Currently, most real-world time series datasets are multivariate and are rich in dynamical information of the underlying system. Such datasets are attracting much attention; therefore, the need for accurate modelling of such high-dimensional datasets is increasing. Recently, the deep architecture of the recurrent neural network (RNN) and its variant long short-term memory (LSTM) have been proven to be more accurate than traditional statistical methods in modelling time series data. Despite the reported advantages of the deep LSTM model, its performance in modelling multivariate time series (MTS) data has not been satisfactory, particularly when attempting to process highly non-linear and long-interval MTS datasets. The reason is that the supervised learning approach initializes the neurons randomly in such recurrent networks, disabling the neurons that ultimately must properly learn the latent features of the correlated variables included in the MTS dataset. In this paper, we propose a pre-trained LSTM-based stacked autoencoder (LSTM-SAE) approach in an unsupervised learning fashion to replace the random weight initialization strategy adopted in deep LSTM recurrent networks. For evaluation purposes, two different case studies that include real-world datasets are investigated, where the performance of the proposed approach compares favourably with the deep LSTM approach. In addition, the proposed approach outperforms several reference models investigating the same case studies. Overall, the experimental results clearly show that the unsupervised pre-training approach improves the performance of deep LSTM and leads to better and faster convergence than other models.

Food security has become an increasingly important challenge for all countries globally, particularly as the world population continues to grow and arable lands are diminishing due to urbanization. Water scarcity and lack of labor add extra negative influence on traditional agriculture and food production. The problem is getting worse in countries with arid lands and harsh climate, which exacerbates the food gap in these countries. Therefore, smart and practical solutions to promote cultivation and combat food production challenges are highly needed. As a controllable environment, greenhouses are the perfect environment to improve crops’ production and quality in harsh climate regions. Monitoring and controlling greenhouse microclimate is a real problem where growers have to deal with various parameters to ensure the optimal growth of crops. This paper shows our research in which we established a multi-tier cloud-based Internet of Things (IoT) platform to enhance the greenhouse microclimate. As a case study, we applied the IoT platform on cucumber cultivation in a soilless medium inside a commercial-sized greenhouse. The established platform connected all sensors, controllers, and actuators placed in the greenhouse to provide long-distance communication to monitor, control, and manage the greenhouse. The implemented platform increased the cucumber yield and enhanced its quality. Moreover, the platform improved water use efficiency and decreased consumption of electrical energy. Based on the positive impact on water use efficiency and enhancement on cucumber fruit yield and quality, the established platform seems quite suitable for the soilless greenhouse cultivation in arid regions.

Pattern classification represents a challenging problem in machine learning and data science research domains, especially when there is a limited availability of training samples. In recent years, artificial neural network (ANN) algorithms have demonstrated astonishing performance when compared to traditional generative and discriminative classification algorithms. However, due to the complexity of classical ANN architectures, ANNs are sometimes incapable of providing efficient solutions when addressing complex distribution problems. Motivated by the mathematical definition of a quantum bit (qubit), we propose a novel autonomous perceptron model (APM) that can solve the problem of the architecture complexity of traditional ANNs. APM is a nonlinear classification model that has a simple and fixed architecture inspired by the computational superposition power of the qubit. The proposed perceptron is able to construct the activation operators autonomously after a limited number of iterations. Several experiments using various datasets are conducted, where all the empirical results show the superiority of the proposed model as a classifier in terms of accuracy and computational time when it is compared with baseline classification models.

Future trends in climate change, water scarcity, and energy costs will motivate agriculturists to develop innovative agricultural systems. In order to achieve sustainable farming in arid regions, there is an urgent need to use artificial intelligence (AI) to predict and estimate the optimum water and energy requirements for the irrigation of date palms. Therefore, this study aimed to predict the optimum water and energy requirements for date palm irrigation depending on the optimum water use efficiency (WUE) and yield in arid conditions. To achieve this aim, four solar-powered micro irrigation systems were developed and evaluated under six irrigation levels for date palm irrigation. Soil moisture sensor-based controllers were used to automate irrigation scheduling for the micro irrigation systems. The water pumping in these systems was powered using a solar photovoltaic (PV) system. In addition, four machine-learning (ML) algorithms, including linear regression (LR), support vector regression (SVR), long short-term memory (LSTM) neural network, and extreme gradient boosting (XGBoost), were developed and validated for prediction purposes. These models were developed in Python programing language using the Keras library. The results indicated that the optimum WUS was achieved when the maximum setpoints of irrigation control were adjusted at the field capacity and by adjusting the minimum setpoints at 40, 50, 70, and 80% of the available water (AW). The optimum yield was achieved by adjusting the minimum setpoints at 60, 70, 80, and 90% of AW for subsurface irrigation, subsurface drip irrigation, drip irrigation, and bubbler irrigation, respectively. Therefore, the dataset was prepared at these levels for four years to train and test the models, and a fifth year was used to validate the performance of the best model. The evaluation of the models showed that the LSTM followed by XGBoost models were more accurate than the SVR and LR models for predicting the optimum irrigation water and energy requirements. The validation result showed that the LSTM was able to predict the water and energy requirements for all irrigation systems with R² ranging from 0.90 to 0.92 based on limited meteorological variables and date palm age. The findings of the current study demonstrated that the developed LSTM model can be a powerful tool in irrigation water and energy management as a fast and easy-to-use approach.

Emotion recognition in text is a fundamental task in natural language processing, underpinning applications such as sentiment analysis, mental health monitoring, and content moderation. Although transformer-based models like RoBERTa have advanced contextual understanding in text, they still face limitations in identifying subtle emotional cues, handling class imbalances, and processing noisy or informal input. To address these challenges, this paper introduces Emotion-Aware RoBERTa, an enhanced framework that integrates an Emotion-Specific Attention (ESA) layer and a TF-IDF based gating mechanism. These additions are designed to dynamically prioritize emotionally salient tokens while suppressing irrelevant content, thereby improving both classification accuracy and robustness. The model achieved 96.77% accuracy and a weighted F1-score of 0.97 on the primary dataset, outperforming baseline RoBERTa and other benchmark models such as DistilBERT and ALBERT with a relative improvement ranging from 9.68% to 10.87%. Its generalization capability was confirmed across two external datasets, achieving 88.03% on a large-scale corpus and 65.67% on a smaller, noisier dataset. An ablation study revealed the complementary impact of the ESA and TF-IDF components, balancing performance and inference efficiency. Attention heatmaps were used to visualize ESA’s ability to focus on key emotional expressions, while inference-time optimizations using FP16 and Automatic Mixed Precision (AMP) reduced memory consumption and latency. Additionally, McNemar’s statistical test confirmed the significance of the improvements over the baseline. These findings demonstrate that Emotion-Aware RoBERTa offers a scalable, interpretable, and deployment-friendly solution for fine-grained emotion recognition, making it well-suited for real-world NLP applications in emotion-aware systems.