Layman Users Research Articles

SCALING: plug-n-play device-free indoor tracking

24/7 continuous recording of in-home daily trajectories is informative for health status assessment (e.g., monitoring Alzheimer’s, dementia based on behavior patterns). Indoor device-free localization/tracking are ideal because no user efforts on wearing devices are needed. However, prior work mainly focused on improving the localization accuracy. They relied on well-calibrated sensor placements, which require hours of intensive manual setup and respective expertise, feasible only at small scale and by mostly researchers themselves. Scaling the deployments to tens or hundreds of real homes, however, would incur prohibitive manual efforts, and become infeasible for layman users. We present SCALING, a plug-and-play indoor trajectory monitoring system that layman users can easily set up by walking a one-minute loop trajectory after placing radar nodes on walls. It uses a self calibrating algorithm that estimates sensor locations through their distance measurements to the person walking the trajectory, a trivial effort without taxing layman users physically or cognitively. We evaluate SCALING via simulations and two testbeds (in lab and home configurations of sizes 3×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes$$\\end{document}6 sq m and 4.5×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes$$\\end{document}8.5 sq m). Experimental results demonstrate that SCALING outperformed the baseline using the approximate multidimensional scaling (MDS, the most relevant method in the context of self calibration) by 3.5 m/1.6 m in 80-percentile error of self calibration and tracking, respectively. Notably, only 1% degradation in performance has been observed with SCALING compared to the classical multilateration with known sensor locations (anchors), which costs hours of intensive calibrating effort. In addition, we conduct Monte Carlo experiments to numerically analyze the impact of sensor placements and develop practical guidelines for deployment in real life scenarios.

Usability and acceptability of oral fluid- and blood-based hepatitis C virus self-testing among the general population and men who have sex with men in Malaysia.

Hepatitis C self-testing (HCVST) is emerging as an additional strategy that could help to expand access to HCV testing. We conducted a study to assess the usability and acceptability of two types of HCVST, oral fluid- and blood-based, among the general population and men who have sex with men (MSM) in Malaysia. An observational study was conducted in three primary care centres in Malaysia. Participants who were layman users performed the oral fluid- and blood-based HCVST sequentially. Usability was assessed by calculating the rate of errors observed, the rate of difficulties faced by participants as well as inter-reader (self-test interpreted by self-tester vs interpreted by trained user) and inter-operator concordances (self-test vs test performed by trained user). The acceptability of HCV self-testing was assessed using an interviewer-administered semi-structured questionnaire. Participants were also required to read contrived test results which included "positive", "negative", and "invalid". There was a total of 200 participants (100 general population, 100 MSM; mean age 33.6 ± 14.0 years). We found a high acceptability of oral fluid- and blood-based HCVST across both general population and MSM. User errors, related to timekeeping and reading within stipulated time, were common. However, the majority of the participants were still able to obtain and interpret results correctly, including that of contrived results, although there was substantial difficulty interpreting weak positive results. The high acceptability of HCVST among the participants did not appreciably change after they had experienced both tests, with 97.0% of all participants indicating they would be willing to use HCVST again and 98.5% of them indicating they would recommend it to people they knew. There was no significant difference between the general population and MSM in these aspects. Our study demonstrates that both oral fluid- and blood-based HCVST are highly acceptable among both the general population and MSM. Both populations also showed comparable ability to conduct the tests and interpret the results. Overall, this study suggests that HCVST could be introduced as an addition to existing HCV testing services in Malaysia. Further studies are needed to establish the optimal positioning of self-testing alongside facility-based testing to expand access to HCV diagnosis in the country.

DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance

Emerging Metaverse applications demand accessible, accurate and easy-to-use tools for 3D digital human creations in order to depict different cultures and societies as if in the physical world. Recent large-scale vision-language advances pave the way for novices to conveniently customize 3D content. However, the generated CG-friendly assets still cannot represent the desired facial traits for human characteristics. In this paper, we present Dream-Face, a progressive scheme to generate personalized 3D faces under text guidance. It enables layman users to naturally customize 3D facial assets that are compatible with CG pipelines, with desired shapes, textures and fine-grained animation capabilities. From a text input to describe the facial traits, we first introduce a coarse-to-fine scheme to generate the neutral facial geometry with a unified topology. We employ a selection strategy in the CLIP embedding space to generate coarse geometry, and subsequently optimize both the detailed displacements and normals using Score Distillation Sampling (SDS) from the generic Latent Diffusion Model (LDM). Then, for neutral appearance generation, we introduce a dual-path mechanism, which combines the generic LDM with a novel texture LDM to ensure both the diversity and textural specification in the UV space. We also employ a two-stage optimization to perform SDS in both the latent and image spaces to significantly provide compact priors for fine-grained synthesis. It also enables learning the mapping from the compact latent space into physically-based textures (diffuse albedo, specular intensity, normal maps, etc.). Our generated neutral assets naturally support blendshapes-based facial animations, thanks to the unified geometric topology. We further improve the animation ability with personalized deformation characteristics. To this end, we learn the universal expression prior in a latent space with neutral asset conditioning using the cross-identity hypernetwork, we subsequently train a neural facial tracker from video input space into the pre-trained expression space for personalized fine-grained animation. Extensive qualitative and quantitative experiments validate the effectiveness and generalizability of DreamFace. Notably, DreamFace can generate realistic 3D facial assets with physically-based rendering quality and rich animation ability from video footage, even for fashion icons or exotic characters in cartoons and fiction movies.

Text2Light

High-quality HDRIs (High Dynamic Range Images), typically HDR panoramas, are one of the most popular ways to create photorealistic lighting and 360-degree reflections of 3D scenes in graphics. Given the difficulty of capturing HDRIs, a versatile and controllable generative model is highly desired, where layman users can intuitively control the generation process. However, existing state-of-the-art methods still struggle to synthesize high-quality panoramas for complex scenes. In this work, we propose a zero-shot text-driven framework, Text2Light , to generate 4K+ resolution HDRIs without paired training data. Given a free-form text as the description of the scene, we synthesize the corresponding HDRI with two dedicated steps: 1 ) text-driven panorama generation in low dynamic range (LDR) and low resolution (LR), and 2 ) super-resolution inverse tone mapping to scale up the LDR panorama both in resolution and dynamic range. Specifically, to achieve zero-shot text-driven panorama generation, we first build dual codebooks as the discrete representation for diverse environmental textures. Then, driven by the pre-trained Contrastive Language-Image Pre-training (CLIP) model, a text-conditioned global sampler learns to sample holistic semantics from the global codebook according to the input text. Furthermore, a structure-aware local sampler learns to synthesize LDR panoramas patch-by-patch, guided by holistic semantics. To achieve super-resolution inverse tone mapping, we derive a continuous representation of 360-degree imaging from the LDR panorama as a set of structured latent codes anchored to the sphere. This continuous representation enables a versatile module to upscale the resolution and dynamic range simultaneously. Extensive experiments demonstrate the superior capability of Text2Light in generating high-quality HDR panoramas. In addition, we show the feasibility of our work in realistic rendering and immersive VR.

AvatarCLIP

3D avatar creation plays a crucial role in the digital age. However, the whole production process is prohibitively time-consuming and labor-intensive. To democratize this technology to a larger audience, we propose AvatarCLIP, a zero-shot text-driven framework for 3D avatar generation and animation. Unlike professional software that requires expert knowledge, AvatarCLIP empowers layman users to customize a 3D avatar with the desired shape and texture, and drive the avatar with the described motions using solely natural languages. Our key insight is to take advantage of the powerful vision-language model CLIP for supervising neural human generation, in terms of 3D geometry, texture and animation. Specifically, driven by natural language descriptions, we initialize 3D human geometry generation with a shape VAE network. Based on the generated 3D human shapes, a volume rendering model is utilized to further facilitate geometry sculpting and texture generation. Moreover, by leveraging the priors learned in the motion VAE, a CLIP-guided reference-based motion synthesis method is proposed for the animation of the generated 3D avatar. Extensive qualitative and quantitative experiments validate the effectiveness and generalizability of AvatarCLIP on a wide range of avatars. Remarkably, AvatarCLIP can generate unseen 3D avatars with novel animations, achieving superior zero-shot capability. Codes are available at https://github.com/hongfz16/AvatarCLIP.

Text2Human

Generating high-quality and diverse human images is an important yet challenging task in vision and graphics. However, existing generative models often fall short under the high diversity of clothing shapes and textures. Furthermore, the generation process is even desired to be intuitively controllable for layman users. In this work, we present a text-driven controllable framework, Text2Human, for a high-quality and diverse human generation. We synthesize full-body human images starting from a given human pose with two dedicated steps. 1) With some texts describing the shapes of clothes, the given human pose is first translated to a human parsing map. 2) The final human image is then generated by providing the system with more attributes about the textures of clothes. Specifically, to model the diversity of clothing textures, we build a hierarchical texture-aware codebook that stores multi-scale neural representations for each type of texture. The codebook at the coarse level includes the structural representations of textures, while the codebook at the fine level focuses on the details of textures. To make use of the learned hierarchical codebook to synthesize desired images, a diffusion-based transformer sampler with mixture of experts is firstly employed to sample indices from the coarsest level of the codebook, which then is used to predict the indices of the codebook at finer levels. The predicted indices at different levels are translated to human images by the decoder learned accompanied with hierarchical codebooks. The use of mixture-of-experts allows for the generated image conditioned on the fine-grained text input. The prediction for finer level indices refines the quality of clothing textures. Extensive quantitative and qualitative evaluations demonstrate that our proposed Text2Human framework can generate more diverse and realistic human images compared to state-of-the-art methods. Our project page is https://yumingj.github.io/projects/Text2Human.html. Code and pretrained models are available at https://github.com/yumingj/Text2Human.

Enabling AI Adoption through Assurance

With the broader adoption of AI-enabled software systems, it is necessary to provide assurance to the layman user that the AI system will behave as intended. This interactive tutorial will provide an overview of AI assurance, introduce a new set of assurance goals for AI systems, discuss the open challenges in AI assurance, and present recommendations to overcome its drawbacks.

Electrosense+: Crowdsourcing radio spectrum decoding using IoT receivers

Web spectrum monitoring systems based on crowdsourcing have recently gained popularity. These systems are however limited to applications of interest for governamental organizations or telecom providers, and only provide aggregated information about spectrum statistics. The result is that there is a lack of interest for layman users to participate, which limits its widespread deployment. We present Electrosense+ which addresses this challenge and creates a general-purpose and open platform for spectrum monitoring using low-cost, embedded, and software-defined spectrum IoT sensors. Electrosense+ allows users to remotely decode specific parts of the radio spectrum. It builds on the centralized architecture of its predecessor, Electrosense, for controlling and monitoring the spectrum IoT sensors, but implements a real-time and peer-to-peer communication system for scalable spectrum data decoding. We propose different mechanisms to incentivize the participation of users for deploying new sensors and keep them operational in the Electrosense network. As a reward for the user, we propose an incentive accounting system based on virtual tokens to encourage the participants to host IoT sensors. We present the new Electrosense+ system architecture and evaluate its performance at decoding various wireless signals, including FM radio, AM radio, ADS-B, AIS, LTE, and ACARS.

Interactive Scene Generation via Scene Graphs with Attributes

We introduce a simple yet expressive image generation method. On the one hand, it does not require the user to paint the masks or define a bounding box of the various objects, since the model does it by itself. On the other hand, it supports defining a coarse location and size of each object. Based on this, we offer a simple, interactive GUI, that allows a layman user to generate diverse images effortlessly.From a technical perspective, we introduce a dual embedding of layout and appearance. In this scheme, the location, size, and appearance of an object can change independently of each other. This way, the model is able to generate innumerable images per scene graph, to better express the intention of the user.In comparison to previous work, we also offer better quality and higher resolution outputs. This is due to a superior architecture, which is based on a novel set of discriminators. Those discriminators better constrain the shape of the generated mask, as well as capturing the appearance encoding in a counterfactual way.Our code is publicly available at https://www.github.com/ashual/scene_generation.

Miniaturized and Portable Home-Based Vital Sign Monitor Design with Android Mobile Application

Frequent or continuous vital sign monitoring could help to decrease mortality rate as early detection of vital sign abnormality allow prompt medical action to be taken for early prevention measurement, especially to elderly people and patients who suffer from chronic disease or infectious disease. However, most of the vital sign monitor are designed for hospital usage and operated by healthcare professionals, which the devices are generally heavy duty, cost-expensive, and complicated user interface for home user. This paper proposes a miniaturized and portable home-based vital sign monitor, named myVitalGear, which can accurately measure heart rate using electrocardiogram (ECG), body temperature and blood oxygen saturation (SpO2), based on Arduino Nano technology. This device aims to enable frequent vital sign monitoring at home by reducing long distance travel to hospital and long waiting hour at hospital. The device consists of an AD8232 chip to acquire ECG for heart rate measurement and further heart rhythm abnormality detection, a high precision DS18B20 temperature sensor for body temperature measurement, and a MAX30100 pulse sensor for SpO2 monitoring. In this device, the Arduino Nano microcontroller acts as the master controller to control all the system peripherals and biomedical sensors to acquire and process all the vital signs. The device also equipped with simple interface like light emitting diode (LED), liquid crystal display (LCD) and buzzer as the status indicator for layman user. A mobile application which targeted to Android-based smart phone is also developed to communicate with myVitalGear through Bluetooth wireless communication. The mobile app support the functionalities of displaying the vital sign measurement result, automated short message service (SMS) notification message and user location sending to the healthcare provider or guardian, in case of any vital sign abnormality is detected. Validation result has shown that the system able to measure vital sign with accuracy of 99.4%, 99.7% and 98.1% for heart rate, body temperature, and SpO2 respectively.

Deep Learning: A Rapid and Efficient Route to Automatic Metasurface Design.

Metasurfaces provide unprecedented routes to manipulations on electromagnetic waves, which can realize many exotic functionalities. Despite the rapid development of metasurfaces in recent years, the design process of metasurface is still time‐consuming and computational resource‐consuming. Moreover, it is quite complicated for layman users to design metasurfaces as plenty of specialized knowledge is required. In this work, a metasurface design method named REACTIVE is proposed on the basis of deep learning, as deep learning method has shown its natural advantages and superiorities in mining undefined rules automatically in many fields. REACTIVE is capable of calculating metasurface structure directly through a given design target; meanwhile, it also shows the advantage in making the design process automatic, more efficient, less time‐consuming, and less computational resource‐consuming. Besides, it asks for less professional knowledge, so that engineers are required only to pay attention to the design target. Herein, a triple‐band absorber is designed using the REACTIVE method, where a deep learning model computes the metasurface structure automatically through inputting the desired absorption rate. The whole design process is achieved 200 times faster than the conventional one, which convincingly demonstrates the superiority of this design method. REACTIVE is an effective design tool for designers, especially for laymen users and engineers.

Tackling topic general words in topic modeling

Topic models are a prevailing tool for exploring latent topics in documents, and for helping to complete many NLP tasks. To obtain good topics for a corpus, a preprocessing step is often needed to remove common stop words and identify topic general words (TGW) from the corpus. Such words can seriously harm the topic formation because they create spurious co-occurrence of unrelated words. Also, they are likely to occupy top positions of multiple topics, lead to many unrelated words being grouped under a topic, and consequently result in inscrutable and similar topics. In an application, one typically manually identifies and removes a list of TGWs in the corpus. This is a time consuming process and very hard to do by a layman user. In this paper, we aim to solve this problem automatically. The proposed approaches can be based on the current corpus alone or multiple corpora. In the latter case, a novel continuous learning method is proposed that learns from past results of multiple domain corpora to help identify TGWs in the current domain. We conduct experiments in two real-world datasets, and the experimental results show that the proposed approaches achieve superior results.

Layman Analytics System: A Cloud-Enabled System for Data Analytics Workflow Recommendation

In today’s big data era, there is a tremendously huge amount of data available. Layman users lack not only the knowledge and experience in data analytics to make sense of these data but also the computational resources for executing the analytics. In this paper, we propose and develop a layman analytics system (LAS), which provides the layman users with a scalable and ready-to-use analytics tool to automatically generate analytics workflows for classification tasks. The LAS is designed to benefit from existing open-source data analytics tools using generic ontological modeling of analytics operators from these tools as well as adaptive constraint refinement for metadata learning. Moreover, the LAS can be deployed on both public and private clouds to cater to the need of scalable computing and easy maintenance. To demonstrate the performance of the LAS, we conducted experiments with 114 data sets obtained from the University of California Irvine Machine Learning Repository. The workflows generated by the LAS were benchmarked against the OpenML whereby each data set has a range of classification accuracy obtained using classifiers designed and fine-tuned by data experts. The comparisons showed that 87 out of 114 data sets have exceeded the 50th percentile of the benchmark data. Among these 87 data sets, the LAS outperforms the 90th percentile of the benchmarks on 49 data sets.

Effect of Selfish Behavior on Power Consumption in Mobile Ad Hoc Network

A multi hop mobile ad hoc network is a peer to peer network of wireless nodes where nodes are required to perform routing activity to provide end to end connectivity among nodes. As mobile nodes are constrained by battery power and bandwidth, some nodes may behave selfishly and deny forwarding packets for other nodes, even though they expect other nodes to forward packets to keep network connected. We simulate two selfish behaviors on top of Dynamic Source Routing (DSR) protocol: the first, selfish nodes do not forward data or control packets (routing packets) for other nodes and the second, selfish nodes turn off their network interface card when they have nothing to communicate. We compare the energy saving to the selfish nodes for both the misbehaviors and show that the second selfish behavior saves more energy. This is important result because most of the cooperation enforcement mechanisms in literature, except PCOM [2], address the first selfish behavior. Also, the second selfish behavior can be easily done by layman users without any protocol level changes. Secondly, with our simulation study we find that in dense mobile ad hoc networks where route breakages are frequent, routing control packets consume significant fraction of node energy and selfish behavior by certain number of nodes reduce the overall routing overhead in network which in turn result in energy saving for both, well behaving nodes and selfish nodes.

Advances towards high‐resolution pack‐and‐go displays: A survey

Abstract— Tiled displays provide high resolution and large scale simultaneously. Projectors can project on any available surface. Thus, it is possible to create a large high‐resolution display by simply tiling multiple projectors on any available regular surface. The tremendous advancement in projection technology has made projectors portable and affordable. One can envision displays made of multiple such projectors that can be packed in one's car trunk, carried from one location to another, deployed at each location easily to create a seamless high‐resolution display, and, finally, dismantled in minutes to be taken to the next location — essentially a pack‐and‐go display. Several challenges must be overcome in order to realize such pack‐and‐go displays. These include allowing for imperfect uncalibrated devices, uneven non‐diffused display surfaces, and a layman user via complete automation in deployment that requires no user invention. We described the advances we have made in addressing these challenges for the most common case of planar display surfaces. First, we present a technique to allow imperfect projectors. Next, we present a technique to allow a photometrically uncalibrated camera. Finally, we present a novel distributed architecture that renders critical display capabilities such as self‐calibration, scalability, and reconfigurability without any user intervention. These advances are important milestones towards the development of easy‐to‐use multi‐projector displays that can be deployed anywhere and by anyone.

Registration Techniques for Using Imperfect and Par tially Calibrated Devices in Planar Multi-Projector Displays

Multi-projector displays today are automatically registered, both geometrically and photometrically, using cameras. Existing registration techniques assume pre-calibrated projectors and cameras that are devoid of imperfections such as lens distortion. In practice, however, these devices are usually imperfect and uncalibrated. Registration of each of these devices is often more challenging than the multi-projector display registration itself. To make tiled projection-based displays accessible to a layman user we should allow the use of uncalibrated inexpensive devices that are prone to imperfections. In this paper, we make two important advances in this direction. First, we present a new geometric registration technique that can achieve geometric alignment {\em in the presence of severe projector lens distortion} using a relatively inexpensive low-resolution camera. This is achieved via a closed-form model that relates the projectors to cameras, in planar multi-projector displays, using rational Bezier patches. This enables us to geometrically calibrate a 3000 x 2500 resolution planar multi-projector display made of 3 x 3 array of nine severely distorted projectors using a low resolution (640 x 480) VGA camera. Second, we present a photometric self-calibration technique for a projector-camera pair. This allows us to photometrically calibrate the same display made of nine projectors using a photometrically uncalibrated camera. To the best of our knowledge, this is the first work that allows geometrically imperfect projectors and photometrically uncalibrated cameras in calibrating multi-projector displays.

3721 初心者ユーザーに着目したマニュアルのユーザビリティ評価(S68-3 感性,感情工学と設計セッション(3),S68 感性,感情工学と設計セッション)

3721 初心者ユーザーに着目したマニュアルのユーザビリティ評価(S68-3 感性,感情工学と設計セッション(3),S68 感性,感情工学と設計セッション)

1507 初心者ユーザーに着目したマニュアルのユーザビリティ評価(OS2 マーケット創造のための設計研究)

1507 初心者ユーザーに着目したマニュアルのユーザビリティ評価(OS2 マーケット創造のための設計研究)

Symbiotic evolution-based design of fuzzy-neural diagnostic system for common acute abdominal pain

Abstract This paper presents a symbiotic evolution-based fuzzy-neural diagnostic system (SE-FNAAPDS) for diagnosis of common acute abdominal pain (AAP) without professional medical examination. The computer-assisted diagnostic system is formatted a multiple-choice symptom questionnaire, with a prompt/help menu to assist a layman user in obtaining accurate symptom data using nothing more technologically sophisticated than a medical-type thermometer and stethoscope. The SE-FNAAPDS combination of fuzzy modeling, back-propagation training and symbiotic evolution function auto-generates its own optimal fuzzy neural architecture, a significant advantage over previous time-consuming manual parameter determination. A set of AAP clinical feature data and confirmed diagnostic results is applied as input/output rule-generation and training data for the fuzzy-neural network. Comparison of system construction time and diagnostic accuracy is made by applying the same database to SE-FNAAPDS and three traditional systems. Compared to traditional methods, diagnostic decisions from SE-FNAAPDS show 94% agreement with professional human medical diagnosis and less CPU time for system construction. The presented design is useful as a core module for more advanced computer-assisted diagnostic systems, and for direct application in AAP diagnosis.

MOD - The “Open” Dialog System for M-4030 Computer

An interactive programming system MDD for M-4030 computer is described which allows to handle the majority of the operating system facilities in an on-line mode. Both programmers and layman users are supplied with the means of man-computer dialogue. The open-endedness of MOD is based on a descriptive language for implementing new user commands; thus it can be readily adapted to changing applications environment. A sublanguage for report formatting facilitates customizing of batch mode programs for interactive use. The mailbox feature of multi-console configuration provides the ease of use in case of expanding common data base and program libraries.