Papers by Riyanarto Sarno
2018 International Seminar on Application for Technology of Information and Communication
Currently, the use of Indonesian language on the internet is growing rapidly and many of the exis... more Currently, the use of Indonesian language on the internet is growing rapidly and many of the existing sentences contain ambiguous words. In Natural Language Processing the problem to find out the meaning of an ambiguous word is called Word Sense Disambiguation. Word sense disambiguation is a problem about how we know the meaning of an ambiguous word in a given sentence. Many uses if we can solve word sense disambiguation problems such as can be used for text classification, text clustering and for machine translation. In this paper, we propose the use of SVM algorithm with TF-IDF as the feature extraction method and Wikipedia as the training data to solve the WSD problem of Indonesian language. The results of our proposed method reach an accuracy level of 0.877.
Travel Route Optimization Using Dynamic Programming
2018 6th International Conference on Information and Communication Technology (ICoICT)
This paper provides research result in determining the optimal route sequence of destination and ... more This paper provides research result in determining the optimal route sequence of destination and travel time on tourism buses with the same start-end point to improve tourism services and operational cost savings. The tourism bus service that will be discussed in this research is the tourism bus belonging to the Department of Culture and Tourism (Disbudpar) Surabaya, namely Surabaya Shopping and Culinary Track (SSCT) bus. SSCT bus currently has only two regular routes, namely Museum Track and Maritime Track, and will increase to several other routes type depends on annual tourism events in Surabaya. Unfortunately, in the calculation of this location is still manual so it allows some disadvantages, and if additional route type also still done manually, this mistake will happen repeatedly. Therefore, in this study the calculation of the optimal distance and travel time of SSCT bus will do in the basic formula of the Dynamic Programming method. The used main parameters are distance and time on road between tourist destinations, while traffic congestion as a limitations of the problem in this study. The final results of this study shows that time on road on the Museum Track and the Maritime Track can be saved up to 58% and 25% compared to the current manual time on road calculations. It certainly will help Disbudpar Surabaya in making the best decision in improving SSCT bus service.
2018 International Seminar on Application for Technology of Information and Communication, 2018
Software effort estimation is one of the main activities in software development project, because... more Software effort estimation is one of the main activities in software development project, because it can indicate whether the project will be successful or failed depending on the accuracy of the estimation. There are some models to estimate effort for software development. One of the well-known models is COCOMO II. The accuracy of COCOMO II effort estimation can still be improved by optimizing its constants. Several research have been conducted to improve COCOMO II constants, such as Differential Evolution, Harmony Search and Genetic Algorithm. In this paper, a model to optimize COCOMO II constants is proposed. The optimized constants are constant A and constant B by using Bat Algorithm with Turkish project dataset. The results of experiment are compared with local calibration and COCOMO II original constants by evaluating the proposed method using Mean Magnitude Relative Error (MMRE). The results show that the proposed model has the smallest value, which means its effort estimation has closer value of actual effort than that of the other methods which exist in the Turkish project dataset.
Management processes without responsive to abnormal activity that might occur can affect the perf... more Management processes without responsive to abnormal activity that might occur can affect the performance of an organization. The Publishing Workflow Ontology (PWO) will be modified for detect abnormal activity, such as wrong pattern, wrong resource, throughput time maximum and wrong duty combine that occurs in the event logs. The new model from modification called “Warning Criterion Ontology (WCO)” can be represent the knowledge base to detect abnormal activity in the business process especially this knowledge can be used distinguishes the activity is allowed to be done by the superior and any activity which should only be done by direct superior. The model used some rule for reasoning, then after reasoning used some SPARQL to detection abnormal activity. Results of detection abnormal activity can be used as attributes for assessment Key Performance Indicator (KPI) activity in determining “The compliance in Standard Operating Procedure (SOP) implementation”. This research obtained a...
2018 International Conference on Information and Communications Technology (ICOIACT), 2018
Home automation is the implementation of information technology and control system to facilitate ... more Home automation is the implementation of information technology and control system to facilitate the daily life easier. The growth of technology make smartphone can control the home appliances. An automated device can work more flexible and efficient, including the use in unlocking door. For busy family or busy people, it is not easy to get out of the seat only to reach the door for unlocking people that already have known and made appointment before. The proposed system presents friendly expense design and implementation of home automation to unlock the door with authentication through speech command or pin via smartphone application. So, it is not only the open button from smartphone application that anyone can control, but also it is added an interface for speech command or pin which also can be useful as security. Users can change the password used by themselves. Thus, only users who know the password can control to unlock the door. The smartphone application designed facilitate the users to be free to choose the authentication between speech command or pin. In speech command, users can easily open the door with say it. Another work being tried is open the door with pin. It can help disabled people with speech impaired to be still able use the application. The design of proposed method is based on Android smartphone application, Bluetooth module and Arduino Board. Android smartphone application is used for serial communication to the Bluetooth module which is connected in Arduino Board to unlock the door. Besides it has low cost, Bluetooth based wireless home automation system can be easy implemented in the home. The suggested system is tested and it gives the expected system with more feature as authentication, either with speech command or with pin. Speech command enacted to the system is also tested the Bluetooth connectivity. The farthest range is 14 m to the controlled hardware system.
Android Application for Controlling Air Conditioner Using Fuzzy Logic
2018 6th International Conference on Information and Communication Technology (ICoICT), 2018
There are many kind of electronic appliances around us such as microwave, lamp, television, and a... more There are many kind of electronic appliances around us such as microwave, lamp, television, and air conditioner around us. Sometimes many people are confuse and do not know how to manage those electronic appliances. It is hard to manage whenever they aren't at home or go to another places. By using electronic appliance in our daily life, it always need our electrical resources and some electronic devices consume more electrical energy such as Air Conditioner, Microwave and also a computer. Those devices are makes our electricity bill can be increased and makes some people surprised when they looked on their bill, they don't know how to reduce the power consumption all those electronic parts since they don't understand how to maintain those parts some people often forgot to turn off the electronic devices when they leave for working, school and any other activities, so this is make that electronic devices would be turn on all day long then makes our electricity resources ...
2018 International Conference on Information and Communications Technology (ICOIACT), 2018
The position of a singer in a band is often important because it will interact directly with the ... more The position of a singer in a band is often important because it will interact directly with the audience. In an organization found a related problem about the selection of the best singers so there needs to be a decision support mechanism to be able to find a best singer. This problem can be solved by combining two decision support methods namely Analytic Hierarchy Process (AHP) for the weighting process of some criteria and Simple Additive Weighting (SAW) for value processing of participants. Based on the experimental results, the criteria used for the consistency weightedness priority level analysis found consistent results that were sufficient to determine the best performers based on all available alternatives. So that alternative ranking results can be used as a basic guideline to help decision making.
Procedia Computer Science, 2017
Meat is one of foodstuff that widely consumed in the world. Unfortunately, the quality of meat ca... more Meat is one of foodstuff that widely consumed in the world. Unfortunately, the quality of meat can easily degrade if not handled properly and become the serious health hazards if consumed. Hence, the food safety system is very important to guarantee the quality of food to be consumed. In this study, we introduced the development of mobile electronic nose for beef quality detection and monitoring. This system is developed using low-cost hardware and possible to integrate with cooling box or refrigerator for real time monitoring and analysis during distribution and storage processes. K-Nearest Neighbor with signal preprocessing is used to classify two, three, and four classes of beef. The experimental results show that the system can perfectly distinguish fresh and spoiled beef. Moreover, it has promising classification accuracy for binary, three classes, and four classes classification with 93.64%, 86.00%, and 85.50%, respectively. Hence, this system has a potential solution to provide low-cost, easy to use, and realtime meat quality monitoring system.
2018 International Seminar on Application for Technology of Information and Communication, 2018
Graph similarity is a method to check the graphic equations between two graphs. Anomaly detection... more Graph similarity is a method to check the graphic equations between two graphs. Anomaly detection in a business process can use the graph similarity method as well. The graph of the ongoing business process compared to the Standard Operating Procedure's graph (SOP's graph) as a reference. Standard Operating Procedures (SOPs) can definitely as a benchmark of a company running a business process. In this study, the case taken to detect anomaly of business processes in the process of replacing parts in wireless device distributors. The method used is dice coefficient to detect vertex or edge overlap and vertex ranking using the Spearman method to detect missing or altered vertices. The result of detecting business process anomaly using dice coefficient found three business process anomalies. While in the vertex ranking method using Spearman coefficient found two anomalies. Anomalies were found in vertex ranking method are the same as the expert judgement's results.
Classification of Male and Female Sweat Odor in the Morning Using Electronic Nose
2021 3rd East Indonesia Conference on Computer and Information Technology (EIConCIT)
Biologically, there are two genders that are declared, which is male and female. Both genders hav... more Biologically, there are two genders that are declared, which is male and female. Both genders have the same hormones but at different levels. The difference in the level of hormones causes both genders can be distinguished from several aspects, and one of them is from their sweat. In this study, we are using Electronic Nose (E-Nose) device for classify the gender between male and female based on their sweat odor and the time that is taken to get the sample is in the morning. E-Nose is a device that can identify various kinds of scents. The results obtained from this tool are signal waves that can be identified, compared, and processed. E-Nose has also been used in various fields. one of them is in the health sector. In this research the E-Nose consists of several sensors TGS, 822, 2612, 2620, 823, 826, 2603, 2600, 813, and SHT-15 connected to an Arduino. The data obtained were sampled and splitting 80% training dan 20% testing. Using regression with various methods, the highest accuracy is SO% using the Support Vector Machine (SVM) method.
3d Reconstruction from 2d Corpus Callosum Segmentation
SSRN Electronic Journal
2018 International Seminar on Application for Technology of Information and Communication, 2018
The success indicator of an institution and company is when the available resources have been use... more The success indicator of an institution and company is when the available resources have been used effectively and efficiently. The limited resources available can cause delays in ongoing business processes. The delay in a business process is always closely related to financing. The slower the business process runs, the more the expenses that must be incurred for labor and material costs. Therefore, it is necessary to optimize the cost and time for an organization. It can be minimized by using goal programming. In goal programming, weights are given to make sense of which activities to be watched. In this research using lingo software to calculate goal programming.
2017 3rd International Conference on Science in Information Technology (ICSITech), 2017
This paper presents a bio-inspired hybrid method which concentrate on the optimal or a near-optim... more This paper presents a bio-inspired hybrid method which concentrate on the optimal or a near-optimal business process model from an event log. The discovery of Hybrid Particle Swarm Optimization (Hybrid PSO) algorithm comes from the combination of Particle Swarm Optimization (PSO) algorithm and Simulated Annealing (SA) method. This paper presents a method which combines Rule discovery task and Hybrid PSO. The proposed method can discover not only classification rules that produce the most optimal business process model from event logs, but also can optimize the quality of process model. To be formulated into an optimization problem, we use rule discovery task to get the high accuracy, comprehensibility and generalization performance. After we get the results from rule discovery task, we use Hybrid PSO to resolve the problem. In this proposed method, we use continuous data as data set and fitness function as evaluation criteria of quality of discovered business process model. As final results, we prove that the proposed method has the best results in terms of average fitness and number of iterations, compared with classical PSO algorithm and original hybrid PSO algorithm.
2018 International Conference on Information and Communications Technology (ICOIACT), 2018
The services of port in Indonesia are increasing from year to year. The traffic of port is increa... more The services of port in Indonesia are increasing from year to year. The traffic of port is increasingly crowded with the number of boats coming to load and unload processes. A lot of ship queues result in delay when exceeding due date from the date of the agreement will cause the higher cost to be issued which is called demurrage. To reduce the costs incurred and the length of queue time on the scheduling at the port, we used Goal Programming (GP). Goal Programming is an algorithm that solves linear programming problems using mathematical formulation to get solutions in getting goals. In this study, optimizing 43 activities and 7 trace variations on loading and unloading activities of container terminal services from events log. The goal programming model from 43 activities has been implemented using Lingo software to obtain objective value in achieving the objectives of each activity used to determine activities that have a major influence on the delay in loading and unloading activities. The result of Goal Programming is that there are two activities which have very high deviation, therefore both of activities are evaluated in performance on container activity.
The process mining multi-organizations does the extraction from the events log of each organizati... more The process mining multi-organizations does the extraction from the events log of each organization in a series of integrated workflow. To prove that the workflow of multiple organization cooperation is logic or soundness, it should be logical in multi-WF-net. The soundness of cooperation organization uses connector. This paper describes the colaboration model capacity sharing using case studies of clearing process in the banks.
International Journal of Advanced engineering, Management and Science, 2016
Enterprise Resource Planning (ERP) implementation is one of key success factors for business orga... more Enterprise Resource Planning (ERP) implementation is one of key success factors for business organization's to endorse their business strategy and goal alignment with information technology recent. In spite of its benefits, yet there are many failures in ERP implementation, whereas between 50% to 75% is categorized has failed due to lack of top level management awareness, change of business processes in project implementation, unsuitable architecture, design, and technological infrastructure. The study proposes an Adaptive ERP system that coverage both management and technology areas with the main characteristic are in visibility, flexibility, and agility. The Adaptive ERP is expected becoming as alternative approach to overcome failures in ERP implementation. The Adaptive ERP has standardized business process transitioning from Project Management (PM) into Operational Management (OM) that generally as baseline for conventional ERP. An addition, Adaptive ERP has standardized Ser...
Corpus Callosum Segmentation from Brain MRI Images Based on Level Set Method
2020 International Seminar on Application for Technology of Information and Communication (iSemantic), 2020
Corpus callosum integrates left and right hemispheres of human brain. There are several methods f... more Corpus callosum integrates left and right hemispheres of human brain. There are several methods for segmenting corpus callosum, but the existing algorithms need several steps to segment images. Therefore, we propose a simple method using level set method to segment corpus callosum. We use level set method as it can handle the structure of the brain easily. This method provides a numerical solution for processing changes in topological contours by representing a curve or surface as a zero level to a higher hyper-dimensional surface. This experiment shows that by implementing level set method to segment the corpus callosum produces Dice Similarity Coefficient (DSC) value of 85.14%.
International Journal of Surgery Case Reports, 2020
INTRODUCTION: Minimally invasive techniques such as stereotactic aspiration of spontaneous intrac... more INTRODUCTION: Minimally invasive techniques such as stereotactic aspiration of spontaneous intracerebral hematoma (SICH) evacuation can minimize brain tissue damage due to surgery. We share our experience of adopting stereotactic aspiration of SICH in our center without compromising safety. PRESENTATION OF CASES: Three stereotactic aspiration procedures for SICH immediately after 24 h of onset are reported. All cases showed good results. Level of consciousness of all the patient returned to normal. Two patients could carry out routine activities independently. One patient has left hemiparesis. DISCUSSION: Stereotactic aspiration of SICH has been newly implemented at our center with acceptable results achieved. Patient selection has an important role in determining the choice of technique. The procedures were done without anticoagulant agent. Stereotactic aspiration of SICH is associated with limited brain tissue damage, shorter duration of surgery, reduced length of stay, faster postoperative healing, and better functional improvement. CONCLUSION: Stereotactic aspiration of SICH is a minimally invasive defined strategy for hematoma evacuation without compromising safety.
International Journal of Intelligent Engineering and Systems, 2020
Most of neuroimaging applications tend to still rely on expert knowledge in determining anatomies... more Most of neuroimaging applications tend to still rely on expert knowledge in determining anatomies of the brain. For example in Parkinson's disease surgery, detection of the anterior commissure (AC) and posterior commissure (PC) are still done manually by doctors. Previously, various methods have been developed related to the automatic detection of AC and PC. However, the majority of previously methods have several drawbacks, such as only compatible on T1-W or T2-W, only compatible for data with the same matrix size, and requires a time-consuming training process. This study proposes a new strategy by combining a multilevel thresholding and morphological relationships approach for automatic detection of AC and PC. The process divided into 4 main stages: preprocessing, multilevel thresholding, segmentation, and detection of AC and PC. The segmentation is performed on several anatomies of the brain including corpus callosum, fornix, and colliculus. From the experiment, it can be concluded that the use of multilevel thresholding and morphological relationship was successfully detecting AC and PC with the mean error were 1.02 mm and 1.06 mm, respectively. The proposed method can perform an automatic detection of AC and PC with simply algorithm, does not require a large of diverse data sets for the training process, without training process that takes up time, and reliable on the diversity of MRI since it is compatible for T1-W and T2-W with various matrix sizes of 256 x 256 and 512 x 512 pixels which cannot be handled by previous researches.
Proceeding of the Electrical Engineering Computer Science and Informatics, 2017
In recent years, process mining is important to discover process model from event logs; however t... more In recent years, process mining is important to discover process model from event logs; however the existing methods have not achieved good in overall fitness. In this context, this paper proposes a combination of the Evolutionary Tree Miner (ETM) and Simulated Annealing (SA). The ETM aims to reduce randomness of population so that it can improved the quality of individuals. SA aims to increase overall fitness in the population. The results of the proposed method which was compared to other approaches show that the proposes method had better in overall fitness and better quality of individuals.
Uploads
Papers by Riyanarto Sarno