To Batch or Not to Batch? Comparing Batching and Curriculum Learning Strategies across Tasks and Datasets

Many natural language processing architectures are greatly affected by seemingly small design decisions, such as batching and curriculum learning (how the training data are ordered during training). In order to better understand the impact of these decisions, we present a systematic analysis of different curriculum learning strategies and different batching strategies. We consider multiple datasets for three tasks: text classification, sentence and phrase similarity, and part-of-speech tagging. Our experiments demonstrate that certain curriculum learning and batching decisions do increase performance substantially for some tasks.

Content-Based Medical Image Retrieval and Intelligent Interactive Visual Browser for Medical Education, Research and Care

Medical imaging is essential nowadays throughout medical education, research, and care. Accordingly, international efforts have been made to set large-scale image repositories for these purposes. Yet, to date, browsing of large-scale medical image repositories has been troublesome, time-consuming, and generally limited by text search engines. A paradigm shift, by means of a query-by-example search engine, would alleviate these constraints and beneficially impact several practical demands throughout the medical field. The current project aims to address this gap in medical imaging consumption by developing a content-based image retrieval (CBIR) system, which combines two image processing architectures based on deep learning. Furthermore, a first-of-its-kind intelligent visual browser was designed that interactively displays a set of imaging examinations with similar visual content on a similarity map, making it possible to search for and efficiently navigate through a large-scale medical imaging repository, even if it has been set with incomplete and curated metadata. Users may, likewise, provide text keywords, in which case the system performs a content- and metadata-based search. The system was fashioned with an anonymizer service and designed to be fully interoperable according to international standards, to stimulate its integration within electronic healthcare systems and its adoption for medical education, research and care. Professionals of the healthcare sector, by means of a self-administered questionnaire, underscored that this CBIR system and intelligent interactive visual browser would be highly useful for these purposes. Further studies are warranted to complete a comprehensive assessment of the performance of the system through case description and protocolized evaluations by medical imaging specialists.

In-Depth Analysis of OLAP Query Performance on Heterogeneous Hardware

Classical database systems are now facing the challenge of processing high-volume data feeds at unprecedented rates as efficiently as possible while also minimizing power consumption. Since CPU-only machines hit their limits, co-processors like GPUs and FPGAs are investigated by database system designers for their distinct capabilities. As a result, database systems over heterogeneous processing architectures are on the rise. In order to better understand their potentials and limitations, in-depth performance analyses are vital. This paper provides interesting performance data by benchmarking a portable operator set for column-based systems on CPU, GPU, and FPGA – all available processing devices within the same system. We consider TPC‑H query Q6 and additionally a hash join to profile the execution across the systems. We show that system memory access and/or buffer management remains the main bottleneck for device integration, and that architecture-specific execution engines and operators offer significantly higher performance.

Chest-Worn Inertial Sensors: A Survey of Applications and Methods

IMU are frequently implemented in wearable devices. Thanks to advances in signal processing and machine learning, applications of IMU are not limited to those explicitly addressing body movements such as AR. On the other hand, wearing IMU on the chest offers a few advantages over other body positions. AR and posture analysis, cardiopulmonary parameters estimation, voice and swallowing activity detection and other measurements can be approached through chest-worn inertial sensors. This survey tries to introduce the applications that come with the chest-worn IMU and summarizes the existing methods, current challenges and future directions associated with them. In this regard, this paper references a total number of 57 relevant studies from the last 10 years and categorizes them into seven application areas. We discuss the inertial sensors used as well as their placement on the body and their associated validation methods based on the application categories. Our investigations show meaningful correlations among the studies within the same application categories. Then, we investigate the data processing architectures of the studies from the hardware point of view, indicating a lack of effort on handling the main processing through on-body units. Finally, we propose combining the discussed applications in a single platform, finding robust ways for artifact cancellation, and planning optimized sensing/processing architectures for them, to be taken more seriously in future research.

Modeling Water Distribution Systems with Graph Neural Networks

<p>Water management has recently explored data-driven models to improve the adaptability of Water Distribution Systems (WDS) and strengthen decision making under uncertain conditions. The focus on these tools is motivated by the increasing availability of information and their proven performance in other fields. Modeling WDS with these techniques has been demonstrated to be useful; however, the traditional machine learning tools do not account for the graph structure present in the WDS. Considering this essential information offers the possibility to increase performance and to help the learning process. In this work, we introduce Graph Neural Networks (GNNs) for modeling WDS. GNNs are processing architectures to perform neural network tasks for data related to a graph. We first present the definitions and interpretations for using this framework in water networks. Then we compare the GNN approach against standard neural networks to predict an overall resilience metric in a benchmark system. The benefits of including the network structure in the learning process by the GNN are shown in the analysis of the obtained results.</p>

Partial Power Processing Based Converter for Electric Vehicle Fast Charging Stations

This paper focuses on the design of a charging unit for an electric vehicle fast charging station. With this purpose, in first place, different solutions that exist for fast charging stations are described through a brief introduction. Then, partial power processing architectures are introduced and proposed as attractive strategies to improve the performance of this type of applications. Furthermore, through a series of simulations, it is observed that partial power processing based converters obtain reduced processed power ratio and efficiency results compared to conventional full power converters. So, with the aim of verifying the conclusions obtained through the simulations, two downscaled prototypes are assembled and tested. Finally, it is concluded that, in case galvanic isolation is not required for the charging unit converter, partial power converters are smaller and more efficient alternatives than conventional full power converters.