Jurnal Ilmu Komputer dan Informasi
Not a member yet
247 research outputs found
Sort by
COVERAGE, DIVERSITY, AND COHERENCE OPTIMIZATION FOR MULTI-DOCUMENT SUMMARIZATION
Get PDFA great summarization on multi-document with similar topics can help users to get useful in¬for¬ma¬tion. A good summary must have an extensive coverage, minimum redundancy (high diversity), and smooth connection among sentences (high coherence). Therefore, multi-document summarization that con¬siders the coverage, diversity, and coherence of summary is needed. In this paper we pro¬pose a novel method on multi-document summarization that optimizes the coverage, diversity, and co¬her¬ence among the summary's sentences simultaneously. It integrates self-adaptive differential evo¬lu¬tion (SaDE) al¬gorithm to solve the optimization problem. Sentences ordering algorithm based on top¬ic¬al closeness ap¬proach is performed in SaDE iterations to improve coherences among the summary's sen¬tences. Ex¬pe¬ri¬ments have been performed on Text Analysis Conference (TAC) 2008 data sets. The ex¬perimental re¬sults showed that the proposed method generates summaries with average coherence and ROUGE scores 29-41.2 times and 46.97-64.71% better than any other method that only consider coverage and di¬versity, re-spect¬ive¬ly
INVESTIGATION OF FLIP-FLOP PERFORMANCE ON DIFFERENT TYPE AND ARCHITECTURE IN SHIFT REGISTER WITH PARALLEL LOAD APPLICATIONS
Get PDFRegister is one of the computer components that have a key role in computer organisation. Every computer contains millions of registers that are manifested by flip-flop. This research focuses on the investigation of flip-flop performance based on its type (D, T, S-R, and J-K) and architecture (structural, behavioural, and hybrid). Each type of flip-flop on each architecture would be tested in different bit of shift register with parallel load applications. The experiment criteria that will be assessed are power consumption, resources required, memory required, latency, and efficiency. Based on the experiment, it could be shown that D flip-flop and hybrid architecture showed the best performance in required memory, latency, power consumption, and efficiency. In addition, the experiment results showed that the greater the register number, the less efficient the system would be
MACULAR EDEMA CLASSIFICATION USING SELF-ORGANIZING MAP AND GENERALIZED LEARNING VECTOR QUANTIZATION
Get PDFAbstract
Macular edema is a kind of human sight disease as a result of advanced stage of diabetic retinopathy. It affects the central vision of patients and in severe cases lead to blindness. However, it is still difficult to diagnose the grade of macular edema quickly and accurately even by the medical doctor's skill. This paper proposes a new method to classify fundus images of diabetics by combining Self-Organizing Maps (SOM) and Generalized Vector Quantization (GLVQ) that will produce optimal weight in grading macular edema disease class. The proposed method consists of two learning phases. In the first phase, SOM is used to obtain the optimal weight based on dataset and random weight input. The second phase, GLVQ is used as main method to train data based on optimal weight gained from SOM. Final weights from GLVQ are used in fundus image classification. Experimental result shows that the proposed method is good for classification, with accuracy, sensitivity, and specificity at 80%, 100%, and 60%, respectively
AUTONOMOUS DETECTION AND TRACKING OF AN OBJECT AUTONOMOUSLY USING AR.DRONE QUADCOPTER
Get PDFAbstract
Nowadays, there are many robotic applications being developed to do tasks autonomously without any interactions or commands from human. Therefore, developing a system which enables a robot to do surveillance such as detection and tracking of a moving object will lead us to more advanced tasks carried out by robots in the future. AR.Drone is a flying robot platform that is able to take role as UAV (Unmanned Aerial Vehicle). Usage of computer vision algorithm such as Hough Transform makes it possible for such system to be implemented on AR.Drone. In this research, the developed algorithm is able to detect and track an object with certain shape and color. Then the algorithm is successfully implemented on AR.Drone quadcopter for detection and tracking
USER EMOTION IDENTIFICATION IN TWITTER USING SPECIFIC FEATURES: HASHTAG, EMOJI, EMOTICON, AND ADJECTIVE TERM
Get PDFAbstract Twitter is a social media application, which can give a sign for identifying user emotion. Identification of user emotion can be utilized in commercial domain, health, politic, and security problems. The problem of emotion identification in twit is the unstructured short text messages which lead the difficulty to figure out main features. In this paper, we propose a new framework for identifying the tendency of user emotions using specific features, i.e. hashtag, emoji, emoticon, and adjective term. Preprocessing is applied in the first phase, and then user emotions are identified by means of classification method using kNN. The proposed method can achieve good results, near ground truth, with accuracy of 92%
DIVERSITY-BASED ATTRIBUTE WEIGHTING FOR K-MODES CLUSTERING
Get PDFAbstract
Categorical data is a kind of data that is used for computational in computer science. To obtain the information from categorical data input, it needs a clustering algorithm. There are so many clustering algorithms that are given by the researchers. One of the clustering algorithms for categorical data is k-modes. K-modes uses a simple matching approach. This simple matching approach uses similarity values. In K-modes, the two similar objects have similarity value 1, and 0 if it is otherwise. Actually, in each attribute, there are some kinds of different attribute value and each kind of attribute value has different number. The similarity value 0 and 1 is not enough to represent the real semantic distance between a data object and a cluster. Thus in this paper, we generalize a k-modes algorithm for categorical data by adding the weight and diversity value of each attribute value to optimize categorical data clustering
THE PAR (PEER ASSESSMENT RATING) CALCULATION ON 2 DIMENSIONAL TEETH MODEL IMAGE FOR THE CENTERLINE COMPONENT AND TEETH SEGMENTATION ON THE OCCLUSAL SURFACE TEETH MODEL IMAGE
No full textAbstract The PAR (Peer Assessment Rating) Index is used by orthodontists around the world to calculate the severeness of a malocclusion. A malocclusion is a dental disease where the teeth are not properly aligned. In Indonesia, the number of malocclusion is relatively high. The occurrence of orthodontics who can treat malocclusion is also low in Indonesia. In 2013, a research is done to create the telehealth monitoring system to provide better treatment of malocclusion in Indonesia. The research is further improved by using different Adaptive Multiple Thresholding methods to segmentate the image. The result will be used to calculate the Centerline component of the PAR Index. The result is a system that could calculate the PAR Index automatically and is compared to the results using manual method
PEER ASSESSMENT RATING (PAR) INDEX CALCULATION ON 2D DENTAL MODEL IMAGE FOR OVER JET, OPEN BITE, AND TEETH SEGMENTATION ON OCCLUSION SURFACE
Get PDFAbstract Malocclusion is a clinical symptom, in which the teeth of maxilla and mandible are not located at the proper location. If malocclusion left untreated, it can lead to complications in the digestive system, headache, and periodontal disease disorders. Malocclusion problems involving abnormalities of teeth, bones, and muscles around the jaw are obligation of orthodontic specialists to treat them. The treatments can be varying based on the type of malocclusion, including tooth extraction and tooth braces. To know certain degree of malocclusion experienced by the patient, an assessment method called Peer Assessment Rating (PAR) Index is usually used by the specialist. To help the works of orthodontic specialists in Indonesia, a new automated calculation system based on 2D image of tooth model for PAR Index is being developed. In this paper, the calculation system for over-jet, open-bite, and teeth segmentation is developed. The result of the developed system is then compared with manual assessment done by orthodontic specialist, in order to verify the accuracy of the system
IMPLEMENTATION OF IMAGE PROCESSING ALGORITHMS AND GLVQ TO TRACK AN OBJECT USING AR.DRONE CAMERA
No full textAbstract
In this research, Parrot AR.Drone as an Unmanned Aerial Vehicle (UAV) was used to track an object from above. Development of this system utilized some functions from OpenCV library and Robot Operating System (ROS). Techniques that were implemented in the system are image processing al-gorithm (Centroid-Contour Distance (CCD)), feature extraction algorithm (Principal Component Analysis (PCA)) and an artificial neural network algorithm (Generalized Learning Vector Quantization (GLVQ)). The final result of this research is a program for AR.Drone to track a moving object on the floor in fast response time that is under 1 second
QUALITY OF SERVICE ORIENTED WEB SERVICE SELECTION: AN EVALUATION OF TECHNIQUES
Get PDFAbstract
In service-oriented computing, web services are the basic foundation that aims to facilitate building of business application in a more flexible and interoperable manner for enterprise collaboration. One of the most promising advantages of web service technology is the possibility of creating added-value services by combining existing ones. A key step for composing and executing services lies in the selection of the individual service to use. Much attention has been devoted to appropriate selection of service functionalities, but also the non-functional properties of the services play a key role. A web service selection technique must take as much as possible the important influencing aspects into account to the selection process in order to minimize the selection efforts. This paper evaluates several web service selection techniques published in literature with the focus on their contributions to web service selection. The evaluation results can be used as a basis for improving web service selection techniques and then simplifying the selection tasks