Статьи журнала - International Journal of Intelligent Systems and Applications
Все статьи: 1173
Real-time Deep Learning Based Mobile Application for Detecting Edible Fungi: Mushapp
Статья научная
Mushroom consumption and wild mushroom gathering are increasing in our country and in the world. Mushroom poisoning has an important place in food poisoning cases. Mushroom poisoning accounts for approximately 7% of poisoning cases in adults. Mushroom collection and consumption is common in many regions of our country. In this study, a deep learning based mobile application was developed to reduce the incidence of mushroom poisoning by taking a photo of a mushroom and determining the type and toxicity of the mushroom from the photo. This mobile application is called MushAPP. In the first phase of the study, 5150 mushroom images of 20 mushroom species were used to create the dataset. The dataset was then pre-processed and converted into a format that can be used by the deep learning algorithm. The mobile application side of the project was developed in Android Studio IDE environment. An artificial intelligence model was integrated into the designed mobile application. In the application, the type and toxicity status of the mushroom viewed from the mobile device camera are determined and presented to the user. The research findings were analyzed and it was determined that the accuracy rate of the application in detecting the mushroom species was 99.8%.
Бесплатно
Recent Trends, Applications, and Challenges of Brain-Computer Interfacing (BCI)
Статья научная
Brain-Computer Interfacing (BCI) enables a communication pathway that is used to directly control certain object or device with the human brain. It is possible to acquire data from the brain with the help of sensors which essentially monitor the physical processes that occur in the brain and with the help of software we can direct a device accordingly. BCI introduces its users a new system that communicates in a special way without the use of muscles. BCI also provides a useful platform for the people with physical disabilities to conveniently perform certain tasks in our society. It uses brain imaging technologies which help in increasing the quality of the communication between humans and machines. There has been significant research effort in the past decade to explore different aspects of this promising field of technology. Previously, BCIs had limited functionality but due to recent advancement in technology it has attained the maturity of its own right by adding new trends and extra features to it. In this paper, research work of development and integration of both hardware and software in BCI and the advancements of BCI are surveyed considering all the possibilities of direct communication of computers with a brain using emerging technologies. Different approaches used up till now with an overview of the methodology are presented to make the reader understand its meaning and functionality in a compact way. This research paper will guide a beginner to end up with a thorough knowledge of what's, how's and why's of BCI. In addition, BCI applications, challenges, possible solutions and future directions have also been discussed.
Бесплатно
Статья научная
Traditionally, Control Chart Patterns (CCP) is widely used as a powerful method to measure, classify,analyze and interpret process data to improve the quality of products and service by detecting instabilities and justifying possible causes. In this study, we have developed an expert system that we called an expert system for control chart patterns recognition for recognition of the common types of control chart patterns (CCPs). The proposed system includes three main modules: the feature extraction module, the classifier module and the optimization module. In the feature extraction module, the multi-resolution wavelets (MRW) are proposed as the effective features for representation of CCPs. In the classifier module, the adaptive neuro-fuzzy inference system (ANFIS) is investigated. In ANFIS training, the vector of radius has a very important role for its recognition accuracy. Therefore, in the optimization module, imperialist competitive algorithm(ICA) is proposed for finding optimum vector of radius. Simulation results show that the proposed system has high recognition accuracy.
Бесплатно
Reduced Multiplicative Tolerance Ranking and Applications
Статья научная
In this paper a reduced multiplicative tolerance - a measure of sensitivity analysis in multi-objective linear programming (MOLP) is presented. By using this new measure a method for ranking the set of efficient extreme solutions is proposed. The idea is to rank these solutions by values of the reduced tolerance. This approach can be applied to many MOLP problems, where sensitivity analysis is important for a decision maker. In the paper, applications of the presented methodology are shown in the market model and the transportation problem.
Бесплатно
Reducing Support Vector Machine Classification Error by Implementing Kalman Filter
Статья научная
The aim of this is to demonstrate the capability of Kalman Filter to reduce Support Vector Machine classification errors in classifying pipeline corrosion depth. In pipeline defect classification, it is important to increase the accuracy of the SVM classification so that one can avoid misclassification which can lead to greater problems in monitoring pipeline defect and prediction of pipeline leakage. In this paper, it is found that noisy data can greatly affect the performance of SVM. Hence, Kalman Filter + SVM hybrid technique has been proposed as a solution to reduce SVM classification errors. The datasets has been added with Additive White Gaussian Noise in several stages to study the effect of noise on SVM classification accuracy. Three techniques have been studied in this experiment, namely SVM, hybrid of Discrete Wavelet Transform + SVM and hybrid of Kalman Filter + SVM. Experiment results have been compared to find the most promising techniques among them. MATLAB simulations show Kalman Filter and Support Vector Machine combination in a single system produced higher accuracy compared to the other two techniques.
Бесплатно
Reduction of Misclassifications in Wildfire Detection: A Weighted Ensemble Deep Learning Approach
Статья научная
Governments worldwide are increasingly prioritizing early wildfire detection to safeguard lives, property, and the environment. Although CNN-based models have demonstrated exceptional performance in various computer vision applications, the evolving nature of wildfire images poses significant challenges for a single CNN-based model in wildfire detection. In this study, we addressed this issue by integrating and weighting the differential learning capabilities of three individual transfer learning models: InceptionV3, ResNet50, and VGG16. Experimental results show that the ensemble deep learning models significantly outperformed all single classifiers across all performance metrics. Both the ensemble and weighted ensemble deep learning models achieved 99.7% accuracy, 99.5% precision, 100% recall, 99.8% F1-score, 0.5%false positive rate, 0.0% false negative rate and 0.3% error rate. Additionally, these models reduced the error rate by 98%, 91%, and 40% compared to the error rates of ResNet50, InceptionV3, and VGG16 respectively. A false negative rate of 0% indicates that our proposed ensemble deep learning models identified and predicted all the wildfire instances present in the test set correctly without a single misclassification. This positions our proposed ensemble deep learning models as superior choices for reducing misclassifications in wildfire detection.
Бесплатно
Redundancy Level Optimization in Modular Software System Models using ABC
Статья научная
The performance of optimization algorithms is problem dependent and as per no free lunch theorem, there exists no such algorithm which can be efficiently applied to every type of problem(s). However, we can modify the algorithm/ technique in a manner such that it is able to deal with a maximum type of problems. In this study we have modified the structure of basic Artificial Bee Colony (ABC), a recently proposed metaheuristic algorithm based on the concept of swarm intelligence to optimize the models of software reliability. The modified variant of ABC is termed as balanced ABC (B-ABC). The simulated results show the efficiency and capability of the variant to solve such type of the problems.
Бесплатно
Reliable Mobile Ad-Hoc Network Routing Using Firefly Algorithm
Статья научная
Routing in Mobile Ad-hoc NETwork (MANET) is a contemporary graph problem that is solved using various shortest path search techniques. The routing algorithms employed in modern routers use deterministic algorithms that extract an exact non-dominated set of solutions from the search space. The search efficiency of these algorithms is found to have an exponential time complexity in the worst case. Moreover this problem is a multi-objective optimization problem in nature for MANET and it is required to consider changing topology layout. This study attempts to employ a formulation incorporating objectives viz., delay, hop-distance, load, cost and reliability that has significant impact on network performance. Simulation with different random topologies has been carried out to illustrate the implementation of an exhaustive search algorithm and it is observed that the algorithm could handle small-scale networks limited to 15 nodes. A random search meta-heuristic that adopts the nature of firefly swarm has been proposed for larger networks to yield an approximated non-dominated path set. Firefly Algorithm is found to perform better than the exact algorithm in terms of scalability and computational time.
Бесплатно
Representation of Fuzzy Matrices Based on Reference Function
Статья научная
Fuzzy matrices in the present form do not meet the most important requirement of matrix representatiom in the form of reference function without which no logical result can be expected. In this article, we intend to represent fuzzy matrices in which there would be the use of reference function. Our main purpose is to deal specially with complement of fuzzy matrices and some of its properties when our new definition of complementation of matrices is considered. For doing these the new definition of complementation of fuzzy sets based on reference function plays a very crucial role. Further, a new definition of trace of a fuzzy matrix is introduced in this article which is in accordance with newly defined fuzzy matrices with the help of reference function and thereby efforts have been made to establish some of the properties of trace of fuzzy matrices.
Бесплатно
Research of Self-Tuning PID for PMSM Vector Control based on Improved KMTOA
Статья научная
The Permanent Magnet Synchronous Motor has been applying widely due to it's high efficiency, high reliability, relatively low cost and low moment of inertia. However, the PMSM drives are easily affected by the uncertain factors such as the variation of motor parameters and load disturbance. In order to realize the control of the PMSM accurately, a novel adaptive chaotic kinetic molecular theory optimization algorithm was implemented for seeking the best parameters of PID controller. In the PMSM vector control system, the speed loop will be adjusted by a CKMTOA PID controller. In modified kinetic molecular theory optimization algorithm, the adaptive inertia weight factors are used to accelerate the convergence speed, and chaotic searching is conducted within the neighbor set of the solutions to avoid the local minima. The model of PMSM and its` space vector control system are set up in the software of MATLAB/Simulink. The effectiveness of the self-tuning CKMTOA PID controller is verified by comparing with the conventional PID and particle swarm optimization algorithm. The extensive simulations and analysis also show the effectiveness of the proposed approach.
Бесплатно
Research on Adaptive Fuzzy PID Synchronous Control Strategy of Double-Motor
Статья научная
The double-motor synchronous control system is widely used in industrial field. Its performance plays an important role in production. Traditional PID controller parameters are difficult to tune when used in control system, as well as the control effect can not satisfy the requirement of producing process when the controller plant is complex non-linear system. In this paper, adaptive fuzzy PID which can tune the parameters on-line is introduced to apply in the double-motor synchronous control system. In MATLAB / SMULINK simulation environment, the speed of master motor is perfectly followed by slave motor, and high robustness and precision are obtained. The simulation results show that fuzzy logic PID control strategy has better performances than traditional controller.
Бесплатно
Research on Association with Freight Transit Period and Forwarding Time base on Logistics conditions
Статья научная
The whole process of freight forwarding includes multiple links. The consumption time of every link and its operational efficiency may affect the entire freight forwarding time, which can influence the transit period of freight, as well as the formulation and achievement of the transportation organizations scheme and the transportation contract. In order to analyze the existed problems in present calculation method of railway transit period, and the effects of logistics on forwarding time, on the basis of investigating and literature, Railway freight forwarding process and factor of logistics on railway freight forwarding time were analyzed, and average speed of through train, ordinary through train and high-speed train, and daily average running tariff kilometer and time were analyzed, and statistical results were exained by adopting 2χtesting method, finally, daily average running tariff kilometer and time of logistics developed and under-developed area were comparative analyzed, from which daily average running tariff kilometer and time were obtained. The analytical results show that the average speed, daily average running tariff kilometer and time respectively obeys normal distribution, the maximum difference value between the transit period calculated by present method and the practical forwarding time of freight is four 4.5 days, which show that the method can not objectively responds the freight forwarding time of each kind of freight transport product under logistics condition.
Бесплатно
Research on Canal System Operation Based on Controlled Volume Method
Статья научная
An operating simulation mode based on storage volume control method for multireach canal system in series was established. In allusion to the deficiency of existing controlled volume algorithm, the improved algorithm was proposed, that is the controlled volume algorithm of whole canal pools, the simulation results indicate that the storage volume and water level of each canal pool can be accurately controlled after the improved algorithm was adopted. However, for some typical discharge demand change operating conditions of canal, if the controlled volume algorithm of whole canal pool is still adopted, then it certainly will cause some unnecessary regulation, and consequently increases the disturbed canal reaches. Therefor, the idea of controlled volume operation method of continuous canal pools was proposed, and its algorithm was designed. Through simulation to practical project, the results indicate that the new controlled volume algorithm proposed for typical operating condition can comparatively obviously reduce the number of regulated check gates and disturbed canal pools for some typical discharge demand change operating conditions of canal, thus the control efficiency of canal system was improved. The controlled volume method of operation is specially suitable for large-scale water delivery canal system which possesses complex operation requirements.
Бесплатно
Research on Key Technology of New Concept Tyre Building Production Line
Статья научная
Tyre building production line gradually transits from stand-alone production to combined production mode. The transformation of work mode from traditional serial intermittent to the parallel continuous has been the key technology research of tire production enterprise. And intelligent robots and other automated equipment have been the first choice of the tyre enterprise’s production line. Considering the combination of the equipment between upper and lower processes in tyre production line, the manual operations in some processes replaced by intelligent robots will improve production efficiency of tyre production enterprise, and will make outstanding contribution in reduce process losses and reduce production costs. This article studies on the key technology of combined application in production line, and makes simulation comparison for the same technical process that using different scheme, to prove the priorities and superiorities of combined production line relatives to the traditional production mode.
Бесплатно
Статья научная
In this paper, according to the structure char-acteristics of steer-by-wire (SBW) system for the TFC20 electric forklift, steering dynamics model and two degree of freedom vehicle model are deduced for SBW forklift. Aiming at the free design features of the angular trans-mission characteristics in the SBW system of electric forklift, the theory of active steering control strategy is studied. After analyzing the influence factors of the an-gular transmission ratio of the steering system, the ideal angular transmission ratio is proposed, which is based on the yaw rate gain invariance. Also, the control strategy of the yaw rate feedback and the full state feedback is stud-ied. The simulation results show that the above strategy is effective for the active steering control; it can improve the operating stability and the response speed of the fork-lift.
Бесплатно
Статья научная
Combined with the transmission ratio charac-teristics of forklift steering-by-wire (SBW) system, through the application of fuzzy control technology, the variable transmission ratio function is designed based on the steering handle angle and vehicle speed, and simula-tion analysis of sinusoidal steering is done at low-speed and high-speed. Simulation results show that the fuzzy variable transmission ratio control can make forklift steering light & sensitive at low-speed and steering steady & heavy at high speed, also it can improve the operation stability and reduce the driver's load. Discuss the relationship between yaw rate and forklift handling stability, propose the yaw rate feedback control strategy based on the fuzzy variable transmission ratio control, and design a fuzzy self-adaptive PID controller. Simula-tion results show that the SBW system based on the fuzzy variable transmission ratio control with yaw rate feedback can accurately and quickly track the desired yaw rate, and reduce or even eliminate the overshoot phenomenon, improve the forklift dynamic performance.
Бесплатно
Research on temperature field and temperature stress of prestressed concrete girders
Статья научная
This paper introduces the establishment and simplification of the temperature field and the general calculation method of temperature stress of the prestressed concrete box girders. Three kinds of sunshine temperature gradient models were loaded to a real bridge respectively, and got stress and displacement curves. Research data of several prestressed concrete box girders were selected from different regions of China to compare the relative error of the calculated and measured value. We indicate that the study of temperature field and thermal stress of prestressed concrete box girders is necessary, and will help engineers to solve the problem in structure design.
Бесплатно
Research on the Layout of National Economic Mobilization Logistics Centers
Статья научная
The problem of the layout of NEMLC (National Economic Mobilization Logistics Center) is one of the most important long-term decision-making issues. The result of NEMLC’s layout directly impacts many aspects of mobilization, such as time, reliability, quality, efficiency, cost, and so on, consequently affects the effect of the mobilization. Reasonable NEMLC layout can bring people convenience in the daily life, reduce costs, and improve service efficiency and competitiveness. Poor NEMLC layout often brings a great deal of inconvenience and loss, and even leads to mobilization failure. Under the restriction of mobilization time, the paper establishes the layout model that one or more mobilization logistics centers provide the material to the mobilization demanding place. The mobilization goods or service can reach the demanding place to carry into mobilization execution within the given time, and the number of the built NEMLCs is the least.
Бесплатно
Review and Comparison of Kernel Based Fuzzy Image Segmentation Techniques
Статья научная
This paper presents a detailed study and comparison of some Kernelized Fuzzy C-means Clustering based image segmentation algorithms Four algorithms have been used Fuzzy Clustering, Fuzzy C-Means(FCM) algorithm, Kernel Fuzzy C-Means(KFCM), Intuitionistic Kernelized Fuzzy C-Means(KIFCM), Kernelized Type-II Fuzzy C-Means(KT2FCM).The four algorithms are studied and analyzed both quantitatively and qualitatively. These algorithms are implemented on synthetic images in case of without noise along with Gaussian and salt and pepper noise for better review and comparison. Based on outputs best algorithm is suggested.
Бесплатно
Review, Design, Optimization and Stability Analysis of Fractional-Order PID Controller
Статья научная
This paper will establish the importance and significance of studying the fractional-order control of nonlinear dynamical systems. The foundation and the sources related to this research scope is going to be set. Then, the paper incorporates a brief overview on how this study is performed and present the organization of this study. The present work investigates the effectiveness of the physical-fractional and biological-genetic operators to develop an Optimal Form of Fractional-order PID Controller (O2Fo-PIDC). The newly developed Fo-PIDC with optimal structure and parameters can, also, improve the performances required in the modeling and control of modern manufacturing-industrial process (MIP). The synthesis methodology of the proposed O2Fo-PIDC can be viewed as a multi-level design approach. The hierarchical Multiobjective genetic algorithm (MGA), adopted in this work, can be visualized as a combination of structural and parametric genes of a controller orchestrated in a hierarchical fashion. Then, it is applied to select an optimal structure and knowledge base of the developed fractional controller to satisfy the various design specification contradictories (simplicity, accuracy, stability and robustness).
Бесплатно
