GIS Based Multi-Criteria decision support system and machine learning for Hospital Site Selection case study Oran - Algeria

The selection of hospital sites is one of the most important choice a decision maker has to take so as to resist the pandemic. The decision may considerably affect the outbreak transmission in terms of efficiency , budget, etc. The main targeted objective of this study is to find the ideal location where to set up a hospital in the willaya of Oran Alg. For this reason, we have used a geographic information system coupled to the multi-criteria analysis method AHP in order to evaluate diverse criteria of physiological positioning , environmental and economical. Another objective of this study is to evaluate the advanced techniques of the automatic learning . the method of the random forest (RF) for the patterning of the hospital site selection in the willaya of Oran. The result of our study may be useful to decision makers to know the suitability of the sites as it provides a high level of confidence and consequently accelerate the power to control the COVID19 pandemic.

Essential Oil Steam Distillation: Manufacturing 4.0

Smart sensors, self-configuration, operational flexibility, and automatic learning, among others, are technological attributes from industry 4.0 appliable to the essential oil extraction by the steam distillation process. These operations are recognized by their simplicity. Nevertheless, lack of automatic controls, process monitoring, and self-adjustment lead to uncontrolled extraction, poor yields, low quality of products. It occurs because of overexposure to high temperatures and overspending resources like energy and water. As far as capacity utilization is concerned, the optimized process is key to planning and managing the production activities.

A Feature-Independent Hyper-Heuristic Approach for Solving the Knapsack Problem

Recent years have witnessed a growing interest in automatic learning mechanisms and applications. The concept of hyper-heuristics, algorithms that either select among existing algorithms or generate new ones, holds high relevance in this matter. Current research suggests that, under certain circumstances, hyper-heuristics outperform single heuristics when evaluated in isolation. When hyper-heuristics are selected among existing algorithms, they map problem states into suitable solvers. Unfortunately, identifying the features that accurately describe the problem state—and thus allow for a proper mapping—requires plenty of domain-specific knowledge, which is not always available. This work proposes a simple yet effective hyper-heuristic model that does not rely on problem features to produce such a mapping. The model defines a fixed sequence of heuristics that improves the solving process of knapsack problems. This research comprises an analysis of feature-independent hyper-heuristic performance under different learning conditions and different problem sets.

Hierarchical Temporal Memory Theory Approach to Stock Market Time Series Forecasting

Over the years, and with the emergence of various technological innovations, the relevance of automatic learning methods has increased exponentially, and they now play a key role in society. More specifically, Deep Learning (DL), with the ability to recognize audio, image, and time series predictions, has helped to solve various types of problems. This paper aims to introduce a new theory, Hierarchical Temporal Memory (HTM), that applies to stock market prediction. HTM is based on the biological functions of the brain as well as its learning mechanism. The results are of significant relevance and show a low percentage of errors in the predictions made over time. It can be noted that the learning curve of the algorithm is fast, identifying trends in the stock market for all seven data universes using the same network. Although the algorithm suffered at the time a pandemic was declared, it was able to adapt and return to good predictions. HTM proved to be a good continuous learning method for predicting time series datasets.

A Markov-Based Intrusion Tolerance Finite Automaton

It is inevitable for networks to be invaded during operation. The intrusion tolerance technology comes into being to enable invaded networks to provide the necessary network services. This paper introduces an automatic learning mechanism of the intrusion tolerance system to update network security strategy, and derives an intrusion tolerance finite automaton model from an existing intrusion tolerance model. The proposed model was quantified by the Markov theory to compute the stable probability of each state. The calculated stable probabilities provide the theoretical guidance and basis for administrators to better safeguard network security. Verification results show that it is feasible, effective, and convenient to integrate the Markov model to the intrusion tolerance finite automaton.