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...     

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.     

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.     

Effect of gamma irradiation and sulphitation treatments on keeping quality of white button mushroom Agaricus bisporus (J. Lge)

Gamma irradiation, alone and in combination with sulphitation, was tested for preventing the browning and maintaining the quality attributes of the white button mushrooms. Mushrooms were subjected to treatment of gamma irradiation in the dose range of 0.5–2.0 kGy and to combination treatments of sulphitation at a concentration of 0.1% potassium metabisulphite (KMS) and gamma irradiation (dose range 0.5–2.0 kGy) followed by storage at 10 ± 2 °C (RH 85%). A dose of 2.0 kGy significantly reduced the weight loss, prevented browning and mould growth. Cap and veil opening of mushrooms was delayed by 9 days and shelf life was extended by 12 days at a dose level of 2.0 kGy. Sulphitation alone at a concentration of 0.1% KMS was effective in controlling browning only upto 3 days, beyond which both browning and cap opening increased significantly ( P  ≤ 0.05) and the samples were unacceptable after 6 days of storage. No synergistic effect of sulphitation and irradiation was observed with respect to the shelf-life extension of mushroom.     

An overview of smart packaging technologies for monitoring safety and quality of meat and meat products

The food packaging sector has experienced much development since its inception. In the past few decades, innovations in packaging sector have led to the development of smart packaging (SP) systems that carve a niche in a highly competitive food industry. SP systems have great potential for improving the shelf‐life, and safety of food products apart from their basic roles of protecting the products against unwanted biological, chemical, and physical damage and keeping them clean. Indicators and sensors, SP components, are used for real‐time monitoring of meat quality and subsequently inform the retailers and consumers about the freshness, microbiological, temperature, and shelf life status of the products. Barcodes and radio‐frequency identification tags are employed in meat packaging for real‐time information about the authenticity, and traceability of the products in the supply chain. Recently, innovations in SP technologies resulted in fast, sensitive, and effective detection, sensing, and record keeping of freshness, microbiological, and shelf life status of meat and meat products. The SP system shows promise for extensive utilization in the meat industry in response to the consumer appreciation for safe, and quality meat products, as well as their waste reduction notions. This paper gives an updated overview of ongoing scientific research, and recent technological advances that offer the perspectives of developing smart meat packaging systems that are capable of monitoring the physical, microbial, and chemical changes of the package contents from producer to the point of sale and even beyond, and remediating potential adverse reactions.     

Protein Engineering Strategies for Improved Pharmacokinetics

Protein therapeutics have gained momentum in recent years and become a pillar in treating many diseases and the only choice in several ailments. Protein therapeutics are highly specific, tunable, and less toxic than conventional small drug molecules. However, reaping the full benefits of therapeutic proteins in the clinics is often hindered by issues of immunogenicity and short half-life due essentially to fast renal clearance and enzymatic degradation. Advances in polymer chemistry and protein engineering allowed overcoming some of these limitations. Strategies to prolong the half-life of proteins rely on increasing their size and stability and/or fusing them to endogenous proteins (albumin, Fc fragment of antibody) to hijack physiological pathways involved in protein recycling. On the downside, these modifications might alter therapeutic proteins structure and function. Therefore, a compromise between half-life and activity is sought. This review covers half-life extension strategies using natural and synthetic polymers as well as fusion to other proteins and sheds light on genetic engineering strategies and chemical and enzymatic reactions to achieve this goal. Promising strategies and successful applications in the clinics are highlighted.     

Centralized dynamic frequency allocation for cell-edge demand satisfaction in fractional frequency reuse networks

Fractional frequency reuse (FFR) has emerged as a well-suited remedy for inter-cell interference reduction in the next-generation networks by allocating frequency reuse factor (FRF) of unity for the cell-center (CC) and higher FRF for the cell-edge (CE) users. However, this strict FFR comes at a cost of equal partitioning of frequency resources to the CE which most likely has varying demands in current networks. In order to mitigate this, we propose a centralized dynamic resource allocation scheme which allocates demand-dependent resources to CE users. The proposed scheme therefore outperforms the fixed allocation scheme of strict FFR for both CC and CE users. Complexity analysis provides a fair means of analyzing the suitability of proposed algorithm. We have also compared the proposed methodology with a reference dynamic fractional frequency reuse (DFFR) scheme. Results show maximum performance gain of up to 30% for 3 reference cells employing Rayleigh fading—through normalized area spectral efficiency (ASE) analysis for both fixed allocation and DFFR. Spectral efficiency analysis also indicates per-cell performance gain for both CC and CE users. Further, detailed three-dimensional ASE plots give insights into the affects to other cells. Due to dynamic nature of traffic loads, the proposed scheme is a candidate solution for satisfying the demands of individual cells.     

A Statistical Approach for Biogenic Synthesis of Nano-Silica from Different Agro-Wastes

Silicon - Biogenic silica is an excellent alternative to synthetic silica because of its capricious configuration, density, composition, less toxicity, environmentally friendly synthesis and...