Learn2Write: Augmented Reality and Machine Learning-Based Mobile App to Learn Writing

Augmented reality (AR) has been widely used in education, particularly for child education. This paper presents the design and implementation of a novel mobile app, Learn2Write, using machine learning techniques and augmented reality to teach alphabet writing. The app has two main features: (i) guided learning to teach users how to write the alphabet and (ii) on-screen and AR-based handwriting testing using machine learning. A learner needs to write on the mobile screen in on-screen testing, whereas AR-based testing allows one to evaluate writing on paper or a board in a real world environment. We implement a novel approach to use machine learning for AR-based testing to detect an alphabet written on a board or paper. It detects the handwritten alphabet using our developed machine learning model. After that, a 3D model of that alphabet appears on the screen with its pronunciation/sound. The key benefit of our approach is that it allows the learner to use a handwritten alphabet. As we have used marker-less augmented reality, it does not require a static image as a marker. The app was built with ARCore SDK for Unity. We further evaluated and quantified the performance of our app on multiple devices.

Internet of Things (IoT): Data Security and Privacy Concerns under the General Data Protection Regulation (GDPR)

Internet of Things (IoT) refers to the seamless communication and interconnectivity of multiple devices within a certain network enabled by sensors and other technologies facilitating unusual processing of personal data for the performance of a certain goal. This article examines the various definitions of the IoT from technical and socio-technical perspectives and goes ahead to describe some practical examples of IoT by demonstrating their functionalities vis a vis the anticipated privacy and information security implications. Predominantly, the article discusses the information security and privacy risks posed by the operationality of IoT as envisaged under the EU GDPR and makes a few recommendations on how to address the risks.

An Improved Framework for C-V2X Systems with Data Integration and Identity-based Authentication

Current trends of autonomous driving apply the hybrid use of on-vehicle and roadside smart devices to perform collaborative data sensing and computing, so as to achieve a comprehensive and stable decision making. The integrated system is usually named as C-V2X. However, several challenges have significantly hindered the development and adoption of such systems. For example, the difficulty of accessing multiple data protocols of multiple devices at the bottom layer, and the centralized deployment of computing arithmetic power. Therefore, this work proposes a novel framework for the design of C-V2X systems. First, a highly aggregated architecture is designed with fully integration with multiple traffic data resources. Then a multilevel information fusion model is designed based on multi-sensors in vehicle-road coordination. The model can fit different detection environments, detection mechanisms, and time frames. Finally, a lightweight and efficient identity-based authentication method is given. The method can realize bidirectional authentication between end devices and edge gateways.

Alignment-Free Wireless Charging of Smart Garments with Embroidered Coils

Wireless power transfer (WPT) technologies have been adopted by many products. The capability of charging multiple devices and the design flexibility of charging coils make WPT a good solution for charging smart garments. The use of an embroidered receiver (RX) coil makes the smart garment more breathable and comfortable than using a flexible printed circuit board (FPCB). In order to charge smart garments as part of normal daily routines, two types of wireless-charging systems operating at 400 kHz have been designed. The one-to-one hanger system is desired to have a constant charging current despite misalignment so that users do not need to pay much attention when they hang the garment. For the one-to-multiple-drawer system, the power delivery ability must not change with multiple garments. Additionally, the system should be able to charge folded garments in most of the folding scenarios. This paper analyses the two WPT systems for charging smart garments and provides design approaches to meet the abovementioned goals. The wireless-charging hanger is able to charge a smart garment over a coupling variance with only 21% charging current variation. The wireless-charging drawer is able to charge a smart garment with at least 20 mA under most folding scenarios and three garments with stable power delivery ability.

Attentive Max Feature Map for Acoustic Scene Classification \\ with Joint Learning considering the Abstraction of Classes

The attention mechanism has been widely adopted in acoustic scene classification. However, we find that during the process of attention exclusively emphasizing information, it tends to excessively discard information although improving the performance. We propose a mechanism referred to as the attentive max feature map which combines two effective techniques, attention and max feature map, to further elaborate the attention mechanism and mitigate the abovementioned phenomenon. Furthermore, we explore various joint learning methods that utilize additional labels originally generated for subtask B (3-classes) on top of existing labels for subtask A (10-classes) of the DCASE2020 challenge. We expect that using two kinds of labels simultaneously would be helpful because the labels of the two subtasks differ in their degree of abstraction. Applying two proposed techniques, our proposed system achieves state-of-the-art performance among single systems on subtask A. In addition, because the model has a complexity comparable to subtask B's requirement, it shows the possibility of developing a system that fulfills the requirements of both subtasks; generalization on multiple devices and low-complexity.

Pilot Study of an Electronic Laboratory Notebook for Research and Development

The laboratory notebook is the fundamental record for research and development. The emergence of cloud-based digital tools to replace or augment the laboratory notebook has shown promise for groups that are multidisciplinary, working asynchronously, or in multiple locations. This paper details a recent pilot study conducted by Sandia National Laboratories (SNL) comparing an electronic lab notebook (ELN) with traditional paper lab notebooks (PLN), including members of SNL’s Primary Standards Laboratory (PSL). Partly motivated by a related pilot study conducted at the National Institute of Standards and Technology (NIST), the focus of the present study was on the integrability of an ELN within the unique constraints of a national lab, including security protocols that limit cloud capabilities and limited WIFI. The study used Microsoft OneNote and commercially available mobile computing hardware. The pilot included 18 participants from the PSL, biosciences, and materials science/engineering labs. In addition to OneNote, participants were provided one of two options for a computer to be used as their note taking device (including a stylus). Usability and gap analyses, as well as interviews with pilot participants were conducted by members from Sandia’s human factors group. Findings from this study indicate that ELNs may be particularly useful for teams where sharing of procedures and results is important. Participants believed that use of the ELN increased organization of their work and facilitated reporting much more than paper lab notebooks (PLNs). Other benefits included searchability and capability for access on multiple devices. Many of the identified drawbacks were specific to the unique constraints of working at a national lab, but some constraints are more general (e.g. use of ELNs in wet labs where hazardous materials may be of concern). Overall, it was found with proper training, collaboration on best practices, and technical support, that ELNs appear to be a promising tool for modernizing recording practices in research. Some examples from PSL will be highlighted, including R&D for qualifying measurement systems, calibration processes, and procedures.

Blood Culture Contamination in a Community Hospital- less than 2% is achievable

Introduction/Objective Blood cultures are commonly obtained to evaluate the presence of bacteria or fungal infection in a patient’s bloodstream. The presence of living microorganisms circulating in the bloodstream is of substantial prognostic and diagnostic importance. A positive blood culture indicates a reason for the patient’s illness and provides the etiological agent for antimicrobial therapy. Collection of blood culture is an exact process that requires time, the proper order of draw, and following of correct protocol. The busy Emergency department that requires multiple demands for nurse’s time, turnover of staff, rushing from one task to another can result in the improper collection and false-positive blood cultures. The national benchmark is set at 3% by the American Society of Clinical Microbiology (ASM) and The Clinical and Laboratory Standard Institute (CLSI). False-positive blood culture results in increased length of stay and unnecessary antimicrobial therapy, resulting in an increased cost burden to the hospital of about $5000 per patient. Methods/Case Report At our 150-bed community hospital, 26 beds Emergency Department, we have come a long way in reduction of our blood culture contamination rates from upwards of 4% to less than 2%, far lower than the national benchmark. Results (if a Case Study enter NA) NA Conclusion There are multiple devices available from various manufacturers claiming to reduce blood culture contamination. These devices do reduce blood culture (BC) contamination but at an added cost of the device. The rate of BC can be reduced and less than 3% is achievable by materials available in the laboratory. We have achieved this by providing training to every new staff by demonstration and direct observation, providing everything required for collection in a kit, using proper technique, the inclusion of diversion method that involves the aseptic collection of a clear tube before collecting blood cultures, and following up monthly on any false positive blood cultures.

Enhancing the Scalability of Multi-FPGA Stencil Computations via Highly Optimized HDL Components

Stencil-based algorithms are a relevant class of computational kernels in high-performance systems, as they appear in a plethora of fields, from image processing to seismic simulations, from numerical methods to physical modeling. Among the various incarnations of stencil-based computations, Iterative Stencil Loops (ISLs) and Convolutional Neural Networks (CNNs) represent two well-known examples of kernels belonging to the stencil class. Indeed, ISLs apply the same stencil several times until convergence, while CNN layers leverage stencils to extract features from an image. The computationally intensive essence of ISLs, CNNs, and in general stencil-based workloads, requires solutions able to produce efficient implementations in terms of throughput and power efficiency. In this context, FPGAs are ideal candidates for such workloads, as they allow design architectures tailored to the stencil regular computational pattern. Moreover, the ever-growing need for performance enhancement leads FPGA-based architectures to scale to multiple devices to benefit from a distributed acceleration. For this reason, we propose a library of HDL components to effectively compute ISLs and CNNs inference on FPGA, along with a scalable multi-FPGA architecture, based on custom PCB interconnects. Our solution eases the design flow and guarantees both scalability and performance competitive with state-of-the-art works.