Статьи журнала - International Journal of Modern Education and Computer Science
Все статьи: 1080
Deep Learning CNN–LSTM Hybrid Approach for Arabic Sentiment Analysis Using Word Embedding Models
Статья научная
In recent years, the widespread use of social networks has empowered online users to freely share their opinions on diverse aspects of life. Sentiment Analysis (SA) has consequently emerged as a pivotal domain within Natural Language Processing (NLP), serving a crucial role in discerning sentiment orientations and extracting valuable insights from public viewpoints. Analyzing sentiment in Arabic poses distinctive challenges due to its varied dialects, as well as its intricate morphological and syntactic structures. Deep Learning (DL) models, particularly Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNNs), have exhibited remarkable proficiency in Sentiment Analysis. LSTM networks excel in capturing sequential data patterns, while CNNs offer inherent advantages in feature selection, yielding superior performance compared to conventional machine learning (ML) algorithms. In our study, we propose an ensemble approach that integrates CNN and LSTM techniques to classify and forecast sentiment in tweets. We evaluate the effectiveness of this hybrid model against individual LSTM and CNN methodologies employing the FastText word embedding model. Experimental findings illustrate that our LSTM-CNN hybrid approach, leveraging the FastText word embedding model, significantly improves text classification accuracy.
Бесплатно
Статья научная
Emotion recognition is a significant research topic for interactive intelligence system with the wide range of applications in different tasks, like education, social media analysis, and customer service. It is the process of perceiving user's emotional response automatically to the multimedia information by means of implicit explanation. With initiation of speech recognition and the computer vision, research on emotion recognition with speech and facial expression modality has gained more popularity in recent decades. Due to non-linear polarity of signals, emotion recognition results a challenging task. To achieve facial emotion recognition using multimodal signals, an effective Bat Rider Optimization Algorithm (BROA)-based deep learning method is proposed in this research. However, the proposed optimization algorithm named BROA is derived by integrating Bat Algorithm (BA) with Rider Optimization Algorithm (ROA), respectively. Here, the multimodal signals include face image, EEG signals, and physiological signals such that the features extracted from these modalities are employed for the process of emotion recognition. The proposed method achieves better performance against exiting methods by acquiring maximum accuracy of 0.8794, and minimum FAR and minimum FRR of 0.1757 and 0.1806.
Бесплатно
Defect Management in Agile Software Development
Статья научная
Agile development reduces the risk of developing low quality software in the first place by minimizing defects. In agile software development formal defect management processes help to build quality software. The core purpose of defect management is to make the software more effective and efficient in order to increase its quality. There are several methods for handling defects like defect prevention, defect discovery and resolution which are used by software developers and testers. Refactoring keeps the system clean by identifying and removing quality defects. To gain the full confidence of the customer defect management should be involved at every stage of development. Agile methodologies focus on delivering the software in form of short iterations. Thus each iteration helps to overcome defects and leads better development and end user satisfaction. This study paints the picture of handling the software defects using agile based Software Development Process.
Бесплатно
Definition Synthesis of Agility in Software Development: Comprehensive Review of Theory to Practice
Статья научная
Software development agility has been regarded as a critical pillar of modern businesses. However, there is still a way to find whether there exists a consistent, complete, precise, agreed and uniformed definition of it. In this regard, this study firstly reviews the existing definitions of agility in the software development domain from the literature. As one of the main results of this phase, we have seen that although agility has a remarkable root in the software development domain, even its definition is still debatable and there are other concepts close to agility in terms of definition but used interchangeably. There is another confusion about how some researchers define agility over other different concepts, although there is no apparent unifying factor in their origins except their historical co-occurrence. In addition, there are particular practices embedded into the agility definitions mostly from the manifesto and Scrum. After uncovering the deficiencies of the existing definitions, we aimed to ratify the definition of the agility concept. Then, we intended to synthesize the underlying facets of the identified definitions and propose a new yet more comprehensive definition revealing the agility characteristics properly by considering the interpretations of the existing definitions. Our study stands out by using a customized synthesis method for analysis, providing inputs to this analysis with a comprehensive literature review, and the comprehensive evaluation of the facets with the support of the literature. We are aware that agreeing on a definition is a valuable exercise and a good starting point for a better understanding of the agility phenomenon that could enable and lead to more realistic implementations, less disappointment and disillusionment, and possibly greater success rates for both practitioners and researchers.
Бесплатно
Density-Based LLE Algorithm for Network Forensics Data
Статья научная
In a network forensic system, there are huge amounts of data that should be processed, and the data contains redundant and noisy features causing slow training and testing processes, high resource consumption as well as poor detection rate. In this paper, a schema is proposed to reduce the data of the forensics using manifold learning. Manifold learning is a popular recent approach to nonlinear dimensionality reduction. Algorithms for this task are based on the idea that the dimensionality of many data sets is only artificially high. In this paper, we reduce the forensic data with manifold learning, and test the result of the reduced data.
Бесплатно
Статья научная
Now-a-days hundreds of millions of people of almost all levels of education and attitudes from different country communicate with each other for different purposes and perform their jobs on internet or other communication medium using various languages. Not all people know all language; therefore it is very difficult to communicate or works on various languages. In this situation the computer scientist introduce various inter language translation program (Machine translation). UNL is such kind of inter language translation program. One of the major problem of UNL is identified a name from a sentence, which is relatively simple in English language, because such entities start with a capital letter. In Bangla we do not have concept of small or capital letters. Thus we find difficulties in understanding whether a word is a proper noun or not. Here we have proposed analysis rules to identify proper noun from a sentence and established post converter which translate the name entity from Bangla to UNL. The goal is to make possible Bangla sentence conversion to UNL and vice versa. UNL system prove that the theoretical analysis of our proposed system able to identify proper noun from Bangla sentence and produce relative Universal word for UNL.
Бесплатно
Design Intelligent Model base Online Tuning Methodology for Nonlinear System
Статья научная
In various dynamic parameters systems that need to be training on-line adaptive control methodology is used. In this paper fuzzy model-base adaptive methodology is used to tune the linear Proportional Integral Derivative (PID) controller. The main objectives in any systems are; stability, robust and reliability. However PID controller is used in many applications but it has many challenges to control of continuum robot. To solve these problems nonlinear adaptive methodology based on model base fuzzy logic is used. This research is used to reduce or eliminate the PID controller problems based on model reference fuzzy logic theory to control of flexible robot manipulator system and testing of the quality of process control in the simulation environment of MATLAB/SIMULINK Simulator.
Бесплатно
Design Intelligent Robust Back stepping Controller
Статья научная
The increasing demand for multi-degree-of-freedom (DOF) continuum robot in presence of highly nonlinear dynamic parameters in a number of industries has motivated a flurry of research in the development of soft computing nonlinear methodology. The robust backstopping controller proposed in this research is used to further demonstrate the appealing features exhibited by the continuum robot. Robust feedback controller is used to position control of continuum robot in presence of uncertainties. Using Lyapunov type stability arguments, a robust backstopping controller is designed to achieve this objective. The controller developed in this research is designed into two steps. Firstly, a robust stabilizing torque is designed for the nominal continuum robot dynamics derived using the constrained Lagrangian formulation based on modified PD backstopping controller. Next, the fuzzy logic methodology applied to it to solution uncertainty problem. The fuzzy model free problem is formulated to estimate the nonlinear formulation of continuum robot. The eventual stability of the controller depends on the torque generating capabilities of the continuum robots.
Бесплатно
Design Intelligent Robust Model-base Sliding Guidance Controller for Spherical Motor
Статья научная
Stability, robust and reliability are the main objectives to design a controller for highly nonlinear spherical motor. Most of linear and nonlinear controllers are stable, model-base controllers are reliable but in this group sliding mode controller is a robust controller. Therefore in this research sliding mode controller is used to design stable, robust and reliable controller. For intelligence part, the minimum rule base Proportional Integral Derivative (PID) Fuzzy hybrid guidance Controller for three dimensions spherical motor is presented in this research. Guidance control in a three dimensions spherical motor is performed by the robust sliding mode controllers producing the control signals which are applied to systems torque. Sliding mode controller has an important problem, namely chattering. In this research, chattering-free sliding mode controller is design as a robust guidance controller to their robust performance in a wide range of operating conditions. In this research the PID-like fuzzy controller can be constructed as a parallel structure of a PD-like fuzzy controller and a PI-like controller to have the minimum rule base. Nonlinear type robust sliding mode controller is used to modify PID fuzzy logic theory to design robust and reliable hybrid guidance methodology. This research is used to reduce or eliminate the fuzzy and conventional sliding mode controller problem based on minimum rule base fuzzy logic theory and modified it by sliding mode method to control of spherical motor system.
Бесплатно
Design Modified Fuzzy Hybrid Technique: Tuning By GDO
Статья научная
The Proportional Integral Derivative (PID) Fuzzy hybrid (switching mode computed torque sliding mode) Controller is presented in this research. The popularity of PID FHC controllers can be attributed to their robust performance in a wide range of operating conditions and partly to their functional simplicity. The process of setting of PID FHC controller can be determined as an optimization task. Over the years, use of intelligent strategies for tuning of these controllers has been growing. Biologically inspired evolutionary strategies have gained importance over other strategies because of their consistent performance over wide range of process models and their flexibility. This paper analyses the manual tuning techniques and compares the same with Gradient Descent tuning methods for tuning PID FHC controllers for flexible robot manipulator system and testing of the quality of process control in the simulation environment of MATLAB/SIMULINK Simulator.
Бесплатно
Design New Intelligent PID like Fuzzy Backstepping Controller
Статья научная
The minimum rule base Proportional Integral Derivative (PID) Fuzzy backstepping Controller is presented in this research. The popularity of PID Fuzzy backstepping controller can be attributed to their robust performance in a wide range of operating conditions and partly to their functional simplicity. The process of setting of PID Fuzzy backstepping controller can be determined as an optimization task. Over the years, use of intelligent strategies for tuning of these controllers has been growing. PID methodology has three inputs and if any input is described with seven linguistic values, and any rule has three conditions we will need 7 × 7 × 7 = 343 rules. It is too much work to write 343 rules. In this research the PID-like fuzzy controller can be constructed as a parallel structure of a PD-like fuzzy controller and a PI-like controller to have the minimum rule base. However backstepping controller is work based on cancelling decoupling and nonlinear terms of dynamic parameters of each link, this controller is work based on manipulator dynamic model and this technique is highly sensitive to the knowledge of all parameters of nonlinear robot manipulator’s dynamic equation. This research is used to reduce or eliminate the backstepping controller problem based on minimum rule base fuzzy logic theory to control of flexible robot manipulator system and testing of the quality of process control in the simulation environment of MATLAB/SIMULINK Simulator.
Бесплатно
Design New PID like Fuzzy CTC Controller: Applied to Spherical Motor
Статья научная
The minimum rule base Proportional Integral Derivative (PID) Fuzzy Computed Torque Controller with application to spherical motor is presented in this research. The popularity of PID Fuzzy Computed Torque Controller can be attributed to their robust performance in a wide range of operating conditions and partly to their functional simplicity. PID methodology has three inputs and if any input is described with seven linguistic values, and any rule has three conditions we will need 343 rules. It is too much work to write 343 rules and have lots of problem to design embedded control system e.g., Field Programmable Gate Array (FPGA). In this research the PID-like fuzzy controller can be constructed as a parallel structure of a PD-like fuzzy controller and a conventional PI controller to have the minimum rule base and acceptable trajectory follow disturbance to control of spherical motor. However computed torque controller is work based on cancelling decoupling and nonlinear terms of dynamic parameters for each direction of three degree of freedom spherical motor, this controller is work based on motor dynamic model and this technique is highly sensitive to the knowledge of all parameters of nonlinear spherical motor’s dynamic equation. This research is used to reduce or eliminate the computed torque controller problem based on minimum rule base fuzzy logic theory to control of three degrees of freedom spherical motor system and testing of the quality of process control in the simulation environment of MATLAB/SIMULINK Simulator.
Бесплатно
Design Sliding Mode Modified Fuzzy Linear Controller with Application to Flexible Robot Manipulator
Статья научная
This paper studies the use of Modified Proportional-Integral-Derivative Sliding Mode Controller (MPIDSMC) control used to control a flexible manipulator. The control gain in the MPIDSMC controller has been determined in an empirical way so far. It is a considerable time-consuming process because the control performance depends not only on the control gain but also on the other parameters such as the payload, references and PID joint servo gains. Hence, the control gain must be tuned considering the other parameters. In order to find the optimal control gain for the MPIDSMC controller, a fuzzy logic approach is proposed in this paper. The proposed fuzzy logic scheme finds an optimum control gain that minimizes the tip vibration for the end effector of the flexible manipulator. Tuned gain response results are compared to results for other types of gains. The effectiveness of using the fuzzy logic appears in the reduction of the computational time and the ability to tune the gain with different loading condition and input parameters.
Бесплатно
Design and Development MIPS Processor Based on a High Performance and Low Power Architecture on FPGA
Статья научная
This paper presents the design and development of a high performance and low power MIPS microprocessor and implementation on FPGA. In this method we for achieving high performance and low power in the operation of the proposed microprocessor use different methods including, unfolding transformation (parallel processing), C-slow retiming technique, and double edge registers are used to get even reduce power consumption. Also others blocks designed based on high speed digital circuits. Because of feedback loop in the proposed architecture C-slow retiming can enhance designs that contain feedback loops. The C-slow retiming is well-known for optimization and high performance technique, it automatically rebalances the registers in the proposed design. The proposed high performance microprocessor is modeled and verified using FPGA and simulation results. The proposed methods in microprocessor have been successfully synthesized and implemented in Quartus II 9.1 and Stratix II FPGA, to target device EP2S15F484C3, and power is analyzed with Xpower analyzer. Results demonstrate that the proposed method has high performance.
Бесплатно
Design and Development of IoT Device to Measure Quality of Water
Статья научная
The conventional method of measuring the quality of water is to take the samples manually and send it to laboratory for analysis. This technique is time overwhelming and not economical. Also it is not feasible to take the water sample to the laboratory after every hour for measuring its quality. To overcome from these problems a new system is proposed in this work. This water quality measuring system will measure the essential qualities of water in real time. The proposed system consists of multiple sensors to measure the standard of water, Raspberry Pi 2 and Ethernet Local Area Network (LAN) to send the information to the controlling center. It's a real time system which is able to endlessly measure the standard of water and send the measured values to the controlling center in each predefined time. The system relies on sensors, Raspberry Pi 2 and Internet.
Бесплатно
Design and Implementation of GPU-Based Prim's Algorithm
Статья научная
Minimum spanning tree is a classical problem in graph theory that plays a key role in a broad domain of applications. This paper proposes a minimum spanning tree algorithm using Prim's approach on Nvidia GPU under CUDA architecture. By using new developed GPU-based Min-Reduction data parallel primitive in the key step of the algorithm, higher efficiency is achieved. Experimental results show that we obtain about 2 times speedup on Nvidia GTX260 GPU over the CPU implementation and 3 times speedup over non-primitives GPU implementation.
Бесплатно
Design and Implementation of IR System for Tigrigna Textual Documents
Статья научная
Nowadays, various amount of information’s are available on the internet. To search relevant documents from the internet development of information retrieval system or search engines is necessary. Therefore, this paper deals with development of Information Retrieval system for Tigrigna textual documents. It helps to find relevant documents from the internet, which are stored in Tigrigna language for the Tigrigna language users to satisfy their information need. The system includes two sub systems those are indexing and searching part. The indexing part is the process of organizing filtered Tigrigna documents using keywords extracted from the entire Tigrigna collection or corpus. It is an offline process carried out by the producers or authors world to speed up searching of information from the entire document as per users query. Searching is the process of scanning documents to find relevant documents that matches to the users query or information need. It is an online process mostly carried out by the users or readers world. Vector space model techniques was applied to implement this system. Vector space model is the most core information retrieval technique used to calculate similarity measure between the query and the documents finally it ranks the most relevant documents to the given query according their similarity score in descending order. According to this, the retrieval system was tested and the experimental results of the system in Tigrinya documents returned an encouraging and promising result. The system has registered, 70% precision and 84% Recall.
Бесплатно
Design and Implementation of a Low Power RSA Processor for Smartcard
Статья научная
Power consumption limits the application of public key cryptosystem in portable devices. This paper proposes a low power design of 1,024-bit RSA. In algorithm, the Chinese Remainder Theorem (CRT) and an improved Montgomery algorithm are selected to decrease the computation of RSA. In architecture and circuit, the operand isolation technique is applied to avoid unnecessary flip-flops of the combinational logic, and the clock gating technique is used to reduce the power dissipation of the registers. The proposed design is functionally verified on Altera FPGA EP2C8Q208C8N device. With SMIC 0.18m CMOS process, the Synopsys synthesizing result shows that the area and the critical path are 7.1k gates and 5.3ns respectively, while the power is 2.56mW and the throughput can reach 49 kbps. Thus the proposed design requires lower power than previous designs.
Бесплатно
Design and Implementation of a Three-operand Multiplier through Carbon Nanotube Technology
Статья научная
Multiplication scheme is one of the most essential factors, which is time consuming. Designers and manufacturers of processors emphasis on methods which would not only perform the multiplication scheme in a rapid manner, but would reduce the physical aspect of the design as well; hence, a reduction in power consumption. Addition is one of the fundamental factors in multiplication. Pre-designing of circuits and transistors' levels used to be made through Metal Oxide Semiconductor Field Effect Transistor (MOSFET), but now, due to scaling and difficulties thereof, new technologies like Single Electron Transistor (SET), Quantum-dot Cellular Automata (QCA) and Carbon Nanotube Field Effect Transistor (CNFET) are introduced. Among the new technologies, CNFET has become center of attention due to similarities in electronic features in relation to MOSFET. A comparison made between CNFET with MOSFET technologies indicate that, power delay product (PDP) and power leakage can be less in nanotube transistors. Field effect transistor circuit's simulations are accomplished through HSPICE simulator. The simulation results indicate that this proposed Three-operand Carbon Nanotube Multiplier has a better performance in comparison with the three-operand multiplication done on computers nowadays, which we call it classical multiplier in this article.
Бесплатно
Design and Implementation of an Intelligent Mobile Game
Статья научная
While the mobile game industry is growing with each passing day with the popularization of 3G smart devices, the creation of successful games, which may interest users, become quite important in terms of the survival of the designed game. Clustering, which has many application fields, is a successful method and its implementation in the field of mobile games is inevitable. In this study, classical ball blasting game was carried out based on clustering. In the game, clustering the color codes with K-means, Iterative K-means, Iterative Multi K-means and K-medoids methods and blasting the balls of colors located in the same cluster by bringing them together were proposed. As a result of the experiments, the suitability of clustering methods for mobile based ball blasting game was shown. At the same time, the clustering methods were compared to produce the more successful clusters and because of obtaining more accurate results and stability, the use of K-medoids method has been chosen for this game.
Бесплатно
