Hyperspectral imaging-based unsupervised adulterated red chili content transformation for classification: Identification of red chili adulterants

Neural Computing and Applications - Preserving red-chili quality is of utmost importance in which the authorities demand quality techniques to detect, classify, and prevent it from impurities. For...     

Gurum Seeds: A Potential Source of Edible Oil

Cucurbitaceae family seeds are mostly discarded as agro-industrial wastes. Gurum (Citrullus lanatus var. colocynthoide) is an underutilized wild cucurbit plant, closely related to desert watermelon, which is grown abundantly in some African countries. Gurum seeds can play a significant role in health and nutrition due to their high oil content. This review describes the nutritional composition of gurum seeds and their oil profile. Gurum seeds are a good source of oil (27–35.5%), fiber (26–31%), crude protein (15–18%), and carbohydrates (14–17%). Gurum seeds oil is extracted by supercritical CO₂ (SFE), screw press, and solvent extraction techniques. The gurum seeds oil is composed of unsaturated fatty acids with a high proportion of linoleic acid (C18:2) and oleic acid (C18:1). Gurum seeds oil contains various bioactive compounds, such as tocopherols, phytosterols, and polyphenols. It is reported that solvent extraction gives a higher yield than the screw press and SFE, but the SFE is preferred due to safety issues. More studies are required for producing better quality gurum seeds oil by using novel extraction techniques that can increase oil yield.     

An open-source multi-DOF articulated robotic educational platform for autonomous object manipulation

This research presents an autonomous robotic framework for academic, vocational and training purpose. The platform is centred on a 6 Degree Of Freedom (DOF) serial robotic arm. The kinematic and dynamic models of the robot have been derived to facilitate controller design. An on-board camera to scan the arm workspace permits autonomous applications development. The sensory system consists of position feedback from each joint of the robot and a force sensor mounted at the arm gripper. External devices can be interfaced with the platform through digital and analog I/O ports of the robot controller. To enhance the learning outcome for beginners, higher level commands have been provided. Advanced users can tailor the platform by exploiting the open-source custom-developed hardware and software architectures. The efficacy of the proposed platform has been demonstrated by implementing two experiments; autonomous sorting of objects and controller design. The proposed platform finds its potential to teach technical courses (like Robotics, Control, Electronics, Image-processing and Computer vision) and to implement and validate advanced algorithms for object manipulation and grasping, trajectory generation, path planning, etc. It can also be employed in an industrial environment to test various strategies prior to their execution on actual manipulators.     

A review on microwell and microfluidic geometric array fabrication techniques and its potential applications in cellular studies

The ability to trap precise quantities of cells or particles into confined areas has numerous applications for biological purposes. In particular, single cell trapping has received considerable attention because it permits the study of heterogeneity in a population, while trapping larger groups of cells have been used to form aggregates. Among several methods, the use of microwell offers a simple platform to capture cells or particles using hydrodynamic forces. This review examines the use of microwells in both static and microfluidic environments, and the application of microfluidic geometric arrays for trapping. This paper discusses the design and fabrication methods of microwells and compares the trapping and release techniques used in both static and microfluidics‐integrated microwells. Finally, we will summarize novel microfluidic geometric arrays used to capture cells or particles through hydrodynamic trapping.     

WiMA: Towards a Multi-Criterion Association in Software Defined Wi-Fi Networks

Despite the planned installation and operations of the traditional IEEE 802.11 networks, they still experience degraded performance due to the number of inefficiencies. One of the main reasons is the received signal strength indicator (RSSI) association problem, in which the user remains connected to the access point (AP) unless the RSSI becomes too weak. In this paper, we propose a multi-criterion association (WiMA) scheme based on software defined networking (SDN) in Wi-Fi networks. An association solution based on multi-criterion such as AP load, RSSI, and channel occupancy is proposed to satisfy the quality of service (QoS). SDN having an overall view of the network takes the association and reassociation decisions making the handoffs smooth in throughput performance. To implement WiMA extensive simulations runs are carried out on Mininet-NS3-Wi-Fi network simulator. The performance evaluation shows that the WiMA significantly reduces the average number of retransmissions by 5%–30% and enhances the throughput by 20%–50%, hence maintaining user fairness and accommodating more wireless devices and traffic load in the network, when compared to traditional client-driven (CD) approach and state of the art Wi-Balance approach.     

Dance performance evaluation using hidden Markov models

We present in this paper a hidden Markov model‐based system for real‐time gesture recognition and performance evaluation. The system decodes performed gestures and outputs at the end of a recognized gesture, a likelihood value that is transformed into a score. This score is used to evaluate a performance comparing to a reference one. For the learning procedure, a set of relational features has been extracted from high‐precision motion capture system and used to train hidden Markov models. At runtime, a low‐cost sensor (Microsoft Kinect) is used to capture a learner's movements. An intermediate step of model adaptation was hence requested to allow recognizing gestures captured by this low‐cost sensor. We present one application of this gesture evaluation system in the context of traditional dance basics learning. The estimation of the log‐likelihood allows giving a feedback to the learner as a score related to his performance. Copyright © 2016 John Wiley & Sons, Ltd.     

Process Optimization and Characterization of Popped Brown Rice

The popping process was optimized for brown rice based on an expansion ratio. A central composite design with interactive effect of three independent variables, including salt content (1–2.5 g/100 g raw material), moisture content (13–17 g/100 g raw material), and popping temperature (210–240°C) was used to study their effects on the expansion ratio of rice using response surface methodology. The experimental values of expansion ratio were ranged from 5.24 to 6.85. On fitting the experimental values of expansion ratio to a second order polynomial equation, a mathematical model with the predictability was developed with the statistical adequacy and validity (p ? 0.05). From the model, the optimal condition including salt content (1.75 g/100 g raw material), moisture content (15 g/100 g raw material), and popping temperature (225°C) were predicted for a maximum expansion ratio of 6.79, which was then proved to be 6.85 through experiment. Raw and popped brown rice were investigated for physical properties including hardness, L*, a*, and b* value, length/breadth ratio, bulk density, and minerals, which showed the significant differences. The optimized popped rice sample was evaluated for structural, spectroscopic, and thermal properties, which showed the significant difference from raw rice.     

Detection of COVID-19 from chest X-ray images: Boosting the performance with convolutional neural network and transfer learning

Coronavirus disease (COVID-19) is a pandemic that has caused thousands of casualties and impacts all over the world. Most countries are facing a shortage of COVID-19 test kits in hospitals due to the daily increase in the number of cases. Early detection of COVID-19 can protect people from severe infection. Unfortunately, COVID-19 can be misdiagnosed as pneumonia or other illness and can lead to patient death. Therefore, in order to avoid the spread of COVID-19 among the population, it is necessary to implement an automated early diagnostic system as a rapid alternative diagnostic system. Several researchers have done very well in detecting COVID-19; however, most of them have lower accuracy and overfitting issues that make early screening of COVID-19 difficult. Transfer learning is the most successful technique to solve this problem with higher accuracy. In this paper, we studied the feasibility of applying transfer learning and added our own classifier to automatically classify COVID-19 because transfer learning is very suitable for medical imaging due to the limited availability of data. In this work, we proposed a CNN model based on deep transfer learning technique using six different pre-trained architectures, including VGG16, DenseNet201, MobileNetV2, ResNet50, Xception, and EfficientNetB0. A total of 3886 chest X-rays (1200 cases of COVID-19, 1341 healthy and 1345 cases of viral pneumonia) were used to study the effectiveness of the proposed CNN model. A comparative analysis of the proposed CNN models using three classes of chest X-ray datasets was carried out in order to find the most suitable model. Experimental results show that the proposed CNN model based on VGG16 was able to accurately diagnose COVID-19 patients with 97.84% accuracy, 97.90% precision, 97.89% sensitivity, and 97.89% of F1-score. Evaluation of the test data shows that the proposed model produces the highest accuracy among CNNs and seems to be the most suitable choice for COVID-19 classification. We believe that in this pandemic situation, this model will support healthcare professionals in improving patient screening.     

Genomics and Epigenomics of Gestational Diabetes Mellitus: Understanding the Molecular Pathways of the Disease Pathogenesis

One of the most common complications during pregnancy is gestational diabetes mellitus (GDM), hyperglycemia that occurs for the first time during pregnancy. The condition is multifactorial, caused by an interaction between genetic, epigenetic, and environmental factors. However, the underlying mechanisms responsible for its pathogenesis remain elusive. Moreover, in contrast to several common metabolic disorders, molecular research in GDM is lagging. It is important to recognize that GDM is still commonly diagnosed during the second trimester of pregnancy using the oral glucose tolerance test (OGGT), at a time when both a fetal and maternal pathophysiology is already present, demonstrating the increased blood glucose levels associated with exacerbated insulin resistance. Therefore, early detection of metabolic changes and associated epigenetic and genetic factors that can lead to an improved prediction of adverse pregnancy outcomes and future cardio-metabolic pathologies in GDM women and their children is imperative. Several genomic and epigenetic approaches have been used to identify the genes, genetic variants, metabolic pathways, and epigenetic modifications involved in GDM to determine its etiology. In this article, we explore these factors as well as how their functional effects may contribute to immediate and future pathologies in women with GDM and their offspring from birth to adulthood. We also discuss how these approaches contribute to the changes in different molecular pathways that contribute to the GDM pathogenesis, with a special focus on the development of insulin resistance.