ASEAN Engineering Journal最新文献

筛选
英文 中文
ANALYSIS OF RWANDA’S GRID POINT OF STABILITY LOSS 卢旺达电网点稳损失分析
ASEAN Engineering Journal Pub Date : 2023-08-30 DOI: 10.11113/aej.v13.18556
Silas Bizimungu, Francis Njoka, Churchhill Saoke, Clement Siame
{"title":"ANALYSIS OF RWANDA’S GRID POINT OF STABILITY LOSS","authors":"Silas Bizimungu, Francis Njoka, Churchhill Saoke, Clement Siame","doi":"10.11113/aej.v13.18556","DOIUrl":"https://doi.org/10.11113/aej.v13.18556","url":null,"abstract":"E\u0000Electricity stability is the key component in ensuring reliable power supply which is a major hurdle in most developing countries. Power angle being part of grid stability pillars, this work sought to theoretically and numerically investigate the maximum power angle variation that the power system in Rwanda could experience while maintaining transient stability at an acceptable range beyond which generators lose synchronism affecting overall system stability. A steady state and dynamic stability assessment of the lightly loaded Rwandan grid is conducted using PSS/E while MATLAB is used to obtain input values for calculating the system stability power angle. This involved collecting actual network parameters, creating an accurate model of the entire Rwandan grid and validating the model simulation results using regularly metered values at various critical busbars of the network. Results from the study show that a sudden drop in load of 11 MW and 6 MVAr leads to a variation of power angle of the largest power plant by 23o triggering transient stability problems leading to loss of synchronism. Both calculated and simulation results show that, a sudden power angle variation of between 23o to 23.5o at the swing bus power plant, causes the monitored generating units to trip triggering a long-term instability. This was done while also interrogating possible mitigation measures based on the developed and validated model. Based on the system status, the study revealed that the grid point of stability can be determined through simulation using software and to further obtain optimum stability, installation of active devices such as shunt reactors helps the grid to counter sudden variation of power angle due to line and load tripping.\u0000B","PeriodicalId":36749,"journal":{"name":"ASEAN Engineering Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42199189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
AN ENSEMBLE APPROACH FOR COFFEE CROP YIELD PREDICTION BASED ON AGRONOMIC FACTORS 基于农艺因子的咖啡产量综合预测方法
ASEAN Engineering Journal Pub Date : 2023-08-30 DOI: 10.11113/aej.v13.18846
C. S. Santhosh, Kattekyathanalli Kalegowda Umesh
{"title":"AN ENSEMBLE APPROACH FOR COFFEE CROP YIELD PREDICTION BASED ON AGRONOMIC FACTORS","authors":"C. S. Santhosh, Kattekyathanalli Kalegowda Umesh","doi":"10.11113/aej.v13.18846","DOIUrl":"https://doi.org/10.11113/aej.v13.18846","url":null,"abstract":"Coffee is the most burned-through handled drink beside water, which is said to be the most exchanged cultivating product followed by oil in the entire globe. The two most significant sorts of coffee assortment filled in India are Arabica and Robusta out of 103 assortments of class coffee bean variety, which are economically exchanged around the planet. In this regard, we are taking major plantation crop in India i.e., Coffee for our research to explore and develop a predictive model for the development of coffee planters to take precise decisions in time during adverse situations in advance. Hence we propose a framework for coffee yield prediction which using machine learning ensemble approach to estimate the influence of agronomic factors to get a good coffee yield. Here, for our research work, the historic dataset is considered which is obtained from Central Coffee Research Institute (CCRI), Karnataka for the year (2008-2019). For the coffee yield prediction, we are considering agronomic factors like Age, Soil Nutrients: Organic carbon (OC), Phosphorus (P), Potassium (K), Alkaline (pH), Zone and Respective yield obtained in chikkamagaluru   region, Karnataka state, India. Different classifiers are used namely, Extra Tree Classifier, Random Forest Classifier, Decision Tree and Boosting Algorithms for prediction and performance of each is compared and analyzed. Our results shown that Extra Tree Classifier and Random forest (RF) classifier with a precision of 91% with good results based on performance metrics considered respectively is an effective and versatile machine-learning method compared to other algorithms used.","PeriodicalId":36749,"journal":{"name":"ASEAN Engineering Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47608487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
CRITICAL RISK ANALYSIS OF TOLL ROAD PUBLIC-PRIVATE PARTNERSHIP (PPP) PROJECT CONSTRUCTION PHASE 收费公路公私合作(ppp)项目建设阶段关键风险分析
ASEAN Engineering Journal Pub Date : 2023-08-30 DOI: 10.11113/aej.v13.19462
Fahira Rhomianti Putri, B. Susanti, Mona Foralisa Toyfur
{"title":"CRITICAL RISK ANALYSIS OF TOLL ROAD PUBLIC-PRIVATE PARTNERSHIP (PPP) PROJECT CONSTRUCTION PHASE","authors":"Fahira Rhomianti Putri, B. Susanti, Mona Foralisa Toyfur","doi":"10.11113/aej.v13.19462","DOIUrl":"https://doi.org/10.11113/aej.v13.19462","url":null,"abstract":"Limited funding in meeting the financing needs for the provision of toll road infrastructure makes the government need to look for alternative financing so that the project can still be carried out. Public Private Partnership (PPP) is an alternative option to overcome this problem. However, infrastructure projects with PPP schemes require large investments and a relatively long concession period, thus allowing risk uncertainty to arise as a result of decisions made during the project. Risk identification in a construction project is important at the beginning of the project. This study was aimed at identifying critical risks, determining risk allocation and risk mitigation strategies, and analyzing the interrelationship between critical risks. The case study was conducted on the Trans Sumatra toll road project in South Sumatra. Quantitative data (questionnaire survey) and qualitative data (interview) were collected from the toll-road private sector. The results of the study identified five critical risks in the construction phase (CP) of the toll road project along with the allocation of risks, namely the risks of geographical conditions (shared), delays in work progress (private sector), design errors (private sector), force majeure (shared) and weather conditions (shared). The mitigation strategy for the risks of geographical conditions and design errors was to redesign the construction structure by adjusting with the land conditions of the toll road. Force majeure (Covid-19) causing delays in work progress required rescheduling and recalculation of construction costs. Weather conditions (heavy rain) occurring on swampy land caused puddles/floods; this condition caused delays in construction work. The mitigation strategy that could be carried out was by coordinating with the Indonesian Meteorology, Climatology, and Geophysics Agency (BMKG) in the region and preparing disaster management Standard Operating Procedures (SOPs). The cause and effect of each risk showed that the critical risks in the construction phase of the toll road project were interrelated to each other which the risks would finally contribute to the increase in the construction costs of the toll road project.","PeriodicalId":36749,"journal":{"name":"ASEAN Engineering Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46660495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
REVIEW OF FINANCIAL PENALTIES IMPLEMENTATION ON NON-COMPLIANCE WITH ROAD PERFORMANCE INDICATORS 检讨对不符合道路表现指标的人士实施罚款的情况
ASEAN Engineering Journal Pub Date : 2023-08-30 DOI: 10.11113/aej.v13.19000
Tisara Sita, A. Mulyono, Suryo Hapsoro Tri Utomo
{"title":"REVIEW OF FINANCIAL PENALTIES IMPLEMENTATION ON NON-COMPLIANCE WITH ROAD PERFORMANCE INDICATORS","authors":"Tisara Sita, A. Mulyono, Suryo Hapsoro Tri Utomo","doi":"10.11113/aej.v13.19000","DOIUrl":"https://doi.org/10.11113/aej.v13.19000","url":null,"abstract":"Indonesia's national road preservation system, mainly routine road maintenance, was initially carried out independently by the project manager as a road section manager. This maintenance has been transformed into a \"long segment\" scheme since 2016. The contractor is subject to financial penalties in the form of withholding payments for each failure to meet the road performance indicators within the specified repair response times. The government, specifically the project manager, has not adequately applied the current financial penalties for late fulfillment of road performance indicators in Indonesia. The implementation of financial penalties that is not adequate is inversely proportional to the number of public complaints related to road performance, which represents the impact of road performance that does not meet the criteria. This study recommends developing a comprehensive policy for penalties related to the late fulfillment of road performance indicators. The policy should consider multiple indicators and components and adjust the coefficient of each component based on the severity of the condition. In addition, this study advises revising the formulation of financial penalties using relevant data, such as average daily traffic volume or public complaints.","PeriodicalId":36749,"journal":{"name":"ASEAN Engineering Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44417606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A PROPOSED TECHNIQUE FOR IMPROVING THE ACCURACY OF TIDAL MODELING OF RIVER NETWORKS CONNECTING TO THE DADAHUP IRRIGATION AREA 一种提高达达胡普灌区河网潮汐模拟精度的方法
ASEAN Engineering Journal Pub Date : 2023-08-30 DOI: 10.11113/aej.v13.19393
A. Zevri, A. P. Rahardjo, D. Legono
{"title":"A PROPOSED TECHNIQUE FOR IMPROVING THE ACCURACY OF TIDAL MODELING OF RIVER NETWORKS CONNECTING TO THE DADAHUP IRRIGATION AREA","authors":"A. Zevri, A. P. Rahardjo, D. Legono","doi":"10.11113/aej.v13.19393","DOIUrl":"https://doi.org/10.11113/aej.v13.19393","url":null,"abstract":"Optimizing the operational management of tidal irrigation networks is a significant factor in the reactivation program of the swamp irrigation areas in Central Kalimantan Province. Appropriate water level and flow rate control in a tidal environment would provide a better solution for this effort. Monitoring water parameters and hydraulic modeling is an intelligent technique for evaluating irrigation canals' gate system operations. This paper focuses on providing more accurate hydraulic modeling that requires proper boundary conditions and calibration of the canal roughness coefficient. This study aims to obtain a more precise downstream boundary condition data calibration method with an appropriate river cross-sectional roughness coefficient value to improve the overall hydraulic modeling accuracy of the river network connecting to the Dadahup Irrigation Area. The hydraulic modeling utilized the HEC-RAS Software, where input data preparation used geometric data derived from the National Geospatial Agency's DEM in the form of river channel network chain, cross-section, and long-section data. Boundary condition data evaluation compared and selected data generated from references and the Tides Application Software. The results show that the tide prediction from the Tides Application Software provides the slightest difference between the predicted tide and the measured ones. The river network's channel roughness coefficient calibration utilized the generated boundary condition tide and simultaneously measured water level data at several locations. The results show that the most minor Root Mean Squared Error (RMSE) of the Manning roughness coefficient differences of the river channel network can reach 0.04 with a minimum RMSE value of 0.027.","PeriodicalId":36749,"journal":{"name":"ASEAN Engineering Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42046000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
3.5 GHZ VIVALDI ANTENNAS: A COMPREHENSIVE PARAMETRIC ANALYSIS FOR UNLEASHING 5G COMMUNICATION TECHNOLOGY 3.5ghz-VIVALDI天线:5G通信技术的全面参数分析
ASEAN Engineering Journal Pub Date : 2023-08-30 DOI: 10.11113/aej.v13.19774
M. Othman, Nur Aishah Shahirah Ruslan, M. H. Misran, M. A. Meor Said, R. Abdul Manap, A. Jaafar, N. I. Hassan, S. Suhaimi
{"title":"3.5 GHZ VIVALDI ANTENNAS: A COMPREHENSIVE PARAMETRIC ANALYSIS FOR UNLEASHING 5G COMMUNICATION TECHNOLOGY","authors":"M. Othman, Nur Aishah Shahirah Ruslan, M. H. Misran, M. A. Meor Said, R. Abdul Manap, A. Jaafar, N. I. Hassan, S. Suhaimi","doi":"10.11113/aej.v13.19774","DOIUrl":"https://doi.org/10.11113/aej.v13.19774","url":null,"abstract":"In this study, we discuss the design and testing of a Vivaldi antenna operating at 3.5 GHz, which is well-suited for mobile mid-band 5G connection. CST Microwave Studio software was used to simulate and evaluate the suggested antenna design, which was printed utilising state-of-the-art 3D printing processes and materials (polylactic acid (PLA) and FR-4 circuit board material). The measured results show that the antenna has a reflection frequency of 3.51 GHz and a gain of -23.695 dB. Parametric analysis was carried out to examine the relationship between antenna performance and design parameters, with special focus on the separation between the antenna and the PLA material in the middle of the spherical construction. The Vivaldi antenna is an attractive choice for 5G mid-band applications because of its wideband features, ease of manufacture using typical industrial processes, and simplicity of impedance matching to the feeding line using microstrip line modelling.\u0000 ","PeriodicalId":36749,"journal":{"name":"ASEAN Engineering Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44819449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
MACHINE LEARNING METHODS FOR EARLY-STAGE DIAGNOSIS OF PARKINSON'S DISEASE THROUGH HANDWRITING DATA 通过手写数据进行帕金森病早期诊断的机器学习方法
ASEAN Engineering Journal Pub Date : 2023-08-30 DOI: 10.11113/aej.v13.18777
Matthew Dionela, Carey Louise B. Arroyo, Mhica S. Torres, Miguel P. Alaan, Sandy C. Lauguico, R. R. Vicerra, R. Concepcion II
{"title":"MACHINE LEARNING METHODS FOR EARLY-STAGE DIAGNOSIS OF PARKINSON'S DISEASE THROUGH HANDWRITING DATA","authors":"Matthew Dionela, Carey Louise B. Arroyo, Mhica S. Torres, Miguel P. Alaan, Sandy C. Lauguico, R. R. Vicerra, R. Concepcion II","doi":"10.11113/aej.v13.18777","DOIUrl":"https://doi.org/10.11113/aej.v13.18777","url":null,"abstract":"Parkinson's disease (PD) deteriorates human cognitive and motor functions, causing slowness of movements and postural shakiness. PD is currently incurable, and managing symptoms in its late stages is difficult. PD diagnosis also has gaps in accuracy due to several clinical challenges. Thus, early-stage detection of PD through its symptoms, such as handwriting abnormality, has become a popular research area using machine learning. Since most related studies focus on advanced algorithms, this study aims to determine the classification accuracies of simpler classical models using the NewHandPD-NewMeander dataset. This study used the 9 features extracted from the meanders drawn by healthy participants and participants diagnosed with Parkinson’s disease and 3 features about the individual. The same features were reduced to the 8 best according to univariate selection and recursive feature elimination. The machine learning algorithms used for the models in this study are Logistic regression, Multilayer perceptron, and Naive Bayes. Additionally, hyperparameter optimization was done. Results have shown that feature selection improved the performances of the default model, while optimization had varying effects depending on the feature selection method used. Among 15 models built, Multilayer perceptron, which utilized top 8 features from univariate selection with default hyperparameters (MLPU8), performed best. It yielded an accuracy of 84.4% in cross-validation, 87.5% in holdout validation, and an F1-score of 87.5%. Remaining models had accuracies ranging from 81.4% - 84.4% in cross-validations and 82.5% - 85.0% in holdout validations. Other studies done on diagnosing PD using similar handwritten datasets resulted in lower accuracies of 87.14% and 77.38% despite utilizing complex algorithms for its models. This proved that the 15 models built using simple architecture can outperform complex classification methods. The 15 models built accurately classify meander data and can be used as an early assessment tool for detecting PD.","PeriodicalId":36749,"journal":{"name":"ASEAN Engineering Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45135959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
ENSEMBLING DEEP CONVOLUTIONAL NEURAL NEWORKS FOR BALINESE HANDWRITTEN CHARACTER RECOGNITION 集成深度卷积神经网络在巴厘岛手写体字符识别中的应用
ASEAN Engineering Journal Pub Date : 2023-08-30 DOI: 10.11113/aej.v13.19582
Desak Ayu Sista Dewi, D. M. S. Arsa, Gusti Agung Ayu Putri, Ni Luh Putu Lilis Sinta Setiawati
{"title":"ENSEMBLING DEEP CONVOLUTIONAL NEURAL NEWORKS FOR BALINESE HANDWRITTEN CHARACTER RECOGNITION","authors":"Desak Ayu Sista Dewi, D. M. S. Arsa, Gusti Agung Ayu Putri, Ni Luh Putu Lilis Sinta Setiawati","doi":"10.11113/aej.v13.19582","DOIUrl":"https://doi.org/10.11113/aej.v13.19582","url":null,"abstract":"While deep learning has proven its performance in various problems and applications, it also opens opportunities in a new way to promote the heterogeneity of cultures and heritages. Balinese script is a cultural heritage in Bali, where it is used to write on palm-leaf manuscripts and contains essential information. Most manuscripts were damaged due to age and lack of maintenance, so a digitalization technique should be developed. In this study, we propose an ensemble of deep convolutional neural networks to recognize the handwritten characters in the Balinese script. We extensively compared various deep convolutional neural network architectures, and the results showed that our ensemble methods achieved the state of the art.","PeriodicalId":36749,"journal":{"name":"ASEAN Engineering Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45984904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
OPTIMIZATION OF ENERGY CONSUMPTION IN SENSOR NODE BASED ON RECEIVED SIGNAL STRENGTH INDICATOR (RSSI) AND SLEEP AWAKE METHOD 基于RSSI和睡眠-唤醒方法的传感器节点能耗优化
ASEAN Engineering Journal Pub Date : 2023-08-30 DOI: 10.11113/aej.v13.19755
P. Rudati, F. Feriyonika, Y. Sudarsa, Hasbi Tri Monda
{"title":"OPTIMIZATION OF ENERGY CONSUMPTION IN SENSOR NODE BASED ON RECEIVED SIGNAL STRENGTH INDICATOR (RSSI) AND SLEEP AWAKE METHOD","authors":"P. Rudati, F. Feriyonika, Y. Sudarsa, Hasbi Tri Monda","doi":"10.11113/aej.v13.19755","DOIUrl":"https://doi.org/10.11113/aej.v13.19755","url":null,"abstract":"The transmission power management in Wireless Sensor Networks (WSN) is a critical problem. This research investigated optimizing power consumption based on transmission power (Tx Power) level according to RSSI and periodic transmission time. We investigated the RSSI value by varying Tx Power Level to get the optimum Tx Power Level. We found the optimum periodic transmission time by transmitting the data with various transmission times. By varying the Tx Power Level, we found the optimum Tx Power Level, resulting in the power consumption decreasing by about 42% and the power supply’s lifetime increasing by about 71% in the 280 m distance between the sensor node and gateway, with a 108 Wh power supply. By varying the periodic transmission time, we found that the optimum periodic transmission time is 8 seconds. Combining the optimum Tx Power Level and periodic transmission time, we found that the power supply’s lifetime is 40 times longer. This result is helpful for WSN applications in remote areas.  \u0000 ","PeriodicalId":36749,"journal":{"name":"ASEAN Engineering Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47393487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
DEVELOPMENT AND ANALYSIS OF DEEP LEARNING MODEL BASED ON MULTICLASS CLASSIFICATION OF RETINAL IMAGE FOR EARLY DETECTION OF DIABETIC RETINOPATHY 基于视网膜图像多类别分类的糖尿病视网膜病变早期检测深度学习模型的开发与分析
ASEAN Engineering Journal Pub Date : 2023-08-30 DOI: 10.11113/aej.v13.19256
Amit Meshram, D. Dembla, Anooja A
{"title":"DEVELOPMENT AND ANALYSIS OF DEEP LEARNING MODEL BASED ON MULTICLASS CLASSIFICATION OF RETINAL IMAGE FOR EARLY DETECTION OF DIABETIC RETINOPATHY","authors":"Amit Meshram, D. Dembla, Anooja A","doi":"10.11113/aej.v13.19256","DOIUrl":"https://doi.org/10.11113/aej.v13.19256","url":null,"abstract":"Diabetic retinopathy (DR) is a leading cause of blindness, and early detection is crucial for effectively managing and preventing vision loss. This paper proposes a deep learning-based model for the early detection of diabetic retinopathy (DR) using retinal images. The proposed model uses a convolutional neural network (CNN) architecture and transfer learning-based EfficientNet architecture for multiclass classification (0- No DR, 1- Low, 2- Medium, 3- High, 4- Proliferative) of DR, on a large dataset of annotated retinal images. The performance of the model is evaluated on an independent test set and compared with CNN and EfficientNet methods. Results show that the efficient model achieves high accuracy and outperforms existing methods for DR detection. Moreover, the model can detect DR at an early stage, enabling timely interventions and preventing vision loss. The results show that we achieved a training accuracy of 94.42% after 20 epochs and a testing accuracy of 81.81%. The model's accuracy and early detection capability make it a promising tool for enhancing DR screening programs and enabling timely interventions to prevent vision loss.","PeriodicalId":36749,"journal":{"name":"ASEAN Engineering Journal","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49482306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信