Search

This paper proposes a CNN accelerator which is optimized Pooling layer operation incorporated in Multiplication And Accumulation(MAC) to reduce the memory size. For optimizing memory and data path circuit, the quantized 8bit integer weights are used instead of 32bit floating-point weights for pre-training of MNIST data set. To reduce chip area, the proposed CNN model is reduced by a convolutional layer, a 4*4 Max Pooling, and two fully connected layers. And all the operations use specific MAC with approximation adders and multipliers. 94% of internal memory size reduction is achieved by simultaneously performing the convolution and the pooling operation in the proposed architecture. The proposed accelerator chip is designed by using TSMC65nmGP CMOS process. That has about half size of our previous paper, 0.8*0.9 = 0.72mm² . The presented CNN accelerator chip achieves 94% accuracy and 77us inference time per an MNIST image. [ABSTRACT FROM AUTHOR]

Autonomous unmanned systems are a significant component of the future battlefield. The team composed of unmanned systems will be flexible depending on the operational situation. Whenever a new team is reorganized, a secure authentication process is required. Unmanned systems can be vulnerable to deceptive activities by an enemy because authentication is limited. This paper proposes a mutual authentication scheme for the secure operation of unmanned systems. In the proposed scheme, the unmanned system extracts the integer belonging to the same team through the individual unique identification number and Chinese Remainder Theorem. With the integer, each unmanned system generates an individual encryption key by repeating the hash operation as many as the extracted integer. Then, by decrypting the received encrypted message, it is authenticated that the received message was from the friendly party. Through performance analysis, we confirmed that the proposed scheme is secure against message replay attacks, spoofing attacks, and message modification attacks and has lower computational costs than existing schemes. [ABSTRACT FROM AUTHOR]

With the recent demand for analysis using data, the size of the knowledge graph, which is the data to be analyzed, gradually increased, reaching about 82 billion edges when extracted from the web as a knowledge graph. A lot of knowledge graphs are represented in the form of Resource Description Framework (RDF), which is a standard of W3C for representing metadata for web resources. Because of the characteristics of RDF, existing RDF storages have the limitations of processing time overhead when converting and storing large amounts of RDF data. To resolve these limitations, in this paper, we propose a method of compressing and converting large amounts of RDF data into integer IDs using MapReduce, and vertically partitioning and storing them. Our proposed method demonstrated a high performance improvement of up to 25.2 times compared to RDF-3X and up to 3.7 times compared to H2RDF+. [ABSTRACT FROM AUTHOR]

Recently, super-resolution has been intensively studied only on upscaling models with integer magnification. However, the need to expand arbitrary magnification is emerging in representative application fields of actual super-resolution, such as object recognition and display image quality improvement. In this paper, we propose a model that can support arbitrary magnification by using the weights of the existing integer magnification model. This model converts super-resolution results into the DCT spectral domain to expand the space for arbitrary magnification. To reduce the loss of high-frequency information in the image caused by the expansion by the DCT spectral domain, we propose a high-frequency attention network for arbitrary magnification so that this model can properly restore high-frequency spectral information. To recover high-frequency information properly, the proposed network utilizes channel attention layers. This layer can learn correlations between RGB channels, and it can deepen the model through residual structures. [ABSTRACT FROM AUTHOR]