http://hdl.handle.net/10366/138329 Thu, 30 Apr 2026 19:33:29 GMT 2026-04-30T19:33:29Z http://hdl.handle.net/10366/141450 Sat, 15 Dec 2018 00:00:00 GMT http://hdl.handle.net/10366/141450 2018-12-15T00:00:00Z http://hdl.handle.net/10366/141449 This article presents the development of a multi-agent system in charge of self-managing a delivery system. The article focuses on the delivery management system and not on the movement systems of the different used vehicles./nThis system consists of different types of vehicles, each with different characteristics, and there may be several instances of each type of vehicle. There will be three operating agents (Drone Operator, Car Operator and Amphibious Operator), an agent that will be responsible for creating random tasks (used only in simulations) and another one that is responsible for distributing these tasks to the operators taking into account the algorithm. This algorithm follows the bases of backtracking and its main function is to assign a task to a vehicle taking into account the distance, the consumption, the limitations of weight and distances, etc. The whole system has been developed in JADE on java. The described software performs a complete simulation with a console in which it is indicated relevant information such as the tasks that are created, the type of vehicle and the instance of that type of vehicle that resolve the delivery, among others. The purpose of this system is to minimize costs and times. Sat, 15 Dec 2018 00:00:00 GMT http://hdl.handle.net/10366/141449 2018-12-15T00:00:00Z http://hdl.handle.net/10366/141448 Two problems related to complex network systems are explained in this paper. These two main problems are: consensus and network synchronization. Both have been studied separately in previous years but only a few people have studied these two problems together as one. Our intention in this article is to show how these two problems might ‘work’ together by simulating a network system with routers and agents, we will try to show how agents must negotiate and communicate in order to achieve their aim. Sat, 15 Dec 2018 00:00:00 GMT http://hdl.handle.net/10366/141448 2018-12-15T00:00:00Z http://hdl.handle.net/10366/141447 Reaching agreement by consensus is fundamental to the operation of distributed systems, such as sensor networks, social networks or multi-robot networks. In real systems, the resource limitations available to individual agents and communication delays typically result in asynchronous control models of discreet time for consensus. In this paper, we model the problem where a set of agents arrive at a consensus on the value of a variable of interest, being guided by one of them. Sat, 15 Dec 2018 00:00:00 GMT http://hdl.handle.net/10366/141447 2018-12-15T00:00:00Z http://hdl.handle.net/10366/141445 A multi-agent systems is described that analyzes texts from two points of view: on the one hand in a lexical and on the other in a semantic way. The main purpose of the system is the efficient processing of the inputted text in order to analyzing it, and as a result, outputting it in the right way. That means that after analyzing each phrase of the imputed text, the main agent will delete each wrong phrase. Agents will exchange messages trying to stably which phrase is correct or incorrect. The system will not only remove wrong phrases, it will also make a list with all the removed ones and the reasons that made the main agent discard them so the person that inputted the text can know why those phrases were in a wrong way. Sat, 15 Dec 2018 00:00:00 GMT http://hdl.handle.net/10366/141445 2018-12-15T00:00:00Z http://hdl.handle.net/10366/141446 Crowd evacuation has attracted great attention, the number of emergencies continues to increase. Thanks to the technology, it is possible to deduce the behavior of the crowd in emergencies, improving security. The multitude enters into a state of panic, so it is necessary to have action protocols for these situations. This work tries to establish a multi-agent model of emotional contagion that simulates the behavior of the crowd in an evacuation. The method is proposed for closed areas such as supermarkets, stadiums, soccer, stadiums, etc. The emotional contagion will accelerate the evacuation, but the congestion will occur if the panic emotion is spread too fast. Sat, 15 Dec 2018 00:00:00 GMT http://hdl.handle.net/10366/141446 2018-12-15T00:00:00Z http://hdl.handle.net/10366/141444 The task of creating algorithms to solve a problem is surely a hard thing as it can be the fact of evaluating them. A well designed algorithm can be very powerful but, it may lack of efficiency at some aspects. This paper proposes a multi-agent system based game with three types of agents: CBot, ABot and QBot, which stands for Coordinator, Answer and Question. They will play a game based on questions and answers, where each of the QBots uses a different algorithm to guess a word. The CBot has the responsibility of the efficiency measurements, receiving and manipulating the ABot reports. The game will finish once all QBots give the correct answer and after that, the efficiency of the algorithms thanks to the CBot. Using this method, it is easier to determine which algorithm is the best with a given performance measurement. Sat, 15 Dec 2018 00:00:00 GMT http://hdl.handle.net/10366/141444 2018-12-15T00:00:00Z http://hdl.handle.net/10366/141443 E-Learning is a new learning approach that involves the use of electronic technologies to access education outside of a conventional classroom (Alonso Rincon,). The objective of E-Learning systems is to increase the students’ learning skills by providing a customized experience to each system user (Rodrigues, 2013). However, to accomplish this, it is necessary to monitor the continuous changes in the environment, mainly the students’ knowledge and skill acquisition. A multi-agent system architecture and a clustering algorithm are proposed for this purpose (as presented in (Rodrigues, 2014) This paper is an extension to the work of (Al-Tarabily, 2018) because it not only monitors changes in the student environment but also in the project environment, increasing the system’s adaptability and accuracy. Sat, 15 Dec 2018 00:00:00 GMT http://hdl.handle.net/10366/141443 2018-12-15T00:00:00Z http://hdl.handle.net/10366/141442 Sat, 15 Dec 2018 00:00:00 GMT http://hdl.handle.net/10366/141442 2018-12-15T00:00:00Z http://hdl.handle.net/10366/139230 Sun, 30 Sep 2018 00:00:00 GMT http://hdl.handle.net/10366/139230 2018-09-30T00:00:00Z http://hdl.handle.net/10366/139229 Evolutionary Algorithms are bio-inspired optimization problem-solving approaches that exploit principles of biological evolution. , such as natural selection and genetic inheritance. This review paper provides the application of evolutionary and swarms intelligence based query optimization strategies in Distributed Database Systems. The query optimization in a distributed environment is challenging task and hard problem. However, Evolutionary approaches are promising for the optimization problems. The problem of query optimization in a distributed database environment is one of the complex problems. There are several techniques which exist and are being used for query optimization in a distributed database. The intention of this research is to focus on how bio-inspired computational algorithms are used in a distributed database environment for query optimization. This paper provides working of bio-inspired computational algorithms in distributed database query optimization which includes genetic algorithms, ant colony algorithm, particle swarm optimization and Memetic Algorithms. Fri, 21 Sep 2018 00:00:00 GMT http://hdl.handle.net/10366/139229 2018-09-21T00:00:00Z http://hdl.handle.net/10366/139228 This paper builds a data mining tool via a classification method using Multi-Layer Perceptron (MLP) with Backpropagation learning method and an algorithm of feature selection along with biomedical testing values for diagnosing heart disease. Addition to that, developing a prototype for heart disease diagnosing with a friendly-user graphical interface (GUI). The purpose to construct this software is that; clinical prosopopoeia is done in any event by doctor’s experience. Despite that, some cases are reported negative diagnosis and treatment; therefore, patients are asked to take a number of tests for diagnosis. Moreover, not all the tests contribute towards an effective diagnosis of a disease, and by using data mining approach to diagnose heart disease that supports the doctors to make more efficient and subtle decisions. Fri, 21 Sep 2018 00:00:00 GMT http://hdl.handle.net/10366/139228 2018-09-21T00:00:00Z http://hdl.handle.net/10366/139227 The semantic gap is distinguished by the difference between two descriptions generated using different representations. This difference has a negative impact on the developer productivity and probably, the quality of the written code. In software development context, the coding phase aims at coding the system consistent with the detailed project developed with a group of designed models. This paper presents an endeavor to consolidate different agent type definitions and implementation concepts for Multi-Agent Systems (MAS) involving the adaptation of the JADE framework regarding the theoretical concepts in MAS. Additionally, it contains a standardization of code generation. The main benefit of the proposed extension is to include the agent internal architectures, entities and relationships in an implementation framework and increase the productivity by code generation, ensuring the consistency between design and code. The applicability of the extension is illustrated by developing a multi-agent system for Moodle. Fri, 21 Sep 2018 00:00:00 GMT http://hdl.handle.net/10366/139227 2018-09-21T00:00:00Z http://hdl.handle.net/10366/139226 Handwritten character recognition is a challenging problem which received attention because of its potential benefits in real-life applications. It automates manual paper work, thus saving both time and money, but due to low recognition accuracy it is not yet practically possible. This work achieves higher recognition rates for handwritten isolated characters using Deep learning based Convolutional neural network (CNN). The architecture of these networks is complex and plays important role in success of character recognizer, thus this work experiments on different CNN architectures, investigates different optimization algorithms and trainable parameters. The experiments are conducted on two different types of grayscale datasets to make this work more generic and robust. One of the CNN architecture in combination with adadelta optimization achieved a recognition rate of 97.95%. The experimental results demonstrate that CNN based end-to-end learning achieves recognition rates much better than the traditional techniques. Fri, 21 Sep 2018 00:00:00 GMT http://hdl.handle.net/10366/139226 2018-09-21T00:00:00Z http://hdl.handle.net/10366/139225 Software development advances focus on productivity of existing software systems and quality is the basic demand of every engineering product. In this paper, we will discuss the complete re-engineering process with aspects of forwarding, reverse and quality assurance mechanism. As we know the software development lifecycle (SDLC) follows a complete mechanism of the engineering process. In forward engineering, we tried to follow selective main phases of software engineering(data,requirements, design, development, implementation).In reverse engineering, we move backward from the last phase of developing the product as it gathers requirements from the implemented product(implementation, coding, design, requirements, data). During reengineering, we add up more quality features on customer demands, but the actual demand is to fulfill quality needs that can be assured by external as well as internal quality attributes such as reliability, efficiency, flexibility, reusability, and robustness in any software system. We discussed a methodological approach to move from re-engineering to the journey of quality assurance. More than 50 studies come into discussion and throughput results proposed by graph and tabular form. We can say if the re-engineering process produces quality attributes, then it can be said by old software system refactoring as code refactoring, data refactoring and architectural refactoring we obtained a quality product at a lower cost instead of new software system development, which causes a decrease in quality attributes as cost, time etc. In future work, testing methodology can be proposed for quality assurance. Thu, 13 Sep 2018 00:00:00 GMT http://hdl.handle.net/10366/139225 2018-09-13T00:00:00Z http://hdl.handle.net/10366/139224 Finding the diameter of a dataset in multidimensional Euclidean space is a well-established problem, with well-known algorithms. However, most of the algorithms found in the literature do not scale well with large values of data dimension, so the time complexity grows exponentially in most cases, which makes these algorithms impractical. Therefore, we implemented 4 simple greedy algorithms to be used for approximating the diameter of a multidimensional dataset; these are based on minimum/maximum l2 norms, hill climbing search, Tabu search and Beam search approaches, respectively. The time complexity of the implemented algorithms is near-linear, as they scale near-linearly with data size and its dimensions. The results of the experiments (conducted on different machine learning data sets) prove the efficiency of the implemented algorithms and can therefore be recommended for finding the diameter to be used by different machine learning applications when needed. Thu, 13 Sep 2018 00:00:00 GMT http://hdl.handle.net/10366/139224 2018-09-13T00:00:00Z