for Journals by Title or ISSN
for Articles by Keywords

Publisher: Universitas Ahmad Dahlan   (Total: 16 journals)   [Sort by number of followers]

Showing 1 - 16 of 16 Journals sorted alphabetically
Ahmad Dahlan J. of English Studies     Open Access   (Followers: 2)
Bahastra     Open Access  
Berkala Fisika Indonesia     Open Access  
Bulletin of Electrical Engineering and Informatics     Open Access   (Followers: 8)
HUMANITAS (Jurnal Psikologi Indonesia)     Open Access   (Followers: 4)
Intl. J. of Advances in Intelligent Informatics     Open Access   (Followers: 7)
J. of Education and Learning     Open Access   (Followers: 11)
Jurnal Hukum Novelty     Open Access  
Jurnal Ilmiah AdMathEdu     Open Access  
Jurnal Informatika     Open Access   (Followers: 1)
Kes Mas : Jurnal Fakultas Kesehatan Masyarakat     Open Access   (Followers: 2)
Media Farmasi     Open Access  
Pharmaciana     Open Access  
Psikopedagogia : Jurnal Bimbingan dan Konseling     Open Access   (Followers: 2)
Spektrum Industri : Jurnal Ilmiah Pengetahuan dan Penerapan Teknik Industri     Open Access  
TELKOMNIKA (Telecommunication, Computing, Electronics and Control)     Open Access   (Followers: 8, SJR: 0.265, CiteScore: 1)
Journal Cover
Bulletin of Electrical Engineering and Informatics
Number of Followers: 8  

  This is an Open Access Journal Open Access journal
ISSN (Print) 2089-3191 - ISSN (Online) 2302-9285
Published by Universitas Ahmad Dahlan Homepage  [16 journals]
  • Development of Respiratory Rate Estimation Technique Using

    • Authors: Nazrul Anuar Nayan
      Abstract: Abnormal vital signs often predict a serious condition of acutely ill hospital patients in 24 hours. The notable fluctuations of respiratory rate (RR) are highly predictive of deteriorations among the vital signs measured. Traditional methods of detecting RR are performed by directly measuring the air flow in or out of the lungs or indirectly measuring the changes of the chest volume. These methods require the use of cumbersome devices, which may interfere with natural breathing, are uncomfortable, have frequently moving artifacts, and are extremely expensive. This study aims to estimate the RR from electrocardiogram (ECG) and photoplethysmogram (PPG) signals, which consist of passive and non-invasive acquisition modules. Algorithms have been validated by using PhysioNet’s Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II)’s patient datasets. RR estimation provides the value of mean absolute error (MAE) for ECG as 1.25 bpm (MIMIC-II) and 1.05 bpm for the acquired data. MAE for PPG is 1.15 bpm (MIMIC-II) and 0.90 bpm for the acquired data. By using 1-minute windows, this method reveals that the filtering method efficiently extracted respiratory information from the ECG and PPG signals. Smaller MAE for PPG signals results from fewer artifacts due to easy sensor attachment for the PPG because PPG recording requires only one-finger pulse oximeter sensor placement. However, ECG recording requires at least three electrode placements at three positions on the subject’s body surface for a single lead (lead II), thereby increasing the artifacts. A reliable technique has been proposed for RR estimation.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Wind Energy Fed UPQC System for Power Quality Improvement

    • Authors: SARITA SAMAL
      Abstract: The extensive use of non-linear loads in domestic, industrial and commercial services origin harmonic complications. Harmonics make malfunctions in profound equipment, voltage drop across the network, conductor heat increases and overvoltage through resonance. All these   problems can be remunerated by using Unified Power Quality Controller (UPQC) and the operation of UPQC depends upon the available voltage across capacitor present in dc link. If the capacitor voltage is maintained constant then it gives satisfactory performance. The proposed research is basically on designing of Wind energy fed to the dc link capacitor of UPQC so as to maintain proper voltage across it and operate the UPQC for power quality analysis. The proposed technique is the grouping of shunt and series Active Power Filter (APF) to form UPQC which is fed wind energy system and connected to grid for better response in the output. In this paper, the simulation model of series APF, shunt APF, UPQC and Wind energy with UPQC are design in Matlab. The proposed Wind energy -UPQC is design in Matlab simulation for reduction of voltage sag, swell, harmonics in load current and compensation of active and reactive power.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Oscillatory Stability Prediction using PSO Based Synchronizing and Damping
           Torque Coefficients

    • Authors: Nor Azwan Mohamed Kamari
      Abstract: This paper presents the assessment of stability domains for the angle stability condition of the power system using particle swarm optimization (PSO) technique. An efficient optimization method using PSO for synchronizing torque coefficients Ks and damping torque coefficients Kd to identify the angle stability condition on multi-machine system. In order to accelerate the determination of angle stability, particle swarm optimization (PSO) is proposed to be implemented in this study. The application of the proposed algorithm has been justified as the most accurate with lower computation time as compared to other optimization techniques such as evolutionary programming (EP) and artificial immune system (AIS). Validation with respect to eigenvalues determination, Least Square (LS) method and minimum damping ratio ξmin confirmed that the proposed technique is feasible to solve the angle stability problems.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Speaker Recognition in Content-Based Image Retrieval for a high degree of

    • Authors: Muhammad Suhartono
      Abstract: Speaker recognition is a process that performed by a computer to recognize a word spoken by a person regardless the identity of the person concerned. The background of this research is to create a speaker recognition system that uses dynamic data. The pattern of speaker recognition obtained is dynamic data; dynamic data is difficult to approach with certain formulas. The speaker recognition method is currently required for a high degree of accuracy. The purpose of this research is to measure the accuracy of speaker recognition. The method used in this research using fuzzy Mamdani method, and Manhattan distance method, in fuzzy Mamdani method used for identification, while in Manhattan distance method used for verification. The sample data obtained from features extraction row mean on spectrogram form image digital. With Content-Based Image Retrieval method, those data of the recording converted to become spectrogram form image digital. Various sizes were used 256x256, 128x128, 64x64, 32x32 and 16x16. To get vector features that give better properties, the process was performed to get vector feature using kekre transform and mean on each sub-image. The vector features then used as input rule in the speaker recognition. As for output rule, the identity of the human voice was used. The system can recognize a person automatically from his or her voice and can provide accuracy of speaker recognition 91% on the size of 32x32 features.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • A Finite State Machine-based Falling Event Detection using Quadrilateral
           Shape Features

    • Authors: Mohd Fadzil Abu Hassan, Mohamad Hanif Md Saad, Mohd Faisal Ibrahim, Aini Hussain
      Abstract: A video-based falling event detection system was presented; which consists of data acquisition, image processing, feature extraction, feature selection, classification and finite state machine. A two-dimensional human posture image was represented by 12 features extracted from the generalisation of a silhouette shape to a quadrilateral. The corresponding feature vectors for three groups of human pose were statistically analysed by using a non-parametric Kruskal Wallis test to assess the different significance level between them. From the statistical test, non-significant features were discarded. Four selected kernel-based Support Vector Machine: linear, quadratics, cubic and Radial Basis Function classifiers were trained to classify three human posture groups. Among four classifiers, the last one performed the best in terms of performance matric on testing set. The classifier outperformed others with high achievement of average sensitivity, precision and F-score of 99.21%, 99.27% and 99.24%, respectively. Such pose classification model output was further used in a simple finite state machine to trigger the falling event alarms. The falling event detection system was tested on different fall video sets and able to detect the presence of normal and falling events in a frame sequence of videos with average sensitivity, precision and F-score of 93.59%, 95.83% and 94.70%, respectively.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Creating Color Image Features Using Local Contrast Method

    • Authors: Ayman Y. Al-Rawashdeh, Ziad Al-Qadi
      Abstract: Digital color images are now one of the most popular data types used in the digital processing environment. Color image recognition plays an important role in many vital applications, which makes the enhancement of image recognition or retrieval system an important issue. Using color image pixels to recognize or retrieve the image, but the issue of the huge color image size that requires accordingly more time and memory space to perform color image recognition and/or retrieval. In the current study, image local contrast was used to create local contrast victor, which was then used as a key to recognize or retrieve the image. The proposed local contrast method was properly implemented and tested. The obtained results proved its efficiency as compared with other methods.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Weather Forecasting Using Merged Long Short-Term Memory Model

    • Authors: Afan Galih Salman, Yaya Heryadi, Edi Abdurahman, Wayan Suparta
      Abstract: Over decades, weather forecasting has attracted researchers from worldwide communities due to its significant effect to global human life ranging from agriculture, air trafic control to public security. Although formal study on weather forecasting has been started since 19th century, research attention to weather forecasting tasks increased significantly after weather big data are widely available. This paper proposed merged-Long Short-term Memory for forecasting ground visibility at the airpot using timeseries of predictor variable combined with another variable as moderating variable. The proposed models were tested using weather weather timeseries data at Hang Nadim Airport, Batam. The experiment results showed the best average accuracy for forecasting visibility using merged Long Short-term Memory model and temperature and dew point  as a moderating variable was (88.6%); whilst, using basic Long Short-term Memory without moderating variable was only (83.8%) respectively (increased by 4.8%).
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Efficient Implementation of Mean, Variance and Skewness Statistic Formula
           for Image Processing Using FPGA Device

    • Authors: Aqwam Rosadi Kardian
      Abstract: Processing statistic formula in image processing and accessing data from memory is easy in software, the other hand for hardware implementation is more dificult considering a lot of constraint. This article proposes an implementation of optimum mean, variance and skewness formula in FGPA Device. The proposed circuit design for all formulas only need three additions component ( in three accumulators) and two divisions using two shift-right-registers, two subtractors, one adder and six multipliers. For 8x8 image size need 64 clock cycles to finish the mean, variance and skewness calculations, comparing other approach that need more than 1024 additions component without skewness calculation. Implementation into FPGA needs 68 slices of flip-flops and 121 of 4 input LUTs.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Weighting of Information for Analyzing Sensitivity of Information

    • Authors: Prajna Deshanta Ibnugraha
      Abstract: Nowadays, information becomes important asset for enterprises to support their business. Involvement of information in almost of enterprises sector makes information having value that must be protected from information leakage. However, enterprises often get limitation in measuring information value when they want to analyze risk related information security assessment. Therefore, this paper has goal to give approach for measuring information value with text mining and Jaccard method. Text mining technique is used to recognize information pattern that categorized in high business impact, medium business impact and low business impact. Weight of each category is estimated by Jaccard method. That weight represents level of risk in information when it has incident related to information security.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Assessing Information System Integration Using Combination of the
           Readiness and Success Models

    • Authors: A'ang Subiyakto
      Abstract: Information system integration (ISI) is one of the development concerns for organizations to enhance business competitiveness. However, the implementations still present its failures. Despite the ISI may successful technically; but it still seems to be unsuccessful because of the human and management issues. The issues may relate to the readiness constructs of ISI. This study was aimed to know the status of the readiness and success of ISI and to assess the influential factors of the integration in the sampled institution. About 160 samples were purposely involved by considering their key informant characteristics. The data were analyzed using the partial least squares-structural equation modeling (PLS-SEM) method. The findings revealed only the user satisfaction variable that mediated the positive effects of the readiness variables towards variable of the system integration success. Besides, the findings may practically helpful for stakeholders in the sampled institution, but it may also theoretically useful for researchers in regard to the readiness and success issues of ISI.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • SPLSCGS Framework : Smart Government in Supply Chain

    • Authors: Ahmad Nurul Fajar
      Abstract: In Indonesia e-government applications, there are
      diversity of software systems developers with diverse technologies
      and designs to develop features of software system. We proposed
      framework for develop software product line in supply chain in
      government area. It is used to enhance and improve the
      development of software systems by multiple software system
      developers. It will be a baseline for construct smart government,
      and more specificity in supply chain area environment. Supply
      chain in domain of government are needed to be managed, in
      order to achieve the smart government. It presents the
      conceptual framework for developing a software product line for
      supply chain in E-government applications which is called
      SPLSCGS Framework. It consists of four layers: presentation
      layer, integration layer, supply chain layer and data layer, and it
      developed based on three stages. Besides that, it consists flow of
      the SPLSCGS Framework and has three mechanism for the
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • E-Learning Effectiveness Analysis in Developing Countries: East Nusa
           Tenggara, Indonesia Perspective

    • Authors: Sfenrianto Sfenrianto, Ellen Tantrisna, Habibullah Akbar, Mochamad Wahyudi
      Abstract: The adoption of e-learning in developing countries like Indonesian Universities have been focused in urban areas like the big cities, especially in Java island. There is a lack of development of e-learning in a remote city like Kupang East Nusa Tenggara Indonesia which is located far away from the capital city. This research aims to assess the effectiveness of e-learning by analyzing three factors in one of the higher institution in Kupang city, i.e. Sekolah Tinggi Kesehatan Citra Mandiri Husada Kupang (STIKes CHMK). The factors include culture, technology and infrastructure, and content satisfaction. The data were collected using questionnaires. Research shows that with proper preparation for e-learning, the acceptance of e-learning in rural areas is significantly high. This finding suggests that e-learning can greatly benefit the students like Kupang city in developing countries.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Maximum Loadability Enhancement with a Hybrid Optimization Method

    • Authors: E. E. Hassan, T. K. A. Rahman, Z. Zakaria, N. Bahaman, M. H. Jifri
      Abstract: Nowadays, a power system is operating in a stressed condition due to the increase in demand in addition to constraint in building new power plants. The economics and environmental constraints to build new power plants and transmission lines have led the system to operate very close to its stability limits. Hence, more researches are required to study the important requirements to maintain stable voltage condition and hence develop new techniques in order to address the voltage stability problem. As an action, most Reactive Power Planning (RPP) objective is to minimize the cost of new reactive resources while satisfying the voltage stability constraints and labeled as Secured Reactive Power Planning (SCRPP).  The new alternative optimization technique called Adaptive Tumbling Bacterial Foraging (ATBFO) was introduced to solve the RPP problems in the IEEE 57 bus system. The comparison common optimization Meta-Heuristic Evolutionary Programming and original Bacterial Foraging techniques were chosen to verify the performance using the proposed ATBFO method. As a result, the ATBFO method is confirmed as the best suitable solution in solving the identified RPP objective functions.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • A New Copy Move Forgery Detection Technique using Adaptive
           over-Segementation and Feature Point Matching

    • Authors: Anil Gupta
      Abstract: With the development of Image processing editing tools and software, an image can be easily manipulated . The image manipulation detection is vital  for the reason that an image can be used  as legal evidence, in the field of forensics investigations, and also in numerous various other fields. The image forgery detection based on pixels aims to validate the digital image authenticity with no aforementioned information of the main image. There are several means intended for tampering a digital image, for example, copy-move or splicing, resampling a digital image (stretch, rotate, resize), removal as well as the addition of an object from your image. Copy move image forgery detection is utilized to figure out the replicated regions as well as the pasted parts, however forgery detection may possibly vary dependant on whether or not there is virtually any post-processing on the replicated part before inserting the item completely to another party. Typically, forgers  utilize many operations like rotation, filtering, JPEG compression, resizing as well as the addition of noise to the main image before pasting, that make this thing challenging to recognize the copy move image forgery. Hence, forgery detector needs to be robust to any or all manipulations and also the latest editing software tools.. This research paper illustrates recent issues in the techniques of forgery detection    and proposes a advanced  copy–move forgery detection scheme using adaptive over-segmentation and feature point matching. The proposed scheme integrates both block-based and key point-based forgery detection methods
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Estimation of Photovoltaic Module Parameters based on Total Error
           Minimization of I-V Characteristic

    • Authors: M. N. Abdullah, M. Z. Hussin, S. A. Jumaat, N. H. Radzi, Lilik J. Awalin
      Abstract: Mathematical Modelling of photovoltaic (PV) modules is important for simulation and performance analysis of PV system. Therefore, an accurate parameters estimation is necessary. Single-diode and two-diode model are widely used to model the PV system. However, it required to determine several parameters such as series and shunt resistances that not provided in datasheet.  The main goal of PV modelling technique is to obtain the accurate parameters to ensure the I-V characteristic is closed to the manufacturer datasheet. Previously, the maximum power error of calculated and datasheet value are considered as objective to be minimized for both models. This paper proposes the PV parameter estimation model based minimizing the total error of open circuit voltage (VOC), short circuit current (ISC) and maximum power (PMAX) where all these parameters are provided by the manufacturer. The performance of single-diode and two-diode models are tested on different type of PV modules using MATLAB. It found that the two-diode model obtained accurate parameters with smaller error compared to single-diode model. However, the simulation time is slightly higher than single-diode model due extra calculation required.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • GA-based Optimisation of a LiDAR Feedback Autonomous Mobile Robot
           Navigation System

    • Authors: Siti Nurhafizah Anual, Mohd Faisal Ibrahim, Nurhana Ibrahim, Aini Hussain, Mohd Marzuki Mustafa, Aqilah Baseri Huddin, Fazida Hanim Hashim
      Abstract: Autonomous mobile robots require an efficient navigation system in order to navigate from one location to another location fast and safe without hitting static or dynamic obstacles. A light-detection-and-ranging (LiDAR) based autonomous robot navigation is a multi-component navigation system consists of various parameters to be configured. With such structure and sometimes involving conflicting parameters, the process of determining the best configuration for the system is a non-trivial task. This work presents an optimisation method using Genetic algorithm (GA) to configure such navigation system with tuned parameters automatically. The proposed method can optimise parameters of a few components in a navigation system concurrently. The representation of chromosome and fitness function of GA for this specific robotic problem are discussed. The experimental results from simulation and real hardware show that the optimised navigation system outperforms a manually-tuned navigation system of an indoor mobile robot in terms of navigation time.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Whale Optimization Algorithm Based Technique for Distributed Generation
           Installation in Distribution System

    • Authors: Mohd Nurulhady Morshidi, Ismail Musirin, Siti Rafidah Abdul Rahim, Mohd Rafi Adzman, Mohamad Hatta Hussain
      Abstract: This paper presents Whale Optimization Algorithm (WOA) Based Technique for Distributed Generation Installation in Transmission System. In this study, WOA optimization engine is developed for the installation of Distributed Generation (DG). Prior to the optimization process, a pre-developed voltage stability index termed Fast Voltage Stability Index (FVSI) was used as an indicator to identify the location for the DG to be installed in the system. Meanwhile, for sizing the DG WOA is employed to identify the optimal sizing. By installing DG in the transmission system, voltage stability and voltage profile can be improved, while power losses can be minimized. The proposed algorithm was tested on 30-bus radial distribution network. Results obtained from the EP were compared with firefly algorithm (FA); indicating better results. This highlights the strength of WOA over FA in terms of minimizing total losses.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • A Comparative Study for Different Sizing of Solar PV System under Net
           Energy Metering Scheme at University Buildings

    • Authors: T. M. N. T. Mansur, N. H. Baharudin, R. Ali
      Abstract: Malaysia has moved forward by promoting the use of renewable energy such as solar PV to the public to reduce dependency on fossil fuel-based energy resources. Due to the concern on high electricity bill, Universiti Malaysia Perlis (UniMAP) is keen to install solar PV system as an initiative for energy saving program to its buildings. The objective of this paper is to technically and economically evaluate the different sizing of solar PV system for university buildings under the Net Energy Metering (NEM) scheme. The study involves gathering of solar energy resource information, daily load profile of the buildings, sizing PV array together with grid-connected inverters and the simulation of the designed system using PVsyst software. Based on the results obtained, the amount of solar energy generated and used by the load per year is between 5.10% and 20.20% from the total annual load demand. Almost all solar energy generated from the system will be self-consumed by the loads. In terms of profit gained, the university could reduce its electricity bill approximately between a quarter to one million ringgit per annum depending on the sizing capacity. Beneficially, the university could contribute to the environmental conservation by avoiding up to 2,000 tons of CO2 emission per year.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Dynamic Economic Dispatch Assessment Using Particle Swarm Optimization

    • Authors: Muhammad Murtadha Othman, Mohd Affendi Ismail Salim, Ismail Musirin, Nur Ashida Salim, Mohammad Lutfi Othman
      Abstract: This paper presents the application of particle swarm optimization (PSO) technique for solving the dynamic economic dispatch (DED) problem. The DED is one of the main functions in power system planning in order to obtain optimum power system operation and control. It determines the optimal operation of generating units at every predicted load demands over a certain period of time. The optimum operation of generating units is obtained by referring to the minimum total generation cost while the system is operating within its limits. The DED based PSO technique is tested on a 9-bus system containing of three generator bus, six load bus and twelve transmission lines.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Improving Classification Accuracy Using Clustering Technique

    • Authors: Norsyela Muhammad Noor Mathivanan, Nor Azura Md.Ghani, Roziah Mohd Janor
      Abstract: Product classification is the key issue in e-commerce domains. Many products are released to the market rapidly and to select the correct category in taxonomy for each product has become a challenging task. The application of classification model is useful to precisely classify the products. The study proposed a method to apply clustering prior to classification. This study has used a large-scale real-world data set to identify the efficiency of clustering technique to improve the classification model. The conventional text classification procedures are used in the study such as preprocessing, feature extraction and feature selection before applying the clustering technique. Results show that clustering technique improves the accuracy of the classification model. The best classification model for all three approaches which are classification model only, classification with hierarchical clustering and classification with K-means clustering is K-Nearest Neighbor (KNN) model. Even though the accuracy of the KNN models are the same across different approaches but the KNN model with K-means clustering had the shortest time of execution. Hence, applying K-means clustering prior to KNN model helps in reducing the computation time.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Sabah Traditional Chinese Medicine Database

    • Authors: Aslina Baharum, Neoh Yee Jin, Shaliza Hayati A. Wahab, Mohd Helmy Abd Wahab, Radzi Ambar, Nurul Hidayah Mat Zain
      Abstract: As technology grows, people tend to use or apply anything digitalized instead of printed, especially for references. This is because the printed form references are not easy to find. Even if the references are found successfully, it has already cost a lot of time, money, energy, etc. At the same time, people also put more emphasize on health issues. They are beginning to be more alert in fields that they have ignored before, such as traditional medicine and Chinese medicine. Based on these two points, it can be said that the effort of transforming Traditional Chinese Medicine (TCM) from printed based reference into online reference as a database is a public beneficial effort. There are a lot of online TCM database outside of Malaysia, especially from the People’s Republic of China, Hong Kong, and Taiwan. Those herbal remedies from overseas are somewhat different from the herbal remedies in Malaysia due to the habits and occurrences of the herbs. Through this project, it is hoped that this database will help the local people to discover and identify the herbs that they could find in the surrounding area. The objectives of this project are to identify the validity of the information of the Sabah TCM using mixed method, to develop the Sabah TCM database, and finally to evaluate the usability of the database designed using meCUE. The methodology used was 4D Appreciative Inquiry Model, which included discovery, dream, design, and destiny phases. The advantage of this model was to take a positive core to make any changes instead of finding the weaknesses of the project. Hopefully through the developed database, local Sabahan can take the advantage in identifying the proper usage of existing herbs in their surroundings
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
  • Evaluation of Support Vector Machine and Decision Tree for Emotion
           Recognition of Malay Folklores

    • Authors: Mastura Md Saad, Nursuriati Jamil, Raseeda Hamzah
      Abstract: In this paper, the performance of Support Vector Machine (SVM) and Decision Tree (DT) in classifying emotions from Malay folklores is presented. This work is the continuation of our storytelling speech synthesis work to add emotions for a more natural storytelling. A total of 100 documents from children short stories are collected and used as the datasets of the text-based emotion recognition experiment. Term Frequency-Inverse Document Frequency (TF-IDF) is extracted from the text documents and classified using SVM and DT.  Four types of common emotions, which are happy, angry, fearful and sad are classified using the two classifiers. Results showed that DT outperformed SVM by more than 22.2% accuracy rate. However, the overall emotion recognition is only at moderate rate suggesting an improvement is needed in future work. The accuracy of the emotion recognition should be improved in future studies by using semantic feature extractors or by incorporating deep learning for classification.
      PubDate: 2018-09-01
      Issue No: Vol. 7 (2018)
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
Home (Search)
Subjects A-Z
Publishers A-Z
Your IP address:
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-