79 research outputs found
Classification system from Optical Coherence Tomography using transfer learning
Get PDFThis research aims to create a decision support system to identify retinal diseases using a four-class classification problem. To achieve this, the proposed system uses deep learning architecture to automatically recognize CNV, DME, and drusen from OCT images. The model employs two transfer learning architectures with several additional layers to classify retinal diseases. The purpose of model training, validation, and testing, the experiment uses 6,000 grayscale images labeled into four classes from the OCT data set. The Inception V3 model’s proposed additional layer exhibits an increase in accuracy of 3.08% and a reduction in the loss by 0.3767. The experiment’s results indicate that the Inception V3 model achieved an accuracy rate of 99.31%, and the VGG-16 model reached 98.83%, which outperformed other deep learning models using the OCT data set
Satellite constellation design and radio resource management using genetic algorithm
No full textAvailable from British Library Document Supply Centre- DSC:DXN064159 / BLDSC - British Library Document Supply CentreSIGLEGBUnited Kingdo
Satellite constellation design and radio resource management using genetic algorithm.
Get PDFA novel strategy for automatic satellite constellation design with satellite diversity is proposed. The automatic satellite constellation design means some parameters of satellite constellation design can be determined simultaneously. The total number of satellites, the altitude of satellite, the angle between planes, the angle shift between satellites and the inclination angle are considered for automatic satellite constellation design. Satellite constellation design is modelled using a multiobjective genetic algorithm. This method is applied to LEO, MEO and hybrid constellations. The advantage of this algorithm is automatic satellite constellation design whilst achieving dual satellite diversity statistics. Furthermore a new strategy of dynamic channel allocation is proposed using a genetic algorithm for use in MSS networks. The main idea behind this algorithm is to use minimum cost as a metric to provide optimum channel solutions for specified interference constraints. The frequency reuse condition for all spotbeams is investigated as a function of time. The update interval time and the sampling time are introduced in order to track time valiant coefficients and constraints of the algorithm. The method is demonstrated for S-UMTS based on a MEO satellite constellation. Using this algorithm, it is shown that the proposed model outperforms conventional DCA schemes in terms of capacity of the system and Quality of Service (QoS).We show in the thesis that the genetic algorithm is a robust method for calculation of dynamic variations in satellite constellation design and provides resource allocation improvements over DCA in MSS system networks
Satellite constellation design and radio resource management using genetic algorithm.
No full textA novel strategy for automatic satellite constellation design with satellite diversity is proposed. The automatic satellite constellation design means some parameters of satellite constellation design can be determined simultaneously. The total number of satellites, the altitude of satellite, the angle between planes, the angle shift between satellites and the inclination angle are considered for automatic satellite constellation design. Satellite constellation design is modelled using a multiobjective genetic algorithm. This method is applied to LEO, MEO and hybrid constellations. The advantage of this algorithm is automatic satellite constellation design whilst achieving dual satellite diversity statistics. Furthermore a new strategy of dynamic channel allocation is proposed using a genetic algorithm for use in MSS networks. The main idea behind this algorithm is to use minimum cost as a metric to provide optimum channel solutions for specified interference constraints. The frequency reuse condition for all spotbeams is investigated as a function of time. The update interval time and the sampling time are introduced in order to track time valiant coefficients and constraints of the algorithm. The method is demonstrated for S-UMTS based on a MEO satellite constellation. Using this algorithm, it is shown that the proposed model outperforms conventional DCA schemes in terms of capacity of the system and Quality of Service (QoS).We show in the thesis that the genetic algorithm is a robust method for calculation of dynamic variations in satellite constellation design and provides resource allocation improvements over DCA in MSS system networks
Simulasi dan Analisis Transmisi Multihop Mobile WiMAX Dengan Metode Hybrid
No full textMakalah ini membahas tentang pengembangan relay station untuk transmisi downlink Mobile WiMAX dengan menggunakan metode hybrid, yaitu metode transmisi yang menggunakan tiga buah transmisi. Ketiga transmisi tersebut yaitu dua buah transmisi yang melewati relay station terlebih dahulu baru ke receiver dan satu buah transmisi langsung dari pengirim ke penerima. Pada relay station ada dua kondisi yang berlaku, yaitu Decode and Forward (DF) dan Amplify and Forward (AF). Hasil simulasi menunjukkan bahwa ketika Relay Station dalam mode forwarding Amplify and Forward (AF) akan memperoleh BER yang kecil sehingga throughput besar dan merupakan perfomansi yang terbaik. Ketika masing-masing relay station diatur agar menggunakan mode forwarding yang berbeda, misalnya AF pada relay station 1 dan DF pada Relay Station 2 atau sebaliknya akan memperoleh hasil yang sama. Sedangkan ketika kedua relay station diatur untuk menggunakan mode forwarding Decode and Forward (DF), maka BER yang dihasilkan besar dan throughput-nya pun kecil, dan kondisi ini merupakan yang terburuk.</jats:p
Simulasi dan Analisis Transmisi Multihop Mobile WiMAX Dengan Metode Hybrid
No full textMakalah ini membahas tentang pengembangan relay station untuk transmisi downlink Mobile WiMAX dengan menggunakan metode hybrid, yaitu metode transmisi yang menggunakan tiga buah transmisi. Ketiga transmisi tersebut yaitu dua buah transmisi yang melewati relay station terlebih dahulu baru ke receiver dan satu buah transmisi langsung dari pengirim ke penerima. Pada relay station ada dua kondisi yang berlaku, yaitu Decode and Forward (DF) dan Amplify and Forward (AF). Hasil simulasi menunjukkan bahwa ketika Relay Station dalam mode forwarding Amplify and Forward (AF) akan memperoleh BER yang kecil sehingga throughput besar dan merupakan perfomansi yang terbaik. Ketika masing-masing relay station diatur agar menggunakan mode forwarding yang berbeda, misalnya AF pada relay station 1 dan DF pada Relay Station 2 atau sebaliknya akan memperoleh hasil yang sama. Sedangkan ketika kedua relay station diatur untuk menggunakan mode forwarding Decode and Forward (DF), maka BER yang dihasilkan besar dan throughput-nya pun kecil, dan kondisi ini merupakan yang terburuk
Development and measurement analysis of transceiver and TNC for IiNUSAT nanosatellite payload communication
No full textRegulatory Framework Analysis of Infrastructure Sharing for Mobile Operators in Indonesia by Using Regulatory Impact Analysis Approach
No full text- …
