Occurrence of ochratoxigenic fungi and ochratoxin A in grapes from a Tunisian vineyard

The occurrence of ochratoxin A (OTA) and the identification of the ochratoxigenic microbiota in Tunisian grapes were studied for the first time. Black aspergilli were the dominant genus among the filamentous fungi isolated from grapes and were the only potential OTA-producing fungi found. The most abundant species were member of Aspergillus niger aggregate (63%) and Aspergillus carbonarius (36%). Uniseriate aspergilli were rarely present (1%). Of the A. carbonarius isolates, 97% were OTA positive but only 3% of the A. niger aggregate isolates were OTA positive. During grape maturation, the frequency of black aspergilli increased due to increase of the numbers of A. carbonarius. Musts (n=24) obtained from grapes collected at the different sampling times were analyzed for their OTA content. Up to 37% of the musts contained OTA at levels varying between 0.59 and 2.57 microg/l. The amounts of OTA in musts increased as grapes matured. These results indicate that A. carbonarius is the main cause of OTA contamination of Tunisian grapes.     

Artificial Intelligence Based Data Offloading Technique for Secure MEC Systems

Mobile edge computing (MEC) provides effective cloud services and functionality at the edge device, to improve the quality of service (QoS) of end users by offloading the high computation tasks. Currently, the introduction of deep learning (DL) and hardware technologies paves a method in detecting the current traffic status, data offloading, and cyberattacks in MEC. This study introduces an artificial intelligence with metaheuristic based data offloading technique for Secure MEC (AIMDO-SMEC) systems. The proposed AIMDO-SMEC technique incorporates an effective traffic prediction module using Siamese Neural Networks (SNN) to determine the traffic status in the MEC system. Also, an adaptive sampling cross entropy (ASCE) technique is utilized for data offloading in MEC systems. Moreover, the modified salp swarm algorithm (MSSA) with extreme gradient boosting (XGBoost) technique was implemented to identification and classification of cyberattack that exist in the MEC systems. For examining the enhanced outcomes of the AIMDO-SMEC technique, a comprehensive experimental analysis is carried out and the results demonstrated the enhanced outcomes of the AIMDO-SMEC technique with the minimal completion time of tasks (CTT) of 0.680.     

Energy-Efficient Routing Using Novel Optimization with Tabu Techniques for Wireless Sensor Network

Wireless Sensor Network (WSN) consists of a group of limited energy source sensors that are installed in a particular region to collect data from the environment. Designing the energy-efficient data collection methods in large-scale wireless sensor networks is considered to be a difficult area in the research. Sensor node clustering is a popular approach for WSN. Moreover, the sensor nodes are grouped to form clusters in a cluster-based WSN environment. The battery performance of the sensor nodes is likewise constrained. As a result, the energy efficiency of WSNs is critical. In specific, the energy usage is influenced by the loads on the sensor node as well as it ranges from the Base Station (BS). Therefore, energy efficiency and load balancing are very essential in WSN. In the proposed method, a novel Grey Wolf Improved Particle Swarm Optimization with Tabu Search Techniques (GW-IPSO-TS) was used. The selection of Cluster Heads (CHs) and routing path of every CH from the base station is enhanced by the proposed method. It provides the best routing path and increases the lifetime and energy efficiency of the network. End-to-end delay and packet loss rate have also been improved. The proposed GW-IPSO-TS method enhances the evaluation of alive nodes, dead nodes, network survival index, convergence rate, and standard deviation of sensor nodes. Compared to the existing algorithms, the proposed method outperforms better and improves the lifetime of the network.     

Automated Deep Learning Based Melanoma Detection and Classification Using Biomedical Dermoscopic Images

Melanoma remains a serious illness which is a common form of skin cancer. Since the earlier detection of melanoma reduces the mortality rate, it is essential to design reliable and automated disease diagnosis model using dermoscopic images. The recent advances in deep learning (DL) models find useful to examine the medical image and make proper decisions. In this study, an automated deep learning based melanoma detection and classification (ADL-MDC) model is presented. The goal of the ADL-MDC technique is to examine the dermoscopic images to determine the existence of melanoma. The ADL-MDC technique performs contrast enhancement and data augmentation at the initial stage. Besides, the k-means clustering technique is applied for the image segmentation process. In addition, Adagrad optimizer based Capsule Network (CapsNet) model is derived for effective feature extraction process. Lastly, crow search optimization (CSO) algorithm with sparse autoencoder (SAE) model is utilized for the melanoma classification process. The exploitation of the Adagrad and CSO algorithm helps to properly accomplish improved performance. A wide range of simulation analyses is carried out on benchmark datasets and the results are inspected under several aspects. The simulation results reported the enhanced performance of the ADL-MDC technique over the recent approaches.     

Artificial Fish Swarm Optimization with Deep Learning Enabled Opinion Mining Approach

Sentiment analysis or opinion mining (OM) concepts become familiar due to advances in networking technologies and social media. Recently, massive amount of text has been generated over Internet daily which makes the pattern recognition and decision making process difficult. Since OM find useful in business sectors to improve the quality of the product as well as services, machine learning (ML) and deep learning (DL) models can be considered into account. Besides, the hyperparameters involved in the DL models necessitate proper adjustment process to boost the classification process. Therefore, in this paper, a new Artificial Fish Swarm Optimization with Bidirectional Long Short Term Memory (AFSO-BLSTM) model has been developed for OM process. The major intention of the AFSO-BLSTM model is to effectively mine the opinions present in the textual data. In addition, the AFSO-BLSTM model undergoes pre-processing and TF-IFD based feature extraction process. Besides, BLSTM model is employed for the effectual detection and classification of opinions. Finally, the AFSO algorithm is utilized for effective hyperparameter adjustment process of the BLSTM model, shows the novelty of the work. A complete simulation study of the AFSO-BLSTM model is validated using benchmark dataset and the obtained experimental values revealed the high potential of the AFSO-BLSTM model on mining opinions.     

Automated Spam Review Detection Using Hybrid Deep Learning on Arabic Opinions

Online reviews regarding purchasing services or products offered are the main source of users’ opinions. To gain fame or profit, generally, spam reviews are written to demote or promote certain targeted products or services. This practice is called review spamming. During the last few years, various techniques have been recommended to solve the problem of spam reviews. Previous spam detection study focuses on English reviews, with a lesser interest in other languages. Spam review detection in Arabic online sources is an innovative topic despite the vast amount of data produced. Thus, this study develops an Automated Spam Review Detection using optimal Stacked Gated Recurrent Unit (SRD-OSGRU) on Arabic Opinion Text. The presented SRD-OSGRU model mainly intends to classify Arabic reviews into two classes: spam and truthful. Initially, the presented SRD-OSGRU model follows different levels of data preprocessing to convert the actual review data into a compatible format. Next, unigram and bigram feature extractors are utilized. The SGRU model is employed in this study to identify and classify Arabic spam reviews. Since the trial-and-error adjustment of hyperparameters is a tedious process, a white shark optimizer (WSO) is utilized, boosting the detection efficiency of the SGRU model. The experimental validation of the SRD-OSGRU model is assessed under two datasets, namely DOSC dataset. An extensive comparison study pointed out the enhanced performance of the SRD-OSGRU model over other recent approaches.     

Optimal Deep Convolutional Neural Network for Vehicle Detection in Remote Sensing Images

Object detection (OD) in remote sensing images (RSI) acts as a vital part in numerous civilian and military application areas, like urban planning, geographic information system (GIS), and search and rescue functions. Vehicle recognition from RSIs remained a challenging process because of the difficulty of background data and the redundancy of recognition regions. The latest advancements in deep learning (DL) approaches permit the design of effectual OD approaches. This study develops an Artificial Ecosystem Optimizer with Deep Convolutional Neural Network for Vehicle Detection (AEODCNN-VD) model on Remote Sensing Images. The proposed AEODCNN-VD model focuses on the identification of vehicles accurately and rapidly. To detect vehicles, the presented AEODCNN-VD model employs single shot detector (SSD) with Inception network as a baseline model. In addition, Multiway Feature Pyramid Network (MFPN) is used for handling objects of varying sizes in RSIs. The features from the Inception model are passed into the MFPN for multiway and multiscale feature fusion. Finally, the fused features are passed into bounding box and class prediction networks. For enhancing the detection efficiency of the AEODCNN-VD approach, AEO based hyperparameter optimizer is used, which is stimulated by the energy transfer strategies such as production, consumption, and decomposition in an ecosystem. The performance validation of the presented method on benchmark datasets showed promising performance over recent DL models.     

Thymoquinone Suppresses Angiogenesis in DEN-Induced Hepatocellular Carcinoma by Targeting miR-1-3p

Hepatocellular carcinoma (HCC) is characterized by its high vascularity and metastasis. Thymoquinone (TQ), the main bio-active constituent of Nigella sativa, has shown anticancer and hepatoprotective effects. TQ’s anticancer effect is mediated through miRNA regulation. miR-1-3p plays a significant role in various cancers but its role in HCC invasiveness remains poorly understood. Bio-informatics analysis predicted that the 3′-UTR of TIMP3 is a target for miR-1-3p; Rats were equally divided into four groups: Group 1, the negative control; Group 2 received TQ; Group 3 received DEN; and Group 4 received DEN after pretreatment with TQ. The expression of TIMP3, MMP2, MMP9, and VEGF in rats’ liver was determined immunohistochemically. RT-qPCR was used to measure the miR-1-3p level in rats’ liver, and TIMP3, MMP2, MMP9, and VEGF in the HepG2 cells after being transfected with miR-1-3p mimic or inhibitor; In rats pretreated with TQ, a decreased expression of MMP2, MMP9 and VEGF, and increased expression levels of TIMP3 and miR-1-3p were detected. Treating the HepG2 cells with miR-1-3p mimic led to the upregulation of TIMP3 and downregulation of MMP2, MMP9, and VEGF, and showed a significant delay in wound healing; These results suggested that the anti-angiogenic effect of TQ in HCC may be mediated through the regulation of miR-1-3p.     

Ochratoxin A and ochratoxigenic black Aspergillus species in Tunisian grapes cultivated in different geographic areas

This paper summarizes the results of a large study on the occurrence of ochratoxigenic fungi and Ochratoxin A from wine and table grapes in Tunisia. Our results revealed that Aspergillus section Nigri were the unique potential OTA producing fungi isolated from grapes. Isolates belonging to Aspergillus niger aggregate were the most abundant species followed by Aspergillus carbonarius isolates, then uniseriate aspergilli. A. carbonarius presented the highest percentage of OTA-positive strains (97%) whereas only 3% of A. niger aggregate isolates were OTA positive. Grapes were analysed for their OTA content and 58% of them contained detectable levels of OTA, between 0.05 and 5.85 μg/l. Only 4 samples out of 39 exceeded the OTA limit of 2 μg/l fixed by the EU for wine and grape juices. The most contaminated grapes were those from Raf-Raf region located in the North-Est and characterized by a humid climate. Grapes from the Regueb region, characterized by an arid climate, were rarely contaminated. Furthermore, A. carbonarius, which is the main OTA producer fungi on grapes, was rarely isolated in Regueb.     

Investigations on the leaf anatomy and ultrastructure of grapevine (Vitis vinifera) under heat stress

Leaf anatomical and ultrastructural responses of "Razegui" and "Muscat Italia" grapevine cultivars to high temperatures were studied under controlled conditions (T > 36°C), based on photonic and electron microscopy. Histological studies performed on leaves from heat-stressed and control grapevines revealed thicker leaf blades under high temperature conditions. Environmental scanning electron microscopy of leaf surfaces from both cultivars allowed observing sinuate epidermal cells on the leaves of grapevines cultivated under heat stress and irregular giant oblong pores on their adaxial surface. When observed by transmission electron microscopy, leaf cross sections in grapevines cultivated under high temperature conditions exhibited folded cuticle and cell wall on the adaxial epidermis layer. Therefore, significantly greater cell wall thicknesses were measured under heat stress than control conditions in both cultivars. Regarding chloroplasts, they were more globular in shape under heat stress compared with control conditions and had disorganized thylakoids with a reduced thickness of grana stacking. The size of starch granule decreased, while the number of plastoglobules increased with heat stress, indicating a reduced carbon metabolism and a beginning of senescence within the 3-month heat stress period. This study confirms widespread adaptive properties in two grapevine cultivars in response to high temperature stress.