• International Journal of Computer Science & Network Security
• /
• v.23 no.2
• /
• pp.47-54
• /
• 2023

This article reviews recent advances and perspectives in neuroscience related to consciousness, cognition, and neural networks in the brain. The neural mechanisms underlying cognitive processes, such as perception, attention, memory, and decision-making, are explored. The article also examines how these processes give rise to our experience of consciousness. The implications of these findings for our understanding of the brain and its functions are presented, as well as potential applications of this knowledge in fields such as medicine, psychology, and artificial intelligence. Additionally, the article explores the concept of a quantum viewpoint concerning consciousness, cognition, and creativity and how incorporating DNA as a key element could reconcile classical and quantum perspectives on human behaviour, consciousness, and cognition, as explained by genomic psychological theory. Furthermore, the article explains how the human brain processes external stimuli through the sensory nervous system and how it can be simulated using an artificial neural network (ANN) consisting of one input layer, multiple hidden layers, and an output layer. The law of learning is also discussed, explaining how ANNs work and how the modification of weight values affects the output and input values. The article concludes with a discussion of future research directions in this field, highlighting the potential for further discoveries and advancements in our understanding of the brain and its functions.

• International Journal of Advanced Culture Technology
• /
• v.11 no.2
• /
• pp.249-255
• /
• 2023

This study aims to empirically confirm the effect and impact of community care design research centered on domestic space and environment on health promotion, diagnosis treatment, disease management, rehabilitation, and mitigation through the year of publication and perspective. To this end, based on 1,227 space and environment design studies from 2,144 community care design research data conducted for about 20 years from 2002 to 2022, when care services began in earnest through the long-term care system for the elderly, SPSS 26.0 was used to create a 'Multi-layer Perceptron' artificial neural network structure model was predicted and neural network analysis was performed. Research Results First, as a result of checking studies in each field of health care by year, there is a significant difference with the number of studies related to health promotion being the highest. Second, the five perspectives are region, time, dimension, function, and content perspective. As a result of inputting these variables as independent variables and analyzing their importance in the artificial neural network, the function perspective had the most influence, followed by the region > content > dimension > time perspective.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2305-2314
• /
• 2023

The governing equations of atmospheric dispersion most often taking the form of a second-order partial differential equation (PDE). Currently, typical computational codes for predicting atmospheric dispersion use the Gaussian plume model that is an analytic solution. A Gaussian model is simple and enables rapid simulations, but it can be difficult to apply to situations with complex model parameters. Recently, a method of solving PDEs using artificial neural networks called physics-informed neural network (PINN) has been proposed. The PINN assumes the latent (hidden) solution of a PDE as an arbitrary neural network model and approximates the solution by optimizing the model. Unlike a Gaussian model, the PINN is intuitive in that it does not require special assumptions and uses the original equation without modifications. In this paper, we describe an approach to atmospheric dispersion modeling using the PINN and show its applicability through simple case studies. The results are compared with analytic and fundamental numerical methods to assess the accuracy and other features. The proposed PINN approximates the solution with reasonable accuracy. Considering that its procedure is divided into training and prediction steps, the PINN also offers the advantage of rapid simulations once the training is over.

• Journal of Intelligence and Information Systems
• /
• v.7 no.1
• /
• pp.135-147
• /
• 2001

This study proposes bankruptcy prediction model using fuzzy neural networks. Neural networks offer preeminent learning ability but they are often confronted with the inconsistent and unpredictable performance for noisy financial data. The existence of continuous data and large amounts of records may pose a challenging task to explicit concepts extraction from the raw data due to the huge data space determined by continuous input variables. The attempt to solve this problem is to transform each input variable in a way which may make it easier fur neural network to develop a predictive relationship. One of the methods selected for this is to map each continuous input variable to a series of overlapping fuzzy sets. Appropriately transforming each of the inputs into overlapping fuzzy membership sets provides an isomorphic mapping of the data to properly constructed membership values, and as such, no information is lost. In addition, it is easier far neural network to identify and model high-order interactions when the data is transformed in this way. Experimental results show that fuzzy neural network outperforms conventional neural network for the prediction of corporate bankruptcy.

• Database Research
• /
• v.34 no.3
• /
• pp.3-13
• /
• 2018

Text classification is one of the text mining technologies that classifies a given textual document into its appropriate categories and is used in various fields such as spam email detection, news classification, question answering, emotional analysis, and chat bot. In general, the text classification system utilizes machine learning algorithms, and among a number of algorithms, naïve Bayes and support vector machine, which are suitable for text data, are known to have reasonable performance. Recently, with the development of deep learning technology, several researches on applying deep neural networks such as recurrent neural networks (RNN) and convolutional neural networks (CNN) have been introduced to improve the performance of text classification system. However, the current text classification techniques have not yet reached the perfect level of text classification. This paper focuses on the fact that the text data is expressed as a vector only with the word dimensions, which impairs the semantic information inherent in the text, and proposes a neural network architecture based upon the semantic tensor space model.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.111-117
• /
• 2023

There is a lot of research on using a combination of graph neural networks and recurrent neural networks as a way to account for both temporal and spatial dependencies. In particular, graph neural networks are an emerging area of research. Seoul's bicycle rental service (aka Daereungi) has rental stations all over the city of Seoul, and the rental information at each station is a time series that is faithfully recorded. The rental information of each rental station has temporal characteristics that show periodicity over time, and regional characteristics are also thought to have important effects on the rental status. Regional correlations can be well understood using graph neural networks. In this study, we reconstructed the time series data of Seoul's bicycle rental service into a graph and developed a rental prediction model that combines a graph neural network and a recurrent neural network. We considered temporal characteristics such as periodicity over time, regional characteristics, and the degree importance of each rental station.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.1019-1029
• /
• 2020

In this paper, we propose a novel knowledge distillation algorithm to create an compressed deep ensemble network coupled with the combined use of local and global features of face images. In order to transfer the capability of high-level recognition performances of the ensemble deep networks to a single deep network, the probability for class prediction, which is the softmax output of the ensemble network, is used as soft target for training a single deep network. By applying the knowledge distillation algorithm, the local feature informations obtained by training the deep ensemble network using facial subregions of the face image as input are transmitted to a single deep network to create a so-called compressed ensemble DCNN. The experimental results demonstrate that our proposed compressed ensemble deep network can maintain the recognition performance of the complex ensemble deep networks and is superior to the recognition performance of a single deep network. In addition, our proposed method can significantly reduce the storage(memory) space and execution time, compared to the conventional ensemble deep networks developed for face recognition.

• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.12
• /
• pp.1023-1030
• /
• 2002

Since the dynamics of autonomous underwater vehicles (AUVs) are highly nonlinear and their hydrodynamic coefficients vary with different vehicle's operating conditions, high performance control systems of AUVs are needed to have the capacities of teaming and adapting to the variations of the vehicle's dynamics. In this paper, a linearly parameterized neural network (LPNN) is used to approximate the uncertainties of the vehicle dynamics, where the basis function vector of the network is constructed according to the vehicle's physical properties. The network's reconstruction errors and the disturbances in the vehicle dynamics are assumed be bounded although the bound may be unknown. To attenuate this unknown bounded uncertainty, a certain estimation scheme for this unknown bound is introduced combined with a sliding mode scheme. The proposed controller is proven to guarantee that all signals in the closed-loop system are uniformly ultimately bounded (UUB). Numerical simulation studies are performed to illustrate the effectiveness of the proposed control scheme.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.10
• /
• pp.86-94
• /
• 1993

This paper presents the two-stage neural network method for efficient channel assignment of cellular mobile radio network. The first stage decomposes the region into non-adjacent groups of cells and the second stage assigns channels to the decomposed groups. The neural network model is tested with an experimental system of eighteen channels dedicated for nineteen hexagonal-cell region. When radom call requests of average density of 2 Erl/Cell to 8 Erl/Cell are presented, the real-time channel assignment method reduces the call-blocking rate up to 16% against the existing SCA(Static Channel Assignment) method.

• Proceedings of the KIEE Conference
• /
• 1991.11a
• /
• pp.189-192
• /
• 1991

This paper presents a modular structure design of analog Hopfield neural network. Each multiplier consists of four MOS transistors which are connected to an op-amp at the front end of a neuron. A pair of MOS transistor is used in order to maintain linear operation of the synapse and can produce positive or negative synaptic weight. This architecture can be expandable to any size neural network by forming tree structure. By altering the connections, other nework paradigms can also be implemented using this basic modules. The stength of this approach is the expandability and the general applicability. The layout design of a four-neuron fully connected feedback neural network is presented and is simulated using SPICE. The network shows correct retrival of distorted patterns.