Recent progress in object recognition from range data

Within the last half decade active devices have been able to provide three-dimensional data directly to vision systems. This paper examines some of the progress that has been made with this data in the field of 3D computer vision. Aspects of this field from acquisition to recognition are discussed and some major research results are reviewed.     

A Novel Hybrid Optimization for Cluster‐Based Routing Protocol in Information-Centric Wireless Sensor Networks for IoT Based Mobile Edge Computing

Wireless Personal Communications - In present days, the utilization of mobile edge computing (MEC) and Internet of Things (IoT) in mobile networks offers a bottleneck in the evolving technological...     

Enhanced Deep Autoencoder Based Feature Representation Learning for Intelligent Intrusion Detection System

In the era of Big data, learning discriminant feature representation from network traffic is identified has as an invariably essential task for improving the detection ability of an intrusion detection system (IDS). Owing to the lack of accurately labeled network traffic data, many unsupervised feature representation learning models have been proposed with state-of-the-art performance. Yet, these models fail to consider the classification error while learning the feature representation. Intuitively, the learnt feature representation may degrade the performance of the classification task. For the first time in the field of intrusion detection, this paper proposes an unsupervised IDS model leveraging the benefits of deep autoencoder (DAE) for learning the robust feature representation and one-class support vector machine (OCSVM) for finding the more compact decision hyperplane for intrusion detection. Specially, the proposed model defines a new unified objective function to minimize the reconstruction and classification error simultaneously. This unique contribution not only enables the model to support joint learning for feature representation and classifier training but also guides to learn the robust feature representation which can improve the discrimination ability of the classifier for intrusion detection. Three set of evaluation experiments are conducted to demonstrate the potential of the proposed model. First, the ablation evaluation on benchmark dataset, NSL-KDD validates the design decision of the proposed model. Next, the performance evaluation on recent intrusion dataset, UNSW-NB15 signifies the stable performance of the proposed model. Finally, the comparative evaluation verifies the efficacy of the proposed model against recently published state-of-the-art methods.     

Automatic Vehicle License Plate Recognition Using Optimal Deep Learning Model

The latest advancements in highway research domain and increase inthe number of vehicles everyday led to wider exposure and attention towards the development of efficient Intelligent Transportation System (ITS). One of the popular research areas i.e., Vehicle License Plate Recognition (VLPR) aims at determining the characters that exist in the license plate of the vehicles. The VLPR process is a difficult one due to the differences in viewpoint, shapes, colors, patterns, and non-uniform illumination at the time of capturing images. The current study develops a robust Deep Learning (DL)-based VLPR model using Squirrel Search Algorithm (SSA)-based Convolutional Neural Network (CNN), called the SSA-CNN model. The presented technique has a total of four major processes namely preprocessing, License Plate (LP) localization and detection, character segmentation, and recognition. Hough Transform (HT) is applied as a feature extractor and SSA-CNN algorithm is applied for character recognition in LP. The SSA-CNN method effectively recognizes the characters that exist in the segmented image by optimal tuning of CNN parameters. The HT-SSA-CNN model was experimentally validated using the Stanford Car, FZU Car, and HumAIn 2019 Challenge datasets. The experimentation outcome verified that the presented method was better under several aspects. The projected HT-SSA-CNN model implied the best performance with optimal overall accuracy of 0.983%.     

Methicillin‐Resistant Staphylococcus aureus in Seafood: Prevalence,Laboratory Detection,Clonal Nature,and Control in Seafood Chain

Methicillin‐resistant Staphylococcus aureus (MRSA), a versatile pathogen bearing multiple virulence determinants, is increasingly being detected in various food‐producing animals, including fish. In addition, it is a potential food poisoning agent. MRSA is not an inherent microbiota of fish; its presence is attributed to pre‐ or postharvest contamination through fish handlers, water, ice, and processing equipment. Several reviews have been written on MRSA in clinical as well as the food animal‐producing sector, but information specific to MRSA in seafood is scant. This review puts forth insights on MRSA detection in seafood, antibiotic resistance, diversity of clones in seafood, and possible control measures in seafood production chain. Emphasis has been given on assessing the variations in the protocols employed for isolation and identification in different food matrices and lay the foundation for researchers to develop optimized procedure.     

Identification of Nanoscale Ingredients in Commercial Food Products and their Induction of Mitochondrially Mediated Cytotoxic Effects on Human Mesenchymal Stem Cells

Titanium dioxide (E171) and silicon dioxide (E551) are common additives found in food products, personal‐care products, and many other consumer products used in daily life. Recent studies have reported that these food additives (manufactured E171 and E551) contain nanosized particles of less than 100 nm. However, the particle size distribution and morphology of added TiO₂ and SiO₂ particles are not typically stated on the package label. Furthermore, there is an increasing debate regarding health and safety concerns related to the use of synthetic food additives containing nanosized ingredients in consumer products. In this study, we identified the size and morphology of TiO₂ and SiO₂ particles in commercially available food products by using transmission electron microscope (TEM). In addition, the in vitro toxicological effects of E171 and E551 on human mesenchymal stem cells (hMSCs), an adult stem cell‐based model, were assessed using the MTT assay and a flow cytometry‐based JC‐1 assay. Our TEM results confirmed the presence of nanoscale ingredients in food products, and the in vitro toxicology results indicated that the nanoscale E171 and E551 ingredients induced dose‐dependent cytotoxicity, changes in cellular morphology, and the loss of mitochondrial trans‐membrane potential in hMSCs. These preliminary results clearly demonstrated that the nanoscale E171 and E551 particles had adverse effects on hMSCs by inducing oxidative stress‐mediated cell death. Accordingly, further studies are needed to identify the specific pathway involved, with an emphasis on differential gene expression in hMSCs.     

Physics-based integration of multiple sensing modalities for sceneinterpretation

The fusion of multiple imaging modalities offers many advantages over the analysis, separately, of the individual sensory modalities. In this paper we present a unique approach to the integrated analysis of disparate sources of imagery for object recognition. The approach is based on physics-based modeling of the image generation mechanisms. Such models make possible features that are physically meaningful and have an improved capacity to differentiate between multiple classes of objects. We illustrate the use of physics-based approach to develop multisensory vision systems for different object recognition application domains. The paper discusses the integration of different suites of sensors, the integration of image-derived information with model-derived information and the physics-based simulation of multisensory imagery     

Experimental investigation on corrosion and hardness of ion implanted AISI 316L stainless steel

The AISI 316L stainless steel has been widely used both in artificial knee and hip joints in bio-medical applications. In the present study AISI 316L SS was implanted with two different ions: nitrogen and helium at 100 keV with a dose of 1 × 10¹⁷ ions/cm² at room temperature. The crystallographic orientation and surface morphology were studied using X-ray diffraction (XRD) and scanning electron microscope (SEM). The effects of ion implantation on the corrosion performance of AISI 316L stainless steel was evaluated in 0.9% NaCl solution using electro chemical test both on the virgin and implanted samples. The subsequent Tafel analysis shows that the ion implanted specimens were more corrosion resistant when compared to the bare specimens. Microhardness was also measured by Vickers method by varying the loads. The results of the studies indicated that there was a significant improvement in both corrosion resistance and hardness of implanted samples.     

Dominant-subspace invariants

Object recognition requires robust and stable features that are unique in feature space. Lie group analysis provides a constructive procedure to determine such features, called invariants, when they exist. Absolute invariants are rare in general, so quasi-invariants relax the restrictions required for absolute invariants and, potentially, can be just as useful in real-world applications. The paper develops the concept of a dominant-subspace invariant, a particular type of quasi-invariant, using the theory of Lie groups. A constructive algorithm is provided that fundamentally seeks to determine an integral submanifold which, in practice, is a good approximation to the orbit of the Lie group action. This idea is applied to the long-wave infrared problem and experimental results are obtained supporting the approach. Other application areas are cited     

Nitrogen-incorporated carbon nanotube derived from polystyrene and polypyrrole as hydrogen storage material

“Synthesis of nitrogen-doped carbon nanotubes from polymeric precursors (polystyrene and polypyrrole) by poly-condensation followed by carbonization under an inert atmosphere is reported. Three different carbonization temperatures (500 °C, 700 °C and 900 °C) were employed to synthesize three different carbon nanostructures with different morphologies. These were designated as NCNR-500 (nitrogen-doped carbon nanorods), NCBCT-700 (nitrogen-doped fused bead carbon nanotubes), and NCNT-900 (nitrogen-doped carbon nanotubes) according to morphology and carbonization temperature. Microstructure, morphology, porosity, and nitrogen content were characterized by several different techniques. The effects of carbonization temperature and the role of functional groups were also investigated. Total and excess hydrogen storage capacities of 2.0 wt% and 1.8 wt%, respectively, were measured at 298 K and 100 bar for the NCNT-900 material. This is higher than the capacities of the NCNR-500 and NCBCT-700 materials. NCNT-900 exhibited a porous structure with high specific surface area and total pore volume of 870 m/g and 0.62 cm³/g, respectively.