Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

29,734 Article Results

A dynamic K-means clustering for data mining

10.11591/ijeecs.v13.i2.pp521-526
Md. Zakir Hossain , Md.Nasim Akhtar , R.B. Ahmad , Mostafijur Rahman
Data mining is the process of finding structure of data from large data sets. With this process, the decision makers can make a particular decision for further development of the real-world problems. Several data clusteringtechniques are used in data mining for finding a specific pattern of data. The K-means method isone of the familiar clustering techniques for clustering large data sets.  The K-means clustering method partitions the data set based on the assumption that the number of clusters are fixed.The main problem of this method is that if the number of clusters is to be chosen small then there is a higher probability of adding dissimilar items into the same group. On the other hand, if the number of clusters is chosen to be high, then there is a higher chance of adding similar items in the different groups. In this paper, we address this issue by proposing a new K-Means clustering algorithm. The proposed method performs data clustering dynamically. The proposed method initially calculates a threshold value as a centroid of K-Means and based on this value the number of clusters are formed. At each iteration of K-Means, if the Euclidian distance between two points is less than or equal to the threshold value, then these two data points will be in the same group. Otherwise, the proposed method will create a new cluster with the dissimilar data point. The results show that the proposed method outperforms the original K-Means method.
Volume: 13
Issue: 2
Page: 521-526
Publish at: 2019-02-01

Robust speaker verification in band-localized noise conditions

10.11591/ijeecs.v13.i2.pp499-506
Ali O. Abid Noor
This research paper presents a robust method for speaker verification in noisy environments. The noise is assumed to contaminate certain parts of the voice’s frequency spectrum. Therefore, the verification method is based on splitting the noisy speech into subsidiary bands then using a threshold to sense the existence of noise in a specific part of the spectrum, hence activating an adaptive filter in that part to track changes in noise’s characteristics and remove it. The decomposition is achieved using low complexity quadrature mirror filters QMF in three levels thus achieving four bands in a non-uniform that resembles human hearing perceptual. Speaker recognition is based on vector quantization VQ or template matching technique. Features are extracted from speaker’s voice using the normalized power in a similar way to the Mel-frequency cepstral coefficients. The performance of the proposed system is evaluated using 60 speakers subjected to five levels of signal to noise ratio SNR using total success rate TSR, false acceptance rate FAR, false rejection rate FRR and equal error rate. The proposed method showed higher recognition accuracy than existing methods in severe noise conditions.
Volume: 13
Issue: 2
Page: 499-506
Publish at: 2019-02-01

Energy efficiency in virtual machines allocation for cloud data centers with lottery algorithm

10.11591/ijece.v9i1.pp546-553
Mehran Tarahomi , Mohammad Izadi
Energy usage of data centers is a challenging and complex issue because computing applications and data are growing so quickly that increasingly larger servers and disks are needed to process them fast enough within the required time period. In the past few years, many approaches to virtual machine placement have been proposed. This study proposes a new approach for virtual machine allocation to physical hosts. Either minimizes the physical hosts and avoids the SLA violation. The proposed method in comparison to the other algorithms achieves better results.
Volume: 9
Issue: 1
Page: 546-553
Publish at: 2019-02-01

Improvement of binarization performance using local otsu thresholding

10.11591/ijece.v9i1.pp264-272
Khairun Saddami , Khairul Munadi , Yuwaldi Away , Fitri Arnia
Ancient document usually contains multiple noises such as uneven-background, show-through, water-spilling, spots, and blur text. The noise will affect the binarization process. Binarization is an extremely important process in image processing, especially for character recognition. This paper presents an improvement to Nina binarization technique. Improvements were achieved by reducing processing steps and replacing median filtering by Wiener filtering. First, the document background was approximated by using Wiener filter, and then image subtraction was applied. Furthermore, the manuscript contrast was adjusted by mapping intensity of image value using intensity transformation method. Next, the local Otsu thresholding was applied. For removing spotting noise, we applied labeled connected component. The proposed method had been testing on H-DIBCO 2014 and degraded Jawi handwritten ancient documents. It performed better regarding recall and precision values, as compared to Otsu, Niblack, Sauvola, Lu, Su, and Nina, especially in the documents with show-through, water-spilling and combination noises.
Volume: 9
Issue: 1
Page: 264-272
Publish at: 2019-02-01

Business intelligence analytics using sentiment analysis-a survey

10.11591/ijece.v9i1.pp613-620
Prakash P. Rokade , Aruna Kumari D
Sentiment analysis (SA) is the study and analysis of sentiments, appraisals and impressions by people about entities, person, happening, topics and services. SA uses text analysis techniques and natural language processing methods to locate and extract information from big data. As most of the people are networked themselves through social websites, they use to express their sentiments through these websites.These sentiments are proved fruitful to an individual, business, government for making decisions. The impressions posted on different available sources are being used by organization to know the market mood about the services they are providing. Analyzing huge moods expressed with different features, style have raised challenge for users. This paper focuses on understanding the fundamentals of sentiment analysis, the techniques used for sentiment extraction and analysis. These techniques are then compared for accuracy, advantages and limitations. Based on the accuracy for expexted approach, we may use the suitable technique.
Volume: 9
Issue: 1
Page: 613-620
Publish at: 2019-02-01

Radial dynamics of electrons in two-section linear accelerator

10.11591/ijece.v9i1.pp215-220
Aleksandr Nikolaevich Filatov , Vladimir Kuz'mich Shilov
This article discusses possibility of harness wiring with the use of focusing system of high frequency eigenfields of accelerating resonators in standing wave linear accelerators on the basis of biperiodic slowing systems. The scopes of business activities and specificity of existing engineering processes applied in industry, especially in chemistry and metallurgy, require for special measures on environmental protection. At present electron linear accelerators operating in pulse mode are used for application purposes. Such accelerators can be characterized by sufficient beam power for efficient industrial use and for environmental protection. The results of numerical analysis of electron dynamics in two-section accelerator upon various initial conditions are presented. The obtained results are applied for development of actual accelerator, calculated and experimental data are given. The performed experimental study confirmed possibility of development of standing wave linear accelerator without external magnetic focusing system with output beam diameter of not higher than . The results of calculations of beam dynamics are experimentally verified.
Volume: 9
Issue: 1
Page: 215-220
Publish at: 2019-02-01

Design and analysis of routing protocol for cognitive radio ad hoc networks in Heterogeneous Environment

10.11591/ijece.v9i1.pp341-351
Hassan Al-mahdi , Yasser Fouad
Multi-hop routing protocol in cognitive radio mobile ad hoc networks (CRMANETs) is a critical issue. Furthermore, the routing metric used in multi-hop CRMANETs should reflect the bands availability, the links quality, the PU activities and quality of service (QoS) requirements of SUs. For the best of our knowledge, many of researchers investigated the performance of the different routing protocols in a homogeneous environment only. In this paper, we propose a heterogeneous cognitive radio routing protocol (HCR) operates in heterogeneous environment (i.e. the route from source to destination utilize the licensed and unlicensed spectrum bands). The proposed routing protocol is carefully developed to make a tradeoff between the channel diversity of the routing path along with the CRMANETs throughput. Using simulations, we discuss the performance of the proposed HCR routing protocol and compare it with the AODV routing protocol using a discrete-event simulation which we developed using JAVA platform.
Volume: 9
Issue: 1
Page: 341-351
Publish at: 2019-02-01

A transient current based micro-grid connected power system protection scheme using wavelet approach

10.11591/ijece.v9i1.pp14-22
S. Chandra Shekar , G.Ravi Kumar , S.V.N.L Lalitha
Micro-grids comprise Distributed Energy Resources (DER’s) with low voltage distribution networks having controllable loads those can operate with different voltage levels are connected to the micro-grid and operated in grid mode or islanding mode in a coordinated way of control. DER’s provides clear environment-economical benefits for society and consumer utilities. But their development poses great technical challenges mainly protection of main and micro grid. Protection scheme must have to respond to both the main grid and micro-grid faults. If the fault is occurs on main grid, the response must isolate the DER’s from the main grid rapidly to protect the system loads. If the fault ocuurs within the micro-grid, the protection scheme must coordinate and isolates the least priority possible part of the grid to eliminate the fault. In order to deal with the bidirectional energy flow due to large numbers of micro sources new protection schemes are required. The system is simulated using MATLAB Wavelet Tool box and Wavelet based Multi-resolution Analysis is considered. Wavelet based Multi-resolution Analysis is used for detection, discrimination and location of faults on transmission network.  This paper is discussed a transient current based micro-grid connected power system protection scheme using Wavelet Approach described on wavelet detailed-coefficients of Mother Biorthogonal 1.5 wavelet. The proposed algorithm is tested in micro-grid connected power systems environment and proved for the detection, discrimination and location of faults which is almost independent of fault impedance, fault inception angle (FIA) and fault distance of feeder line.
Volume: 9
Issue: 1
Page: 14-22
Publish at: 2019-02-01

Topic Discovery of Online Course Reviews Using LDA with Leveraging Reviews Helpfulness

10.11591/ijece.v9i1.pp426-438
Fetty Fitriyanti Lubis , Yusep Rosmansyah , Suhono H. Supangkat
Despite the popularity of the Massive Open Online Courses, small-scale research has been done to understand the factors that influence the teaching-learning process through the massive online platform. Using topic modeling approach, our results show terms with prior knowledge to understand e.g.: Chuck as the instructor name. So, we proposed the topic modeling approach on helpful subjective reviews. The results show five influential factors: “learn easy excellent class program”, “python learn class easy lot”, “Program learn easy python time game”, and “learn class python time game”. Also, research results showed that the proposed method improved the perplexity score on the LDA model.
Volume: 9
Issue: 1
Page: 426-438
Publish at: 2019-02-01

Augmented reality application for chemical bonding based on android

10.11591/ijece.v9i1.pp445-451
Alexander Setiawan , Silvia Rostianingsih , Timotius Reinaldo Widodo
Augmented Reality can provide information that can be more easily understood by the user. Because of its advantages, Augmented Reality can be utilized to create learning applications that can support teaching and learning process. Chemical learning about chemical reactions is usually boring by students. This is because students only know the theory of the book and the explanation of teachers only. This research utilized Augmented Reality to be able to see 3D model of each chemical element and also can see animation of merging between elements. In order to bring up 3D objects of chemical elements then made a card that will be used as a marker / tracker. In addition, there can be a combination of several chemical elements based on several cards detected from the camera. The test is performed for chemical elements with periodic table such as H, Ca, Na, K, C, Cl, Br, O, S, SO2, CO2, OH. Testing the application by performing several merge elements such as HCl, NaCl, H20, CO2, MgS, SO2, O2, CaCl2, HCN, N2, and others. The results of this study will be tested on several students to see the benefits of student learning.
Volume: 9
Issue: 1
Page: 445-451
Publish at: 2019-02-01

Iterative improved learning algorithm for petrographic image classification accuracy enhancement

10.11591/ijece.v9i1.pp289-296
Ashutosh Marathe , Priya Jain , Vibha Vyas
Rock image classification using image processing has been practiced to assist trained geologists in decision making. However, the study of microstructures of rocks and their use in geological investigations offer challenges in the areas of Image processing and Pattern Classification due to the stochastic nature of the mineral textures that is revealed at the microscopic level. Locally relevant Igneous Rock Microstructure images were classified from Volcanic and Plutonic Rock subtypes. The imaging method used mineral grain size as the key physical feature of classification. Three algorithms, namely Radial Basis Function (RBF) Support Vector Machine classifier; Improved (RBF) Support Vector Machine classifier; and AdaBoost algorithm with Improved RBF Support Vector Machine algorithm as base classifier, were used as a base classifier in a novel ‘Iterative Improved Learning (IIL)’ approach. Implementing the IIL approach in the chosen algorithm resulted in accurately classified images that were added to the training set to enhance the ‘breadth and depth’ of the learning knowledge. The algorithm iterated through all available classifier approaches and compared the inter-classifier performance and knowledge of the misclassified images accumulated during the execution of all algorithms.
Volume: 9
Issue: 1
Page: 289-296
Publish at: 2019-02-01

A comparative study of laravel and symfony PHP frameworks

10.11591/ijece.v9i1.pp704-712
Majida Laaziri , Khaoula Benmoussa , Samira Khoulji , Kerkeb Mohamed Larbi , Abir El Yamami
With the current explosion of Information Systems, the market offers a wide range of interesting technological solutions. Yet, this does not mean adopting a technology without considering its impact on the existing information system and user expectations. It is recommended to identify and implement the technological solutions most suited to the Information Systems strategy. Therefore, new methods are emerging and design tools are still evolving; the PHP Frameworks are part of it, which open up new perspectives in terms of information system enrichment. In this context, this paper focuses on the elaboration of a comparative study between Laravel, symfony framworks, which are the most popular PHP frameworks.  Thus, it provides an effective comparison model that merges seven dimensions: Features, Multilingual, System requirements, Technical architecture, Code Organization, Continuous Integration (CI) and finally Documentation and learning curve dimension. Results show that our model can be beneficial for IT project developers to select the suitable PHP Framework. 
Volume: 9
Issue: 1
Page: 704-712
Publish at: 2019-02-01

Word2Vec model for sentiment analysis of product reviews in Indonesian language

10.11591/ijece.v9i1.pp525-530
M. Ali Fauzi
Online product reviews have become a source of greatly valuable information for consumers in making purchase decisions and producers to improve their product and marketing strategies. However, it becomes more and more difficult for people to understand and evaluate what the general opinion about a particular product in manual way since the number of reviews available increases. Hence, the automatic way is preferred. One of the most popular techniques is using machine learning approach such as Support Vector Machine (SVM). In this study, we explore the use of Word2Vec model as features in the SVM based sentiment analysis of product reviews in Indonesian language. The experiment result show that SVM can performs well on the sentiment classification task using any model used. However, the Word2vec model has the lowest accuracy (only 0.70), compared to other baseline method including Bag of Words model using Binary TF, Raw TF, and TF.IDF. This is because only small dataset used to train the Word2Vec model. Word2Vec need large examples to learn the word representation and place similar words into closer position.
Volume: 9
Issue: 1
Page: 525-530
Publish at: 2019-02-01

A secure image steganography based on burrows wheeler transform and dynamic bit embedding

10.11591/ijece.v9i1.pp460-467
Ahmed Toman Thahab
In modern public communication networks, digital data is massively transmitted through the internet with a high risk of data piracy. Steganography is a technique used to transmit data without arousing suspicion of secret data existence.  In this paper, a color image steganography technique is proposed in spatial domain. The cover image is segmented into non-overlapping blocks which are scattered among image size window using Burrows Wheeler transform before embedding. Secret data is embedded in each block according to its sequence in the Burrows Wheeler transform output. The hiding method is an operation of an exclusive-or between a virtual bit which is generated from the most significant bit and the least significant bits of the cover pixel. Results of the algorithm are analyzed according to its degradation of the output image and embedding capacity. The results are also compared with other existing methods.
Volume: 9
Issue: 1
Page: 460-467
Publish at: 2019-02-01

Granularity analysis of classification and estimation for complex datasets with MOA

10.11591/ijece.v9i1.pp409-416
Chanintorn Jittawiriyanukoon
Dispersed and unstructured datasets are substantial parameters to realize an exact amount of the required space. Depending upon the size and the data distribution, especially, if the classes are significantly associating, the level of granularity to agree a precise classification of the datasets exceeds. The data complexity is one of the major attributes to govern the proper value of the granularity, as it has a direct impact on the performance. Dataset classification exhibits the vital step in complex data analytics and designs to ensure that dataset is prompt to be efficiently scrutinized. Data collections are always causing missing, noisy and out-of-the-range values. Data analytics which has not been wisely classified for problems as such can induce unreliable outcomes. Hence, classifications for complex data sources help comfort the accuracy of gathered datasets by machine learning algorithms. Dataset complexity and pre-processing time reflect the effectiveness of individual algorithm. Once the complexity of datasets is characterized then comparatively simpler datasets can further investigate with parallelism approach. Speedup performance is measured by the execution of MOA simulation. Our proposed classification approach outperforms and improves granularity level of complex datasets.
Volume: 9
Issue: 1
Page: 409-416
Publish at: 2019-02-01
1 2 3
...
1982 1983
Show 1330 of 1983

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration