dry density, particle size distribution, unconfined compressive strength, pH, hydraulic conductivity, and leachate characteristics over a period of one year. The in-place stabilization by lime column technique has been found effective in increasing the unconfined compressive strength and reducing hydraulic conductivity of pond ash deposits in addition to modifying other geotechnical parameters. The method has also proved to be useful in reducing the contamination potential of the ash leachates, thus mitigating the adverse environmental effects of ash deposits.     

Fake News Identification and Classification Using DSSM and Improved Recurrent Neural Network Classifier

ABSTRACT

The widespread use of social media has enormous consequences for the society, culture and business with potentially positive and negative effects. As online social networks are increasingly used for dissemination of information, at the same they are also becoming a medium for the spread of fake news for various commercial and political purposes. Technologies such as Artificial Intelligence (AI) and Natural Language Processing (NLP) tools offer great promise for researchers to build systems, which could automatically detect fake news. However, detecting fake news is a challenging task to accomplish as it requires models to summarize the news and compare it to the actual news in order to classify it as fake. This project proposes a framework that detects and classifies fake news messages using improved Recurrent Neural Networks and Deep Structured Semantic Model. The proposed approach intuitively identifies important features associated with fake news without previous domain knowledge while achieving accuracy 99%. The performance analysis method used for the proposed system is based on accuracy, specificity and sensitivity.     

Phytol Derivatives as Drug Resistance Reversal Agents

Phytol was chemically transformed into fifteen semi‐synthetic derivatives, which were evaluated for their antibacterial and drug resistance reversal potential in combination with nalidixic acid against E. coli strains CA8000 and DH5α. The pivaloyl ( 4 ), 3,4,5‐trimethoxybenzoyl ( 9 ), 2,3‐dichlorobenzoyl ( 10 ), cinnamoyl ( 11 ), and aldehyde ( 14 ) derivatives of phytol ((2E,7R,11R)‐3,7,11,15‐tetramethyl‐2‐hexadecen‐1‐ol) were evaluated by using another antibiotic, tetracycline, against the MDREC‐KG4 clinical isolate of E. coli. Derivative 4 decreased the maximal inhibitory concentration (MIC) of the antibiotics by 16‐fold, while derivatives 9 , 10 , 11 , and 14 reduced MIC values of the antibiotics up to eightfold against the E. coli strains. Derivatives 4 , 9 , 10 , 11 , and 14 inhibited the ATP‐dependent efflux pump; this was also supported by their in silico binding affinity and down‐regulation of the efflux pump gene yojI, which encodes the multidrug ATP‐binding cassette transporter protein. This study supports the possible use of phytol derivatives in the development of cost‐effective antibacterial combinations.     

Environmental microscopy in stone conservation

The natural weathering of stone is accelerated by the combined effects of acid rain, salt crystallization, and the freeze-thaw cycles of water. Since weathering will take place until the system reaches chemical equilibrium, we can mitigate the loss to historic stone monuments and structures by treatments of the stone that retard hydrolysis and impart mechanical strength. While macroscopic studies of stone weathering have been performed addressing the causes, the reactions, and the kinetics involved, the mechanisms of weathering, and the chemical remediation of stone need to be better understood at a microscopic level. Our approach uses environmental scanning electron microscopy where samples can be imaged in their wet, natural state, thus facilitating the in situ study of the weathering processes. The environment in the microscope is set up to simulate the conditions of degradation by introducing corrosive liquids and gases and varying the temperature, pressure, and water content in the environmental chamber of the microscope. In this study, we observed specimens of limestone, treated calcite, and sandstone. We have characterized the morphology, structure, and chemical constituents of the samples for comparison at a later stage when protective coatings will be applied. In situ leaching tests were performed on limestone samples to study the mechanisms of degradation. Granular disintegration due to leaching of the binding material between the grains was seen. We have also observed, in situ, the changes in the structure of sodium sulfate, used in salt crystallization tests, during hydration and dehydration cycles; it changed from that of dense grains to hydrated mesoporous granules with the generation of new surface area.