This paper proposes a learning approach for dynamic parameterization of ant colony optimization algorithms. In fact, the specific optimal configuration for each optimization problem using these algorithms, whether at the level of preferences, the level of evaporation of the pheromone, or the number of ants, makes the dynamic approach an interested one. The new idea suggests the addition of a knowledge center shared by the colony members, combining the optimal evaluation of the configuration parameters proposed by the colony members during the experiments. This evaluation is based on qualitative criteria explained in detail in the article. Our approach indicates an evolution in the quality of the results over the course of the experiments and consequently the approval of the concept of machine learning.

This paper aims to implement Fuzzy Logic for cost prediction. Fuzzy Logic using Tsukamoto Model and Sugeno Model. Predicted costs consist of communication cost, transportation cost, and social cost as the external cost. The external cost is one component of living cost. High external cost becomes one of the causes of the high cost of living. The high cost of living is one of the factors causing high-cost economy. In this case, the cost prediction using Fuzzy Logic. Experimental results show that Fuzzy Logic using Tsukamoto Model with value is 1891. Fuzzy Logic using Sugeno Model with value 1621. Both models produce a feasible cost prediction. Feasible is meaning accurate and proper (value cost between low cost and high cost from all of cost). There are 46.56 % of the population of middle class in Indonesia. This means that 46.56% of the population of Indonesia has the potential to reduce the high cost economy. High cost economy (living cost) can be reduced, it can drive economic growth (social cost) and be able to improve social welfare (social cost).

The paper deals with the problem of estimating the execution time of firmware. Any firmware is bound to wait for a response from peripheral devices such as external memory chips, displays, analog-to-digital converters, etc. The firmware’s execution is frozen until the expected response is obtained. Thus, any firmware’s execution time depends not only on the computational resources of the embedded system being inspected but also on peripheral devices each of which is able to perform a set of operations during some random time period residing, however, within a known interval. The paper introduces a model of a computer application for evaluation of microcontroller-based embedded systems’ firmware’s execution time that takes into consideration the type of the microcontroller, the total duration of all the assembler-like instructions for a specific microcontroller, all the occasions of waiting for a response from hardware components, and the possible time periods for all the responses being waited for. Besides, we proposed the architecture of the computer application that assumes a reusable database retaining data on microcontrollers’ instructions.

As the global demand for electricity is growing continuously, the sources use more fossil fuels to generate electricity which in turn increases the level of carbon dioxide in the atmosphere. Moreover the electrical system becomes unreliable during the peak hours if the demand for electricity is very high. So there is a need to have a grid system which can handle these cases in a smarter way. A Smart Grid is such an electrical grid system which can control and manage electricity demand in a more reliable and economic manner using various energy efficient resources and a variety of operational measures like smart meters, smart appliances and smart communication system. The smart grid uses a technique called energy demand management at consumer side which motivates the consumers to control and reduce their demand for energy during peak hours. This makes the whole system more reliable and efficient. The demand side management (DSM) includes various methods such as increasing awareness among the consumers and giving them some financial incentives which can encourage them to be a part of the DSM program. In this paper a novel Demand Side Management technique has been proposed for a typical smart grid scenario which comprises users with energy storage devices using a metaheuristic approach to have an optimal load scheduling that results in reduced peak hour demands.

The Internet of Things (IoT) has extended the internet connectivity to reach not just computers and humans, but most of our environment things. The IoT has the potential to connect billions of objects simultaneously which has the impact of improving information sharing needs that result in improving our life. Although the IoT benefits are unlimited, there are many challenges facing adopting the IoT in the real world due to its centralized server/client model. For instance, scalability and security issues that arise due to the excessive numbers of IoT objects in the network. The server/client model requires all devices to be connected and authenticated through the server, which creates a single point of failure. Therefore, moving the IoT system into the decentralized path may be the right decision. One of the popular decentralization systems is blockchain. The Blockchain is a powerful technology that decentralizes computation and management processes which can solve many of IoT issues, especially security. This paper provides an overview of the integration of the blockchain with the IoT with highlighting the integration benefits and challenges. The future research directions of blockchain with IoT are also discussed. We conclude that the combination of blockchain and IoT can provide a powerful approach which can significantly pave the way for new business models and distributed applications.

Matrix multiplication is widely used in a variety of applications and is often one of the core components of many scientific computations. This paper will examine three algorithms to compute the product of two matrices: the Naive, Strassen’s and Winograd’s algorithms. One of the main factors of determining the efficiency of an algorithm is the execution time factor, how much time the algorithm takes to accomplish its work. All the three algorithms will be implemented and the execution time will be calculated and we find that Winograd’s algorithm is the best and fast method experimentally for finding matrix multiplication. Deep Neural Networks are used for many applications. Training a Deep Neural Network is a time consuming process, especially when the number of hidden layers and nodes is large. The mechanism of Backpropagation Algorithm and Boltzmann Machine Algorithm for training a Deep Neural Network is revisited and considered how the sum of weighted input is computed. The process of computing the sum of product of weight and input matrices is carried out for several hundreds of thousands of epochs during the training of Deep Neural Network. We propose to modify Backpropagation Algorithm and Boltzmann Machine Algorithm by using fast Winograd’s algorithm. Finally, we find that the proposed methods reduce the long training time of Deep Neural Network than existing direct methods.

Most design optimization problems in engineering are in general extremely nonlinear and deal with various design variables under complex restrictions. Traditional mathematical optimization procedure may fail to find the optimum solution to real-world problems. Evolutionary Algorithms (EAs) can serve as an efficient approach for these types of optimization problems. In this paper, Particle Swarm Optimization (PSO), Differential Evolution (DE) and Cuckoo Search (CS) algorithms are used to find the optimal solution for some typical unimodal and multimodal benchmark functions. The source codes of all these algorithms are developed using C language and tested on a core i5, 2.4 GHz processor with 8 GB internal RAM. PSO algorithm has a simplicity of implementation and good convergence speed. In contrast, CS algorithm has good ability to find a global optimum solution. To use the advantages of CS and PSO algorithms, a hybrid algorithm of CS and PSO (CSPSO) is implemented and tested with the same benchmark functions. The experimental simulation results obtained by all these algorithms show that hybrid CSPSO outperforms with PSO, DE and CS algorithms.

Soft computing is used to solve the problems where input data is incomplete or imprecise. This paper demonstrate designing fully connected neural network system using four different weight calculation algorithms. Input data for weight calculation is constructed in the matrix format based on the pairwise comparison of input constraints. This comparison is performed using saaty’s method. This input matrix helps to build judgment between several individuals, forming a single judgment. Algorithm considered here are Geometric average mean, Linear algebra calculation, Successive matrix squaring method, and analytical hierarchical processing method. Based on the quality parameter of performance, it is observed that analytical hierarchical processing is the most promising mathematical method for finding appropriate weight. Analytical hierarchical processing works on structuration of the problem into sub problems, Hence it the most prominent method for weight calculation in fully connected NN.