Intelligent Data Analytics laboratory, Division of Information Systems, School of Computer Science and Engineering, The University of Aizu, Fukushima 965-8580, Japan
Prof. Dr. Incheon Paik
Intelligent Data Analytics laboratory, Division of Information Systems, School of Computer Science and Engineering, The University of Aizu, Fukushima 965-8580, Japan
Most academic courses in information and communication technology (ICT) or engineering disciplines are designed to improve practical skills; however, practical skills and theoretical knowledge are equally important to achieve high academic performance. This research aims to explore how practical skills are influential in improving students’ academic performance by collecting real-world data from a computer programming course in the ICT discipline. Today, computer programming has become an indispensable skill for its wide range of applications and significance across the world. In this paper, a novel framework to extract hidden features and related association rules using a real-world dataset is proposed. An unsupervised k-means clustering algorithm is applied for data clustering, and then the frequent pattern-growth algorithm is used for association rule mining. We leverage students’ programming logs and academic scores as an experimental dataset. The programming logs are collected from an online judge (OJ) system, as OJs play a key role in conducting programming practices, competitions, assignments, and tests. To explore the correlation between practical (e.g., programming, logical implementations, etc.) skills and overall academic performance, the statistical features of students are analyzed and the related results are presented. A number of useful recommendations are provided for students in each cluster based on the identified hidden features. In addition, the analytical results of this paper can help teachers prepare effective lesson plans, evaluate programs with special arrangements, and identify the academic weaknesses of students. Moreover, a prototype of the proposed approach and data-driven analytical results can be applied to other practical courses in ICT or engineering disciplines.
Quantum computing is expected to fundamentally change computer systems in the future. Recently, a new research topic of quantum computing is the hybrid quantum–classical approach for machine learning, in which a parameterized quantum circuit, also called quantum neural network (QNN), is optimized by a classical computer. This hybrid approach can have the benefits of both quantum computing and classical machine learning methods. In this early stage, it is of crucial importance to understand the new characteristics of quantum neural networks for different machine learning tasks. In this paper, we will study quantum neural networks for the task of classifying images, which are high-dimensional spatial data. In contrast to previous evaluations of low-dimensional or scalar data, we will investigate the impacts of practical encoding types, circuit depth, bias term, and readout on classification performance on the popular MNIST image dataset. Various interesting findings on learning behaviors of different QNNs are obtained through experimental results. To the best of our knowledge, this is the first work that considers various QNN aspects for image data.
With growing data volumes and the scaling of data center clusters, communication resources often become a bottleneck in service provisioning for many MapReduce applications (e.g., training machine learning models). Therefore, data placements that bring data blocks closer to data consumers (e.g., MapReduce applications) are seen as a promising solution. In this article, we propose an efficient data-placement technique that considers network traffic reduction as well as QoS guarantees for the data blocks to optimize the communication resources. We first formulate the joint optimization of the data-placement problem, propose a generic model for minimizing communication costs, and show that the joint data-placement problem is NP-hard. To solve this problem, we propose a heuristic algorithm considering traffic flows in the network topology of data centers by first seeking optimal QoS-aware data placement based on golden division on a Zipflike replica distribution, then transforming the joint data-placement problem into a block-dependence tree (BDT) construction problem, and finally reducing the BDT construction to a graph-partitioning problem. The experimental results demonstrate that our data-placement approach could effectively improve the performance of MapReduce jobs with lower communication costs and less job execution time for big-data processing.
Data augmentation has recently become an important method for improving performance in deep learning. It is also a significant issue in machine translation, and various innovations such as back-translation and noising have been made. In particular, current state-of-the-art model architectures such as BERT-fused or efficient data generation using the GPT model provide good inspiration to improve the translation performance. In this study, we propose the generation of additional data for neural machine translation (NMT) using a sentence generator by GPT-2 that produces similar characteristics to the original. BERT-fused architecture and back-translation are employed for the translation architecture. In our experiments, the model produced BLEU scores of 27.50 for tatoebaEn-Ja, 30.14 for WMT14En-De, and 24.12 for WMT18En-Ch.
Machine learning techniques and algorithm-based approaches are becoming more and more vital to support clinical decision-making. In the medical area, natural language processing (NLP) techniques have shown the ability to extract useful information from electronic health records. On the one hand, statistic, semantic, and contextualized word embedding-based models and on the other hand preprocessing approaches are the keys to a better representation of a document. Using narratives from the Intensive Care Unit, we elaborated a comparison of the most used methods and preprocessing approaches to tackle an outcome prediction problem and guide researchers into NLP pipelines in the medical area.We used real data from Medical Information Mart for Intensive Care-III (MIMIC-III).We selected all notes related to patients with pneumonia. We conducted a deep analysis on text preprocessing tasks producing three datasets: raw data with minor preprocessing, meticulous preprocessing, and extreme preprocessing filtering only medical-related terminologies using Named Entity Recognition algorithms. We then used these three sets in five models, of which two are based on the traditional noncontextual word embedding techniques and three use contextualized word embedding based on a transformer. We demonstrated that transformer-based models outperform other word embedding models and a profound preprocessing yielded an accuracy of 98.2 F1-score. These results show the highly competitive ability of NLP predictive models against other models that use medical data. With an appropriate NLP pipeline, the information contained in medical narratives can be used to draw up a patient profile, and admission notes can help to ascertain a mortality risk of a patient admitted to the Intensive Care Unit.