Offensive content on social media such as verbal attacks, demeaning comments or hate speech has many negative effects on its users. The automatic detection of offensive language on Arabic social media is an important step towards the regulation of such content for Arabic speaking users of social media. This paper presents the results of evaluating the performance of four different neural network architectures for this task: Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (Bi-LSTM), Bi-LSTM with attention mechanism, and a combined CNN-LSTM architecture. These networks are trained and tested on a labeled dataset of Arabic YouTube comments. We run this dataset through a series of pre-processing steps and use Arabic word embeddings to represent the comments. We also apply Bayesian optimization techniques to tune the hyperparameters of the neural network models. We train and test each network using 5-fold cross validation. The CNN-LSTM achieves the highest recall (83.46%), followed by the CNN (82.24%), the Bi-LSTM with attention (81.51%) and the Bi-LSTM (80.97%).

The escalating global water usage and the increasing strain on major cities due to water shortages highlights the critical need for efficient water management practices. In water-stressed regions worldwide, significant water wastage is primarily attributed to leakages, inefficient use, and aging infrastructure. Undetected water leakages in buildings’ pipelines contribute to the water waste problem. To address this issue, an effective water leak detection method is required. In this paper, we explore the application of edge computing in smart buildings to enhance water management. By integrating sensors and embedded Machine Learning models, known as TinyML, smart water management systems can collect real-time data, analyze it, and make accurate decisions for efficient water utilization. The transition to TinyML enables faster and more cost-effective local decision-making, reducing the dependence on centralized entities. In this work, we propose a solution that can be adapted for effective leakage detection in real-world scenarios with minimum human intervention using TinyML. We follow an approach that is similar to a typical machine learning lifecycle in production, spanning stages including data collection, training, hyperparameter tuning, offline evaluation and model optimization for on-device resource efficiency before deployment. In this work, we considered an existing water leakage acoustic dataset for polyvinyl chloride pipelines. To prepare the acoustic data for analysis, we performed preprocessing to transform it into scalograms. We devised a water leak detection method by applying transfer learning to five distinct Convolutional Neural Network (CNN) variants, which are namely EfficientNet, ResNet, AlexNet, MobileNet V1, and MobileNet V2. The CNN models were found to be able to detect leakages where a maximum testing accuracy, recall, precision, and F1 score of 97.45%, 98.57%, 96.70%, and 97.63%, respectively, were observed using the EfficientNet model. To enable seamless deployment on the Arduino Nano 33 BLE edge device, the EfficientNet model is compressed using quantization resulting in a low inference time of 1932 ms, a peak RAM usage of 255.3 kilobytes, and a flash usage requirement of merely 48.7 kilobytes.

One of the major problems confronted in precision agriculture is uncertainty about how exactly would yield in a certain area respond to decreased application of certain nutrients. One way to deal with this type of uncertainty is the use of scenarios as a method to explore future projections from current objectives and constraints. In the absence of data, soft computing techniques can be used as effective semi-quantitative methods to produce scenario simulations, based on a consistent set of conditions. In this work, we propose a dynamic rule-based Fuzzy Cognitive Map variant to perform simulations, where the novelty resides in an enhanced forward inference algorithm with reasoning that is characterized by magnitudes of change and effects. The proposed method leverages expert knowledge to provide an estimation of crop yield, and hence it can enable farmers to gain insights about how yield varies across a field, so they can determine how to adapt fertilizer application accordingly. It allows also producing simulations that can be used by managers to identify effects of increasing or decreasing fertilizers on yield, and hence it can facilitate the adoption of precision agriculture regulations by farmers. We present an illustrative example to predict cotton yield change, as a response to stimulated management options using proactive scenarios, based on decreasing Phosphorus, Potassium and Nitrogen. The results of the case study revealed that decreasing the three nutrients by half does not decrease yield by more than 10%.

The aim of this work is to propose a new river water quality index using fuzzy logic. The proposed fuzzy index combines quality indicators’ prescribed thresholds extracted mainly from the Moroccan and the Quebec water legislations. The latter is reputed for its strict water quality assessment. The proposed index combines six indicators, and not only does it exhibit a tool that accounts for the discrepancy between the two base indices, but also provides a quantifiable score for the determined water quality. These classifications with a membership grade can be of a sound support for decision-making, and can help assign each section of a river a gradual quality sub-objective to be reached.