Accurate assessment of crop nutritional status is critical for effective farm management, affecting both environmental sustainability and economic viability. Nitrogen, an essential nutrient for plant growth, is critical in detecting crop health and making fertilization decisions. However, standard nitrogen level estimation methods frequently include labor-intensive and environmentally dangerous laboratory analyses. In response, this study investigates the possibilities of modern technologies, notably machine learning (ML) and remote sensing, for improving nitrogen estimate in crops. Remote sensing, which uses sensors mounted on satellites, drones, or other airborne platforms, provides a non-destructive and efficient alternative to traditional methods for obtaining extensive spectral data. Machine learning techniques improve upon this approach by processing massive amounts of data to uncover significant patterns and relationships. Although previous studies have primarily relied on vegetation indices generated from spectral observations, this study provides an alternate technique. By auto-encoding raw spectral data, machine-learned features are developed as an alternative to vegetation indices, providing a new perspective on leaf nitrogen content (LNC) estimation. To test performance, a number of machine learning algorithms are examined, including random forest, support vector machines, and extreme gradient boosting. Our findings suggest that the autoencoder-based methodology outperforms established methods, highlighting its potential for reshaping nitrogen estimate in agriculture.

Wasteful irrigation systems are significant contributors to water scarcity on the globe. Irrigation Scheduling based on Machine Learning (ML) algorithms is considered essential in helping reduce these wastes significantly. We conducted in this study a systematic mapping of ML-based Irrigation scheduling to identify how researchers approached Irrigation Scheduling and which ML models have been used in this area. It builds a comprehensive overview of what has been investigated on irrigation scheduling and discusses the open issues to be addressed in the future.

Welcome to the 19th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA'2022), organized from December 5-7, 2022 in Zayed University- Abu Dhabi, United Arab Emirates (UAE). As co-chairs of the Program Committee (PC), we are delighted to introduce this year's technical program and proceedings of AICCSA'2022.

Smart irrigation has many advantages in optimizing resource usage (e.g., saving water, reducing energy consumption) and improving crop productivity. In this paper, we contribute to this field by proposing a robust and accurate machine learning-based approach that combines the power of feature selection methods and stacking ensemble method to effectively determine the optimal quantity of water needed for a plant. Random Forest, Recursive Feature Elimination (RFE), and SelectKBest are used to assess the importance of the features. Then, based on the best subset of features, a stacking ensemble model is proposed that combines CART, Gradient Boost Regression (GBR), Random Forest (RF) and XGBoost regressors. The different models involved in this approach are trained and tested using a collected dataset about various crops such as tomatoes, grapes, and lemon and encompasses different features such as meteorological data, soil data, irrigation data, and crop data. The experiments demonstrated the performance of RF in analyzing the feature importance. The findings of feature selection highlight the importance level of the evapotranspiration, the depletion, and the deficit to maximize the model’s accuracy. The results also showed that the proposed stacking model (Stacking_GBR+CART+RF+XGB) with the 10 most essential features outperforms individual models and other stacking models by achieving low error rates (i.e., MSE=0.0026, MAE=0.0279, RMSE=0.0509) and high R2score (i.e., 0.9927).

As cloud services are reaching a considerable maturity level, several academics and researchers are exploiting this paradigm to benefit from its advantages. More specifically, with SaaS services' advent, a tremendous number of enterprises rely on their composition as an alternative to their Information Technology infrastructure. While composing SaaS services, achieving the Business Process (BP) goals and objectives through this cloud model is becoming easier and even beneficial; composing multiple SaaS services to support the BP execution is not a trivial practice regarding the complex nature of the BP. Indeed, BP is composed of a set of activities with various functional requirements, data that should be exchanged between each SaaS service, and roles imposing that only authorized actors can perform a specific activity. This paper proposes a comprehensive framework for business process-based SaaS composition that covers the semantic matching between BP activities and SaaS labels and the allocation of BP activities to SaaS services using a genetic algorithm while considering the data and the activities access control issues.

A cloud service is usually classified as Infrastructure as a Service, Platform as a Service or Software as a Service. This classification is not sufficient, when Business Processes are considered. Therefore, the next level of abstraction above SaaS is Business Process as a Service (BPaaS) [1]. BPaaS runs in a dynamic and volatile environment such as cloud computing and has hence very changing QoS (Quality of Service) parameters. Therefore, the BPaaS monitoring and adaptation are of a great importance to guarantee the QoS parameters defined in the Service Level Agreement (SLA). To address these issues, in this paper we proposed two Fuzzy systems for self-adaptive BPaaS that aim to prevent the SLA violations. The proposed approach objective is to satisfy two important issues: (i) the selection of service adaptation strategies and (ii) the cost as well as the impact of changes. We also presented the results of the experiments achieved to evaluate the proposed approach. These experimental results prove the effectiveness of the fuzzy systems.

The efficient monitoring of Cloud infrastructure is a topic that is currently attracting significant interest. Understanding the behaviour of the variety of monitoring tools and how to manage them optimally are challenging tasks. Monitoring tools and techniques have an important role to play in this area by gathering the information required to make informed decisions. Surveying these monitoring tools can identify the fitness of these tools in serving certain objectives for both Cloud providers and consumers in different Cloud operational areas.

Cloud computing is increasingly being used to deliver infrastructure, platform and/or software as services over the Internet. The resulting Cloud-based services with various types create complex management situations at the Cloud provider side. In particular, face to a large and dynamic number of service loads, a Cloud provider needs a means to maintain QoS (Quality of Service) levels it has agreed-upon with its customers. To properly operate and manage such complex situations, an effective and efficient monitoring is necessary. Most of the monitoring propositions are for the infrastructure and platform layers. This paper presents a multi tenant framework for QoS Monitoring and Detection of SLA Violations (QMoDeSV) for composite services implemented as BPEL (Business Process Execution Language) processes and deployed in a Cloud environment. It presents the complete design of QMoDeSV and a preliminary experimental evaluation of its performance.