International Journal of Intelligent Systems and Applications @ijisa
Journal articles - International Journal of Intelligent Systems and Applications
All articles: 1264
Fault Diagnosis of Mixed-Signal Analog Circuit using Artificial Neural Networks
Scientific article
This paper presents parametric fault diagnosis in mixed-signal analog circuit using artificial neural networks. Single parametric faults are considered in this study. A benchmark R2R digital to analog converter circuit has been used as an example circuit for experimental validations. The input test pattern required for testing are reduced to optimum value using sensitivity analysis of the circuit under test. The effect of component tolerances has also been taken care of by performing the Monte-Carlo analysis. In this study parametric fault models are defined for the R2R network of the digital to analog converter. The input test patterns are applied to the circuit under test and the output responses are measured for each fault model covering all the Monte-Carlo runs. The classification of the parametric faults is done using artificial neural networks. The fault diagnosis system is developed in LabVIEW environment in the form of a virtual instrument. The artificial neural network is designed using MATLAB and finally embedded in the virtual instrument. The fault diagnosis is validated with simulated data and with the actual data acquired from the circuit hardware.
Free
Fault Tolerant Multi-Criteria Multi-Path Routing in Wireless Sensor Networks
Scientific article
The Ad Hoc On-Demand Multi-Path Distance Vector (AOMDV) routing protocol allows the transport of data along one or more paths in wireless sensor networks (WSNs). The path chosen is based on a single shortest path hop count metric. The data on some WSNs is mission critical, for example, military and health care applications. Hence, fault tolerance in WSNs is becoming increasingly important. To improve the fault tolerance of WSNs in lossy environments, this work adds to the AOMDV routing protocol as it incorporates an additional packet loss metric. This Multi-criteria AOMDV or M-AOMDV is evaluated using the ns2 simulator. Simulations show that M-AOMDV maintains relatively low packet loss rates when the WSN is experiencing loss.
Free
Scientific article
Propagated electromagnetic signal over the cellular radio communication channels and interfaces are usually highly stochastic and complex with unequal noise variation pattern. This is due to multipath nature of the propagation channels and diverse radio propagation mechanisms that impact the signal strength at the receiver en-route the transmitter, and verse versa. This also makes measurement, predictive modeling and estimation based analysis of such signal very challenging and complex as well. One important and popular parametric modelling and estimation technique in mathematics and engineering science, especially for signal processing applications is the least square regression (LSR). The dominance use and popularity of the LSR approach may be attributed to its simplified supporting theory, relatively fast application procedure and ubiquitous application packages. However, LSR is known to be very sensitive to outliers and unusual stochastic signal data. In this work, we propose the application of weighted least square regression method for enhanced propagation practical field strength estimation modelling over cellular radio communication networks interface. The signal data was collected from a commercial LTE networks service provider. Also, we provide statistical computational analyses to compare the resultant estimation outcome of the weighted least square and the standard least approach. From the result, it is found that the WLSR approach is reliably better the most popular standard least square method. The significance and academic of value of this paper is that our proposed and implemented WLSR method can used as replacement of the standard LSR approach for robust mobile signal processing of future communication system networks.
Free
Filter Loop Reduction in DT BP Sigma-Delta Modulator Assisted by Noise Coupling Technique
Scientific article
In bandpass modulators, a 2N-order loop filter can lead to an N-order noise shaping in the band of interest. This caused a bandpass modulator with more complex structure than a lowpass modulator and increased the power consumption and area of the modulator. In this paper, we proposed a discrete-time bandpass modulator using the noise-coupling technique that only needs to a second- order loop filter to have a second-order noise shaping. To realize a noise coupled bandpass modulator, we need to implement Z-2 delay block in the analog domain, but the proposed modulator uses only Z-1 delay blocks to apply the noise coupling technique. This simplifies the structure of the modulator and reduces the power consumption, area, and nonlinearity of the modulator. The error in the coupling path is considered and the effect of it on the modulator resolution is analyzed. According to the simulation results, the proposed modulator results in SNR = 84.9 dB at 80 MHz sampling frequency, 200 KHz bandwidth and OSR = 200.
Free
Finding Representative Test Case for Test Case Reduction in Regression Testing
Scientific article
Software testing is one of the important stages of software development. In software development, developers always depend on testing to reveal bugs. In the maintenance stage test suite size grow because of integration of new technique. An addition of new technique force to create new test case which increase the size of test suite. In regression testing new test case may be added to the test suite during the whole testing process. These additions of test cases create possibility of presence of redundant test cases. Due to limitation of time and resource, reduction techniques should be used to identify and remove them. Research shows that a subset of the test case in a suit may still satisfy all the test objectives which is called as representative set. Redundant test case increase the execution cost of the test suite, in spite of NP-completeness of the problem there are few good reduction techniques have been available. In this paper a new approach for test case reduction is proposed. This algorithm use genetic algorithm technique iteratively with varying chromosome length to reduce test case in a test suit by finding a representative set of test cases that are fulfill the testing criteria.
Free
Finding Within Cluster Dense Regions Using Distance Based Technique
Scientific article
One of the main categories in Data Clustering is density based clustering. Density based clustering techniques like DBSCAN are attractive because they can find arbitrary shaped clusters along with noisy outlier. The main weakness of the traditional density based algorithms like DBSCAN is clustering the different density level data sets. DBSCAN calculations done according to given parameters applied to all points in a data set, while densities of the data set clusters may be totally different. The proposed algorithm overcomes this weakness of the traditional density based algorithms. The algorithm starts with partitioning the data within a cluster to units based on a user parameter and compute the density for each unit separately. Consequently, the algorithm compares the results and merges neighboring units with closer approximate density values to become a new cluster. The experimental results of the simulation show that the proposed algorithm gives good results in finding clusters for different density cluster data set.
Free
Finding the Number of Clusters in Data and Better Initial Centers for K-means Algorithm
Scientific article
The k-means is the most well-known algorithm for data clustering in data mining. Its simplicity and speed of convergence to local minima are the most important advantages of it, in addition to its linear time complexity. The most important open problems in this algorithm are the selection of initial centers and the determination of the exact number of clusters in advance. This paper proposes a solution for these two problems together; by adding a preprocess step to get the expected number of clusters in data and better initial centers. There are many researches to solve each of these problems separately, but there is no research to solve both problems together. The preprocess step requires o(n log n); where n is size of the dataset. This preprocess step aims to get initial portioning of data without determining the number of clusters in advance, then computes the means of initial clusters. After that we apply k-means on original data using the resulting information from the preprocess step to get the final clusters. We use many benchmark datasets to test the proposed method. The experimental results show the efficiency of the proposed method.
Free
Football match prediction with tree based model classification
Scientific article
This paper presents the football match prediction using a tree-based model algorithm (C5.0, Random Forest, and Extreme Gradient Boosting). Backward wrapper model was applied as a feature selection methodology to help select the best feature that will improve the accuracy of the model. This study used 10 seasons of football data match history (2007/2008 – 2016/2017) in the English Premier League with 15 initial features to predict the match results. With the tuning process, each model showed improvement in accuracy. Random Forest algorithm generated the best accuracy with 68,55% while the C5.0 algorithm had the lowest accuracy at 64,87% and Extreme Gradient Boosting algorithm produced accuracy of 67,89%. With the output produced in this study, the Decision Tree based algorithm is concluded as not good enough in predicting a football match history.
Free
Force-Directed Method in Mirror Frames for Graph Drawing
Scientific article
The most widely used algorithms for graph drawing are force-directed algorithms. We should modify a hybrid force model that is coupling a traditional spring force model and a novel repulsive force model will be proposed to solve the graph drawing problems in 2-D space. Especially, regular triangle drawing frame can be applied to binary tree drawing problems that on an important contribution to computer science. And apply circle drawing frame to normal graph drawing problems, we get satisfactory and aesthetic criteria graphics.
Free
Forecasting Performance of Random Walk with Drift and Feed Forward Neural Network Models
Scientific article
In this study, linear and nonlinear methods were used to model forecasting performances on the daily crude oil production data of the Nigerian National Petroleum Corporation (NNPC). The linear model considered here is the random walk with drift, while the nonlinear model is the feed forward neural network model. The results indicate that nonlinear methods have better forecasting performance greater than linear methods based on the mean error square sense. The root mean square error (RMSE) and the mean absolute error (MAE) were applied to ascertain the assertion that nonlinear methods have better forecasting performance greater than linear methods. Autocorrelation functions emerging from the increment series, that is, log difference series and difference series of the daily crude oil production data of the NNPC indicates significant autocorrelations. As a result of the foregoing assertion we deduced that the daily crude oil production series of the NNPC is not firmly a random walk process. However, the original daily crude oil production series of the NNPC was considered to be a random walk with drift when we are not trying to forecast immediate values. The analysis for this study was simulated using MATLAB software, version 8.03.
Free
Forecasting of dry freight index data by using machine learning algorithms
Scientific article
Discovery of meaningful information from the data and design of an expert system are carried out within the frame of machine learning. Supervised learning is used commonly in practical machine learning. It includes basically two stages: a) the training data are sent to as input to the classifier algorithms, b) the performance of pre-learned algorithm is tested on the testing data. And so, knowledge discovery is carried out through the data. In this study, the analysis of Lloyd data is performed by utilizing Gradient Boosted Trees and Multi-Layer Perceptron learning algorithms. Lloyd data consist of the Baltic Dry Index, Capesize Index, Panamax Index and Supramax Index values, updated daily. Accurate prediction of these data is very important in order to eliminate the risks of commercial organization. Eight datasets from Lloyd data are obtained within the frame of two scenarios: a) the last three index values in the freight index datasets; b) the last three index values in both crude oil price and freight index datasets. The results show that the models designed with Gradient Boosted Trees and Multi-Layer Perceptron algorithms are successful for Lloyd data prediction and so proved their applicability.
Free
Formal and Informal Modeling of Fault Tolerant Noc Architectures
Scientific article
The suggested new approach based on B-Event formal technics consists of suggesting aspects and constraints related to the reliability of NoC (Network-On-chip) and the over-cost related to the solutions of tolerances on the faults: a design of NoC tolerating on the faults for SoC (System-on-Chip) containing configurable technology FPGA (Field Programmable Gates Array), by extracting the properties of the NoC architecture. We illustrate our methodology by developing several refinements which produce QNoC (Quality of Service of Network on chip) switch architecture from specification to test. We will show how B-event formalism can follow life cycle of NoC design and test: for example the code VHDL (VHSIC Hardware Description Language) simulation established of certain kind of architecture can help us to optimize the architecture and produce new architecture; we can inject the new properties related to the new QNoC architecture into formal B-event specification. B-event is associated to Rodin tool environment. As case study, the last stage of refinement used a wireless network in order to generate complete test environment of the studied application.
Free
Formal validation of data warehouse complexity metrics using distance framework
Scientific article
Data Warehouse is the cornerstone for organizations that base their strategic decisions on the large scale processing of numerical data. The success of the organization depends on these decisions and hence it becomes extremely important to have a quality data warehouse. Conceptual models have been widely recognized as a key determinant of data warehouse quality during the early stages of design. Recently, metrics have been proposed by authors based on hierarchies to quantify the complexity and inturn quality of the conceptual models of data warehouse. They have formally corroborated the measures against Briand’s property based framework to ensure their validity. However, Briand’s set of properties for software measures are a set of necessary but not sufficient measure axioms. They are advantageous to refute software metrics but not to validate them. Thus, we focus on the theoretical validation of the data warehouse conceptual model metrics using the Distance framework whose sufficiency is ensured by the measurement theory. The results indicate that the metrics are valid measures of the complexity of data warehouse conceptual models. Besides, validation by Distance framework assures that the metrics are in the ratio scale which further aids in data analysis.
Free
Formation of optimum temperature graph of paper web warming
Scientific article
To date, the requirements for the quality of paper products are increasing. At the same time, the most common trend in recent years is improving the resource and energy conservation of all technological processes. From the point of view of specialists in the field of paper industry in technological process of production on a paper machine, the greatest attention must be paid to the drying of a paper web. This process is the most expensive and decisive for a large number of quality parameters of finished products. In order to satisfy these requirements, it is necessary to implement a system of optimal control for this technological process. The first and one of the most important parts of the development of such system is the formation of a criterion for the optimal control and calculation of the optimal mode of operation of the first stage of drying - the heating of a paper web. For this purpose, the problem of calculating the optimal temperature graph of heating the paper web in the drying section of a paper machine is considered. Proposed quality control criterion ensures the maintenance of the parameters of finished products within the limits defined by the standard. Established limitations on the dynamics of temperature change on each drying cylinder and the final values. The calculation of the optimal temperature schedule is made by taking into account the characteristics of the material, the changes in the parameters of heat and mass transfer, which are functional dependences on the temperature of the paper web. The formulas for calculating the temperature of the paper at the exit from each drying cylinder and the free movement sections are based on the data on partial pressure on the surface of the paper web and in the environment. Results of the work are presented in the form of a step-by-step algorithm. Implementation of the developed algorithm ensures uniform heating of the paper web and reaches the optimum temperature for effective removal of moisture.
Free
Scientific article
The paper presents a detailed discussion on the structural organisation of a Fuzzy Inference System Planner (FISPLAN) for Autonomous Underwater Vehicles (AUVs), including elaboration of membership functions for the inputs as well as outputs. The inference mechanism is detailed with discussions on the rule base, which in essence incorporates the planning logic. In order to assess the effectiveness of the planner as a means of reactive escape under critical situations, a case study is studied with reference to a state of the art AUV. An approximate subsea current model is developed from field observations, and residual energy is estimated by referring to a typical Lithium-polymer cell discharge characteristic together with data recorded in actual field trials. Situations are simulated by considering different combinations of sea-currents as well as status of resident energy. Results reveal that the simulated system, by virtue of the planner, is capable of perceiving situations, thereby realizing their imminence and making a decisive action thereupon. In concise, the fuzzy planner may be considered to provide human-like perception of situations on the basis of crisp observations. Furthermore dynamics of the system are modelled with actual parameters, and subsequently controller responses for pitching and velocity correction are illustrated. Choice of planning interval is also expressed as a function of the controllers' response.
Free
Fractional Order EOQ Model with Linear Trend of Time-Dependent Demand
Scientific article
In this paper we introduce the classical EOQ model with a linear trend of time-dependent demand having no shortages using the concept of fractional calculus. The application of fractional calculus has been already used in classical EOQ model where the demand is assumed to be constant. In this present article fractional differential calculus can be used to describe EOQ model with time-dependent linear trend of demand to develop more generalized EOQ model. Here, we want to discuss more deeply its role as a tool for describing the traditional classical EOQ model with time dependent demand.
Free
Framework for Incident Identification Based on LLMs and Cybersecurity Ontologies
Scientific article
Accurate and immediate incident identification is essential in the cybersecurity area, as it allows the timely detection of threats, along with countermeasures and mitigation, ensuring security for organizations and individuals. This reduces false positives and enables efforts to be concentrated on real risks. This paper presents a framework that integrates ontologies and Large Language Models (LLMs) to identify incidents from events within the context of security threats. Ontology rules are employed to infer probable incidents, resulting in an initial set of incidents for analysis. Furthermore, ontologies provide contextual information, which is combined with event data to formulate queries for LLMs. These interactions with LLMs produce a second set of probable incidents. The outputs from ontol-ogy-based inferences and LLM-driven responses are then compared, and the discrepancies are leveraged to refine ontology rules and adjust LLM responses. Experimental results, focusing on context generation and incident detection, demonstrate that the integration of ontologies and LLMs significantly enhances the accuracy of incident identification when compared to using only LLMs.
Free
Frameworks in Problems of Structural Identification Systems
Scientific article
The new approach to structural identification of nonlinear dynamic systems under uncertainty is pro-posed. It is based on the analysis of virtual frameworks (VF), reflecting a state of a nonlinear part system. Con-struction VF is based on obtaining special an informa-tional set describing a steady state of a nonlinear dynamic system. Introduction VF demands an estimation of structural identifiability of a system. This concept is associated with nonlinearity of system and properties VF. The method of an estimation of structural identifiability is proposed. The appearance of the insignificant virtual frameworks, not satisfying to the condition of structural identifiability, is considered. Algorithms for an estimation of a nonlinearity class on the basis of the analysis of sector sets are proposed. Methods and procedures of the estimation of framework single-valued and multiple-valued nonlinearities are proposed. The method of the structurally-frequency analysis is proposed and applied to validate the obtained solutions. VF is proposed for identification of an order and a spectrum of eigenvalues of a linear dynamic system. The possibility of application VF for the problem solving of identification static systems is shown.
Free
From Nature to UAV - A Study on Collision Avoidance in Bee Congregation
Scientific article
Insects engage in a variety of survival-related activities, including feeding, mating, and communication, which are frequently motivated by innate impulses and environmental signals. Social insects, such as ants and bees, exhibit complex collective behaviors. They carry out well-organized duties, including defense, nursing, and foraging, inside their colonies. For analyzing the behavior of any living entity, we selected honeybees (Apis Mellifera) and worked on a small portion of it. We have captured the video of honeybees flying close to a hive (human-made artificial hive) while the entrance was temporarily sealed which resulted in the” bee cloud”. An exploration of the flight trajectories executed and a 3D view of the” bee cloud” constructed. We analyzed the behaviors of honeybees, especially on their speed and distance. The results showed that the loitering honeybees performed turns that are fully coordinated, and free of sideslips so thus they made no collision between themselves which inspired us to propose a method for avoiding collision in unmanned aerial vehicle. This paper gives the collective behavioral information and analysis report of the small portion of data set (honeybees), that bee maintains a safe distance (35mm) to avoid collision.
Free
Scientific article
This paper proposes a heuristic method for the sensor selection problem that uses a state vector fusion approach as a data fusion method. We explain the heuristic to estimate a stationary target position. Given a first sensor with specified accuracy and by using genetic algorithm, the heuristic selects second sensor such that the fusion of two sensor measurements would yield an optimal estimation in a target localization scenario. Optimality in our method means that a trade-off between estimation error and cost of sensory system should be created. The heuristic also investigates the importance of proportion between the range and bearing measurement accuracy of selected sensor. Monte Carlo Simulation results for a target position estimation scenario showed that the error in heuristic is less than the estimate error where sensors are used alone for estimation, while considering the trade-off between cost and accuracy.
Free
