Статьи журнала - International Journal of Intelligent Systems and Applications
Все статьи: 1159
Source Code Author Attribution Using Author's Programming Style and Code Smells
Статья научная
Source code is an intellectual property and using it without author's permission is a violation of property right. Source code authorship attribution is vital for dealing with software theft, copyright issues and piracies. Characterizing author's signature for identifying their footprints is the core task of authorship attribution. Different aspects of source code have been considered for characterizing signatures including author's coding style and programming structure, etc. The objective of this research is to explore another trait of authors' coding behavior for personifying their footprints. The main question that we want to address is that "can code smells are useful for characterizing authors' signatures? A machine learning based methodology is described not only to address the question but also for designing a system. Two different aspects of source code are considered for its representation into features: author's style and code smells. The author's style related feature representation is used as baseline. Results have shown that code smell can improves the authorship attribution.
Бесплатно
Speed up linear scan in high-dimensions by sorting one-dimensional projections
Статья научная
High-dimensional indexing is a pervasive challenge faced in multimedia retrieval. Existing indexing methods applying linear scan strategy, such as VA-file and its variations, are still efficient when the dimensionality is high. In this paper, we propose a new access idea implemented on linear scan based methods to speed up the nearest-neighbor queries. The idea is to map high-dimensional points into two kinds of one-dimensional values using projection and distance computation. The projection values on the line determined by the first Principal Component are sorted and indexed using a B+-tree, and the distances of each point to a reference point are also embedded into leaf node of the B+-tree. When performing nearest neighbor search, the Partial Distortion Searching and triangular inequality are employed to prune search space. In the new search algorithm, only a small portion of data points need to be linearly accessed by computing the bounded distance on the one-dimensional line, which can reduce the I/O and processor time dramatically. Experiment results on large image databases show that the new access method provides a faster search speed than existing high-dimensional index methods.
Бесплатно
Spiking neural network and bull genetic algorithm for active vibration control
Статья научная
Systems with flexible structures display vibration as a characteristic property. However, when exposed to disturbing forces, then the component and/or structural nature of such systems are damaged. Therefore, this paper proposes two heuristics approaches to reduce the unwanted structural response delivered due to the external excitation; namely, bull genetic algorithm and spiking neural network. The bull genetic algorithm is based on a new selection property inherited from the bull concept. On the other hand, spiking neural network possess more than one synaptic terminal between each neural network layer and each synaptic terminal is modelled with a different period of delay. Extensive simulations have been conducted using simulated platform of a flexible beam vibration. To validate the proposed approaches, we performed a qualitative comparison with other related approaches such as traditional genetic algorithm, general regression neural network, bees algorithm, and adaptive neuro-fuzzy inference system. Based on the obtained results, it is found that the proposed approaches have outperformed other approaches, while bull genetic algorithm has a 5.2% performance improvement over spiking neural network.
Бесплатно
Статья научная
Soil cave foundation is a common type in the soil foundation in karst area, the stability of the foundation will be directly affected by the soil cave collapse destruction. Currently, the stability evaluation of soil cave foundation is mostly focus on the quantitative evaluation, such as the collapse mechanism and prevention, while the qualitative assessment is rare. Based on the plastoelasticity theory, firstly analyze the stress state of the soil cave wallsurrounding body in the foundation, distinguish the stress concentration influence area, then improve the soil cave foundation stability computation model by using Molecoulomb strength criterion, finally, take a soil cave foundation stability evaluation as the example in Tongren area, Guizhou, confirming the feasibility and reliability of the improvement model. The influence of the foundation bed size, buried depth, soil cave shape and groundwater level depth was further studied, which reveals the mechanism of the soil cave collapse destruction. And the research indicated that the improved model is feasible, when the foundation bed size is smaller, the buried depth is shallower, the hole shape is more spiky and the groundwater level depth is shallower, the soil cave stability coefficient will be bigger, which is more advantageous to the stability, and the influence of groundwater level depth is more sensitive to the soil cave stability, once the groundwater level depth dropped a little, the stable soil cave will become into failure and instability. Therefore, the quantitative evaluation should be paid more attention in soil cave foundation stability evaluation, particularly under the ground water environment, simultaneously, the calculation results, like soil cave foundation maximum size, the critical buried depth, the maximum water level buried depth, have the strong directive function to the soil cave foundation treatment and design.
Бесплатно
Static Security Enhancement and Loss Minimization Using Simulated Annealing
Статья научная
This paper presents a developed algorithm for optimal placement of thyristor controlled series capacitors (TCSC’s) for enhancing the power system static security and minimizing the system overall power loss. Placing TCSC’s at selected branches requires analysis of the system behavior under all possible contingencies. A selective procedure to determine the locations and settings of the thyristor controlled series capacitors is presented. The locations are determined by evaluating contingency sensitivity index (CSI) for a given power system branch for a given number of contingencies. This criterion is then used to develop branches prioritizing index in order to rank the system branches possible for placement of the thyristor controlled series capacitors. Optimal settings of TCSC’s are determined by the optimization technique of simulated annealing (SA), where settings are chosen to minimize the overall power system losses. The goal of the developed methodology is to enhance power system static security by alleviating/eliminating overloads on the transmission lines and maintaining the voltages at all load buses within their specified limits through the optimal placement and setting of TCSC’s under single and double line outage network contingencies. The proposed algorithm is examined using different IEEE standard test systems to shown its superiority in enhancing the system static security and minimizing the system losses.
Бесплатно
Static Timing Analysis of Different SRAM Controllers
Статья научная
Timing-critical path analysis is one of the most significant terms for the VLSI designer. For the formal verification of any kinds of digital chip, static timing analysis (STA) plays a vital role to check the potentiality and viability of the design procedures. This indicates the timing status between setup and holding times required with respect to the active edge of the clock. STA can also be used to identify time sensitive paths, simulate path delays, and assess Register transfer level (RTL) dependability. Four types of Static Random Access Memory (SRAM) controllers in this paper are used to handle with the complexities of digital circuit timing analysis at the logic level. Different STA parameters such as slack, clock skew, data latency, and multiple clock frequencies are investigated here in their node-to-node path analysis for diverse SRAM controllers. Using phase lock loop (ALTPLL), single clock and dual clock are used to get the response of these controllers. For four SRAM controllers, the timing analysis shows that no data violation exists for single and dual clock with 50 MHz and 100 MHz frequencies. Result also shows that the slack for 100MHz is greater than that of 50MHz. Moreover, the clock skew value in our proposed design is lower than in the other three controllers because number of paths, number of states are reduced, and the slack value is higher than in 1st and 2nd controllers. In timing path analysis, slack time determines that the design is working at the desired frequency. Although 100MHz is faster than 50MHz, our proposed SRAM controller meets the timing requirements for 100MHz including the reduction of node to node data delay. Due to this reason, the proposed controller performs well compared to others in terms slack and clock skew.
Бесплатно
Steganographic Data Hiding using Modified APSO
Статья научная
In this paper we are analyzing the steganographic data hiding using the least significant bit technique. This paper describes the particle swarm optimisation. The particle swarm optimisation algorithm is applied to the spatial domain technique. The improved algorithm called the accelerated particle swarm optimisation converges faster than the usual particle swarm optimisation and improves the performance. This paper also analyses the modified particle swarm optimisation on the spatial domain technique which improved the PSNR and also reduced the computation time.
Бесплатно
Step Response Enhancement of Hybrid Stepper Motors Using Soft Computing Techniques
Статья научная
This paper presents the use of different soft computing techniques for step response enhancement of Hybrid Stepper Motors. The basic differential equations of hybrid stepper motor are used to build up a model using MATLAB software package. The implementation of Fuzzy Logic (FL) and Proportional-Integral-Derivative (PID) controllers are used to improve the motor performance. The numerical simulations by a PC-based controller show that the PID controller tuned by Genetic Algorithm (GA) produces better performance than that tuned by Fuzzy controller. They show that, the Fuzzy PID-like controller produces better performance than the other linear Fuzzy controllers. Finally, the comparison between PID controllers tuned by genetic algorithm and the Fuzzy PID-like controller shows that, the Fuzzy PID-like controller produces better performance.
Бесплатно
Stimulate Engagement and Motivation in MOOCs Using an Ontologies Based Multi-Agents System
Статья научная
Today, Massive Open Online Courses (MOOCs) have the potential to enable free online education on an enormous scale. However, a concern often raised about MOOCs is the consistently high drop-out rate of MOOC learners. Although many thousands of learners enroll on these courses, a very small proportion actually complete the course. This work is at the heart of this issue. It is interested in contributing on multi-agents systems and ontologies to describe the learning preferences and adapt educational resources to learner profile in MOOCs platforms. The primary aim of this work is to exploit the potential of multi-agents systems and ontologies to improve learners' engagement and motivation in MOOCs platforms and therefore reduce the drop-out rates. As part of the contribution of this work, the paper proposes a model of Multi-Agent System (MAS), based on ontologies for adapting the learning resources proposed to a learner in a MOOCs platform according to his learning preferences. To model an adequate online course, the determination of learner's preferences is done through the analysis of learner behavior relying on his indicator MBTI (Myers Briggs Type Indicator). The proposed model integrates the main functionalities of an intelligent tutoring system: profiling, updating of the profile, selection, adaptation and presentation of adequate resources. The architecture of the proposed system is composed on two main agents, four ontologies and a set of modules implemented.
Бесплатно
Strategic Sensor Placement for Intrusion Detection in Network-Based IDS
Статья научная
Network Intrusion Detection Systems (NIDSs) can be composed of a potentially large number of sensors, which monitor the traffic flowing in the network. Deciding where sensors should be placed and what information they need in order to detect the desired attacks can be a demanding task for network administrators, one that should be made as automatic as possible. Some few works have been done on positioning sensors using attack graph analysis, formal logic-based approach and Network Simulator NS2 which were studied to determine a strategy for sensors placement on the network. This paper analysed the major considerations for sensors placements, typical sensors deployments in NIDS, and established an extended model for sensors deployment to further strengthen the network for intrusion detection which was based on the escape of some malicious activities through the firewall.
Бесплатно
String Variant Alias Extraction Method using Ensemble Learner
Статья научная
String variant alias names are surnames which are string variant form of the primary name. Extracting string variant aliases are important in tasks such as information retrieval, information extraction, and name resolution etc. String variant alias extraction involves candidate alias name extraction and string variant alias validation. In this paper, string variant aliases are first extracted from the web and then using seven different string similarity metrics as features, candidate aliases are validated using ensemble classifier random forest. Experiments were conducted using string variant name-alias dataset containing name-alias data for 15 persons containing 30 name-alias pairs. Experimental results show that the proposed method outperforms other similar methods in terms of accuracy.
Бесплатно
Structural Identifiability of Nonlinear Dynamic Systems under Uncertainty
Статья научная
Approach to the analysis of nonlinear dynamic systems structural identifiability (SI) under uncertainty proposed. This approach has a difference from methods applied to SI estimation of dynamic systems in the parametrical space. Structural identifiability interpreted as of the structural identification possibility a nonlinear system part. We show that the input has S-synchronization property for the solution of the SI task. The identifiability method based on the analysis of structures. The input parameter effect on the possibility of the system SI estimation is studied.
Бесплатно
Structural Identification of Dynamic Systems with Hysteresis
Статья научная
The method of structural identification dynamic systems with a hysteresis in the conditions of uncertainty is developed. The method is based on selection of the special set containing the information on properties of a nonlinear part system. The virtual structure (VS) which allows the make the decision about hysteresis structure is offered. The concept of structural identifiability of nonlinear dynamic systems is introduced. Structural identifiability is a necessary condition of obtaining the original form of hysteresis. The criterion of structural identifiability is proposed. The solution of a problem selection the class of the functions belonging to hysteresis to nonlinearities is given. The procedure of structural identification of hysteresis functions is developed. Procedure realization is based on the phenomenological analysis of structure VS. Defini-tion of features and properties of the VS is the goal of phenomenological analysis. Each non-linearity introduces the features in the behavior of the system. Therefore, their detection gives only the concrete analysis of VS. Algorithms of estimation structural parameters the hysteresis in the conditions of uncertainty are offered. They analyze the data in special structural space and are based on the application of secant method VS. Such approach gives adequate estimations of parameters hysteresis. The method of the structurally-frequency analysis is offered for check of the obtained results and estimations. It is based on the analysis of fragments VS in two planes. Such analysis allows the make a decision about hysteresis structure. We show that the offered methodology is applicable to unstable dynamic systems. Results of the computer simulation are given.
Бесплатно
Structural Identification of Nonlinear Dynamic Systems
Статья научная
The method of structural identification nonlinear dynamic systems is offered in the conditions of uncertainty. The method of construction the set containing the data about a nonlinear part of system is developed. The concept of identifiability system for a solution of a problem structural identification is introduced. The special class of structures S for a solution of problem identification is introduced. We will show that the system is identified, if the structure S is closed. The method of estimation the class of nonlinear functions on the basis of the analysis sector sets for the offered structure S is described. We showed, as on S a preliminary conclusion about a form of nonlinear function to make. We offer algorithms of structural identification of single-valued and many-valued nonlinearities. Examples of structural identification of nonlinear systems are considered.
Бесплатно
Structural Identification of Nonlinear Static System on Basis of Analysis Sector Sets
Статья научная
Methods of structural identification of static systems with a vector input and several nonlinearities in the conditions of uncertainty are considered. We consider inputs irregular. The concept of structural space is introduced. In this space special structures (virtual portraits) are analyzed. The Holder condition is applied to construction of sector set, to which belongs a virtual portrait of system of identification. Criteria of decision-making on a class of nonlinear functions on the basis of the analysis of proximity of sector sets are described. Procedures of an estimation of structural parameters of two classes of nonlinearities are stated: power and a hysteresis.
Бесплатно
Structural Identification of Systems with Distributed Lag
Статья научная
The problem of structural identification of systems with the distributed lag in the conditions of uncertainty is considered. Known statistical approaches are laborious and not always allow making the decision on lag structure. Therefore in work for the problem decision the special class of static structures (SS) (virtual portraits) explored system is introduced. Process of the decision of a problem consists of two steps. At the first step set of secants for initial system is under construction. Completeness of set of secants is a sign of linearity of system. Nonfulfilment of conditions of completeness is a sign of nonlinearity of system. Estimation of nonlinearity of system execute on an indicator of level of nonlinearity of the system, offered in work. At the second step the special structural space is introduced and is defined SS for a nonlinear part of system. The estimation of nonlinear properties of system is executed on the basis of identification of parameters of set of secants SS. Criteria and algorithms of decision-making on structure of a lag on the basis of the analysis of virtual portraits are offered. The analogue of criterion of Durbin-Watson is offered. The received results are generalized on a case of the distributed lag in input and output variables of system. It is shown that to structural identification of systems with the distributed lag we will not apply the analysis of sector sets. The approach to parametrical identification of system with the distributed lag in the conditions of uncertainty is offered.
Бесплатно
Structural Methods of Estimation Lyapunov Ex-ponents Linear Dynamic System
Статья научная
The problem of structural identification linear dynamic systems on the basis of the analysis Lyapunov exponent in the conditions of uncertainty is considered. The method of estimation the general solution system on the basis of application static model is developed. Defini-tion of Lyapunov exponent (LE) on the analysis of a coefficient structural properties system is grounded. On the basis of a coefficient of structural properties the special structures reflecting change LE are introduced. The criterion of estimation an order system on the basis of the analysis behaviour these structures are offered. The decision-making method about type of roots dynamic system on the basis of the analysis of time series and the structures reflecting change LE is developed. Two approaches to an estimation of the largest LE and the Perron bottom indexes are offered. The first approach to identification of a change in a coefficient of structural properties with the help secant method for various classes of roots is grounded. The second approach is the structurally-frequency method grounded on definition of estimations LE by means of the analysis of local minima of structures offered in work. The frequency method which is a modification of a method a bar graph in the statistical theory is applied to a validation of the obtained estimations. Results of simulation confirm effectiveness of the offered methods, structures and procedures.
Бесплатно
Статья научная
Structural transformations of incoming informational signal by a single nonlinear oscillatory neuron or an artificial nonlinear neural network are investigated. The neurons are modeled as threshold devices so that the artificial nonlinear neural network under consideration are systems of nonlinear van der Pol type oscillatory neurons. The neurons are coupled by synaptic weight coefficients to endow the systems with the configuration topology of a chain or a ring. It is shown that the morphology of the outgoing signal – with respect to the shape, amplitude and time dependence of the instantaneous frequency of the signal – at the output of such a neural network has a higher degree of stochasticity than the morphology of the signal at the output of a single neuron. We conclude that the process of coding by a single neuron or an entire chain-like or circular neural network may be considered in terms of frequency modulations, which are known in Physics as a way to transmit information. We conjecture that frequency modulations constitute one of the ways of coding of information by the neurons in these types of neural networks.
Бесплатно
Structural-parametrical design method of adaptive observers for nonlinear systems
Статья научная
The structural-parametrical method for design of adaptive observers (AO) for nonlinear dynamic systems under uncertainty is proposed. The design of AO is consisting of two stages. The structural stage allowed identifying a class of nonlinearity and its structural parameters. The solution of this task is based on an estimation of the system structural identifiability (SI). The method and criteria of the system structural identifiability are proposed. Effect of an input on the SI is showed. We believe that the excitation constancy condition is satisfied for system variables. Requirements to the input at stages of structural and parametrical design of AO differ. The parametrical design stage AO uses the results obtained at the first stage of the adaptive observer construction. Two cases of the structural information application are considered. The main attention is focused on the case of the insufficient structural information. Adaptive algorithms for tuning of parameters AO are proposed. The uncertainty estimation procedure is proposed. Stability of the adaptive system is proved. Simulation results confirmed the performance of the proposed approach.
Бесплатно
Study of Memory Effect in a Fuzzy EOQ Model with No Shortage
Статья научная
The feature of the fractional order derivative and fractional order integration is one of the important tools to realize the beauty of the fractional calculus. Fractional order derivative and integration has a long history like classical calculus but its users are much less compared to the classical calculus. The purpose of this paper is to study an inventory model with linear type demand rate under the fuzzy environment. This paper also wants to introduce the memory effect property of fractional order derivative which can help to setup the model more authentic. Two advantages have been included to the model (i) memory effect,(ii) fuzzy environment. Here, the fractional order model is defuzzyfied using (i) signed distance method,(ii) graded mean integration method. Fuzzification can close to the reality with incorporating uncertainty behavior of some economic parameters of the inventory system and fractional order can explain the memory phenomena. For this problem due to illustrate defuzzification, set up cost, holding cost per unit, per unit cost are assumed as triangular fuzzy numbers. Fractional order derivative and integration are applied to develop the whole work. It is known that fractional calculus is a valuable tool to describe memory phenomena. Fractional order is established as the index of the memory. In this paper, depending on strength of memory, memory phenomena considered in two steps(i) long memory,(ii) short memory. The proposed fuzzy models and technique lastly have been illustrated. Results of two defuzzyfications are compared with graphical presentations. This present studies can help to moderate the classical fuzzy inventory model. From the numerical studied it is observed that in long memory effect, profit is good compared to the low memory effect or memory less system.
Бесплатно
