International Journal of Advances in Intelligent Informatics
Not a member yet
235 research outputs found
Sort by
Analogy-based model for software project effort estimation
Get PDFAccurate effort estimation of software development plays an important role to predict how much effort should be prepared during the works of a software project so that it can be completed on time and budget. Some sectors, e.g. banking sectors, were renowned fields of software projects, not only due to its huge size of project, but also extremely expensive and takes a long time to completion. Project estimation is essential for software development project able to run on time and budget with maximum quality. This study aims to investigate the accuracy of software project effort estimation with the Analogy method using three parameters: Euclidean, Manhattan and Minkowski distance. Analogy based estimation consists several stage included similarity measure, analogy adaptation, estimation calculation and model evaluation. The results showed that the best combination of Analogy methods was using Manhattan distance with an accuracy of 50% MMRE, 28% MdMRE and Pred(25) 48%. Thus, we can concluded that this model can be used to predict accurately
Multiscale tsallis entropy for pulmonary crackle detection
Get PDFAbnormalities in the lungs can be detected from the sound produced by the lungs. Diseases that occur in the lungs or respiratory tract can produce a distinctive lung sound. One of the examples of the lung sound is the pulmonary crackle caused by pneumonia or chronic bronchitis. Various digital signal processing techniques are developed to detect pulmonary crackle sound automatically, such as the measurement of signal complexity using Tsallis entropy (TE). In this study, TE measurements were performed through several orders on the multiscale pulmonary crackle signal. The pulmonary crackle signal was decomposed using the coarse-grained procedure since the lung sound as the biological signal had a multiscale property. In this paper, we used 21 pulmonary crackle sound and 22 normal lung sound for the experiment. The results showed that the second order TE on the scale of 1-15 had the highest accuracy of 97.67%. This result was better compared to the use of multi-order TE from the previous study, which resulted in an accuracy of 95.35%
Hybrid SSA-TSR-ARIMA for water demand forecasting
Get PDFWater supply management effectively becomes challenging due to the human population and their needs have been growing rapidly. The aim of this research is to propose hybrid methods based on Singular Spectrum Analysis (SSA) decomposition, Time Series Regression (TSR), and Automatic Autoregressive Integrated Moving Average (ARIMA), known as hybrid SSA-TSR-ARIMA, for water demand forecasting. Monthly water demand data frequently contain trend and seasonal patterns. In this research, two groups of different hybrid methods were developed and proposed, i.e. hybrid methods for individual SSA components and for aggregate SSA components. TSR was used for modeling aggregate trend component and Automatic ARIMA for modeling aggregate seasonal and noise components separately. Firstly, simulation study was conducted for evaluating the performance of the proposed methods. Then, the best hybrid method was applied to real data sample. The simulation showed that hybrid SSA-TSR-ARIMA for aggregate components yielded more accurate forecast than other hybrid methods. Moreover, the comparison of forecast accuracy in real data also showed that hybrid SSA-TSR-ARIMA for aggregate components could improve the forecast accuracy of ARIMA model and yielded better forecast than other hybrid methods. In general, it could be concluded that the hybrid model tends to give more accurate forecast than the individual methods. Thus, this research in line with the third result of the M3 competition that stated the accuracy of hybrid method outperformed, on average, the individual methods being combined and did very well in comparison to other methods
An efficient meta-heuristic algorithm for solving capacitated vehicle routing problem
Get PDFThis work aims to develop an enhanced Perturbation based Variable Neighborhood Search with Adaptive Selection Mechanism (PVNS ASM) to solve the capacitated vehicle routing problem (CVRP). This approach combined Perturbation based Variable Neighborhood Search (PVNS) with Adaptive Selection Mechanism (ASM) to control perturbation scheme. Instead of stochastic approach, selection of perturbation scheme used in the algorithm employed an empirical selection based on success rate of each perturbation scheme along the search. The ASM helped algorithm to get more diversification degree and jumping from local optimum condition using most successful perturbation scheme empirically in the search process. A comparative analysis with existing heuristics in the literature has been performed on 21 CVRP benchmarks. The computational results proof that the developed method is competitive and very efficient in achieving high quality solution within reasonable computation time
Principal component analysis implementation for brainwave signal reduction based on cognitive activity
Get PDFHuman has the ability to think that comes from the brain. Electrical signals generated by brain and represented in wave form. Â To record and measure the activity of brainwaves in the form of electrical potential required electroencephalogram (EEG). In this study a cognitive task is applied to trigger a specific human brain response arising from the cognitive aspect. Â Stimulation is given by using nine types of cognitive tasks including breath, color, face, finger, math, object, password thinking, singing, and sports. Principal component analysis (PCA) is implemented as a first step to reduce data and to get the main component of feature extraction results obtained from EEG acquisition. The results show that PCA succeeded reducing 108 existing datasets to 2 prominent factors with a cumulative rate of 65.7%. Factor 1 (F1) includes mean, standard deviation, and entropy, while factor 2 (F2) includes skewness and kurtosis
Usability testing on intelligent mobile web pre-fetching of cloud storage scheme
Get PDFMobile device and Cloud Storage (CS) represent the trends of technology usage of the last few years. However, the difficulty in managing the data when there are too many simultaneous uses of cloud storage services at the same time that can cause latency or delayed time. This paper evaluates mobile cloud storage services using usability testing, which is intended to access by multiple of Cloud Storage Services (CSS) with the proposed Intelligent Mobile Web Pre-fetching of Cloud Storage Scheme (MOBICS). The results show most of the respondents with 95.65% agreeing that MOBICS system was very practical and has enhanced the speed in accessing and storing data by Mobile Cloud Storage (MCS). Besides, MOBICS reduces time of interaction up to 19.28% for the local pre-fetching and 18.80% for the intelligent pre-fetching
Human action recognition using support vector machines and 3D convolutional neural networks
Get PDFRecently, deep learning approach has been used widely in order to enhance the recognition accuracy with different application areas. In this paper, both of deep convolutional neural networks (CNN) and support vector machines approach were employed in human action recognition task. Firstly, 3D CNN approach was used to extract spatial and temporal features from adjacent video frames. Then, support vector machines approach was used in order to classify each instance based on previously extracted features. Both of the number of CNN layers and the resolution of the input frames were reduced to meet the limited memory constraints. The proposed architecture was trained and evaluated on KTH action recognition dataset and achieved a good performance
Semantic data mapping technology to solve semantic data problem on heterogeneity aspect
Get PDFThe diversity of applications developed with different programming languages, application/data architectures, database systems and representation of data/information leads to heterogeneity issues. One of the problem challenges in the problem of heterogeneity is about heterogeneity data in term of semantic aspect. The semantic aspect is about data that has the same name with different meaning or data that has a different name with the same meaning. The semantic data mapping process is the best solution in the current days to solve semantic data problem. There are many semantic data mapping technologies that have been used in recent years. This research aims to compare and analyze existing semantic data mapping technology using five criteria’s. After comparative and analytical process, this research provides recommendations of appropriate semantic data mapping technology based on several criteria’s. Furthermore, at the end of this research we apply the recommended semantic data mapping technology to be implemented with the real data in the specific application. The result of this research is the semantic data mapping file that contains all data structures in the application data source. This semantic data mapping file can be used to map, share and integrate with other semantic data mapping from other applications and can also be used to integrate with the ontology language
Exploring natural language understanding in robotic interfaces
Get PDFNatural Language Understanding is a major aspect of the intelligence of robotic systems. A main goal of improving their artificial intelligence is to allow a robot to ask questions, whenever the given instructions are not complete, and also by using implicit information. These enhanced communicational abilities can be based on the voids of an output data structure that corresponds to a systemic-semantic model of language communication, as grammar formalism. In addition, the enhancing process also improves the learning abilities of a robot. Accordingly, the presented herein experimental project was conducted by using a simulated (by a plain PC) robot and a simple constructed language that facilitated semantic orientation
Wavelet discrete transform, ANFIS and linear regression for short-term time series prediction of air temperature
Get PDFThis paper investigates the ability of Discrete Wavelet Transform and Adaptive Network-Based Fuzzy Inference System in time-series data modeling of weather parameters. Plotting predicted data results on Linear Regression is used as the baseline of the statistical model. Data were tested in every 10 minutes interval on weather station of Bungus port in Padang, Indonesia. Mean absolute errors (MAE), the coefficient of determination (R2), Pearson correlation coefficient (r) and root mean squared error (RMSE) are used as performance indicators. The result of Plotting ANFIS data against linear regression using 1-input data is the optimal values combination of output predictions