99741 research outputs found
Sort by
Perancangan Alat Bantu Diagnosis Tumor Otak Menggunakan Transfer Learning ResNet101V2
No full textPenanganan tumor otak dilakukan oleh dokter dan dituntut untuk cepat dan akurat. Sehingga menimbulkan masalah seperti beban kerja tinggi, memerlukan waktu banyak, dan adanya kesalahan manusia. Alat bantu diagnosis menggunakan DL adalah solusi karena dapat mengurangi hingga meniadakan kesalahan manusia, efisien, menghasilkan keputusan yang tidak bias, dan selalu tersedia (availability). Model DL yang dirancang menggunakan transfer learning ResNet101V2 untuk mengklasifikasi tumor meningioma, glioma, pituitary, dan normal dari hasil citra MRI. Penelitian ini akan merancang DL sebagai alat bantu diagnosis.
Perancangan dilakukan dengan tahapan berikut. Pertama, pengumpulan data yang membahas penerapan, aturan terkait, dan ketersediaan data. Kedua, pengolahan data untuk membuat data dapat dipelajari model. Ketiga, model engineering yang merancang arsitektur dan algoritma model agar dapat menggeneralisasi data dengan baik. Terakhir, evaluasi model yang akan mengevaluasi performa model untuk pengambilan keputusan model terbaik atau perancangan kembali.
Penelitian ini menghasilkan 3 model dengan pertimbangan dari evaluasi model. Model 3 adalah model terbaik dengan akurasi pada data latih, validasi, dan tes secara urut adalah 98,38%, 96,97%, dan 96,15% sedangkan loss-nya adalah 0,05, 0,09, dan 0,11. Alat bantu diagnosis dapat digunakan untuk memprediksi tumor dari sebuah gambar hasil citra MRI dan/atau dari sekumpulan gambar hasil cita MRI dari seorang pasien
The antecedents and moderation roles of internal e-commerce institutional mechanisms: The case of gopay in Indonesia
No full textThe emergence of financial technology has enabled online business platforms to provide e-commerce institutional mechanisms (EIM). There are some concerns regarding the use of EIM such as trust in e-commerce platform and value of transactions. While prior literatures mostly focused on EIM, the roles of internal EIM is less studied specially in Indonesian context. The current study examines contingency factors that determine the use of internal e-commerce institutional mechanisms (IEIM). This study also investigates whether the use of internal e-commerce institutional mechanisms can reduce the need for trust factor in e-commerce transactions. GOPAY that is one of the internal e-commerce institutional mechanisms in Indonesia is used as study case. Data are collected through an online survey of 117 GOPAY users. Multiple regression and moderated regression analyses are applied to analyze the data. This study finds that essential needs products and micropayment transactions are associated with the use of GOPAY. Also, trust in a platform is associated with repurchase intention. However, the use of GOPAY does not decrease the need for trust in a platform in e-commerce purchase intention. A low banking penetration environment in Indonesia does not relate with the use of internal e-commerce institutional mechanisms. In conclusion, this study provides insights into how Indonesian people use the internal e-commerce institutional mechanisms as part of micropayment to support online essential needs product transactions. © 2023 Author(s)
Green Tourism Planning for Coastal Development in Gunungsewu Geopark, Indonesia
No full textHaving spectacular views of the karst landscape area, Gunungsewu Geopark (GG) has increasingly become a popular tourist area in the southern part of Java Island, Indonesia. With a significant increase in tourist visits and tourism development along the beaches area, the fragile environment of GG is severely threatened. This study aims to propose a design of green tourism planning in the coastal area of GG. We collected data through in-depth interviews, brainstorming, expert meeting, and focus group discussions with the key informants representing all stakeholders. The results show that GG could be grouped into two clusters to develop coastal green tourism namely cluster 1 that can be developed as public tourism and cluster 2 that can be focused on natural landscape preservation. Furthermore, seven recommendations are proposed to be carried out in the future in order to develop sustainable tourism in GG. © Geoinformatics International
The effect of changes in labor absorption on structural economic transformation in Riau province before and during the COVID - 19 pandemic
No full textRiau, as a province with a population of more than 50, including the labor force, certainly has an impact on the dynamics of labor absorption. This study aims to analyze the shift in labor absorption and its effect on the structural transformation of the economy in Riau Province during the pre-pandemic (2018–2019) and during the pandemic (2020) as well as the employment challenges faced by Riau Province using quantitative descriptive methods. The measurement of employment conditions uses secondary data obtained from the publications of the Central Statistics Agency. The results of the analysis show that employment in Riau Province has begun to shift (structural transformation) from the primary sector, such as agriculture, to the secondary sector, such as industry, and tertiary sectors such as trade and services, especially in urban areas such as Dumai City and Pekanbaru in the pre-pandemic period. In addition, it can be seen that the COVID-19 pandemic has affected structural transformation changes, marked by an increase in the primary sector workforce and a decrease in the secondary and tertiary sector workforce during the 2020 pandemic. © 2023 EDP Sciences. All rights reserved
Discovering water relations using hydrochemistry, isotopic data, and mass-balance calculation approaches to reduce the risk of impacts from limestone mining
No full textThis study aims to determine whether limestone mining does not affect the sustainability of the springs in the vicinity. We simulated the linkages between several water sources in the prospective limestone mining area and its surroundings with various geological formations. The approach in this study is by integrating hydrochemical analysis, isotope data, and mass-balance calculations to understand the hydrological system's linkages in a geologically complex area, particularly in the proposed limestone mining site. Twenty-two samples for hydrochemical and isotopic analysis were taken spatially (in each geological formation) to represent various water sources: springs, caves, shallow groundwater, and deep groundwater. Hydrochemical analysis indicates that both caves and springs have a low degree of mineralization and mostly simple facies (Ca–HCO3). Further, both have lighter isotope values (δ18O and δ2H), meaning they are relatively younger and have not experienced advanced hydrochemical processes. Yet, the most interesting point is that the mass-balance modelling shows the bold information that the southern caves are not related to the springs. It is due to the mismatch between the thermodynamic calculation and the actual condition. The southern caves are primarily supplied by rainwater, where >95 of the ions are evolved due to water-rock interaction, while the springs receive recharge from rainwater (40) and other systems. Synthesizing the information, we hypothesize that mining the limestone in the southern part (consisting of the caves) will not disturb the springs as they are unrelated. © 2023 Elsevier B.V
Machine Learning-Based Rice Field Mapping in Kulon Progo using a Fusion of Multispectral and SAR Imageries
No full textThe land-conversion of rice fields can reduce rice production and negatively impact food security. Consequently, monitoring is essential to prevent the loss of productive agricultural land. This study uses a combination of Sentinel-2 MSI, Sentinel-1 SAR, along with SRTM (elevation and slope data) to monitor rice fields land-conversion. NDVI, NDBI and NDWI indices are transformed from the annual median composite Sentinel-2 MSI images used to identify different rice fields with another object. A monthly median composite of SAR images from Sentinel-1 data are used to identify cropping patterns of rice fields in the inundation phase. The classification is performed by using the Random Forest machine learning algorithm in the Google Earth Engine (GEE) platform. Random Forest classification is run using 1000 trees, with a 70:30 ratio of training and testing data from sample features extracted by visual interpretation of high-resolution Google Earth imagery. In this study, Random Forest classification is effective in computing a high amount of multitemporal and multi-sensory data to map rice-field land conversion with an accuracy rate of 96.16 (2021) and 95.95 (2017) for mapping paddy fields. From the multitemporal rice field maps in 2017—2021, a conversion of 826.66 hectares of rice-fields to non-rice fields was identified. Based on the spatial distribution, the conversion from rice-field to non-rice field is higher at the area near the roads, built area and Yogyakarta International Airport. Therefore, it is important to assess and ensure that National Strategic Projects are managed with due regard to environmental impacts and food security. © 2023 by the authors
Exploring socio-economic determinants of energy choices for cooking: the case of eastern Indonesian households
No full textGlobally, nearly 1.3 billion people have no access to electricity, and 3.0 billion people rely on ‘dirty’ fuel such as firewood and biomass for cooking and heating. In Indonesia, firewood is still the fuel of choice when cooking due to its low cost and abundant availability in rural areas. However, the adverse consequences of the indoor air pollution produced through cooking are neglected. Furthermore, the use of firewood for household energy is also associated with slash and burn practices, which drive deforestation and environmental degradation. The use of clean energy, therefore, is imperative for improving people's health and minimizing their environmental footprint. Having this insight, this study aims to examine the factors associated with households’ choice of energy for cooking. Using Indonesia Family Life Survey-East, which specifically collected information from households in the eastern part of Indonesia, the study demonstrates that reliance on clean energy is highest among affluent households and households with better socio-economic indicators (including higher education, non-farm livelihoods, smaller sizes, and electricity connectivity). Households located in urban areas and households located closer to markets tend to rely more on gas for cooking energy. In contrast, poorer rural households residing in villages with abundant natural resources (i.e., with a high share of forests and farmland) generally use firewood as their main source of energy when cooking. The findings of this research also show that energy prices are important in explaining the use of clean or dirty fuel for cooking. It is suggested that efforts to enhance household clean energy use are driven by improved household economic status (especially income and education), access to markets, and stable energy prices. Policy interventions that account for energy and environment issues need to be designed to reduce the overuse of firewood for cooking energy in households living next to common property resources. © 2022, The Author(s), under exclusive licence to Springer Nature B.V
The Dynamics of Sustainable Livelihoods and Agroforestry in Gunungkidul Karst Area, Yogyakarta, Indonesia
No full textThe livelihoods of farmers in developing countries are often associated with the existence of forests, especially agroforestry. The dynamics of agroforestry and livelihoods could not be separated from the political context and developments in Indonesia. In this paper, the dynamics of Sustainable Livelihood Assets (SLA) owned by smallholder farmers are explored using three political sequences, namely the New Order Era, the Reform Era, and the Post-Reform Era. The result showed that the development of agroforestry in Gunungkidul had been primarily influenced by political initiatives that have a connection with vegetation coverage, livelihood assets, and species composition in the systems. The livelihoods possessed by farmers have been relatively sustainable during the past five decades; only a slight change could be observed in the ownership of capital. The political initiatives have been an enabling environment for agroforestry development that support sustainable livelihoods. The study recommends that the socio-political culture needs to consider the traditional agroforestry system in order to sustain the livelihoods of the people. © 2022 by Forest and Society
Aesthetic and cultural value of Nglanggeran ancient volcano geoheritage: A cultural geomorphology perspective
No full textNglanggeran Ancient Volcano is a residual hill over from an ancient volcano. The Government of the Republic of Indonesia and the Government of the Special Region of Yogyakarta have designated the area as a Geoheritage, but the aesthetic and cultural aspects of the landscape have not been studied further and are still considered separately. In fact, a landscape is composed of abiotic, biotic, and cultural aspects, all of which interact with each other in the earth system. This study focuses on the aesthetic and cultural aspects of Nglanggeran Ancient Volcano in the perspective of cultural geomorphology. The method used is descriptive qualitative exploratory method. Cultural and aesthetic values are explored through literature studies and field surveys. The results of this study are the immaterial cultural values and aesthetic values of the Nglanggeran Ancient Volcano Geoheritage, such as Nglanggeran Legend, Kampung Pitu’s Folklore, the beauty of nglanggeran landscape, nglanggeran ecotourism, and nglanggeran as artistic inspiration. This study will strengthen the legal basis of Nglanggeran Ancient Volcano as a geoheritage and provide scientific awareness of the relationship between aesthetic and cultural aspects and landforms in a landscape framework. © 2023 EDP Sciences. All rights reserved
Multitemporal water quality analysis of a karst spring affected by allogenic recharge
No full textThis research aimed to study the multitemporal water quality of a karst spring affected by allogenic recharge. Allogenic refers to water from adjacent non-karstic regions that replenish karst groundwater through ponors. Research samples were collected for a year at Gremeng Resurgence, the outlet of Gremeng Karst Drainage Basin. The water quality analysis compared the laboratory test outcomes and measurements with existing drinking water quality standards and included hydrogeochemical studies using both trilinear and rectangular Piper plots. The analysis results indicate that rainwater causes dilution; hence, parameter values are relatively low in the rainy season but high in the dry season. Despite this variation, the groundwater at the Gremeng Resurgence meets the quality standards throughout the year. The Piper diagram analysis classifies it as unpolluted, calcium-enriched, average bicarbonate, and bicarbonate groundwater, supporting the finding. © 2023 Author(s)