• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권9호
• /
• pp.4665-4683
• /
• 2019

Previous methods build image annotation model by leveraging three basic dependencies: relations between image and label (image/label), between images (image/image) and between labels (label/label). Even though plenty of researches show that multiple dependencies can work jointly to improve annotation performance, different dependencies actually do not "work jointly" in their diagram, whose performance is largely depending on the result predicted by image/label section. To address this problem, we propose the adaptive attention annotation model (AAAM) to associate these dependencies with the prediction path, which is composed of a series of labels (tags) in the order they are detected. In particular, we optimize the prediction path by detecting the relevant labels from the easy-to-detect to the hard-to-detect, which are found using Binary Cross-Entropy (BCE) and Triplet Margin (TM) losses, respectively. Besides, in order to capture the inforamtion of each label, instead of explicitly extracting regional featutres, we propose the self-attention machanism to implicitly enhance the relevant region and restrain those irrelevant. To validate the effective of the model, we conduct experiments on three well-known public datasets, COCO 2014, IAPR TC-12 and NUSWIDE, and achieve better performance than the state-of-the-art methods.

• 전자공학회논문지C
• /
• 제34C권9호
• /
• pp.43-52
• /
• 1997

Processors using the superscalar rchitecture can achieve high performance by executing multipel instructions in a clock cycle. It is made possible by having multiple functional units and issuing multiple instructions to functional units simultaneously. But instructions can be dependent on one another and these dependencies prevent some instructions form being issued at the same cycle. In this paper, we designed an issue unit of a superscalar RISC microprocessor that can issue four instructions per cycle. The issue unit receives instructions form a prefetch unit, and issues them in order at a rate of as high as four instructions in one cycle for maximum utilization of functional units. By using an instruction buffer, the unit decouples instruction fetch and issue to improve instruction ussue rate. The issue unit is composed of an instruction buffer and an instruction decoder. The instruction buffer aligns and stores instructions from the prefetch unit, and sends the earliest four available isstructions to the instruction decoder. The instruction decoder decodes instructions, and issues them if they are free form data dependencies and necessary functional units and rgister file prots are available. The issue unit is described with behavioral level HDL (lhardware description language). The result of simulation using C programs shows that instruction issue rate is improved as the instruction buffer size increases, and 12-entry instruction buffer is found to be optimum considering performance and hardware cost of the instruction buffer.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.88-97
• /
• 2023

Traffic flow prediction is of great significance in urban planning and traffic management. As the complexity of urban traffic increases, existing prediction methods still face challenges, especially for the fusion of spatiotemporal information and the capture of long-term dependencies. This study aims to use the fusion model of graph neural network to solve the spatio-temporal information fusion problem in traffic flow prediction. We propose a new deep learning model Spatio-Temporal Information Fusion using Graph Neural Networks (STFGNN). We use GCN module, TCN module and LSTM module alternately to carry out spatiotemporal information fusion. GCN and multi-core TCN capture the temporal and spatial dependencies of traffic flow respectively, and LSTM connects multiple fusion modules to carry out spatiotemporal information fusion. In the experimental evaluation of real traffic flow data, STFGNN showed better performance than other models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권1호
• /
• pp.229-240
• /
• 2012

Advances in MEMS and CMOS technologies have motivated the development of low cost/power sensors and wireless multimedia sensor networks (WMSN). The WMSNs were created to ubiquitously harvest multimedia content. Such networks have allowed researchers and engineers to glimpse at new Machine-to-Machine (M2M) Systems, such as remote monitoring of biosignals for telemedicine networks. These systems require the acquisition of a large number of data streams that are simultaneously generated by multiple distributed devices. This paradigm of data generation and transmission is known as event-streaming. In order to be useful to the application, the collected data requires a preprocessing called data fusion, which entails the temporal alignment task of multimedia data. A practical way to perform this task is in a centralized manner, assuming that the network nodes only function as collector entities. However, by following this scheme, a considerable amount of redundant information is transmitted to the central entity. To decrease such redundancy, data fusion must be performed in a collaborative way. In this paper, we propose a collaborative data alignment approach for event-streaming. Our approach identifies temporal relationships by translating temporal dependencies based on a timeline to causal dependencies of the media involved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• pp.1-14
• /
• 2024

Time-series forecasting is extensively used in the actual world. Recent research has shown that Transformers with a self-attention mechanism at their core exhibit better performance when dealing with such problems. However, most of the existing Transformer models used for time series prediction use the traditional encoder-decoder architecture, which is complex and leads to low model processing efficiency, thus limiting the ability to mine deep time dependencies by increasing model depth. Secondly, the secondary computational complexity of the self-attention mechanism also increases computational overhead and reduces processing efficiency. To address these issues, the paper designs an efficient multi-layer attention-based time-series forecasting model. This model has the following characteristics: (i) It abandons the traditional encoder-decoder based Transformer architecture and constructs a time series prediction model based on multi-layer attention mechanism, improving the model's ability to mine deep time dependencies. (ii) A cross attention module based on cross attention mechanism was designed to enhance information exchange between historical and predictive sequences. (iii) Applying a recently proposed sparse attention mechanism to our model reduces computational overhead and improves processing efficiency. Experiments on multiple datasets have shown that our model can significantly increase the performance of current advanced Transformer methods in time series forecasting, including LogTrans, Reformer, and Informer.

• 품질경영학회지
• /
• 제23권3호
• /
• pp.84-92
• /
• 1995

A method is proposed for the simultaneous optimization of several response functions that depend on the same set of controllable variables and are adequately represented by a response surface model (polynomial regression model) with the same degree and with constraint that the individual responses have the target values. First, the multiple responses data are checked for linear dependencies among the responses by eigenvalue analysis. Thus a set of responses with no linear functional relationships is used in developing a function that measures the distance estimated responses from the target values. We choose the optimal condition that minimizes this measure. Also, under the different degree of importance two step procedures are proposed.

• 통합자연과학논문집
• /
• 제13권2호
• /
• pp.69-75
• /
• 2020

Multiple Input Multiple Output (MIMO) is one of the important wireless communication technologies. This paper proposes MIMO system capacity enhancement by using convolution of periodic circulating vector signals. This signal represents statistical dependencies between transmission signal with discrete noise and receiver signal with the linear shifting of MIMO channel capacity by positive extents. We examine the channel capacity, outage probability and SNR of MIMO receiver by adding log determinant signal with validated in terms of numerical simulation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권7호
• /
• pp.2614-2632
• /
• 2015

A multiple symbol detection (MSD) algorithm is proposed relying on soft information for ultra-wideband systems, where differential space-time block code is employed. The proposed algorithm aims to calculate a posteriori probabilities (APP) of information symbols, where a forward and backward message passing mechanism is implemented based on the BCJR algorithm. Specifically, an MSD metric is analyzed and performed for serving the APP model. Furthermore, an autocorrelation sampling is employed to exploit signals dependencies among different symbols, where the observation window slides one symbol each time. With the aid of the bidirectional message passing mechanism and the proposed sampling approach, the proposed MSD algorithm achieves a better detection performance as compared with the existing MSD. In addition, when the proposed MSD is exploited in conjunction with channel decoding, an iterative soft-input soft-output MSD approach is obtained. Finally, simulations demonstrate that the proposed approaches improve detection performance significantly.

• 한국산업정보학회논문지
• /
• 제4권2호
• /
• pp.44-50
• /
• 1999

본 논문은 순환이동불변 플로우 그래프로 표시된 디지털 필터를 여러 개의 누산기 및 내부 데이터패스를 가진 파이프라인 프로세서에 최적으로 구현할 수 있는 기법에 대하여 기술하였다. 이와 관련하여 본 논문에서는 상용의 DSP 프로세서를 이용하여 다중프로세서를 구성했을 때를 고려한 스케쥴링 기법을 개발하였으며, 연구 결과는 다음의 세 가지로 요약할 수 있다. 첫째, 상용 DSP프로세서의 구조와 유사한 n개의 누산기와 3 개의 내부 데이터패스를 가지는 파이프라인 프로세서의 모델을 제시하였다. 둘째, 주어진 구조를 가지는 시스템에 순환이동불변 플로우 그래프로 표시된 디지털 필터를 구현하고자 할 때 얻을 수 있는 최소 반복 주기 및 간단한 스케쥴링 모델을 구했으며, 제약조건을 부여한 깊이 탐색기법에 바탕을 둔 최적의 스케쥴링 기법을 개발하였다. 마지막으로 본 연구에서 개발된 스케쥴러를 이용하여 잘 알려진 디지털 필터에 대하여 성능 시험을 한 결과 대부분의 경우 이론적으로 얻을 수 있는 최소의 반복 주기를 만족시켜주는 스케쥴링 결과를 얻을 수 있음을 확인하였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제27권8호
• /
• pp.855-863
• /
• 2000

K개의 인식기로부터 관찰된 K개 결정을 결합하는 결합 방법론 중의 하나인 BKS (Behavior-Knowledge Space) 방법은 아무런 가정 없이 이들 결정을 결합하지만, 관찰된 K개 결정을 저장하고 관리하려면 이론적으로 기하학적인 저장 공간을 만들어야 한다. 즉, K개의 인식기 결정을 결합하기 위하여 (K+1)차 확률 분포를 필요로 하는데, 작은 K라 할지라도 그 확률 분포를 저장하거나 평가하는 것이 어렵다는 것은 이미 잘 알려져 있다. 그러한 문제점을 극복하기 위해서는 고차 확률 분포를 몇 개의 구성 분포로 나누고, 이들 구성 분포의 곱(product)으로 고차 확률 분포를 근사시켜야 한다. 그러한 이전 방법 중의 하나는 그 확률 분포에 조건부 독립 가정을 적용하는 것이고, 다른 방법으로는 [1]에서와 같이 그 확률 분포를 단지 트리 의존관계 또는 2차 구성 분포의 곱으로 근사하는 것이다. 본 논문에서는, 구성 분포의 곱으로 근사하는 방법에서, 2차 이상의 고차 구성 분포까지 고려하여 (K+1)차 확률 분포를 d차 ($1{\le}d{\le}K$) 의존관계에 의한 최적의 곱으로 근사하고, 베이지안 방법과 그 곱을 기반으로 다수 인식기의 결정을 결합하는 의존관계 기반의 프레임워크를 제안한다. 이 프레임워크는 표준 CENPARMI 데이타베이스로 실험되어 평가되었다.