Neural networks are supposed to recognise blurred images (or patterns) of N pixels (bits) each. Application of the network to an initial blurred version of one of P pre-assigned patterns should converge to the correct pattern. In the "standard" Hopfield model, the N "neurons" are connected to each other via N 2 bonds which contain the information on the stored patterns. Thus computer time and memory in general grow with N 2 . The Hebb rule assigns synaptic coupling strengths proportional to the overlap of the stored patterns at the two coupled neurons. Here we simulate the Hopfield model on the Barabási-Albert scale-free network, in which each newly added neuron is connected to only m other neurons, and at the end the number of neurons with q neighbours decays as 1/q 3 . Although the quality of retrieval decreases for small m, we find good associative memory for 1 ≪ m ≪ N . Hence, these networks gain a factor N/m ≫ 1 in the computer memory and time.
A finite volume method for the solution of fluid flows coupled with the mechanical behavior of compacting porous media AIP Conf.Abstract. Seismic wave parameter plays very important role to characterize reservoir properties whereas pore parameter is one of the most important parameter of reservoir. Therefore, wave propagation phenomena in pore media is important to be studied. By referring this study, in-direct pore measurement method based on seismic wave propagation can be developed. Porosity play important role in reservoir, because the porosity can be as compartment of fluid. Many type of porosity like primary as well as secondary porosity. Carbonate rock consist many type of porosity, i.e.: inter granular porosity, moldic porosity and also fracture porosity. The complexity of pore type in carbonate rocks make the wave propagation in these rocks is more complex than sand reservoir. We have studied numerically wave propagation in carbonate rock by finite difference modeling in time-space domain. The medium of wave propagation was modeled by base on the result of pattern recognition using artificial neural network. The image of thin slice of carbonate rock is then translated into the velocity matrix. Each mineral contents including pore of thin slice image are translated to velocity since mineral has unique velocity. After matrix velocity model has been developed, the seismic wave is propagated numerically in this model. The phenomena diffraction is clearly shown while wave propagates in this complex carbonate medium. The seismic wave is modeled in various frequencies. The result shows dispersive phenomena where high frequency wave tends to propagate in matrix instead pores. In the other hand, the low frequency waves tend to propagate through pore space even though the velocity of pore is very low. Therefore, this dispersive phenomena of seismic wave propagation can be the future indirect measurement technology for predicting the existence or intensity of pore space in reservoir rock. It will be very useful for the future reservoir characterization.
Riset mengenai Jaringan Syaraf Tiruan telah banyak diimplementasikan dalam bidang keilmuan, khususnya Geografi, yang mengidentifikasi pola citra peta untuk membedakan kenampakan geografis, dan diterapkan pada Google Maps. Proses pengolahan citra, dengan memperbaiki kualitas citra agar mudah diinterpretasi oleh manusia atau mesin (komputer). Teknik yang digunakan adalah teknik Segmentasi. Metode training menggunakan algoritma Levenberg-Marquardt. Hasil penelitian pada proses training diperoleh nilai epoch sebanyak 17 dari 100 iterasi. Waktu yang digunakan selama proses training sebanyak 6 detik, nilai performance = 2,06; nilai gradient = 8,49; Mu = 1,00; validation check = 6 dan nilai regresi (R) proses training dan keseluruhan proses berturut-turut sebesar 0.95889 dan 0.91483. Nilai regresi menunjukan adanya hubungan linier antara output jaringan dengan target. Identifikasi pola telah berhasil membuat pola citra baru yang diidentifikasikan sebagai daerah daratan dan bukan daratan. Secara keseluruhan, aplikasi yang dibuat berhasil memenuhi fungsi yang diinginkan, yaitu untuk membantu penderita buta warna. Kata kunci: Jaringan Syaraf Tiruan, Pengolahan Citra, Teknik Segmentasi, Levenberg-Marquardt.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.