Browsing by Author "Boulkamh Chouaib"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A Smart home energy management system using Iot and machine learning
    (Université de Larbi Ben M’hidi-Oum Oum El Bouaghi, 2021) Tobal Salim Ameur; Belala Yacine; Boulkamh Chouaib
    Internet of things or simply "IoT" is a system of interrelated computing devices that allow objects to connect to each other; Devices, machines, objects, even animals and people can be part of this system just by having a unique identifier and a way to transmit data throughout network without any manual intervention. Nowadays, IoT is invading many areas and has different domain of applications such as healthcare, smart city, security and automation. Smart home is a major application system and essential in automation. It's a really efficient way to ensure power saving, comfier life specially when it including energy management system This intelligent energy management software control system is designed to reduce energy consumption, improve the utilization of the system, increase reliability, predict electrical system performance, and optimize energy usage to reduce cost. This project has the aim of making a solution for energy consumption problem, by implementing software and a hardware solution throughout an IoT system. The first half consist of equipping the house with actuators and sensors that would do measure the power , and then the software solution consists cloud application that allows monitoring of the system and control the actuators and of course receiving consumption in real time with possibility of predicting future consumption This solution is based on Wi-Fi technology to permit access to data anytime anywhere in the world and also cloud computing technology for data processing and storage with machine learning.
  • No Thumbnail Available
    Item
    Optimization of hyperparameters of ANNs – application to the second Virial coefficient (B) of fluid mixtures
    (Université de Larbi Ben M’hidi-Oum Oum El Bouaghi, 2021) Houssam Ahmed; Amin Bahi; Boulkamh Chouaib
    Machine learning is without a doubt one of the most powerful technologies in today's world, and its use has spread to reach all application and all fields. In machine learning building a good model is crucial to find a solution to a given problem and since hyperparameters have an important influence on the performance of the machine learning model therefore we must choose wisely its hyperparameters configuration. This thesis defines the hyperparameter optimization problem and its challenges and studies the use of several hyperparameter optimization methods on the problem of the prediction of the B coefficient of organic and inorganic mixtures, reflecting the PVT (pressure, volume, temperature) behaviour of fluids, using the fluids' critical properties, acentric factors and dipole moments as inputs. Moreover, this thesis offer various experiments comparing the performances of ten hyperparameter optimization methods such as Grid search, Bayesian Optimization, Optuna, etc. In addition we implemented a GUI that eases the usage of these methods, which makes it very easy for the non-expert to exploit these methods with only a basic knowledge of machine learning. The results obtained in this work show that using hyperparameters optimization methods have a high value and quality to find good configuration for our model.