Meaningful Learning for Deep Facial Emotional Features

Neural Processing Letters - Facial expression is an important aspect to recognize emotions between humans. However, this task remains difficult for machines. Several approaches have been developed...     

Halloysite Nanotubes Modified by Fe3O4 Nanoparticles and Applied as a Natural and Efficient Nanocatalyst for the SymmetricalHantzsch Reaction

Halloysite as an impressive natural eco-friendly nanotube with aluminosilicate structure has been investigated recently due to its unique features such as specific morphology and excellent bio-adaptability. In this research, Fe₃O₄ nanoparticles have been loaded on the tubular halloysite by co-precipitation method in order to synthesis magnetic halloysite (Hal-Fe₃O₄₎. To characterize this recoverable nanocatalyst, applicable analyses such as Fourier-transform infrared (FT-IR) spectroscopy, energy-dispersive X-ray (EDX) analysis, field-emission scanning electron microscopy (FE-SEM) images, X-ray diffraction (XRD) pattern, Thermogravimetric analysis (TGA) and vibrating sample magnetometer (VSM) curves have been carried out. The results confirmed that Fe₃O₄ nanoparticles with cubic structure, and uniform distribution, were located at halloysite nanotubes (HNTs). This aluminosilicate nanocomposite with high thermal stability, crystalline structure, and stable morphology was evaluated as a heterogeneous catalyst in the symmetrical Hantzsch reaction for the first time. Easy synthesis process, green media, high performance, recoverable catalyst and reusing of the Hal-Fe₃O₄ as a nanocatalyst for 8 times are the main features of this protocol.

     

An Efficient Digital Confidentiality Scheme Based on Commutative Chaotic Polynomial

Multimedia Tools and Applications - One of the most critical aspects of this technologically progressive era is the propagation of information through an unsecured communication channel. The...     

Learning a Deep Predictive Coding Network for a Semi-Supervised 3D-Hand Pose Estimation

In this paper we present a CNN based approach for a real time 3D-hand pose estimation from the depth sequence. Prior discriminative approaches have achieved remarkable success but are facing two main challenges: Firstly, the methods are fully supervised hence require large numbers of annotated training data to extract the dynamic information from a hand representation. Secondly, unreliable hand detectors based on strong assumptions or a weak detector which often fail in several situations like complex environment and multiple hands. In contrast to these methods, this paper presents an approach that can be considered as semi-supervised by performing predictive coding of image sequences of hand poses in order to capture latent features underlying a given image without supervision. The hand is modelled using a novel latent tree dependency model (LDTM) which transforms internal joint location to an explicit representation. Then the modeled hand topology is integrated with the pose estimator using data dependent method to jointly learn latent variables of the posterior pose appearance and the pose configuration respectively. Finally, an unsupervised error term which is a part of the recurrent architecture ensures smooth estimations of the final pose. Experiments on three challenging public datasets, ICVL, MSRA, and NYU demonstrate the significant performance of the proposed method which is comparable or better than state-of-the-art approaches.      

Micro‐morphological,environmental and phytochemical investigation of herbal medicines by using LM and SEM: A quality control tool

The use of quality control tool for authentication of Jadwar (Delphinium denudatum Wall. ex Hook.f. & Thomson), a folk herbal drug used for the treatment of different ailments, was studied. People face problems of adulteration for this drug at global, regional, national and local levels. Two different plant species are commercially marketed in the Indo‐Pak Subcontinent under the same trade name of Jadwar. One is D. denudatum Wall. ex Hook.f. & Thomson and the other is Aconitum heterophyllum Wall. ex Royle. To focus on this problem, a marketable available drug sample of Jadwar was authenticated by using basic microscopy tools (LM) and advanced chemo‐taxonomic markers. Authentication, quality and standardization of this drug was achieved using morphology, organoleptography, UV and IR analyses, scanning electron microscopy of pollen and anatomical investigations. The techniques used for authentication marked the clear difference between the studied plants. Microscopic studies, chemotaxonomic investigation and other techniques used in this project provided the basis for the authentication of this species.     

Evaluation of TBM performance prediction models and sensitivity analysis of input parameters

Bulletin of Engineering Geology and the Environment - In recent years, anumber of models and formulas have been proposed to estimate the penetration rate of hard rock tunnel boring machines (TBMs)....     

A novel efficient image encryption algorithm based on affine transformation combine with linear fractional transformation

Multidimensional Systems and Signal Processing - Algebraic structures and their hardware–software implementation gain considerable attention in the field of information security and coding...     

COVID-19 Infected Lung Computed Tomography Segmentation and Supervised Classification Approach

The purpose of this research is the segmentation of lungs computed tomography (CT) scan for the diagnosis of COVID-19 by using machine learning methods. Our dataset contains data from patients who are prone to the epidemic. It contains three types of lungs CT images (Normal, Pneumonia, and COVID-19) collected from two different sources; the first one is the Radiology Department of Nishtar Hospital Multan and Civil Hospital Bahawalpur, Pakistan, and the second one is a publicly free available medical imaging database known as Radiopaedia. For the preprocessing, a novel fuzzy c-mean automated region-growing segmentation approach is deployed to take an automated region of interest (ROIs) and acquire 52 hybrid statistical features for each ROIs. Also, 12 optimized statistical features are selected via the chi-square feature reduction technique. For the classification, five machine learning classifiers named as deep learning J4, multilayer perceptron, support vector machine, random forest, and naive Bayes are deployed to optimize the hybrid statistical features dataset. It is observed that the deep learning J4 has promising results (sensitivity and specificity: 0.987; accuracy: 98.67%) among all the deployed classifiers. As a complementary study, a statistical work is devoted to the use of a new statistical model to fit the main datasets of COVID-19 collected in Pakistan.     

Super Compact UWB Monopole Antenna for Small IoT Devices

This article introduces a novel, ultrawideband (UWB) planar monopole antenna printed on Roger RT/5880 substrate in a compact size for small Internet of Things (IoT) applications. The total electrical dimensions of the proposed compact UWB antenna are 0.19 λ_o × 0.215 λ_o × 0.0196 λ_o with the overall physical sizes of 15 mm × 17 mm × 1.548 mm at the lower resonance frequency of 3.8 GHz. The planar monopole antenna is fed through the linearly tapered microstrip line on a partially structured ground plane to achieve optimum impedance matching for UWB operation. The proposed compact UWB antenna has an operation bandwidth of 9.53 GHz from 3.026 GHz up to 12.556 GHz at −10 dB return loss with a fractional bandwidth (FBW) of about 122%. The numerically computed and experimentally measured results agree well in between. A detailed time-domain analysis is additionally accomplished to verify the radiation efficiency of the proposed antenna design for the ultra-wideband signal propagation. The fabricated prototype of a compact UWB antenna exhibits an omnidirectional radiation pattern with the low peak measured gain required of 2.55 dBi at 10 GHz and promising radiation efficiency of 90%. The proposed compact planar antenna has technical potential to be utilized in UWB and IoT applications.     

Hybrid Computational Modeling for Web Application Security Assessment

Transformation from conventional business management systems to smart digital systems is a recurrent trend in the current era. This has led to digital revolution, and in this context, the hardwired technologies in the software industry play a significant role However, from the beginning, software security remains a serious issue for all levels of stakeholders. Software vulnerabilities lead to intrusions that cause data breaches and result in disclosure of sensitive data, compromising the organizations’ reputation that translates into, financial losses as well. Most of the data breaches are financially motivated, especially in the healthcare sector. The cyber invaders continuously penetrate the E-Health data because of the high cost of the data on the dark web. Therefore, security assessment of healthcare web-based applications demands immediate intervention mechanisms to weed out the threats of cyber-attacks. The aim of this work is to provide efficient and effective healthcare web application security assessment. The study has worked with the hybrid computational model of Multi-Criteria Decision Making (MCDM) based on Analytical Hierarchy Process (AHP) and Technique for Order of Preference by Similarity to Ideal-Solutions (TOPSIS) under the Hesitant Fuzzy (HF) environment. Hesitant fuzzy sets provide effective solutions to address decision making problems where experts counter hesitation to make a decision. The proposed research endeavor will support designers and developers in identifying, selecting and prioritizing the best security attributes for web applications’ development. The empirical analysis concludes that Robustness got highest priority amongst the assessed security attributes set followed by Encryption, Authentication, Limit Access, Revoke Access, Data Validation, and Maintain Audit Trail. The results of this research endeavor depict that this proposed computational procedure would be the most conversant mechanism for determining the web application security. The study also establishes guidelines which the developers can refer for the identification and prioritization of security attributes to build more secure and trustworthy web-based applications.