The Experts below are selected from a list of 297 Experts worldwide ranked by ideXlab platform
Aziz Kustiyo - One of the best experts on this subject based on the ideXlab platform.
-
Identifikasi Daun Shorea menggunakan KNN dengan Ekstraksi Fitur 2DPCA
Jurnal Ilmu Komputer dan Agri-Informatika, 2017Co-Authors: Erni Yusniar, Aziz KustiyoAbstract:Shorea adalah jenis meranti yang memiliki nilai ekonomis yang tinggi. Shorea tergolong dalam famili Dipterocarpaceae yang memiliki 194 spesies yang tumbuh di daerah tropis. Shorea merupakan jenis yang sulit untuk diidentifikasi karena memiliki banyak kemiripan. Untuk mengatasi kesulitan tersebut, penelitian ini mengidentifikasi Shorea berdasarkan citra daun. Jumlah spesies yang digunakan penelitian ini adalah 10 jenis Shorea. Metode ekstraksi fitur yang digunakan adalah 2 dimensional principal component analysis (2D-PCA) dengan metode klasifikasi KNN. Penelitian ini memiliki 4 percobaan yang dibagi menjadi komponen R, G, B, dan grayscale. Hasil rata-rata akurasi terbaik sebesar 75% pada komponen G dengan kontribusi nilai eigen 85%.<br /><br />Kata kunci: 2 Dimensional Principal Component Analysis, K-Nearest Neighbour, Shorea
-
Shorea Species Classification Based on Leave Morphology Characteristics Using Levenberg-Marquardt Backpropagation Neural Network
2014Co-Authors: Cory Diana Lestari, Aziz KustiyoAbstract:Nama Peneliti/Mahasiswa CORY DIANA LESTARI (G64104074) Judul Klasifikasi Jenis Shorea Berdasarkan Morfologi daun Menggunakan Jaringan Saraf Tiruan Propagasi Balik Levenberg-Marquardt Judul ( English ) Shorea Species Classification Based on Leave Morphology Characteristics Using Levenberg-Marquardt Backpropagation Neural Network Pembimbing/Supervisor Aziz Kustiyo Abstrak/Ringkasan CORY DIANA LESTARI. Shorea Species Classification Based on Leave Morphology Characteristics Using Levenberg-Marquardt Backpropagation Neural Network. Supervised by AZIZ KUSTIYO. Shorea belongs to the Dipterocarpaceae family and is one of tropical rain forest plants which is being used in timber production. Due to the existence of its various species, Shorea’s identification remains a challenge. The aim of this research was classifying Shorea’s species using Levenberg-Marquardt Backpropagation Neural Network based on 23 morphological characteristics of its leaves. This research utilized the data from 10 species of Shorea that lived in Bogor Botanical Garden, with 10 samples each. Those species were Shorea johorensis foxwf, Shorea pinanga sp, Shorea macroptera dyer, Shorea leprosula miq, Shorea lepida blume, Shorea materialis ridley, Shorea platyclados, Shorea javanica koord & val, Shorea palembanica, dan Shorea seminis. It was found that a 100% identification accuracy can be obtained with Hidden Neuron 8 and 10. Keywords : Backpropagation, Levenberg-Marquardt, Neural Network, Shorea
-
Shorea Species Identification Based on Leaf Morphology Using Probabilistic Neural Network
2014Co-Authors: Yuni Purnamasari Hutabarat, Aziz KustiyoAbstract:Nama Peneliti/Mahasiswa: YUNI PURNAMASARI HUTABARAT (G64096069) Judul: Indentifikasi Jenis Shorea Berdasarkan Morfologi Daun Menggunakan Probabilistic Neural Network Judul (English): Shorea Species Identification Based on Leaf Morphology Using Probabilistic Neural Network Pembimbing/Supervisor: Aziz Kustiyo Abstrak/Abstract: YUNI PURNAMASARI HUTABARAT. Shorea Species Identification Based on Leaf Morphology Using Probabilistic Neural Network. Supervised by AZIZ KUSTIYO. Indonesia is a country which has a large forest area. Dipterocarpaceae is the best timber tree of tropical rain forest. Shorea is a genus of Dipterocarpaceae family which consist of 194 species. Shorea has a considerable number of benefits. It is the most important timber source. Shorea can be used to produce varnish, paint and other chemical materials. Species diversity and morphological similarity may lead to difficulty in identifying the species of Shorea. Mistake in identifying Shorea can lead to inappropriate selection for the final usability. Identification using leaf is the first choice for plant classification compared to biology methods which use cell and molecule. This research aims to develop an identification system to identify Shorea based on morphological characteristic of Shorea. The system identifies 10 species of Shorea. The identification system being built uses Probabilistic Neural Network. The data are divided into five subsets. The five subsets are used as training data and test data. The PNN is trained using 80 leaves to kinds of Shorea. The identification using Probabilistic Neural Network produced 84% average accuracy. Keywords : Shorea, Probabilistic Neural Network (PNN).
-
Indentifikasi Shorea Menggunakan Jaringan Sharaf Tiruan Propagasi balik Resilient Berdasarkan Karakteristik Morfologi daun
2014Co-Authors: Anggi Putriani, Aziz KustiyoAbstract:Nama Peneliti/Mahasiswa: ANGGI PUTRIANI (G64086024) Judul: Indentifikasi Shorea Menggunakan Jaringan Sharaf Tiruan Propagasi balik Resilient Berdasarkan Karakteristik Morfologi daun Judul (English): Identification of Shorea Using Resilient Backpropagation Neural Network Based on Morphological Characteristic of Leaves Pembimbing/Supervisor: Aziz Kustiyo Abstrak/Abstract: ANGGI PUTRIANI. Identification of Shorea Using Resilient Backpropagation Neural Network Based on Morphological Characteristic of Leaves. Supervised by AZIZ KUSTIYO. Shorea (Meranti) is one of the best kind of wood from tropical forests in Indonesia, and one of the best timber of the family Dipterocarpaceae. Shorea has the highest species diversity among its family, which consists about 194 species. This makes it difficult to identify the species of Shorea. Experts in the field of automatic Shorea identification is still rare. Hence, identification using the morphological characteristic of Shorea leaves is more preferred. This research is focused to identify Shorea species using morphological characteristics of leaves. The data used are manual measurement from a sample of the leaves which are taken from each type of Shorea ovalis, Shorea leprosula, Shorea platyclados, Shorea seminis, and Shorea beccariana. Sample of the leaves is taken from the Shorea collection at the Bogor Botanical Gardens. Classification model is built by using resilient backpropagation neural network. After the data has been collected, the feature values of these five species of Shorea is used in the experiment for training and testing the resilient backpropagation neural network. In the training process, we use a variation of the resilient backpropagation neural network parameters in a 5-fold cross-validation experiment. Each experiment unit is divided into two types: with regression and without regression. Overall, the accuracies of the experiment was 98%. Both types produce the same accuracy with different resilient backpropagation neural network optimal parameters, and the same incorrect identification, which is an instance of Shorea leprosula being identified as an instance of Shorea ovalis. Keywords : Resilient Backpropagation Neural Network, Shorea.
Gray A. Williams - One of the best experts on this subject based on the ideXlab platform.
-
ALIFE - The virtual rocky shore - linking A-life with ecological and pedagogical research.
Artificial Life, 2008Co-Authors: Richard Stafford, Mark S. Davies, Gray A. WilliamsAbstract:The design and analysis of manipulative experiments is a key skill for undergraduate ecologists to learn. Despite this, students rarely conduct a true manipulative experiment with appropriate control treatments in the field, because of practical constraints such as time. Meaningful ecological experiments typically require months to obtain results, as well as constant maintenance and attention; and often require the use of large areas of undisturbed habitat. One solution to this problem is to allow students access to a virtual ecosystem in which they can conduct a possibly unlimited range of experiments which will quickly provide realistic data for subsequent statistical analysis and interpretation. Currently, virtual ecosystems fall into two basic categories: those that are vast oversimplifications of real ecosystems, displaying simplistic and pre-programmed behaviours; and those that bear little resemblance to real ecosystems, made entirely of interacting digital organisms. While the latter are of more interest to the A-Life community, they are not user-friendly to biology students who are generally not computer literate beyond the basics of word processing, spreadsheets and internet technologies. “The Virtual Rocky Shore”, is grounded in a variety of A-life techniques, including agent-based modelling, self-organisation, evolutionary algorithms and cellular automata. The present version of The Virtual Rocky Shore is based on the high intertidal region, a simple consumer / resource ecosystem consisting of grazing snails and a photosynthetic mat or biofilm of lichens, diatoms and bacteria. Although the system is simple, research underpinning the system’s models has demonstrated that these intertidal snails show many similar behavioural rules to those displayed by classic A-Life inspirations such as ants. The intertidal snails, for example, exhibit self-organisation as a result of trail following. The dynamics of the photosynthetic components of the virtual shore are also suitable to being modelled in space and time by use of cellular automata and computer-based optimisation processes including evolutionary algorithms. Current development of The Virtual Rocky Shore using a user-friendly interface has already provided novel insights into the functioning and evolution of intertidal communities; with many of these insights backed up by empirically derived data from real shores and published in peer reviewed journals. The first implementation of the Virtual Rocky Shore allows experiments to be designed and analysed in a matter of minutes, rather than the many months traditionally required, facilitating the active and potentially deep experiential learning of experimental design by students. The results obtained from the simulation are also similar, and result in comparable statistical analysis, to those obtained from experiments on real shores. The full potential of The Virtual Rocky Shore, however, lies in its expansion to cover the mid and lower shore systems. The complexity found at these shore levels will allow many opportunities for further research at the interface of ecology and computer science, as well as the development of a wide range of potential experiments beyond simple grazer / biofilm interactions.
-
computer simulations of high shore littorinids predict small scale spatial and temporal distribution patterns on rocky shores
Marine Ecology Progress Series, 2007Co-Authors: Richard Stafford, Gray A. WilliamsAbstract:High shore littorinid snails exhibit complex spatial distribution patterns, forming dense aggregations both in crevices and on crevice-free sections of rocky shores. To understand how these patterns may form, an individual-based computer simulation of littorinid behaviour, similar to those used to model social insects, was used to mimic snail movement on rocky shores. Individual littorinid movement patterns were simulated, along with chance interactions with other littorinids, their trails, crevices and any resultant decisions made by the littorinids when these interactions occurred. The simulation investigated how simple behavioural rules can predict spatial aggregation patterns and the persistence and variation of these aggregation patterns over timescales of several tidal cycles. Morisita’s index of dispersal showed good agreement between the simulation and observed patterns of littorinids on-shore. Trail-following was vital in the simulation, since points where trails intersected with crevices, or points where 2 or more trails met, formed the site of aggregations. Both in the simulation and in reality, aggregations often occurred in identical positions over several tidal cycles, both within and outside crevices. This temporal predictability may be due to the persistence of mucus trails on the shore over successive tidal cycles. Removal of the influence of past mucus trails from the simulation resulted in far lower persistence of aggregations over time. The simulation, therefore, is an important tool in examining behavioural mechanisms of intertidal animals. It provides insights into how simple behaviour of grazing animals can explain complex population patterns and subsequently the community dynamics of algal-herbivore interactions.
-
intraspecific variation in foraging behaviour influence of shore height on temporal organization of activity in the chiton acanthopleura japonica
Marine Ecology Progress Series, 2006Co-Authors: Jasmine S S Ng, Gray A. WilliamsAbstract:The chiton Acanthopleura japonica has a wide vertical distribution on moderately exposed Hong Kong shores, and it shows limited seasonal vertical migration. Observations revealed that chitons were active while awash on ebbing or flooding tides during both day- and night-time, but they were inactive in refuges at their resting shore heights when conditions were unfavourable. The most intense activity was always associated with awash periods, but the timing of activity peaks and percentage activity varied between seasons, tidal conditions and the shore height individuals'occupied. Activity periods were longer in summer than winter, but varied from day to day, depending on weather conditions such as wind speed and hours of sunshine. Duration of activity also varied with shore height; chitons living in the high-shore remaining active for nearly twice as long as those lower on the shore. Laboratory studies showed that activity Was controlled by a circalunidian endogenous rhythm, but can be overridden by exogenous, environmental factors, such as wave splash. Therefore, the temporal organization of activity in A. japonica is controlled by both exogenous and endogenous mechanisms, of which the timing and duration of the awash phase of the tide appears to be the dominant controlling factor. To optimize foraging success, individuals exhibit a continuum of foraging strategies determined by season and the shore height they occupy, resulting in intraspecific variability in the duration and timing of activity.
-
An improved and simplified trap for quantifying the distribution and supply of planktonic larvae to rocky shores
Journal of Plankton Research, 2004Co-Authors: Yan Yan, Benny K K Chan, Gray A. WilliamsAbstract:This paper describes a modified and improved plankton trap for use on rocky shores. The trap is composed of a simple filtering device and collection bag which allows assessment of spatial and temporal variation of on-shore larval supply.
Nur Supardi Md Noor - One of the best experts on this subject based on the ideXlab platform.
-
community structure of pre dispersal seed predatory insects on eleven Shorea dipterocarpaceae species
Journal of Tropical Ecology, 2009Co-Authors: Tetsuro Hosaka, Takakazu Yumoto, Hiroaki Kojima, Furumi Komai, Nur Supardi Md NoorAbstract:The Dipterocarpaceae in South-East Asia are known for their strict mast fruiting. During fruiting, pre-dispersal seed predation by insects contributes to mortality of dipterocarp seeds. We documented the community dispersal seed predation by insects contributes to mortality of dipterocarp seeds. We documented the community structure of insect seed predators on 11 Shorea species in Peninsular Malaysia. Fruits were sampled sequentially throughout seed development, and 2144 and 1655 individuals of seed predator weevils and moths were collected in two mast-fruiting events. Four weevils: Nanophyes Shoreae, nanophyid sp. 1, Alcidodes dipterocarpi and Alcidodes humeralis, and one moth Andrioplecta Shoreae were abundant in seeds of the Shorea species. The proportion of N. Shoreae to the total predators became larger in the latter fruiting event than the former while that of Alcidodes spp. became smaller. The predator species composition changed during seed development: nanophyid spp. emerged from immature fruits while Alcidodes spp. emerged from mature fruits. Andrioplecta Shoreae emerged from both immature and mature fruits. The level of host specificity measured by Kullback-Leibler distance was low for most predator species in both events. Predator species composition of many Shorea was similar to each other due to the dominance of N. Shoreae though it might gradually differ with the phylogenetic distance between hosts. In conclusion, predator species composition of Shorea varied during seed development within a host rather than among hosts. Intermittent synchronized fruiting by congeneric Shorea trees would be advantageous to avoid pre-dispersal insect seed predators, and contribute to their reproduction.
-
Community structure of pre-dispersal seed predatory insects on eleven Shorea (Dipterocarpaceae) species.
Journal of Tropical Ecology, 2009Co-Authors: Tetsuro Hosaka, Takakazu Yumoto, Hiroaki Kojima, Furumi Komai, Nur Supardi Md NoorAbstract:Abstract:The Dipterocarpaceae in South-East Asia are known for their strict mast fruiting. During fruiting, pre-dispersal seed predation by insects contributes to mortality of dipterocarp seeds. We documented the community structure of insect seed predators on 11 Shorea species in Peninsular Malaysia. Fruits were sampled sequentially throughout seed development, and 2144 and 1655 individuals of seed predator weevils and moths were collected in two mast-fruiting events. Four weevils: Nanophyes Shoreae, nanophyid sp. 1, Alcidodes dipterocarpi and Alcidodes humeralis, and one moth Andrioplecta Shoreae were abundant in seeds of the Shorea species. The proportion of N. Shoreae to the total predators became larger in the latter fruiting event than the former while that of Alcidodes spp. became smaller. The predator species composition changed during seed development; nanophyid spp. emerged from immature fruits while Alcidodes spp. emerged from mature fruits. Andrioplecta Shoreae emerged from both immature and mature fruits. The level of host specificity measured by Kullback–Leibler distance was low for most predator species in both events. Predator species composition of many Shorea was similar to each other due to the dominance of N. Shoreae though it might gradually differ with the phylogenetic distance between hosts. In conclusion, predator species composition of Shorea varied during seed development within a host rather than among hosts. Intermittent synchronized fruiting by congeneric Shorea trees would be advantageous to avoid pre-dispersal insect seed predators, and contribute to their reproduction.
Tetsuro Hosaka - One of the best experts on this subject based on the ideXlab platform.
-
community structure of pre dispersal seed predatory insects on eleven Shorea dipterocarpaceae species
Journal of Tropical Ecology, 2009Co-Authors: Tetsuro Hosaka, Takakazu Yumoto, Hiroaki Kojima, Furumi Komai, Nur Supardi Md NoorAbstract:The Dipterocarpaceae in South-East Asia are known for their strict mast fruiting. During fruiting, pre-dispersal seed predation by insects contributes to mortality of dipterocarp seeds. We documented the community dispersal seed predation by insects contributes to mortality of dipterocarp seeds. We documented the community structure of insect seed predators on 11 Shorea species in Peninsular Malaysia. Fruits were sampled sequentially throughout seed development, and 2144 and 1655 individuals of seed predator weevils and moths were collected in two mast-fruiting events. Four weevils: Nanophyes Shoreae, nanophyid sp. 1, Alcidodes dipterocarpi and Alcidodes humeralis, and one moth Andrioplecta Shoreae were abundant in seeds of the Shorea species. The proportion of N. Shoreae to the total predators became larger in the latter fruiting event than the former while that of Alcidodes spp. became smaller. The predator species composition changed during seed development: nanophyid spp. emerged from immature fruits while Alcidodes spp. emerged from mature fruits. Andrioplecta Shoreae emerged from both immature and mature fruits. The level of host specificity measured by Kullback-Leibler distance was low for most predator species in both events. Predator species composition of many Shorea was similar to each other due to the dominance of N. Shoreae though it might gradually differ with the phylogenetic distance between hosts. In conclusion, predator species composition of Shorea varied during seed development within a host rather than among hosts. Intermittent synchronized fruiting by congeneric Shorea trees would be advantageous to avoid pre-dispersal insect seed predators, and contribute to their reproduction.
-
Community structure of pre-dispersal seed predatory insects on eleven Shorea (Dipterocarpaceae) species.
Journal of Tropical Ecology, 2009Co-Authors: Tetsuro Hosaka, Takakazu Yumoto, Hiroaki Kojima, Furumi Komai, Nur Supardi Md NoorAbstract:Abstract:The Dipterocarpaceae in South-East Asia are known for their strict mast fruiting. During fruiting, pre-dispersal seed predation by insects contributes to mortality of dipterocarp seeds. We documented the community structure of insect seed predators on 11 Shorea species in Peninsular Malaysia. Fruits were sampled sequentially throughout seed development, and 2144 and 1655 individuals of seed predator weevils and moths were collected in two mast-fruiting events. Four weevils: Nanophyes Shoreae, nanophyid sp. 1, Alcidodes dipterocarpi and Alcidodes humeralis, and one moth Andrioplecta Shoreae were abundant in seeds of the Shorea species. The proportion of N. Shoreae to the total predators became larger in the latter fruiting event than the former while that of Alcidodes spp. became smaller. The predator species composition changed during seed development; nanophyid spp. emerged from immature fruits while Alcidodes spp. emerged from mature fruits. Andrioplecta Shoreae emerged from both immature and mature fruits. The level of host specificity measured by Kullback–Leibler distance was low for most predator species in both events. Predator species composition of many Shorea was similar to each other due to the dominance of N. Shoreae though it might gradually differ with the phylogenetic distance between hosts. In conclusion, predator species composition of Shorea varied during seed development within a host rather than among hosts. Intermittent synchronized fruiting by congeneric Shorea trees would be advantageous to avoid pre-dispersal insect seed predators, and contribute to their reproduction.
Furumi Komai - One of the best experts on this subject based on the ideXlab platform.
-
community structure of pre dispersal seed predatory insects on eleven Shorea dipterocarpaceae species
Journal of Tropical Ecology, 2009Co-Authors: Tetsuro Hosaka, Takakazu Yumoto, Hiroaki Kojima, Furumi Komai, Nur Supardi Md NoorAbstract:The Dipterocarpaceae in South-East Asia are known for their strict mast fruiting. During fruiting, pre-dispersal seed predation by insects contributes to mortality of dipterocarp seeds. We documented the community dispersal seed predation by insects contributes to mortality of dipterocarp seeds. We documented the community structure of insect seed predators on 11 Shorea species in Peninsular Malaysia. Fruits were sampled sequentially throughout seed development, and 2144 and 1655 individuals of seed predator weevils and moths were collected in two mast-fruiting events. Four weevils: Nanophyes Shoreae, nanophyid sp. 1, Alcidodes dipterocarpi and Alcidodes humeralis, and one moth Andrioplecta Shoreae were abundant in seeds of the Shorea species. The proportion of N. Shoreae to the total predators became larger in the latter fruiting event than the former while that of Alcidodes spp. became smaller. The predator species composition changed during seed development: nanophyid spp. emerged from immature fruits while Alcidodes spp. emerged from mature fruits. Andrioplecta Shoreae emerged from both immature and mature fruits. The level of host specificity measured by Kullback-Leibler distance was low for most predator species in both events. Predator species composition of many Shorea was similar to each other due to the dominance of N. Shoreae though it might gradually differ with the phylogenetic distance between hosts. In conclusion, predator species composition of Shorea varied during seed development within a host rather than among hosts. Intermittent synchronized fruiting by congeneric Shorea trees would be advantageous to avoid pre-dispersal insect seed predators, and contribute to their reproduction.
-
Community structure of pre-dispersal seed predatory insects on eleven Shorea (Dipterocarpaceae) species.
Journal of Tropical Ecology, 2009Co-Authors: Tetsuro Hosaka, Takakazu Yumoto, Hiroaki Kojima, Furumi Komai, Nur Supardi Md NoorAbstract:Abstract:The Dipterocarpaceae in South-East Asia are known for their strict mast fruiting. During fruiting, pre-dispersal seed predation by insects contributes to mortality of dipterocarp seeds. We documented the community structure of insect seed predators on 11 Shorea species in Peninsular Malaysia. Fruits were sampled sequentially throughout seed development, and 2144 and 1655 individuals of seed predator weevils and moths were collected in two mast-fruiting events. Four weevils: Nanophyes Shoreae, nanophyid sp. 1, Alcidodes dipterocarpi and Alcidodes humeralis, and one moth Andrioplecta Shoreae were abundant in seeds of the Shorea species. The proportion of N. Shoreae to the total predators became larger in the latter fruiting event than the former while that of Alcidodes spp. became smaller. The predator species composition changed during seed development; nanophyid spp. emerged from immature fruits while Alcidodes spp. emerged from mature fruits. Andrioplecta Shoreae emerged from both immature and mature fruits. The level of host specificity measured by Kullback–Leibler distance was low for most predator species in both events. Predator species composition of many Shorea was similar to each other due to the dominance of N. Shoreae though it might gradually differ with the phylogenetic distance between hosts. In conclusion, predator species composition of Shorea varied during seed development within a host rather than among hosts. Intermittent synchronized fruiting by congeneric Shorea trees would be advantageous to avoid pre-dispersal insect seed predators, and contribute to their reproduction.