Статьи журнала - International Journal of Intelligent Systems and Applications
Все статьи: 1159
Статья научная
Deep learning has improved image captioning. Transformer, a neural network architecture built for natural language processing, excels at image captioning and other computer vision applications. This paper reviews Transformer-based image captioning methods in detail. Convolutional neural networks (CNNs) extracted image features and RNNs or LSTM networks generated captions in traditional image captioning. This method often has information bottlenecks and trouble capturing long-range dependencies. Transformer architecture revolutionized natural language processing with its attention strategy and parallel processing. Researchers used Transformers' language success to solve image captioning problems. Transformer-based image captioning systems outperform previous methods in accuracy and efficiency by integrating visual and textual information into a single model. This paper discusses how the Transformer architecture's self-attention mechanisms and positional encodings are adapted for image captioning. Vision Transformers (ViTs) and CNN-Transformer hybrid models are discussed. We also discuss pre-training, fine-tuning, and reinforcement learning to improve caption quality. Transformer-based image captioning difficulties, trends, and future approaches are also examined. Multimodal fusion, visual-text alignment, and caption interpretability are challenges. We expect research to address these issues and apply Transformer-based image captioning to medical imaging and distant sensing. This paper covers how Transformer-based approaches have changed image captioning and their potential to revolutionize multimodal interpretation and generation, advancing artificial intelligence and human-computer interactions.
Бесплатно
Optimized Planning of Resources Demand Curve in Ground Handling based on Machine Learning Prediction
Статья научная
Determining the resource requirements at airports especially in-ground services companies is essential to successful planning in the future, which is represented in the resources demand curve according to the future flight schedule, through which staff schedules are created at the airport to cover the workload with ensuring the highest possible quality service provided. Given in the presence of variety service level agreements used on flight service vary according to many flight features, the resources assumption method makes planning difficult. For instance, flight position is not included in future flight schedule but it's efficacious in the identification of flight resources. In this regard, based on machine learning, we propose a model for building a resource demand curve for future flight schedules. It is divided into two phases, the first is the use of machine learning to predict resources of the service level agreement required on future flight schedules, and the second is the use of implement a resource allocation algorithm to build a demand curve based on predicted resources. This proposal could be applicable to airports that will provide efficient and realistic for the resources demand curve to ensure the resource planning does not deviate from the real-time resource requirements. the model has proven good accuracy when using one day of flights to measuring deviation between the proposed model predict demand curve when flights did not include the location feature and the actual demand curve when flights include location.
Бесплатно
Статья научная
Cloud computing refers to a sophisticated technology that deals with the manipulation of data in internet-based servers dynamically and efficiently. The utilization of the cloud computing has been rapidly increased because of its scalability, accessibility, and incredible flexibility. Dynamic usage and process sharing facilities require task scheduling which is a prominent issue and plays a significant role in developing an optimal cloud computing environment. Round robin is generally an efficient task scheduling algorithm that has a powerful impact on the performance of the cloud computing environment. This paper introduces a new approach for round robin based task scheduling algorithm which is suitable for cloud computing environment. The proposed algorithm determines time quantum dynamically based on the differences among three maximum burst time of tasks in the ready queue for each round. The concerning part of the proposed method is utilizing additive manner among the differences, and the burst times of the processes during determining the time quantum. The experimental results showed that the proposed approach has enhanced the performance of the round robin task scheduling algorithm in reducing average turn-around time, diminishing average waiting time, and minimizing number of contexts switching. Moreover, a comparative study has been conducted which showed that the proposed approach outperforms some of the similar existing round robin approaches. Finally, it can be concluded based on the experiment and comparative study that the proposed dynamic round robin scheduling algorithm is comparatively better, acceptable and optimal for cloud environment.
Бесплатно
Optimized and Self-Organized Fuzzy Logic Controller for pH Neutralization Process
Статья научная
To conform to strict environmental safety regulations, pH control is used in many industrial applications. For this purpose modern process industries are increasingly relying on intelligent and adaptive control strategies. On one hand intelligent control strategies try to imitate human way of thinking and decision making using artificial intelligence (AI) based techniques such as fuzzy logic whereas on the other hand adaptive mechanism ensures adjusting of the controller parameters. A self-organized fuzzy logic controller (SOFLC) is intelligent in nature and adapts its performance to meet the figure of merit. This paper presents an optimized SOFLC for pH control using performance correction table. The fuzzy adaptation mechanism basically involves a penalty for the output membership functions if the controller performance is poor. The evolutionary genetic algorithm (GA) is used for optimization of input-output scaling factors of the conventional fuzzy logic controller (FLC) as well as elements of the fuzzy performance correction table. The resulting optimized SOFLC is compared with optimized FLC for servo and regulatory control. Comparison indicate superior performance of SOFLC over FLC in terms of much reduced integral of squared error (ISE), maximum overshoot and undershoot, and increased speed of response.
Бесплатно
Optimizing Artificial Neural Networks using Cat Swarm Optimization Algorithm
Статья научная
An Artificial Neural Network (ANN) is an abstract representation of the biological nervous system which has the ability to solve many complex problems. The interesting attributes it exhibits makes an ANN capable of “learning”. ANN learning is achieved by training the neural network using a training algorithm. Aside from choosing a training algorithm to train ANNs, the ANN structure can also be optimized by applying certain pruning techniques to reduce network complexity. The Cat Swarm Optimization (CSO) algorithm, a swarm intelligence-based optimization algorithm mimics the behavior of cats, is used as the training algorithm and the Optimal Brain Damage (OBD) method as the pruning algorithm. This study suggests an approach to ANN training through the simultaneous optimization of the connection weights and ANN structure. Experiments performed on benchmark datasets taken from the UCI machine learning repository show that the proposed CSONN-OBD is an effective tool for training neural networks.
Бесплатно
Optimizing parameters of automatic speech segmentation into syllable units
Статья научная
An automatic speech segmentation into syllable is an important task in a modern syllable-based speech recognition. It is generally developed using a time-domain energy-based feature and a static threshold to detect a syllable boundary. The main problem is the fixed threshold should be defined exhaustively to get a high generalized accuracy. In this paper, an optimization method is proposed to adaptively find the best threshold. It optimizes the parameters of syllable speech segmentation and exploits two post-processing methods: iterative-splitting and iterative-assimilation. The optimization is carried out using three independent genetic algorithms (GAs) for three processes: boundary detection, iterative-splitting, and iterative-assimilation. Testing to an Indonesian speech dataset of 110 utterances shows that the proposed iterative-splitting with optimum parameters reduce deletion errors more than the commonly used non-iterative-splitting. The optimized iterative-assimilation is capable of removing more insertions, without over-merging, than the common non-iterative-assimilation. The sequential combination of optimized iterative-splitting and optimized iterative-assimilation gives the highest accuracy with the lowest deletion and insertion errors.
Бесплатно
Orbit and Attitude Control of Asymmetric Satellites in Polar Near-Circular Orbit
Статья научная
In this paper, the general problem about the orbit and attitude dynamic model is discussed. A feedback linearization control method is introduced for this model. Due to the asymmetric structure, the orbital properties of such satellites are the same as traditional symmetric ones, but the attitude properties are greatly different from the symmetric counterparts. With perturbations accumulate with time, the attitude angles increase periodically with time, but the orbital elements change much slower than the attitude angles. In the attitude dynamic model, chaos could appear. Traditional linear controllers can not compensate enough for asymmetric satellite when the mission is complex, especially in maneuver missions. Thus nonlinear control method is required to solve such problem in large scale. A feedback linearization method, one robust nonlinear control method, is introduced and applied to the asymmetric satellite in this paper. Some simulations are also given and the results show that feedback linearization controller not only stabilizes the system, but also exempt the chaos in the system.
Бесплатно
Overlapped Segmental Active Constellation Extension for the PAPR Reduction of the OFDM-OQAM System
Статья научная
Orthogonal frequency division multiplexing with Offset Quadrature Amplitude Modulation (OFDM-OQAM) technique has drawn significant interests in recent years. However, most of the existing OFDM peak-to-average ratio (PAPR) reduction schemes cannot be used in the OFDM-OQAM system directly. In this paper, a modified scheme called overlapped segmental Active Constellation Extension (OS-ACE) is proposed to deal with the high PAPR problem specifically in the OFDM-OQAM system. For the proposed OS-ACE scheme, the input signals are divided into a number of overlapped segments and then the ACE operation is processed on each segment. Simulation results show that the modified scheme used in the OFDM-OQAM system can provide better performance than conventional ACE scheme directly used in the OFDM-OQAM system, and even outperforms conventional ACE scheme applied in the OFDM system.
Бесплатно
PD Controller Structures: Comparison and Selection for an Electromechanical System
Статья научная
Many different PD controller modeling, configurations and control algorithms have been developed. These methods differ in their theoretical basis and performance under the changes of system conditions. In the present paper we review the methods used in the design of PD control systems. We highlight the main difficulties and summarize the more recent developments in their control techniques. Intelligent control systems like PD fuzzy control can be used to emulate the qualitative aspects of human knowledge with several advantages such as universal approximation theorem and rule-based algorithms.
Бесплатно
PID controller design for SOPDT using direct synthesis method
Статья научная
Direct synthesis method based PID controller was proposed for the second order plus dead time stable process having a zero in the numerator. The desired closed loop transfer function was considered as a second order time delay model and the Maclaurin series expansion technique was used to convert the obtained controller into the ideal form of the PID controller. The tuning parameter α was selected in such a way that gives the robustness level i.e. maximum sensitivity Ms value in the range of 1.2-1.8 which was the same as other recent tuning methods. The proposed method was applied to six different first and second order time delay process. The closed-loop performance in term of various performance indices such as settling time (ts), rise time (tr), Overshoot (%OS), and the time integral error indices such as IAE, ISE, and ITAE was compared to other similar design approaches. The comparative results show that the proposed method was superior to other methods.
Бесплатно
PLC based Smart Street Lighting Control
Статья научная
Conventional street lighting systems in most of the areas are Online at regular intervals of time irrespective of the seasonal variations. The street lights are simply switched on at afternoon and turned off in the morning. The consequence is that a large amount of Power is wasted meaninglessly. As energy consumption is an issue of increasing interest, possible energy savings in public street lighting systems are recently discussed from different viewpoints. The purpose of this work is to describe the Smart Street Lighting system, an approach to accomplish the demand for flexible public lighting systems using a Programmable Logic controller (PLC). The main difference from other computers is that PLCs are armoured for severe conditions such as dust, moisture, heat, cold etc., and have the facility for extensive input/output (I/O) arrangements. In the proposed paper, street lights are controlled using millennium 3 PLC taking the seasonal variations into consideration.
Бесплатно
PSO-Based NBI Resistant Asynchronous MC-CDMA Multiuser Detector
Статья научная
Nowadays with the increase of demand in multimedia communication, a reliable and error-free wireless communication system is the need of the hour. MC-CDMA is being investigated as a potential radio technology to provide fourth generation (4G) and fifth generation (5G) cellular mobile services. Narrowband interference (NBI) signals corrupts the subcarriers of MC-CDMA system and as a result its performance degrades. All the available NBI elimination methods uses some kind of filters and other circuitry prior to the demodulator (receiver) to filter out NBI. So addition of extra hardware to the system makes the system complex and slow. Moreover CDMA based systems are affected by digital NBI which gets superimposed with wideband spread spectrum signal. Multiuser detection could be an efficient technique to suppress NBI and multiple access interference (MAI). Computational complexity of opti-mum multiuser detector is an impediment in the way of an efficient multiuser detector. In this paper we propose a particle swarm optimization (PSO) based optimum multiuser detector to eliminate NBI. Simulation results show that performance of proposed PSO based multiuser detector is capable of eliminating NBI with much lesser amount of computational complexity.
Бесплатно
PSO-Based PI Controller for Shunt APF in Distribution Network of Multi Harmonic Sources
Статья научная
PI controller tuning with the assumption of linear PWM model leads to unsatisfactory results under varying operating conditions. Optimal tuning of PI gains is required to get the best response of PI controllers. This paper presents a new method for harmonic suppression using particle swarm optimization (PSO) based PI controller (PSOPI) to estimate an efficient shunt active power filter (SAPF). The proposed filter is tested on a 13 bus industrial distribution system. The study system with the 18 study cases are simulated through MATLAB Simulink with different loading condition and single and multi harmonic sources. The results of applying the PIPSO controller are compared with those out of a double proportional controller (DPC). The obtained results ensure the effectiveness of the proposed filter and its superiority in reducing harmonics.
Бесплатно
Parallel Implementation of a Video-based Vehicle Speed Measurement System for Municipal Roadways
Статья научная
Nowadays, Intelligent Transportation Systems (ITS) are known as powerful solutions for handling traffic-related issues. ITS are used in various applications such as traffic signal control, vehicle counting, and automatic license plate detection. In the special case, video cameras are applied in ITS which can provide useful information after processing their outputs, known as Video-based Intelligent Transportation Systems (V-ITS). Among various applications of V-ITS, automatic vehicle speed measurement is a fast-growing field due to its numerous benefits. In this regard, visual appearance-based methods are common types of video-based speed measurement approaches which suffer from a computationally intensive performance. These methods repeatedly search for special visual features of vehicles, like the license plate, in consecutive frames. In this paper, a parallelized version of an appearance-based speed measurement method is presented which is real-time and requires lower computational costs. To acquire this, data-level parallelism was applied on three computationally intensive modules of the method with low dependencies using NVidia’s CUDA platform. The parallelization process was performed by the distribution of the method’s constituent modules on multiple processing elements, which resulted in better throughputs and massively parallelism. Experimental results have shown that the CUDA-enabled implementation runs about 1.81 times faster than the main sequential approach to calculate each vehicle’s speed. In addition, the parallelized kernels of the mentioned modules provide 21.28, 408.71 and 188.87 speed-up in singularly execution. The reason for performing these experiments was to clarify the vital role of computational cost in developing video-based speed measurement systems for real-time applications.
Бесплатно
Parameter Tuning via Genetic Algorithm of Fuzzy Controller for Fire Tube Boiler
Статья научная
The optimal use of fuel energy and water in a fire tube boiler is important in achieving economical system operation, precise control system design required to achieve high speed of response with no overshot. Two artificial intelligence techniques, fuzzy control (FLC) and genetic-fuzzy control (GFLC) applied to control both of the water/steam temperature and water level control loops of boiler. The parameters of the FLC are optimized to locating the optimal solutions to meet the required performance objectives using a genetic algorithm. The parameters subject to optimization are the width of the membership functions and scaling factors. The performance of the fire tube boiler that fitted with GFLC has reliable dynamic performance as compared with the system fitted with FLC.
Бесплатно
Статья научная
This work falls within the framework of the Arabic natural language processing. We are interested in parsing Arabic texts. Existing parsers generate parse trees that give an idea about the structure of the sentence without considering the syntactic functions specific to the Arabic language. Thus, the results are still insufficient in terms of syntactic information. The system we have developed in this article takes into consideration all these syntactic functions. This system begins with a morphological analysis in the context. Then, it uses a CFG grammar to extract the phrases and ends by exploiting the formalism of unification grammar and traditional grammar to combine these phrases and generate the final sentence structure.
Бесплатно
Passenger body vibration control in active quarter car model using hybrid ANFIS PID controller
Статья научная
The objective of this paper is to improve the passenger ride comfort and safety in an active quarter car model. For this purpose, a quarter car model with passenger body and seat is considered to capture the dynamic behaviour of a real complete car system. To achieve the desired target, two different controllers such as Adaptive Neuro Fuzzy (ANFIS) controller and Hybrid ANFIS PID controller (HANFISPID) are designed. The controllers selection and design was aimed to achieve good passenger ride comfort and health, taking passenger body acceleration and displacement response under random road excitations. The performance of designed controllers are evaluated using simulation work in time and frequency domain. Simulation results show that the proposed HANFISPID control scheme can succesfully achieve the desired ride comfort and safety of passenger compared to passive and ANFIS controlled cases in an active quarter car model.
Бесплатно
Passivity analysis of neutral fuzzy system with linear fractional uncertainty
Статья научная
In this paper, the passivity analysis of Takagi-Sugeno (T-S) fuzzy neutral system with interval time-varying delay and linear fractional parametric uncertainty is investigated. Based on the Lyapunov-Krasovskii functional and the free weighting matrix method, delay-dependent sufficient conditions for solvability of the passive problem are obtained in terms of Linear matrix inequalities (LMIs). Finally, a simulation example is provided to demonstrate effectiveness and applicability of the theoretical results.
Бесплатно
Pattern Formation in Swarming Spacecrafts using Tersoff-Brenner Potential Field
Статья научная
We present a distributed control strategy that lets a swarm of spacecrafts autonomously form a lattice in orbit around a planet. The system, based on the artificial potential field approach, proposes a novel way to divide the artificial field into two main terms: a global artificial potential field mainly based on the famous C-W equations that gathers the spacecrafts around a predefined meeting point, and a local term exploited the well-known Tersoff-Brenner potential that allows a spacecraft to place itself in the correct position relative to its closest neighbors. Moreover, in order to obtain convergence from all initial distributions of the spacecrafts, a dissipation term depended on the velocity of agent is introduced. The new methodology is demonstrated in the problem of forming a hexagon lattice, the structure unit of graphite. It is shown that a pattern formation can operate around a planet. By slightly changing the scenario our method can be easily applied to shape other configurations, such as a regular tetrahedron (with central point), the structure unit, etc.
Бесплатно
Performance Analysis of Multi Functional Bot System Design Using Microcontroller
Статья научная
This paper includes performance analysis of a multipurpose microcontroller based system which has various modes to control distinct applications. The paper elucidates how a single chip microcontroller can process different signals and accomplish different tasks. The system discussed in this paper has seven modes. Each mode controls different applications. Radio frequency signals are used for controlling the system wirelessly and each mode is triggered by giving a suitable 4-bit logic by the transmitter. The different modes which the system works in consist of security tracking, temperature measurement, sound actuated control, voltmeter mode, door automation, pits avoider and obstacle avoider. The versatility of the system is tested using Xilinx software v10.1. It is found that the system is functioning properly under normal conditions and the variations of the different parameters for a particular mode have been plotted in MATLAB R2013a v8.1 to validate the accuracy of the system.
Бесплатно
