فهرست مطالب seyyed mohammad r. hashemi

In the domain of financial forecasting, machine learning (ML) models have garnered significant attention in recent years. One prominent application lies in the cryptocurrency market, where intelligent trading bots facilitate a substantial portion of daily transactions.

This paper investigates the efficacy of ML-based methods for identifying optimal trade entry points. Specifically, we employ the Relative Strength Index (RSI) and Simple Moving Average (SMA) indicators to extract a set of trend and crossover features. Subsequently, these features are utilized to train multilayer neural network, support vector machine, and nearest neighbor learning models. The performance of each model is then evaluated using digital currency market data encompassing the first seven months of 2023 for a variety of cryptocurrencies.

Our findings demonstrate that, firstly, the extracted features exhibit promising efficacy. Secondly, the nearest neighbor model achieved the highest profitability during the evaluation period compared to the other investigated models.

In the research conducted in this field, technical indicators are often used directly in market forecasting but in the proposed method of this article, instead of directly using the values of the indicators as the input of the classification methods, trend behaviors and their intersections have been used. In the continuation of this research, it is possible to determine the best exit points from the transaction with the help of machine learning and the use of volume indicators in the learning process.

Smart buildings equipped with communication and control infrastructure offer the potential to optimize energy management, leading to increased productivity and significant cost reductions. These buildings typically consist of multiple residential units with common electrical appliances like washing machines and TVs. The energy management system must not only supply electrical needs but also provide thermal energy for heating and sanitation. Modern smart buildings often integrate various energy sources like photovoltaic systems, combined heat and power (CHP) units, boilers, alongside electrical and thermal storage devices. A key challenge in this field is the coordinated management of both thermal and electrical energy to minimize building operating costs. This paper proposes a comprehensive model for this purpose.

The model's convexity allows for finding the global optimal solution using the YALMIP toolbox and mathematical solvers like CPLEX. To validate the model, a simulated smart building was created in MATLAB, where the proposed model was solved with two particle swarm algorithms and YALMIP.

To validate the model, a simulated smart building was created in MATLAB, where the proposed model was solved with two particle swarm algorithms and YALMIP. The results demonstrate the superiority of YALMIP in finding the optimal solution.

The energy management system must not only supply electrical needs but also provide thermal energy for heating and sanitation. Modern smart buildings often integrate various energy sources like photovoltaic systems, combined heat and power (CHP) units, boilers, alongside electrical and thermal storage devices. A key challenge in this field is the coordinated management of both thermal and electrical energy to minimize building operating costs. This paper proposes a comprehensive model for this purpose. The model considers flexible scheduling of electrical equipment like vacuum cleaners, along with the operation of the boiler, CHP unit, and storage devices, all aimed at minimizing energy costs. The model ensures that all photovoltaic system output is consumed within the building, and all thermal and electrical demands are met efficiently without load shedding. The model's convexity allows for finding the global optimal solution using the YALMIP toolbox and mathematical solvers like CPLEX. To validate the model, a simulated smart building was created in MATLAB, where the proposed model was solved with two particle swarm algorithms and YALMIP. The results demonstrate the superiority of YALMIP in finding the optimal solution.