International Journal of Intelligent Systems and Applications @ijisa
Статьи журнала - International Journal of Intelligent Systems and Applications
Все статьи: 1173
Статья научная
This paper describes a method for semantic analysis of natural language queries for Natural Language Interface to Database (NLIDB) using domain ontology. Implementation of NLIDB for serious applications like railway inquiry, airway inquiry, corporate or government call centers requires higher precision. This can be achieved by increasing role of language knowledge and domain knowledge at semantic level. Also design of semantic analyzer should be such that it can easily be ported for other domains as well. In this paper a design of semantic analyzer for railway inquiry domain is reported. Intermediate result of the system is evaluated for a corpus of natural language queries collected from casual users who were not involved in the system design.
Бесплатно
Semantic Enabled Role Based Social Network
Статья научная
Communication is the most common but an intricate activity that we perform every day. Sender sends message, discussions, greetings, gestures, emotics and texts through numerous channels, (e.g. e-mail, messengers, social networks and so on) intending the receiver to understand. The means of personal or group communication has been radically changed over last decade. Geographical, ethnicity, nationality, race, religion are no more hindrance for the sake of social communication. Forms of communication, event, gathering, greetings almost have altered into virtual society. But this hi-tech society has still yet enough room to strengthen its semantic nature. We have made an endeavor to conglomerate the socio-psycho-technical aspect of so-called social networks which could be more realistic, logically inferable and convincible towards people to claim its analogousness with real society. Our devised SN is able to eliminate some weird problems that we face in current SNs, imperfect relationship assignment policies and possibility of data interference among desired and intruder groups.
Бесплатно
Semantic Schema Matching Using DBpedia
Статья научная
In semantic computing, Match is an operator that takes as an input two graph-like structures; it can be database schemas or XML schemas and generates a mapping between the corresponding nodes of the two graphs. In semantic schema matching, we attempt to explore the mappings between the two schemas; based on their semantics by employing any semantic similarity measure. In this study, we have defined taxonomy of all possible semantic similarity measures; moreover we also proposed an approach that exploits semantic relations stored in the DBpedia dataset while utilizing a hybrid ranking system to dig out the similarity between nodes of the two graphs.
Бесплатно
Статья научная
This paper focuses on the construction of a Semi Automatic Ontological tree in the domain of Pilgrimage Tourism in South India for the purpose of enhancing the efficiency in the online Information Retrieval. The proposed system uses two languages Tamil and English for the input query and document retrieval. The user can pose the query in either Tamil or English and the resultant document will be displayed in the query language. In order to retrieve more relevant documents, a semi-automatic Ontology tree has been constructed. The semi automatic ontological tree uses only the English language. Machine Translation approach is used to translate the retrieved result to the language that of the user’s query. Our system produces the better results for the simple user’s query about Pilgrimage Tourism in South India for which the answers could be retrieved from the updated semi automatic ontological tree itself.
Бесплатно
Sensitive Data Protection Based on Intrusion Tolerance in Cloud Computing
Статья научная
Service integration and supply on-demand coming from cloud computing can significantly improve the utilization of computing resources and reduce power consumption of per service, and effectively avoid the error of computing resources. However, cloud computing is still facing the problem of intrusion tolerance of the cloud computing platform and sensitive data of new enterprise data center. In order to address the problem of intrusion tolerance of cloud computing platform and sensitive data in new enterprise data center, this paper constructs a virtualization intrusion tolerance system based on cloud computing by researching on the existing virtualization technology, and then presents a method of intrusion tolerance to protect sensitive data in cloud data center based on virtual adversary structure by utilizing secret sharing. This system adopts the method of hybrid fault model, active and passive replicas, state update and transfer, proactive recovery and diversity, and initially implements to tolerate F faulty replicas in N=2F+1 replicas and ensure that only F+1 active replicas to execute during the intrusion-free stage. The remaining replicas are all put into passive mode, which significantly reduces the resource consuming in cloud platform. At last we prove the reconstruction and confidentiality property of sensitive data by utilizing secret sharing.
Бесплатно
Sensitivity Analysis Using Simple Additive Weighting Method
Статья научная
The output of a multiple criteria decision method often has to be analyzed using some sensitivity analysis technique. The SAW MCDM method is commonly used in management sciences and there is a critical need for a robust approach to sensitivity analysis in the context that uncertain data is often present in decision models. Most of the sensitivity analysis techniques for the SAW method involve Monte Carlo simulation methods on the initial data. These methods are computationally intensive and often require complex software. In this paper, the SAW method is extended to include an objective function which makes it easy to analyze the influence of specific changes in certain criteria values thus making easy to perform sensitivity analysis.
Бесплатно
Статья научная
Social Networks such as Facebook, Twitter, Linked In etc… are rich in opinion data and thus Sentiment Analysis has gained a great attention due to the abundance of this ever growing opinion data. In this research paper our target set is movie reviews. There are diverge range of mechanisms to express their data which may be either subjective, objective or a mixture of both. Besides the data collected from World Wide Web consists of lot of noisy data. It is very much true that we are going to apply some pre-processing techniques and compare the accuracy using Machine Learning algorithm Naïve Bayes Classifier. With ever growing demand to mine the Big Data the open source software technologies such as Hadoop using map reducing paradigm has gained a lot of pragmatic importance. This paper illustrates a comparitive study of sentiment analysis of movie reviews using Naïve Bayes Classifier and Apache Hadoop in order to calculate the performance of the algorithms and show that Map Reduce paradigm of Apache Hadoop performed better than Naïve Bayes Classifier.
Бесплатно
Sentiment Analysis on Twitter Data: Comparative Study on Different Approaches
Статья научная
Social media has become incredibly popular these days for communicating with friends and for sharing opinions. According to current statistics, almost 2.22 billion people use social media in 2016, which is roughly one third of the world population and three times of the entire population in Europe. In social media people share their likes, dislikes, opinions, interests, etc. so it is possible to know about a person’s thoughts about a specific topic from the shared data in social media. Since, twitter is one of the most popular social media in the world; it is a very good source for opinion mining and sentiment analysis about different topics. In this research, SVM with different kernel functions and Adaboost are experimented using CPD and Chi-square feature extraction techniques to explore the best sentiment classification model. The reported average accuracy of Adaboost for Chi-square and CPD are 70.2% and 66.9%. The SVM radial basis kernel and polynomial kernel with Chi-square n-grams reported average accuracy of 73.73% and 68.67% respectively. Among the performed experimentation, SVM sigmoid kernel with Chi-square n-grams provided the maximum accuracy that is 74.4%.
Бесплатно
Sentiment Analysis: A Perspective on its Past, Present and Future
Статья научная
The proliferation of Web-enabled devices, including desktops, laptops, tablets, and mobile phones, enables people to communicate, participate and collaborate with each other in various Web communities, viz., forums, social networks, blogs. Simultaneously, the enormous amount of heterogeneous data that is generated by the users of these communities, offers an unprecedented opportunity to create and employ theories & technologies that search and retrieve relevant data from the huge quantity of information available and mine for opinions thereafter. Consequently, Sentiment Analysis which automatically extracts and analyses the subjectivities and sentiments (or polarities) in written text has emerged as an active area of research. This paper previews and reviews the substantial research on the subject of sentiment analysis, expounding its basic terminology, tasks and granularity levels. It further gives an overview of the state- of – art depicting some previous attempts to study sentiment analysis. Its practical and potential applications are also discussed, followed by the issues and challenges that will keep the field dynamic and lively for years to come.
Бесплатно
Sentiment Predictions using Support Vector Machines for Odd-Even Formula in Delhi
Статья научная
This paper analyzes the odd-even formula in Delhi using tweets posted on Twitter from December 2015 to August 2016. Twitter is a social network where users post their feelings, opinions and sentiments for any event using hashtags and mentions. The tweets posted publicly can be viewed by anyone interested. This paper transforms the unstructured tweets into structured information using open source libraries. Further objective is to build a model using Support Vector Machines (SVM) to classify unseen tweets on the same context. This paper collects tweets on this event under the hashtag "#oddeven formula". This study explores four freely available resources in the form of Application Programming Interfaces (APIs)/Packages for labeling tweets for academic research. Four machine learning models using SVM multi-class classifier were built using the labels provided by the APIs/Packages. The performances of these four models are evaluated through standard evaluation metrics. The experimental results reveal that TextBlob and Pattern python packages outperformed Vivekn and Meaning Cloud APIs. This study may also help in decision making of this event to some extent.
Бесплатно
Sequential Adaptive Fuzzy Inference System Based Intelligent Control of Robot Manipulators
Статья научная
The present paper is dedicated to the presentation and implementation of an optimized technique allowing an on-line estimation of a robot manipulator parameters to use them in a computed torque control. Indeed the proposed control law needs the exact robot model to give good performances. The complexity of the robot manipulator and its strong non-linearity makes it hard to know its parameters. Therefore, we propose in this paper to use neuro-fuzzy networks Sequential Adaptive Fuzzy Inference System (SAFIS) to estimate the parameters of the controlled robot manipulator.
Бесплатно
Sequential Adaptive RBF-Fuzzy Variable Structure Control Applied to Robotics Systems
Статья научная
In this paper, we present a combination of sequential trained radial basis function networks and fuzzy techniques to enhance the variable structure controllers dedicated to robotics systems. In this aim, four RBFs networks were used to estimate the model based part parameters (Inertia, Centrifugal and Coriolis, Gravity and Friction matrices) of a variable structure controller so to respond to model variation and disturbances, a sequential online training algorithm based on Growing-Pruning "GAP" strategy and Kalman filter was implemented. To eliminate the chattering effect, the corrective control of the VS control was computed by a fuzzy controller. Simulations are carried out to control three degrees of freedom SCARA robot manipulator where the obtained results show good disturbance rejection and chattering elimination.
Бесплатно
Short Term Electrical Load Forecasting Based on Weather Parameters under Multiple FIS of Processing
Статья научная
The electrical load forecasting plays a vital role on the economy of a country in context of fuel saving, working hours of employee and depreciation cost of equipment of power generating station. In this paper, we use several machine learning techniques relevant to fuzzy system to forecast the demand of electrical load on short-term basis. Here, we consider temperature, humidity, wind speed, types of day such as working day or holiday, barometric pressure as the parameters, which govern the demand of electrical load. To cope with the variables and the power demand, the previous data of Bangladesh Power Development Board (BPDB) and Bangladesh Space Research and Remote Sensing Organization (SPARRSO) were taken for training purpose and then data of current day was used as the test data. For each of the weather parameter several membership functions (MFs) were used as the fuzzy input and then Takagi-Sugeno, Mamdani rule, FCM + Mamdani and ANFIS were applied to acquire the output as the demand of load. The average percentage of error as the difference between forecasted demand and actual demand of test data was found 1.675% for Takagi-Sugeno, 1.91% for Mamdani (centroid), 2.56% for FCM + Mamdani and 3.62% for ANFIS, which were found superior to some previous research works.
Бесплатно
Simplified real-, complex-, and quaternion-valued neuro-fuzzy learning algorithms
Статья научная
The conventional real-valued neuro-fuzzy method (RNF) is based on classic fuzzy systems with antecedent membership functions and consequent singletons. Rules in RNF are made by all the combinations of membership functions; thus, the number of rules as well as total parameters increase rapidly with the number of inputs. Although network parameters are relatively less in the recently developed complex-valued neuro-fuzzy (CVNF) and quaternion neuro-fuzzy (QNF), parameters increase with number of inputs. This study investigates simplified fuzzy rules that constrain rapid increment of rules with inputs; and proposed simplified RNF (SRNF), simplified CVNF (SCVNF) and simplified QNF (SQNF) employing the proposed simplified fuzzy rules in conventional methods. The proposed simplified neuro-fuzzy learning methods differ from the conventional methods in their fuzzy rule structures. The methods tune fuzzy rules based on the gradient descent method. The number of rules in these methods are equal to the number of divisions of input space; and hence they require significantly less number of parameters to be tuned. The proposed methods are tested on function approximations and classification problems. They exhibit much less execution time than the conventional counterparts with equivalent accuracy. Due to less number of parameters, the proposed methods can be utilized for the problems (e.g., real-time control of large systems) where the conventional methods are difficult to apply due to time constrain.
Бесплатно
Simulation Model of Magnetic Levitation Based on NARX Neural Networks
Статья научная
In this paper, we present analysis of different training types for nonlinear autoregressive neural network, used for simulation of magnetic levitation system. First, the model of this highly nonlinear system is described and after that the Nonlinear Auto Regressive eXogenous (NARX) of neural network model is given. Also, numerical optimization techniques for improved network training are described. It is verified that NARX neural network can be successfully used to simulate real magnetic levitation system if suitable training procedure is chosen, and the best two training types, obtained from experimental results, are described in details.
Бесплатно
Simulation and Analysis of Umbilical Blood Flow using Markov-based Mathematical Model
Статья научная
The intra-uterine development of the fetus depends on various factors, one such critical factor is umbilical blood flow because the quantity of oxygen delivered to the placenta and to the fetus is directly limited by umbilical blood flow rate. Since the measurement of the hemodynamic quantities such as blood pressure and blood flow rate is not possible in utero hence the use of patient-specific mathematical modeling is beneficial for the assessment of feto-maternal well-being. A Markov model based mathematical model of fetal circulation is developed by taking three node concept. The fetus, the umbilical cord, and the placenta represent the 3 nodes of Markov model. A LabVIEW-based virtual instrument is designed to simulate the mathematical model which results in waveform similar to Doppler blood flow velocimetry of umbilical artery. The model is simulated at various degree of conductivity of the umbilical cord to the oxygenated blood. Simulation results show that the umbilical artery blood flow velocity waveform depends on gestation age, fetal heart rate, uterine contraction and placental insufficiency. The Doppler indices calculated from simulation helps in predicting both fetal and maternal abnormalities at various degrees of the conductivity to the blood flow passage. Therefore, integrating patient-specific models along with established medical equipments will be helpful in identifying true intra-uterine growth restricted fetuses from normal fetuses and helps clinicians to take timely interventions.
Бесплатно
Simulation for the reverse extrapolation of radar threats and their verification
Статья научная
Various and unpredictable electronic warfare situations drive the development of an integrated electronic warfare (EW) simulator that can perform electronic warfare modeling and simulation on radar threats. This paper introduces the basic components of simulation system that enables our agents to be operational in EW settings. In various simulation of EW environments, our agents can preset their path in the existence of enemy radars' surveillance and autonomously be aware of radar threats while they proceed in their own route. As reversely extrapolating radar threats given radio-active parameters received, our agents perform an appropriate jamming technique in order to deceive the enemy radar keeping track of our agents. Based upon the response of the radar threat attacked by the jamming techniques, our agents figure out the types of the radar threat and verify its identification. For the actual and helpful information, real radars with the probability of similarity could be prioritized from radar database. The integrated EW simulator that we have designed and developed in this paper enables our agents to perform such capabilities as reverse extrapolation of RF threats, its verification using jamming, and recommendation of similar radars, and to evaluate their autonomous behaviors in a tapestry of realistic scenarios.
Бесплатно
Статья научная
This paper introduces the status of parallel-type Electrostatic Fabric Filter was researched, and the factors influencing collection efficiency were analyzed in this paper. Using software Gambit, which also meshed the calculating region, a three-dimensional structure model of the precipitator was established. And then the numerical simulation of the air distribution characteristic was carried on with the software of fluent 6.2, which sets the boundary conditions, standard k-ε 2-equation model and SIMPLE algorithm; Then draw the path line and contour chart of the cross-section, obtained the mean square deviation value, analyzed the airflow distribution situation and the reasons for why its uneven. By setting an appropriate opening rate for the airflow distribution plates and collection plates to improve the air distribution. The results show that the airflow distribution can be uniformed by improving the opening rate of the collection plates. The numerical simulation result is more reasonable and can be used as the reference of optimizing the structural design of Electrostatic Fabric Filter.
Бесплатно
Simulation of Fuzzy Logic Based Shunt Hybrid Active Filter for Power Quality Improvement
Статья научная
This paper deals with the implementation of fuzzy logic based Shunt Hybrid Active Filter (SHAF) with non-linear load to minimize the source current harmonics and provide reactive power compensation. Comparison with Proportional Integral (PI) based SHAF is also analyzed. Shunt Hybrid Active Filter is constituted by Active Filter connected in shunt and shunt connected three phase single tuned LC filter for 5th harmonic frequency with rectifier load. The Active Filtering System is based on Synchronous Reference Frame. The proposed fuzzy logic based control strategy improves active filter operation and reduces the selective harmonic contents. The control strategies are demonstrated through MATLAB Simulated Environment.
Бесплатно
Simulation of High Step-Up DC–DC Converter for Photovoltaic Module Application using MATLAB/SIMULINK
Статья научная
As per the present scenario lot of power shortages are there in all over the world especially country like India the grid transferring problem is also high. Almost the power from the fossil fuels are becoming so less some of the examples of the fossil fuels are (coal, lignite, oil, and gases).So most of them looking in forward for the power from green or renewable based energies like solar, wind, biomass, tidal etc. Which does not cause any pollution to the environment. In this paper the simulation and analysis of the PV panel and also high efficient boost converter design and simulation is also performed. Even though the solar based systems are renewable based energies when compared to other renewable energies like wind, biomass it does not connect to more number of grid connections. Lot of necessary steps want to be taken one of the main important factor that high efficient boost converter is needed, here in this paper the input voltage to the boost converter is given as 15V and receives the output voltage of 55.64V
Бесплатно
