Husni Teja Sukmana

A rule-based question answering system on relevant documents of Indonesian Quran Translation

This paper presents work in development of a question answering (QA) system by using a combination of two different architectures i.e. the one used relevant documents and another used rule-based method, which those two contribute for answer extraction. Base on previous researches testing result, it could be inferred that each of the methods could be a complement for another method in order to increase system performance. This QA was purposed to gather information from Indonesian Quran Translation. The new architecture was designed to gather relevant documents toward the keywords and be used subsequentially to gather answer candidates by using rule-based method. The initial results indicate that system still restricted with retrieved relevant documents, and caused delivering only 60% correct answers. This achievement is not better than the previous one that used rule-based method only.

Semantically annotated corpus model of Indonesian Translation of Quran: An effort in increasing question answering system performance

This paper presents our work in defining a model to build a semantic-based corpus of Indonesian Translation of the Quran. This task was being an effort to increase Question Answering System (QAS) performance on Indonesian Translation of the Quran that has been developed in 2013[1]. As the QAS run on three kinds of question type i.e. Siapa (Who), Kapan (When), and Di mana (Where), this model designed specifically to deal with those question types. The model is ready to be implemented and evaluated. Since we want to measure how significance semantic approach is on QAS performance, evaluation will be conducted by using the same scheme used. Furthermore, our model also will be assessed by comparing it with other corpus developed by using graph database model.

The prototype of Zakat management system in Indonesia by using the social society approach: A case study

Giving alms (Zakat) to people in need is an obligation for Muslims to create justice for others. In Indonesia, there are already several institutions dealing with the issue for zakat, among others the body formed by the government, namely Badan Amil Zakat (BAZNAS) or a body formed by the community. Each Zakat institution already has a system used to register Muzaki (the person giving Zakat) and Mustahiq (the recipient of Zakat). However, there are some disadvantages to their system. First, the level of distribution of Zakat to the needy is still very low compare to the level of Zakat acceptance, which is about 60%. This is due to Mustahiq data owned by Zakat institutions are not real-time due to lack of officers in searching for Mustahiq data. Second, the data among the Zakat institutions that are still not integrated, thus allowing duplication of giving Zakat to the same Mustahiq. On the other hand, there is the possibility of Mustahiq not receiving any donations at all. In this research, we have created a new approach involving civil society to participate recommending Mustahiqs data and allow Muzaki to be able to give Zakat directly to Mustahiq. Then, we created a proxy database for communication among existing Zakat institutions. The result of this research is the design and prototype of new system

Models and software measurement using Goal/Question/Metric method and CMS Matrix parameter (Case study discussion forum)

Existence of a CMS as a tool in making a website has been used extensively by the communities. Currently, there are many CMS available as options, especially CMS bulletin board. The number of options is an obstacle for someone to choose a suitable CMS to fulfill their needs. Because of the lack of research on this CMS bulletin board comparison, this research tries to compare and search the best CMS bulletin board. This research uses metrics for modeling and software measurement to identify the caracteristics of existing CMS bulletin board. This research used Goal/Question/Metric (GQM) for modelling method and CMS Matrix as the parameters. As for the CMS bulletin board, in this study, we choose PhpBB, MyBB, and SMF. The results of this study indicate that SMF bulletin board has the best score compared to MyBB and phpBB CMS bulletin board.

Optimization of multiple depot vehicle routing problem (MDVRP) on perishable product distribution by using genetic algorithm and fuzzy logic controller (FLC)

Distribution has a large portion of the total cost of sales of goods or product. It cause high cost transport and risk to the quality of the goods which are distributed, especially perishable product. Perishable product quality is greatly influenced by distribution, thus when the distribution not optimal, it will risk very big deal of broken product. In connection with this matter, the distribution process needed to optimize especially to perishable product. Optimal distribution problem can be solved using Multiple Depot Vehicle Distribution Routing Problem (MDVRP) model, which was development of Vehicle Routing Problem (VRP). To get the optimal solution of MDVRP, genetic Algorithm (GA) was used. Using GA, more than one alternative solution with good fitness value were gained. Then Fuzzy Logic Controller (FLC) was used to control these parameter values in order not to trap into local optimum. After new pm and pc value were obtained, the GA process was conducted to get the shortest route. The result of this research showed that the value of the probability of crossover and mutation affected the fitness values. The higher fitness value, the smaller the distance which reached. It will reduce the risk of rot caused by travel time. Testing results showed some alternative solutions which is not much different in fitness value. Level of optimality increased when FLC process were conducted. From 10 times evaluation reached 89, 9%.

A semantic-based question answering system for indonesian translation of Quran

This paper presents a work in developing a semantic-based question answering system (QAS) for Indonesian Translation of Quran (ITQ). This research is motivated by the lacks of previous built QAS that caused by a keyword-based retrieval. Instead of keeping the retrieval method, we shifted to a semantic approach where the retrieval process is done by using a semantic similarity measurement. In doing so, we built an ontology of ITQ to get the concepts as well as verses where they appear in. We applied three factoid question types on the QAS that including Who, Where, and When. Furthermore, a weighted vector for each concept that belongs to respective expected answering type (also called as named entity group) i.e. Person, Location, and Time is generated in order to feed semantic interpreter on user question. From 222 concepts defined from the ontology, we clustered them into 77, 24, and 6 concepts for Person, Location, and Time respectively. Since we found there are some characteristics of texts in ITQ, we developed our own modules to deal with including generate the inverted index and named entity recognition. Answer extraction is conducted by applying some features extraction in order to score the answer candidates. Evaluation of the system is designed by providing two data set of question and answer where the first one is purposed to measure the effectiveness of semantic approach comparing with keyword-based retrieval and the last one aims to know system performance in regard the appearance of concepts in ITQ.

Implementation of Server Consolidation Method on a Data Center by using Virtualization Technique: A Case Study

Data center is a place where data and applications placed and run. Those data and applications saved various server based on function of application run such as server of database, proxy, portal, website, application, mikrotic and so on. The more vary application run, the more server types needed. There are several implications when data center encounter “server flood”, including more electrical energy must be provided. In addition to the relationship between energy and the utilization rate is still low, there is still one problem faced by system administrators with the number of servers in the data center, the more the server to be maintained. The maintenance requirement is usually done as a result of periodic maintenance, hardware upgrades, system upgrades and hardware damage. The maintenance process requires a fairly long time, starts from new server preparation, application and system preparation, and also on the network side. The solution that can be done to solve this situation is by using virtualization (VM) of the servers. After several processes, such as categorization process, consolidation, design and implementation, the results made are by using VM terms of energy consumption, it can provide a savings of more than 50%. We conduct the virtualization concept on Syarif Hidayatullah State Islamic University of Jakarta (UIN Jakarta) as our case study. Before VM applied, the consumption of energy used is equal to 7855 watts, whereas after VM applied energy consumption will be 3890 watts. Efficient data center management can be applied and can save time for maintenance. Before the use of the VM, the time required to process improvement at least 3 hours, but after the use of VM takes just less than 1 hour.

Application of genetic algorithm for class scheduling (Case study: Faculty of science and technology UIN Jakarta)

The objective of this research is about building a class scheduling application using genetic algorithm. The parameters used in genetic algorithms namely: iteration, PM (Probability Mutation), PC (Probability crossover). In Faculty of Science and Technology UIN Jakarta, class schedule built by a staff. The staff faces numbers of obstacles when building the schedule, among others: the limitations of the classroom and schedule of lectures, and large number of students. However, it is able to overcome the obstacles but it takes quite a long time to build. To optimize the tasks, an application using genetic algorithm is suggested. In this research, interviews and literature studies are used as research methodology, Waterfall as application development methods and genetic algorithms for scheduling. This application was developed using HTML, PHP, and MySQL. To get the optimal parameter values,_some variance of iteration (ns), PC, PM values were tested. The results show that the optimal value for gaining the best schedule are maximum of 20 iterations, PC 0.8 and PM 0.01. Using this values, the class scheduling application generates approximately 1,201 without any clash among the data and this application can facilitate the building of class schedule.

Developing mobile-based academic information system: A case study at Islamic State University (UIN) Syarif Hidayatullah Jakarta

Application of academic information system designed to support teaching and learning activities will be undertaken by universities in Indonesia. State Islamic University (UIN) Syarif Hidayatullah Jakarta has implemented web-based academic information system that is accessible to the academic community through the Internet network, namely the Academic Information System (AIS). Development of information technology has made access to the Internet more flexible, especially through mobile devices. AIS can also be accessed through a variety of devices, but this system would perform optimally when accessed via the Personal Computer (PC) or laptop. AIS accessing via mobile devices has limitations in terms of display and interaction with the web-based system. Therefore, the research focuses on developing mobile-based academic information system to make AIS data center. This application will be devoted to the two types of users, namely students and lecturers as they are the most frequent users of the system and choose the phonegap framework as the manufacture of mobile applications. Thus, the academic community will find it easier to access academic information systems via mobile devices. This study shows that AIS mobile version has made AIS become user-friendly and easy to use application for the proposed users.