Hasil Pencarian  ::  Simpan CSV :: Kembali

"This book describes hybrid intelligent systems using type-2 fuzzy logic and modular neural networks for pattern recognition applications. Hybrid intelligent systems combine several intelligent computing paradigms, including fuzzy logic, neural networks, and bio-inspired optimization algorithms, which can be used to produce powerful pattern recognition systems. Type-2 fuzzy logic is an extension of traditional type-1 fuzzy logic that enables managing higher levels of uncertainty in complex real world problems, which are of particular importance in the area of pattern recognition. The book is organized in three main parts, each containing a group of chapters built around a similar subject. The first part consists of chapters with the main theme of theory and design algorithms, which are basically chapters that propose new models and concepts, which are the basis for achieving intelligent pattern recognition. The second part contains chapters with the main theme of using type-2 fuzzy models and modular neural networks with the aim of designing intelligent systems for complex pattern recognition problems, including iris, ear, face and voice recognition. The third part contains chapters with the theme of evolutionary optimization of type-2 fuzzy systems and modular neural networks in the area of intelligent pattern recognition, which includes the application of genetic algorithms for obtaining optimal type-2 fuzzy integration systems and ideal neural network architectures for solving problems in this area."

"Modeling, simulation, design and engineering of WDM systems and networks provides readers with the basic skills, concepts, and design techniques used to begin design and engineering of optical communication systems and networks at various layers. The latest semi-analytical system simulation techniques are applied to optical WDM systems and networks, and a review of the various current areas of optical communications is presented. Simulation is mixed with experimental verification and engineering to present the industry as well as state-of-the-art research. This contributed volume is divided into three parts. The first part of the book presents modeling approaches and simulation tools mainly for the physical layer including transmission effects, devices, subsystems, and systems), whereas the second part features more engineering/design issues for various types of optical systems including ULH, access, and in-building systems. The third part of the book covers networking issues related to the design of provisioning and survivability algorithms for impairment-aware and multi-domain networks."

"ABSTRACTBackpropagation neural network merupakan salah satu algoritme machine learning yang mengizinkan sebuah mesin untuk melakukan pembelajaran dari sekumpulan data, sehingga tidak perlu diprogram secara eksplisit. Namun, backpropagation neural network yang baik memerlukan proses pembelajaran dengan waktu lama dengan data dalam jumlah banyak. Penelitian ini akan merancang sebuah program backpropagation neural network yang dapat dieksekusi secara paralel untuk mendapatkan waktu eksekusi yang lebih cepat. Pembuatan program ini dilakukan menggunakan OpenMP API dalam bahasa pemrograman C. Hasil pengujian membuktikan bahwa adanya pengurangan waktu eksekusi, yakni secara berurutan sebesar 2,2653 detik dan 0,5838 detik untuk masing-masing mesin pengujian yang digunakan, untuk pertambahan setiap jumlah thread yang bekerja pada program. Namun, program masih memiliki skalabilitas yang kurang bagus dikarenakan oleh terjadinya fenomena false sharing pada program. Program memiliki sifat kenaikan waktu eksekusi linier sebesar 0,9263 detik untuk setiap pertambahan jumlah sampel input. Hal ini dikarenakan oleh pertambahan jumlah sampel hanya menambah jumlah data yang harus diproses program saja. Sedangkan, program memiliki sifat kenaikan waktu eksponensial sebesar e0,0103 detik untuk setiap pertambahan jumlah dimensi sampel input. Hal ini dikarenakan oleh pertambahan jumlah dimensi tidak hanya menambah jumlah data yang harus diproses saja, melainkan juga menambah sejumlah variabel yang bekerja pada program yang menimbulkan pertambahan komputasi pada setiap sampel input.

---

ABSTRACTBackpropagation neural networks is one of many machine learning algorithms that allows a machine to do a learning process from a set of data, instead of programming it explicitly. However, a good backpropagation neural network program needs a lot amount of learning time and involves huge amount of data. This experiment made a backpropagation neural network program that can be executed in parallel fashion in order to reduce its execution time using OpenMP API in C programming language. The program rsquo s test results show that there are 2.2653 and 0.5838 second execution time decreases, each corresponds to each testing machine, for every thread added to the program. However, the program rsquo s scalability is not good enough due to false sharing phenomenon that appeared in time of execution. Program has a 0.9263 second linear execution time increase for every input samples added to the program. This is because of the addition will only effect on how much data the program needs to process. However, the program has an e0.0103 second exponential execution time increase for every input sample rsquo s feature added. This is because of the addition will not only effect on how much data that needs to be processed, but also generate some additional variables involved inside program which affects the computational process of each input sample."