김선우 교수

Abstract The mutation method assesses test quality by examining the ability of a test set to distinguish syntactic deviations representing specific types of faults from the program under test. This paper describes an empirical study performed to evaluate the effectiveness of object‐oriented (OO) test strategies using the mutation method. The test sets for the experimental system are generated according to three selected OO test strategies and their effectiveness is compared by determining how we

Higher-order interactions (HOIs) are ubiquitous in real-world complex systems and applications. Investigation of deep learning for HOIs, thus, has become a valuable agenda for the data mining and machine learning communities. As networks of HOIs are expressed mathematically as hypergraphs, hypergraph neural networks (HNNs) have emerged as a powerful tool for representation learning on hypergraphs. Given the emerging trend, we present the first survey dedicated to HNNs, with an in-depth and step-

In this letter we propose a fully angle-domain frequency-selective sparse channel estimation algorithm for multiple-input multiple-output orthogonal frequency division multiplexing underwater acoustic communication (MIMO-OFDM UAC) systems. The algorithm is divided into two stages (finding nonzero tap positions and finding nonzero angle-domain coefficients) to reduce the computational complexity. It has been demonstrated that the 2-stage orthogonal matching pursuits algorithm provides an efficien

Channel estimation and distributed positioning algorithms are presented for geolocation in a wireless ad hoc network. The network uses a direct-sequence code-division multiple-access-based handshaking protocol, in which nodes receive multiple acknowledgment packets in response to a request-to-send waveform. Round-trip travel time (RTT) and angle-of-arrival (AOA) measurements are obtained using the generalized successive interference cancellation/matching pursuits (GSIC/MP) algorithm. The perform

In realistic speech enhancement settings for end-user devices, we often encounter only a few speakers and noise types that tend to reoccur in the specific acoustic environment. We propose a novel personalized speech enhancement method to adapt a compact denoising model to the test-time specificity. Our goal in this test-time adaptation is to utilize no clean speech target of the test speaker, thus fulfilling the requirement for zero-shot learning. To complement the lack of clean speech, we emplo

This paper proposes a Bitwise Gated Recurrent Unit (BGRU) network for the single-channel source separation task. Recurrent Neural Networks (RNN) require several sets of weights within its cells, which significantly increases the computational cost compared to the fully-connected networks. To mitigate this increased computation, we focus on the GRU cells and quantize the feedforward procedure with binarized values and bitwise operations. The BGRU network is trained in two stages. The real-valued

This paper presents a tutorial on Deep Learning (DL) with Federated Learning (FL)-based indoor localization method for non-Independently and Identically Distributed (non-IID) fingerprinting databases. To this end, this paper explains systematic approaches for addressing privacy concerns and performance degradation issues in non-IID fingerprinting databases. The method presented in this tutorial entails the application of a personalized layer, model reliability, and Layer-wise local model’s Weigh

In this letter, we propose a deep learning-based technique to recover a Euclidean distance matrix <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</b> in IoT network localization. In contrast to conventional localization algorithms that search <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</b> over a whole set of matrices, the proposed technique, called multiple deep neural networks for localizati

The Schumpeterian model emphases entrepreneurship as the central axis of economic growth. Growth in the managed economy comes from stability, specialization, and scale, but in the entrepreneurial economy, growth comes from entrepreneurship based on flexibility, creativity and connectivity. So, it is necessary to monitor entrepreneurship more academically. This study analyzed the articles related to entrepreneurship provided by the Web of Science. The representative bibliometric analysis of entre

This work develops a deep-learning-based cooperative localization technique for high localization accuracy and real-time operation in vehicular networks. In cooperative localization, the noisy observation of the pairwise distance and the angle between vehicles causes nonlinear optimization problems. To handle such a nonlinear optimization task at each vehicle, a deep neural network (DNN) technique is to replace a cumbersome solution of nonlinear optimization along with the saving of the computat

Recent techniques to solve photorealistic style transfer within deep convolutional neural networks (CNNs) generally require intensive training from large-scale datasets, thus having limited applicability and poor generalization ability to unseen images or styles. To overcome this, we propose a novel framework, dubbed Deep Translation Prior (DTP), to accomplish photorealistic style transfer through test-time training on given input image pair with untrained networks, which learns an image pair-sp

&lt;div class="htmlview paragraph"&gt;Increasing demands on the emission reduction of high speed direct injection (HSDI) diesel engines require more accurate control of injection parameters such as the injection timing, injection rate, and injection quantity. In order to meet injection requirements, the piezo injector, which has a piezoelectric element as an actuator, has been recently developed. Compared with solenoid-actuated injectors, piezo-actuated injectors yield greater force and give fas