Filter By Year

1945 2024


Found 25,189 documents
Search Information

FEATURE SELECTION METHODS BASED ON MUTUAL INFORMATION FOR CLASSIFYING HETEROGENEOUS FEATURES Ratri Enggar Pawening; Tio Darmawan; Rizqa Raaiqa Bintana; Agus Zainal Arifin; Darlis Herumurti
Jurnal Ilmu Komputer dan Informasi Vol 9, No 2 (2016): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information)
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (283.816 KB) | DOI: 10.21609/jiki.v9i2.384

Abstract

Datasets with heterogeneous features can affect feature selection results that are not appropriate because it is difficult to evaluate heterogeneous features concurrently. Feature transformation (FT) is another way to handle heterogeneous features subset selection. The results of transformation from non-numerical into numerical features may produce redundancy to the original numerical features. In this paper, we propose a method to select feature subset based on mutual information (MI) for classifying heterogeneous features. We use unsupervised feature transformation (UFT) methods and joint mutual information maximation (JMIM) methods. UFT methods is used to transform non-numerical features into numerical features. JMIM methods is used to select feature subset with a consideration of the class label. The transformed and the original features are combined entirely, then determine features subset by using JMIM methods, and classify them using support vector machine (SVM) algorithm. The classification accuracy are measured for any number of selected feature subset and compared between UFT-JMIM methods and Dummy-JMIM methods. The average classification accuracy for all experiments in this study that can be achieved by UFT-JMIM methods is about 84.47% and Dummy-JMIM methods is about 84.24%. This result shows that UFT-JMIM methods can minimize information loss between transformed and original features, and select feature subset to avoid redundant and irrelevant features.
Interactive Image Segmentation using Neighborhood Spatial Information and Statistical Grey Level on Dental Panoramic Radiograph Shabrina Choirunnisa; Ari Firmanto; Agus Zaenal
Jurnal Ilmu Komputer dan Informasi Vol 12, No 1 (2019): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (717.399 KB) | DOI: 10.21609/jiki.v12i1.622

Abstract

 In dental panoramic radiographs, grey-level intensity information has been widely used for object segmentation in digital image. However, low contrast in the radiograph image causes high ambiguity  that can cause the inconsistency of classification result. Since the grey-level intensity of background and object is almost similar, so in order to improve the segmentation result, the spatial distance on neighborhod region is applied.  In this paper, we proposed a novel strategy to measure the distance using neighborhod spatial information and statistical grey level technique for image segmentation. The proposed method starts by calculating adjacency matrix and measured spatial distance on neighborhood region. Since the value of both distances are not in the same range, then the normalization is needed. The distances merging is approached by tuning the weight using several constant values. The experiment results show that our proposed merging strategy has better segmentation result based on Relative Foreground Area Error value.
AQ-2 Reformation in Public Information Announcement Technique of Agricultural Quarantine by Using Digital Applications Adil Kari Salam Harahap
Hemera Zoa Proceedings of the 20th FAVA & the 15th KIVNAS PDHI 2018
Publisher : Hemera Zoa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (527.027 KB)

Abstract

In the implementation of Public Service Information System, an agency needs to provide openly public service information that can be accessed easily, quickly, accurately, and accountably. The information system is a series of activities which include the storaging and managing information and also mechanism of delivering information from organizer to the public which are presented electronically (PermenpanRB No. 13 Tahun 2017).Public information must be conveyed and announced periodicly, soonly, and available in everytime (UU No. 14 Years 2008). With the reformation of this public information announcement technique, it is believed that the objective of UU 14 Years 2008 about Public Information Openness can be achieved. The intended purposes are listed in Article 3:1)    to ensure the right of citizens to know public policy making plans, public policy programs, and public decision-making processes, and the reasons for public decision making;2)    to encourage public participation in the public policy-making process;3)    to enhance the community's active role in public policy making and good Public Agency management;4)    to realize good state administration, which is transparent, effective and efficient, accountable and accountable;5)    to know the reasons for public policy affecting the livelihood of the public;6)    to develop science and intellectual life of the nation; and / or improve the management and information services within the Public Agency to produce quality information services.The First Class of Agricultural Quarantine Station in Tanjung Balai Asahan use social media as a system information. The informations provide in 2 (two) forms, its are photos and videos. Photos and videos are uploaded on Instagram account of the First Class Agricultural Quarantine Station in Tanjung Balai Asahan (@karantina_tbasahan).
Cooperative is an economic organization of farmers who have strategic positions in improving the welfare of its members and is a constitutional mandate to strengthen the national economy in anticipation of neoliberal economic development in an era of global trade.  To strengthen the Village Unit Cooperatives (KUD) requires information through the development model of effective KUD organizational communication.  The purposes of this research were (1) to examine the role of KUD organizational comm Parlaungan A. Rangkuti; Sumardjo .; Amiruddin Saleh; E. Namaken Sembiring
Forum Pasca Sarjana Vol. 34 No. 2 (2011): Forum Pascasarjana
Publisher : Forum Pasca Sarjana

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Cooperative is an economic organization of farmers who have strategic positions in improving the welfare of its members and is a constitutional mandate to strengthen the national economy in anticipation of neoliberal economic development in an era of global trade.  To strengthen the Village Unit Cooperatives (KUD) requires information through the development model of effective KUD organizational communication.  The purposes of this research were (1) to examine the role of KUD organizational communication factors for performance and capacity development as agriculture economic organization, (2) to analyze the correlation of KUD organizational communication factors in associated with KUD role in efforts to improve utilization of rice milling, (3) to formulate a model of KUD organizational communication in anticipating the globalization era.  KUD sample of fair active category as the analysis unit consists of five KUD in Karawang District, they are KUD Sri Mukya, KUD Sumber Padi, KUD Warga Bakti, KUD Warga Tani and KUD Mitra Tani.  This research was designed with survey method using SEM analysis (structural equation model).  It was conducted at research location in December 2009 until March 2010. SEM analysis result showed that there was a positive and significance of the KUD performance to KUD capacity for KUD service quality improvement in the utilization of rice milling, which means testing the main hypothesis or alternative hypothesis (Ha) is accepted.   Key words: organization communication, village unit cooperatives, role of agricultural mechanization
The mangrove area of Togean Islands have been used for marine ecotourism activities.  The increasing of anthropogenic activities affected to decreasing of mangrove area and mangrove tourism attractive.  This research aim to assess characteristic and suitability of mangrove forest area for mangrove ecotourism uses.  The data were analyzed using principal component analysis (PCA) and spatial analysis with geographic information system (GIS) approach.  The result showed that the correlation value o Alimudin Laapo; Achmad Fahrudin; Dietriech G. Bengen; Ario Damar
Forum Pasca Sarjana Vol. 33 No. 4 (2010): Forum Pascasarjana
Publisher : Forum Pasca Sarjana

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The mangrove area of Togean Islands have been used for marine ecotourism activities.  The increasing of anthropogenic activities affected to decreasing of mangrove area and mangrove tourism attractive.  This research aim to assess characteristic and suitability of mangrove forest area for mangrove ecotourism uses.  The data were analyzed using principal component analysis (PCA) and spatial analysis with geographic information system (GIS) approach.  The result showed that the correlation value of those four parameters was relatively higher in November than in July.  Those parameters were the component that forms the main axis in both month. The increasing of turbidity and decreasing of salinity in November rather than in July were correlated with rainy season.  Generally, mangrove area in Togean Islands was suitable with conditional categories to mangrove ecotourism uses.  Ecotourism has the most potential to meet these goals and it will be able to tackle most of the problems when GIS technology would be used as a tool to minimize the impact.   Keywords: area suitability, mangrove, ecotourism, Togean Islands
Predicting Spatial Distribution of Argilic Horizon Using Auxilary Information in Regional Scale Yiyi Sulaeman; D Djaenudin
Jurnal Ilmu Tanah dan Lingkungan Vol 7 No 2 (2005): Jurnal Ilmu Tanah dan Lingkungan
Publisher : Departemen Ilmu Tanah dan Sumberdaya Lahan, Fakultas Pertanian, IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (368.674 KB) | DOI: 10.29244/jitl.7.2.48-53

Abstract

For supporting better soil management, the spatial distribution of soils having argilic hori=on (argilic soils) must berecognized and it can be delineate in soil survey mapping activity, but this activity consumes much time and money. This study aimed to build a decision tree model for predicting the spatial distribution of argillic hori=on based on auxiliary information using 3 predicting environmental variables; namely, geomorphic sUrface or substrate, landsurjace unit, and ecoregion beh.Three-based modeling technique was used to generate classification tree model from 318 pedon of Lampung Province,Indonesia. Argillic horizon is predicted to present in hot belt (elevation of 0-200 m above sea level) on interfluve-seepageslope with probability 84% for acid igneous rock, 83% for basic igneous rock, and 90% for acid sedimentary rock. Argillichorizon is also predicted to present in hot belt on transportational midslope with the probability 65% for transported acid sedimentary rock. Argillic horizon is predicted absent with the probability to occur ranging from 0% to 32% on otlrer combinations of landsurface unit, ecoregion belt, and substrate.
Fisheries development aim to increase earnings and prosperity socialize fishermen with remain to take care of sustainable of fish resources. One of pre-eminent commodity in territorial water of Pamekasan is anchovy. Anchovy catching in this region is done to use payang. Information about certainty of expense of investment and sum up advantage obtained in exploiting of anchovy resources with do not disregard its sustainability not yet been made available, so that needed by study of bio-technique Moch Prihatna Sobari; Karyadi .; Diniah .
Buletin Ekonomi Perikanan Vol. 6 No. 3 (2006): Buletin Ekonomi Perikanan
Publisher : Buletin Ekonomi Perikanan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Fisheries development aim to increase earnings and prosperity socialize fishermen with remain to take care of sustainable of fish resources. One of pre-eminent commodity in territorial water of Pamekasan is anchovy. Anchovy catching in this region is done to use payang. Information about certainty of expense of investment and sum up advantage obtained in exploiting of anchovy resources with do not disregard its sustainability not yet been made available, so that needed by study of bio-technique and financial. Actual effort and catch in 2004 each equal to 199,410 trips and 3,603,000 kilograms. Effort and catch at MSY condition each equal to 239.003 trips per year and 3,787,384.94 kilograms per year. Exploiting level in 2004 pursuant to MSY condition has reached number 95.13%. Mean investment of payang fishing unit equal to Rp30,570,000.00. Mean total cost released by Rp43,700,691.67, mean total revenue equal to Rp65,120,000.00, so that the fisherman mean profit equal to Rp21 ,419,308.33. RIC value is 1.49, payback period 1.43 year. NPV of during age of business activity of equal to Rp83,281 ,066.94, net B/C is 3.72, and IRR is 81.75%. With increase of price of solar diesel fuel, hence result of analysis sensitivity obtained by NPV of equal to Rp60,584,350.07, B/C of equal to 2.48 and IRR of equal to 65.29%. Pursuant to conducted analysis, hence the effort of fishing unit payang can be continued, but need of existence control from Department of Fishery and Marine Affair in clear licensing and arrangement hit effort conducted by fishery perpetrator (fishermen).
It has been known that phytoplasma inducing witches broom disease can infect various kind of leguminous plants in Indonesia, among others soybean. Information on the resistance of various kind of soybean varieties to the phytoplasma is still limited. Experiments were conducted to eveluate the resistance of ten soybean varieties/lines to the phytoplasma. The evaluation was carried out by inoculation method through Orosius argentatus Evans, with two days of acquisition feeding period, ten days lat Asniwita Asniwita; Rusmilah Suseno; Sri Hendrastuti Hidayat; Budi Tjahjono
Buletin Hama dan Penyakit Tumbuhan Vol. 11 No. 2 (1999): Buletin Hama dan Penyakit Tanaman
Publisher : Buletin Hama dan Penyakit Tumbuhan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

It has been known that phytoplasma inducing witches broom disease can infect various kind of leguminous plants in Indonesia, among others soybean. Information on the resistance of various kind of soybean varieties to the phytoplasma is still limited. Experiments were conducted to eveluate the resistance of ten soybean varieties/lines to the phytoplasma. The evaluation was carried out by inoculation method through Orosius argentatus Evans, with two days of acquisition feeding period, ten days latent period and two days inoculation feeding period. Observation was conducted on the presence of phytoplasma, incubation period, symptom and number & weight of seed. The result indicated that line Malang 3474 was resistant, Sindiro and Sriono were tolerant, while the other tested varieties/lines, i.e. Galunggung, Orba, Ringgit, Wilis, Malang 2999, Malang 2805 and Sicinang were susceptible
SOCIAL MEDIA AND USERS’ PARTICIPATION: IDENTIFYING THE ATTRIBUTES AND ITS IMPACT ON INFORMATION POLICY Sayogo, Djoko Sigit
Jurnal Reviu Akuntansi dan Keuangan Vol 9, No 1: Jurnal Reviu Akuntansi dan Keuangan
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (954.125 KB) | DOI: 10.22219/jrak.v9i1.8324

Abstract

Social media has grown remarkably and transform the communication mechanism. This recent advent of social media has escalated the hope of better and increase quality of users’ participation. This paper thus studies the impact of the determinants of social media usage on information policies, in particular information stewardship and usefulness. A combination of literary analysis, descriptive statistics of data from PEW Internet, and content analysis from interview were used as methodology to support the arguments. This study argues for five challenges related to the technological and users’ related usage of social media. These challenges are: a) clarity of users’ identity, b) conflict of information ownership & confidentiality, c) distinguishing public versus private information, d) definition of records & creation of meta data, and e) longevity of data & retention of records. Furthermore, this study proposes four critical factors that should be consider in the design and development of information policy governing the steward and use of information. These critical factors are: a) information credibility, integrity, and accuracy, b) security, privacy, and confidentiality of information, c) ensuring information access and availability, and d) data sharing and public-private partnership.
Improvement and Comparison of Mean Shift Tracker using Convex Kernel Function and Motion Information S. B. Chaudhari; K. K. Warhade; V. M. Wadhai; N. N. Choudhari
Computer Engineering and Applications Journal Vol 2 No 3 (2013)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1185.342 KB) | DOI: 10.18495/comengapp.v2i3.35

Abstract

Any tracking algorithm must be able to detect interested moving objects in its field of view and then track it from frame to frame. The tracking algorithms based on mean shift are robust and efficient. But they have limitations like inaccuracy of target localization, object being tracked must not pass by another object with similar features i.e. occlusion and fast object motion. This paper proposes and compares an improved adaptive mean shift algorithm and adaptive mean shift using a convex kernel function through motion information. Experimental results show that both methods track the object without tracking errors. Adaptive method gives less computation cost and proper target localization and Mean shift using convex kernel function shows good results for the tracking challenges like partial occlusion and fast object motion faced by basic Mean shift algorithm.

Page 284 of 2519 | Total Record : 25189