Leveraging Transfer Learning for Spatio-Temporal Human Activity Recognition from Video Sequences

Human Activity Recognition (HAR) is an active research area due to its applications in pervasive computing, human-computer interaction, artificial intelligence, health care, and social sciences. Moreover, dynamic environments and anthropometric differences between individuals make it harder to recognize actions. This study focused on human activity in video sequences acquired with an RGB camera because of its vast range of real-world applications. It uses two-stream ConvNet to extract spatial and temporal information and proposes a fine-tuned deep neural network. Moreover, the transfer learning paradigm is adopted to extract varied and fixed frames while reusing object identification information. Six state-of-the-art pre-trained models are exploited to find the best model for spatial feature extraction. For temporal sequence, this study uses dense optical flow following the two-stream ConvNet and Bidirectional Long Short Term Memory (BiLSTM) to capture long-term dependencies. Two state-of-the-art datasets, UCF101 and HMDB51, are used for evaluation purposes. In addition, seven state-of-the-art optimizers are used to fine-tune the proposed network parameters. Furthermore, this study utilizes an ensemble mechanism to aggregate spatial-temporal features using a four-stream Convolutional Neural Network (CNN), where two streams use RGB data. In contrast, the other uses optical flow images. Finally, the proposed ensemble approach using max hard voting outperforms state-of-the-art methods with 96.30% and 90.07% accuracies on the UCF101 and HMDB51 datasets.     

A model to measure QoE for virtual personal assistant

Until now the virtual assistants (like Siri, Google Now and Cortana) have primarily been confined to voice input and output only. Is there a justification for voice only confinement or can we enhance the user experience by adding a visual output? We hypothesized that providing a higher level of visual/auditory immersion would enhance the quality of user experience. In order to test this hypothesis, we first developed 4 variants of virtual assistant, each with a different audio/visual level of immersion. Developed virtual assistant systems were the following; audio only, audio and 2D visual display, audio and 3D visual display and audio and immersive 3D visual display. We developed a plan for usability testing of all 4 variants. The usability testing was conducted with 30 subjects against eight (8) dependent variables included presence, involvement, attention, reliability, dependency, easiness, satisfaction and expectations. Each subject rated these dependent variables based on a scale of 1–5, 5 being the highest value. The raw data collected from usability testing was then analyzed through several tools in order to determine the factors contributing towards the quality of experience for each of the 4 variants. The significant factors were then used develop a model that measures the quality of user experience. It was found that each variant had a different set of significant variables. Hence, in order to rate each system there is a need to develop a scale that is dependent upon the unique set of variables for the respective variant. Furthermore, it was found that variant 4 scored the highest rate for Quality of Experience (QoE). Lastly several other qualitative conclusions were also drawn from this research that will guide future work in the field of virtual assistants.     

Solubility Enhancement of Fe in ZnO Nanoparticles Prepared by Co-Precipitation Method

Journal of Superconductivity and Novel Magnetism - Crystalline ZnO offers an excellent host matrix to create a dilute magnetic semiconductor (DMS) owing to its facile Zn-atom substitution with the...     

N‐halamine‐modified polyglycolide (PGA) multifilament as a potential bactericidal surgical suture: In vitro study

In this study, new cationic homopolymer and anionic copolymer were synthesized, and deposited onto polyglycolide sutures using a layer‐by‐layer assembly technique. The coated sutures were rendered antibacterial by chlorinating with dilute solution of household bleach solution at pH 7. The chlorination treatment transformed the N? H groups of anionic copolymer into N‐halamine structures. The N‐halamine‐modified sutures were challenged with Staphylococcus aureus and Escherichia coli O157:H7 bacteria at different contact times. The suture with chlorine loading of 0.22% completely inactivated both bacterial strains in 30 min contact time. Fourier transform infrared spectroscopy, scanning electron microscopy, and analytical titration confirmed the successful deposition of the N‐halamine multilayers. The effect of layer‐by‐layer coatings of polyelectrolytes on the chlorine loading and antibacterial efficacy of sutures was evaluated. The straight‐pull and knot‐pull strength tests performed on the sutures reported slight decline in tensile properties after chlorination treatment. The in vitro hemolysis and cytocompatibility tests revealed that the N‐halamines‐based antibacterial sutures were biocompatible. © 2015 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2015 , 132, 42483.     

Double Repositioning: Veterinary Antiparasitic to Human Anticancer

Drug repositioning, the approach of discovering different uses for existing drugs, has gained enormous popularity in recent years in the anticancer drug discovery field due to the increasing demand for anticancer drugs. Additionally, the repurposing of veterinary antiparasitic drugs for the treatment of cancer is gaining traction, as supported by existing literature. A prominent example is the proposal to implement the use of veterinary antiparasitics such as benzimidazole carbamates and halogenated salicylanilides as novel anticancer drugs. These agents have revealed pronounced anti-tumor activities and gained special attention for “double repositioning”, as they are repurposed for different species and diseases simultaneously, acting via different mechanisms depending on their target. As anticancer agents, these compounds employ several mechanisms, including the inhibition of oncogenic signal transduction pathways of mitochondrial respiration and the inhibition of cellular stress responses. In this review, we summarize and provide valuable information about the experimental, preclinical, and clinical trials of veterinary antiparasitic drugs available for the treatment of various cancers in humans. This review suggests the possibility of new treatment options that could improve the quality of life and outcomes for cancer patients in comparison to the currently used treatments.     

Prediction of warp and weft yarn crimp in cotton woven fabrics

The aim of this study was to develop statistical models for the prediction of warp and weft crimp percentage of cotton woven fabrics. The developed models are based on the empirical data obtained from carefully developed 60 fabric samples with different yarn linear densities, fabric densities, and weave designs. The predictability and accuracy of the developed models was assessed by correlation analysis of the predicted and actual crimp values of another set of eight fabric samples which was not used for the development of models. The results show fairly good capability and accuracy of the prediction models.     

Wheat gluten: high molecular weight glutenin subunits--structure, genetics, and relation to dough elasticity

ABSTRACT:  Gluten proteins, representing the major protein fraction of the starchy endosperm, are predominantly responsible for the unique position of wheat amongst cereals. These form a continuous proteinaceous matrix in the cells of the mature dry grain and form a continuous viscoelastic network during the mixing process of dough development. These viscoelastic properties underline the utilization of wheat to prepare bread and other wheat flour based foodstuffs. One group of gluten proteins is glutenin, which consists of high molecular weight (HMW) and low molecular weight (LMW) subunits. The HMW glutenin subunits (HMW-GS) are particularly important for determining dough elasticity. The common wheat possesses 3 to 5 HMW subunits encoded at the Glu-1 loci on the long arms of group 1 chromosomes (1A, 1B, and 1D). The presence of certain HMW subunits is positively correlated with good bread-making quality. Glutamine-rich repetitive sequences that comprise the central part of the HMW subunits are actually responsible for the elastic properties due to extensive arrays of interchain hydrogen bonds. Genetic engineering can be used to manipulate the amount and composition of the HMW subunits, leading to either increased dough strength or more drastic changes in gluten structure and properties.     

Project Oriented Problem Based Learning: A Wireless Sensor Network Perspective

Every nation rely on latest engineering technologies to foster in today’s technological era. Wireless Sensor Networks (WSNs) is one of the latest emerging technologies being the center of interest of today’s researchers. All the researchers work hard to produce quick deliverables through Research and Development (RandD) and by applying different learning pedagogues. Currently, the learning pedagogues in Engineering RandD are Project Based Learning and Problem Based Learning (PBL). Based on these pedagogues, this paper propose and implements a hybrid pedagogy called Project Oriented PBL (PO-PBL) which is time effective and result oriented learning pedagogy. It has resulted in providing impetus to RandD in WSNs. Further the proposed pedagogy is divided into two paradigms namely PO-PBL Macro Model and PO-PBL Micro Model. We observed that PO-PBL Macro Model results in optimal number of deliverables in time restricted manner over large scale. Moreover, we have also implemented PO-PBL Micro Model, compared it with PO-PBL Macro Model and propose PO-PBL Micro Model as basis for designing self-learning algorithm for WSNs devices.     

Physiological and Nutraceutical Perspectives of Fructan

Functional and nutraceutical foods have captured the global market owing to trends and perceptions of consumers on the natural products and diet-health linkages. Health promoting potential of such foods has been attributed to the presence of essential bioactive moieties. Wheat, being staple food in many parts of the world, gained substantial attention of researchers particularly for the extraction of various functional components. Among these, fructan oligosaccharides in nature bestow quality of baked products and provide protection against various physiological disorders. Addition of fructan in various baked products enhances softness and color, especially in bread, and also imparts textural improvement. Moreover, fructans boost mineral absorption, hypocholesterolemic, and hypoglycemic perspectives, bifidogenic nature and controlling cancer insurgence. The benefits allied with fructan are mainly dose and time dependent. In this context, its industrial applications for vulnerable groups are increasing worldwide.