Detection of Black Hole attacks is one of the most challenging and critical routing security issues in vehicular ad hoc networks (VANETs) and autonomous and connected vehicles (ACVs). Malicious vehicles or nodes may exist in the cyber-physical path on which the data and control packets have to be routed converting a secure and reliable route into a compromised one. However, instead of passing packets to a neighbouring node, malicious nodes bypass them and drop any data packets that could contain emergency alarms. We introduce an intelligent black hole attack detection scheme (IDBA) tailored to ACV. We consider four key parameters in the design of the scheme, namely, Hop Count, Destination Sequence Number, Packet Delivery Ratio (PDR), and End-to-End delay (E2E). We tested the performance of our IDBA against AODV with Black Hole (BAODV), Intrusion Detection System (IdsAODV), and EAODV algorithms. Extensive simulation results show that our IDBA outperforms existing approaches in terms of PDR, E2E, Routing Overhead, Packet Loss Rate, and Throughput.

No abstract

Production of different processed cheese sauces using corn starch (CS)and sodium alginate (SA) or guar gum (GG) as thickening agents were successfully achieved. Thus, 6 treatments were manufactured containing the combination: 1 : 1 means 1.5 % corn starch + 0.25 % (guar gum or sodium alginate), 2 : 1 means 2.0 % corn starch + 0.16 % (guar gum or sodium alginate) and 1 : 2 means 1.0 % corn starch + 0.33 % (guar gum or sodium alginate). Processed cheese sauce blends were adjusted to contain 25 % dry matter, 40 % F / DM in the finished product of processed cheese sauce.There were a slight and non-significant differences in the pH values, and the average of all treatments was 5.82. Addition of corn starch and sodium alginate or guar gum mixtures in the processed cheese sauces formulas was of different effects on the oil separation index values of the resultant processed cheese sauces with sodium alginate or even with guar gum.The differences in viscosity values among treatments with different stabilizing mixtures could be due to difference in the ability of each stabilizer to bind water. All of the resultant cheese sauces were evaluated when fresh for chemical composition. Treatments were also examined for pH, SN, oil separation index, viscosity and sensory properties, when fresh and after 1 & 3 months of storage either at (5 ± 2 ºC) or at (25 ± 2 ºC). Three replicates were carried out for each treatment, and the data obtained were statistically analyzed at p ≤ 0.05.

BACKGROUND Contact tracing has been globally adopted in the fight to control the infection rate of COVID-19. Thanks to digital technologies, such as smartphones and wearable devices, contacts of COVID-19 patients can be easily traced and informed about their potential exposure to the virus. To this aim, several interesting mobile applications have been developed. However, there are ever-growing concerns over the working mechanism and performance of these applications. The literature already provides some interesting exploratory studies on the community’s response to the applications by analyzing information from different sources, such as news and users’ reviews of the applications. However, to the best of our knowledge, there is no existing solution that automatically analyzes users’ reviews and extracts the evoked sentiments. OBJECTIVE In this paper, we analyze how AI models can help in automatically extract and classify the polarity of users’ sentiments and propose a sentiment analysis framework to automatically analyze users’ reviews on COVID-19 contact tracing mobile applications. METHODS we propose a pipeline starting from manual annotation via a crowd-sourcing study and concluding on the development and training of AI models for automatic sentiment analysis of users’ reviews. In detail, we collected and annotated a large-scale dataset of Android and iOS mobile application users’ reviews for COVID-19 contact tracing. After manually analyzing and annotating users’ reviews, we employed both classical (i.e., Naïve Bayes, SVM, Random Forest) and deep learning (i.e., fastText, and different transformers) methods for classification experiments. This resulted in eight different classification models. RESULTS We employed eight different methods on three different tasks achieving up to an average F1-Scores 94.8% indicating the feasibility of automatic sentiment analysis of users’ reviews on the COVID-19 contact tracing applications. Moreover, the crowd-sourcing activity resulted in a large-scale benchmark dataset composed of 34,534 reviews manually annotated from the contract tracing applications of 46 distinct countries. CONCLUSIONS The existing literature mostly relies on the manual/exploratory analysis of users’ reviews on the application, which is a tedious and time-consuming process. Moreover, in the existing studies, generally, data from fewer applications are analyzed. In this work, we showed that automatic sentiment analysis can help in analyzing users’ responses to the application more quickly with significant accuracy. Moreover, we also provided a large-scale benchmark dataset composed of 34,534 reviews from 47 different applications. We believe the presented analysis and the dataset will support future research on the topic.

No abstract

The paper presents our proposed solutions for the MediaEval 2020 Flood-Related Multimedia Task, which aims to analyze and detect flooding events in multimedia content shared over Twitter. In total, we proposed four different solutions including a multi-modal solution combining textual and visual information for the mandatory run, and three single modal image and text-based solutions as optional runs. In the multi-modal method, we rely on a supervised multimodal bitransformer model that combines textual and visual features in an early fusion, achieving a micro F1-score of .859 on the development data set. For the text-based flood events detection, we use a transformer network (i.e., pretrained Italian BERT model) achieving an F1-score of .853. For image-based solutions, we employed multiple deep models, pre-trained on both, the Ima-geNet and places data sets, individually and combined in an early fusion achieving F1-scores of .816 and .805 on the development set, respectively.

No abstract

No abstract