<span id="docs-internal-guid-345787a5-7fff-6d93-73dd-f99a81d82f61"><span>The massive network traffic data between connected devices in the internet of things have taken a big challenge to many traditional intrusion detection systems (IDS) to find probable security breaches. However, security attacks lean towards unpredictability. There are numerous difficulties to build up adaptable and powerful IDS for IoT in order to avoid false alerts and ensure a high recognition precision against attacks, especially with the rising of Botnet attacks. These attacks can even make harmless devices becoming zombies that send malicious traffic and disturb the network. In this paper, we propose a new IDS solution, baptized BotIDS, based on deep learning convolutional neural networks (CNN). The main interest of this work is to design, implement and test our IDS against some well-known Botnet attacks using a specific Bot-IoT dataset. Compared to other deep learning techniques, such as simple RNN, LSTM and GRU, the obtained results of our BotIDS are promising with 99.94% in validation accuracy, 0.58% in validation loss, and the prediction execution time is less than 0.34 ms.</span></span>

Sentiment analysis (SA) is widely used today in many areas such as crime detection (security intelligence) to detect potential security threats in realtime using social media platforms such as Twitter. The most promising techniques in sentiment analysis are those of deep learning (DL), particularly bidirectional encoder representations from transformers (BERT) in the field of natural language processing (NLP). However, employing the BERT algorithm to detect crimes requires a crime dataset labeled by the lexiconbased approach. In this paper, we used a hybrid approach that combines both lexicon-based and deep learning, with BERT as the DL model. We employed the lexicon-based approach to label our Twitter dataset with a set of normal and crime-related lexicons; then, we used the obtained labeled dataset to train our BERT model. The experimental results show that our hybrid technique outperforms existing approaches in several metrics, with 94.91% and 94.92% in accuracy and F1-score respectively.

No abstract

<span lang="EN-US">The impact of wildfires, even following the fire's extinguishment, continues to affect harmfully public health and prosperity. Wildfires are becoming increasingly frequent and severe, and make the world's biodiversity in a growing serious danger. The fires are responsible for negative economic consequences for individuals, corporations, and authorities. Researchers are developing new approaches for detecting and monitoring wildfires, that make use of advances in computer vision, machine learning, and remote sensing technologies. IoT sensors help to improve the efficiency of detecting active forest fires. In this paper, we propose a novel approach for predicting wildfires, based on machine learning. It uses a regression model that we train over NASA's fire information for resource management system (FIRMS) dataset to predict fire radiant power in megawatts. The analysis of the obtained simulation results (more than 99% in the R2 metric) shows that the ensemble learning model is an effective method for predicting wildfires using an IoT device equipped with several sensors that could potentially collect the same data as the FIRMS dataset, such as smart cameras or drones.</span>

Deep learning (DL) approaches use various processing layers to learn hierarchical representations of data. Recently, many methods and designs of natural language processing (NLP) models have shown significant development, especially in text mining and analysis. For learning vector-space representations of text, there are famous models like Word2vec, GloVe, and fastText. In fact, NLP took a big step forward when BERT and recently GTP-3 came out. In this paper, we highlight the most important language representation learning models in NLP and provide an insight of their evolution. We also summarize, compare and contrast these different models on sentiment analysis, and thus discuss their main strengths and limitations. Our obtained results show that BERT is the best language representation learning model.