• Journal of IKEEE
• /
• v.15 no.4
• /
• pp.354-362
• /
• 2011

One of the unsolved problems in Artificial Neural Networks is related to the capacity of a neural network. This paper presents a CoreNet which has a multi-leveled input and a multi-leveled output as a 2-layered artificial neural network. I have suggested an equation for calculating the capacity of the CoreNet, which has a p-leveled input and a q-leveled output, as $a_{p,q}=\frac{1}{2}p(p-1)q^2-\frac{1}{2}(p-2)(3p-1)q+(p-1)(p-2)$. With an odd value of p and an even value of q, (p-1)(p-2)(q-2)/2 needs to be subtracted further from the above equation. The simulation model 1(3)-1(6) has 3 levels of an input and 6 levels of an output with no hidden layer. The simulation result of this model gives, out of 216 possible functions, 80 convergences for the number of implementable function using the cot(x) input leveling method. I have also shown that, from the simulation result, the two diverged functions become implementable by precalculating the weight values. The simulation result and the precalculation of the weight values give the same result as the above equation in the total number of implementable functions.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.19 no.4
• /
• pp.334-344
• /
• 2013

In order to understand the characteristics of oceanic environment in the coastal aquaculture waters of the East Sea, the observation of the CTD (temperature and salinity), dissolved oxygen, chlorophyll a and N/P (DIN ($NO_2$-N, $NO_3$-N, $NH_4$-N) : DIP($PO_4$-P)) ratio was carried out at Sokcho, Jukbyon and Gampo in February, April, June, August, October, December 2013. Based on T(temperature)-S(salinity) diagram analysis, the water masses in the study area were divided into 3 groups; Tsushima Surface Water (TSW: $20-28.3^{\circ}C$ temperatures and 31.04-33.75 salinities), Tsushima Middle Water (TMW: $8.1-16.3^{\circ}C$ and 33.00-34.49), and North Korean Cold Water (NKCW: $1.8-9.4^{\circ}C$ and 33.78-34.42). In winter, DO concentrations in the northern part were higher than those in southern part. In spring and fall, they were low in the surface layer, and increased in summer. Chl-a concentrations < $0.4{\mu}g/L$ dominated in February, April, October and December. Chl-a concentrations were higher in June and August. In particular, the highest Chl-a concentration > $2{\mu}g/L$ was observed in the middle layer of Gampo in August. In February, April, June and December, the N/P ratio in the most of the water masses was less than the Redfield ratio (16), indicating that nitrate did act as a limiting factor in phytoplankton growth. On the contrary, in August and October, the N/P ratio in surface and sub-surface layer was greater than the Redfield ratio, suggesting that phosphate was a limiting factor.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.42 no.4 s.334
• /
• pp.19-28
• /
• 2005

In this paper, we proposed a parallel fast 2-D discrete wavelet transform hardware architecture based on lifting scheme. The proposed architecture improved the 2-D processing speed, and reduced internal memory buffer size. The previous lifting scheme based parallel 2-D wavelet transform architectures were consisted with row direction and column direction modules, which were pair of prediction and update filter module. In 2-D wavelet transform, column direction processing used the row direction results, which were not generated in column direction order but in row direction order, so most hardware architecture need internal buffer memory. The proposed architecture focused on the reducing of the internal memory buffer size and the total calculation time. Reducing the total calculation time, we proposed a 4-way data flow scheduling and memory based parallel hardware architecture. The 4-way data flow scheduling can increase the row direction parallel performance, and reduced the initial latency of starting of the row direction calculation. In this hardware architecture, the internal buffer memory didn't used to store the results of the row direction calculation, while it contained intermediate values of column direction calculation. This method is very effective in column direction processing, because the input data of column direction were not generated in column direction order The proposed architecture was implemented with VHDL and Altera Stratix device. The implementation results showed overall calculation time reduced from $N^2/2+\alpha$ to $N^2/4+\beta$, and internal buffer memory size reduced by around $50\%$ of previous works.