Author name cluster

Aomar Osmani

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

ECAI Conference 2024 Conference Paper

Enhancing Decision-Making in Energy Management Systems Through Action-Independent Dynamics Learning

Théo Zangato
Aomar Osmani
Pegah Alizadeh

Incorporating auxiliary objectives into Reinforcement Learning allows agents to acquire additional knowledge, thereby increasing their search for the optimal policy. This article presents the Model-Predictor Proximal Policy Optimization (MP-PPO) algorithm, which merges the concepts of various PPO variants with a Transformer probabilistic prediction module. This model capitalizes on the time dependence inherent in energy management systems, predicting future state transitions by learning to predict certain state characteristics. Notably, our algorithm seamlessly integrates this predictive capability into the Actor-Critic architecture, avoiding the need for an external model. Through experiments on real data, we demonstrate that integrating predictive capabilities for partial state prediction improves both the sample effectiveness and efficiency of the original PPO approach without requiring exterior prior information.

Details

AAAI Conference 2022 Conference Paper

Clustering Approach to Solve Hierarchical Classification Problem Complexity

Aomar Osmani
Massinissa Hamidi
Pegah Alizadeh

In a large domain of classification problems for real applications, like human activity recognition, separable spaces between groups of concepts are easier to learn than each concept alone. This is because the search space biases required to separate groups of classes (or concepts) are more relevant than the ones needed to separate classes individually. For example, it is easier to learn the activities related to the body movements group (running, walking) versus ”on-wheels” activities group (bicycling, driving a car), before learning more specific classes inside each of these groups. Despite the obvious interest of this approach, our theoretical analysis shows a high complexity for finding an exact solution. We propose in this paper an original approach based on the association of clustering and classification approaches to overcome this limitation. We propose a better approach to learn the concepts by grouping classes recursively rather than learning them class by class. We introduce an effective greedy algorithm and two theoretical measures, namely cohesion and dispersion, to evaluate the connection between the clusters and the classes. Extensive experiments on the SHL dataset show that our approach improves classification performances while reducing the number of instances used to learn each concept.

PDF Details

AAAI Conference 2021 Conference Paper

Augmented Experiment in Material Engineering Using Machine Learning

Aomar Osmani
Massinissa Hamidi
Salah Bouhouche

The synthesis of materials using the principle of thermogravimetric analysis to discover new anticorrosive paints requires several costly experiments. This paper presents an approach combining empirical data and domain analytical models to reduce the number of real experiments required to obtain the desired synthesis. The main idea is to predict the behavior of the synthesis of two materials with well-defined mass proportions as a function of temperature. As no exact equational model exists to predict the new material, we integrate a machine learning approach circumscribed by existing domain analytical models such as heating equation in order to derive a generative model of augmented experiments. Extensive empirical evaluation shows that using machine learning approach guided by analytic models, it is possible to substantially reduce the number of needed physical experiments without losing the approximation quality. 1

PDF Details

IJCAI Conference 2019 Conference Paper

Monitoring of a Dynamic System Based on Autoencoders

Aomar Osmani
Massinissa Hamidi
Salah Bouhouche

Monitoring industrial infrastructures are undergoing a critical transformation with industry 4. 0. Monitoring solutions must follow the system behavior in real time and must adapt to its continuous change. We propose in this paper an autoencoder model-based approach for tracking abnormalities in industrial application. A set of sensors collects data from turbo-compressors and an original two-level machine learning LSTM autoencoder architecture defines a continuous nominal vibration model. Normalized thresholds (ISO 20816) between the model and the system generates a possible abnormal situation to diagnose. Experimental results, including hyper-parameter optimization on large real data and domain expert analysis, show that our proposed solution gives promising results.

PDF Details

AAAI Conference 2000 Short Paper

Model-Based-Diagnosis for Fault Management in Telecommunications Networks

Aomar Osmani

We propose in this paper a model-based approach to diagnose fault situations in greatest French telecommunication networks: TRANSPAC. This approach is based on two steps: (1) Off-line step: The first step to studying faults management is to build a model. This construction is done using two abstraction levels: structural abstraction where components of the network are modeled by temporal graph and behavioral model where each component is modeled by temporal and communicating finite state machines. When the model is built, single and multiple faults are simulated in the model. Corresponding to the two level abstraction We have proposed two kind of algorithm: propagating algorithm associated to the structural level and deducting algorithm associated to the behavioral level. At the end of simulation a learning database of fault situationsis built. This database is used by discrimination module to classify given fault in the space of sequences of alarms; (2) On-line step: the expert system generated by the off-line step is used to recognize on-fly fault situations from the stream of alarms arriving at the supervisor.

PDF Details