User Steps Research Articles

DSG-GAN: Multi-turn text-to-image synthesis via dual semantic-stream guidance with global and local linguistics

Multi-turn text-to-image synthesis task aims to manipulate desired visual content according to the user's intention step by step, which has recently attracted a lot of research interest in the community of language and vision. Different from traditional text-to-image synthesis, multi-turn text-to-image synthesis is more challenging as 1) it needs to continuously recognize the user's intention from spoken instruction and perceive the visual information from the source image; 2) it requires reasoning about the position, appearance, and characteristics of fresh modifications in target images as well as connecting objects in instructions with visual components in source images. To deal with this issue, in this paper, we propose a Dual Semantic-stream Guidance with global and local linguistics Generative Adversarial Network (DSG-GAN), which reasons and learns the user's intention from text description and iteratively manipulates visual information. Specifically, we design a novel dual semantic-stream discriminator, which combines with a hierarchical instruction encoder to evaluate the logic and quality between human intention in linguistic instruction and generates visual content from the perspective of global and fine-grained consistency matching. Meanwhile, the discriminator's backpropagation gradient is used to optimize the instruction encoder, which incentivizes it to purify the user's intention into global and local information that is consistent with the manipulation's visual representation. Extensive experiments show that even when producing high-resolution images and making deep iterative turns, our method performs significantly better due to local fine-grained linguistic information being combined with cross-modal correlation.

User Requirements Analysis of Digital-Based Solutions for Supporting Disabilities using User Journey Map (Case Study of PSLD Brawijaya University)

Disability is any condition of the body or mind that makes it more difficult for the person with the condition to do certain activities and interact with the world around them. Persons with disabilities need assistance in various fields related to their limitations to improve their quality of life. Either area that needs to be optimized to fulfill the rights of persons with disabilities is inclusive education. Brawijaya University supports inclusive education by establishing an organizational institution called Pusat Studi dan Layanan Disabilitas Universitas Brawijaya (PSLD UB). PSLD UB provides peer tutoring services by involving non-disabled students (volunteers) to assist students with disabilities during academic activities. So far, the process of implementing peer tutoring has often encountered problems due to schedule changes or other unexpected activities, causing schedule mismatches between volunteers and students with disabilities. To fulfill disability rights, it’s necessary to have a digital solution in peer tutoring activities, while to design the solution it’s necessary to analyze the right user requirements. Therefore, the purpose of this research is to analyze user requirements to optimize user experience, so that developers can use it to develop peer tutoring systems. This study applies a User Journey Map to analyze user requirements to know the description of the user's steps in achieving the goal. The selection of respondents was based on purposive sampling technique with the criteria of respondents who had carried out the peer tutoring process. From the results of this study, it was found three main features that suit user requirements are automatic replacement, emergency requests, and list of available volunteers.

GraphIPS: Calibration-Free and Map-Free Indoor Positioning Using Smartphone Crowdsourced Data

Indoor positioning plays an important role in a variety of applications under Internet of Things (IoT). Conventional WiFi fingerprinting-based indoor positioning systems (IPSs) usually require extensive manual calibrations to construct radio maps. This process severely limits the system scalability and adaptiveness. Pedestrian dead reckoning (PDR) is a popular method that can avoid the calibration process. However, PDR-based IPSs typically suffer from accumulated errors. To tackle this problem, many refinement methods require map information or floorplans which may not be available or up-to-date in practice. With the development of IoT, various types of crowdsourced data become available. In this work, we propose GraphIPS, a calibration-free and map-free IPS which dynamically generates accurate radio maps by utilizing smartphone crowdsourced WiFi and inertial measurement unit (IMU) data. GraphIPS fuses the crowdsourced data into a graph-based formulation and applies the multidimensional scaling (MDS) algorithm to compute the positions of the user's steps. The experimental results show that GraphIPS achieves comparable accuracy to the calibration-based method in a significantly shorter run time than optimization-based methods. In addition to smartphones, GraphIPS is also potentially applicable for the smart wearables with embedded WiFi modules and IMUs.

A Mechatronic System for Studying Energy Optimization During Walking.

A general principle of human movement is that our nervous system is able to learn optimal coordination strategies. However, how our nervous system performs this optimization is not well understood. Here we design, build, and test a mechatronic system to probe the algorithms underlying the optimization of energetic cost in walking. The system applies controlled fore-aft forces to a hip-belt worn by a user, decreasing their energetic cost by pulling forward, or increasing it by pulling backward. The system controls the forces, and thus energetic cost as a function of how the user is moving. In testing, we found that the system can quickly, accurately, and precisely apply target forces within a walking step. We next controlled the forces as a function of the user's step frequency and found that we could predictably reshape their energetic cost landscape. Finally, we tested whether users adapted their walking in response to the new cost landscapes created by our system, and found that users shifted their step frequency toward the new energetic minima. Our system design appears to be effective for reshaping energetic cost landscapes in human walking to study how the nervous system optimizes movement.

An Adaptive, Data-Driven Personalized Advisor for Increasing Physical Activity.

In recent years, there has been growing interest in the use of fitness trackers and smartphone applications for promoting physical activity. Many of these applications use accelerometers to estimate the level of activity that users engage in and provide visual reports of a user's step counts. When provided, most recommendations are limited to popular general health advice. In our study, we develop an approach for providing data-driven and personalized recommendations for intraday activity planning. We generate an hour-by-hour activity plan that is based on the user's probability of adhering to the plan. The user's probability of adherence to the plan is personalized, based on his/her past activity patterns and current activity target. Using this approach, we can tailor notifications (e.g., reminders, encouragement) to each user. We can also dynamically update the user's activity plan at mid-day, if his/her actual activity deviates sufficiently from the original plan. In this paper, we describe an implementation of our approach and report our technical findings with respect to identifying typical activity patterns from historical data, predicting whether an activity target will be achieved, and adapting an activity plan based on a user's actual performance throughout the day.

MAVE: Maze‐based immersive virtual environment for new presence and experience

AbstractTo provide users with a sense of presence and experience, this study presents a maze‐based immersive virtual environment (MAVE). MAVE consists of a new immersive virtual scene and immersive interaction optimized for such maze. The algorithm for calculating a finite maze is defined to automatically generate diverse maze patterns; an interactive editing function and sketch‐based maze retrieval make it easier to generate maze patterns intuitively. With the integration of these procedures, MAVE proposes a user‐oriented maze terrain authoring system that can reconstruct two‐dimensional maze patterns into three‐dimensional maze terrains. It also provides an interaction system that enables users to be immersed in a broad virtual maze environment within a limited space. As an Arduino‐based portable walking simulator, this system detects the user's steps as he or she walks in place and controls the user's motions in the virtual environment. This study confirms through various technical and statistical experiments that MAVE can lead to new research on immersion enhancement without virtual reality sickness via virtual reality content.

Development of JARoW-II active robotic walker reflecting pelvic movements while walking

This paper addresses the problem of a novel walking assist scheme considering pelvic movements. Generally, pelvic motion includes pelvic tilt, pelvic rotation, and lateral pelvic displacement. When a human walks, the pelvis is meant to both tilt and rotate. Specifically, rotational movement on the pelvis' transverse plane and tilting movement on its coronal plane are related to stride length and step width in walking and center-of-gravity swaying in the left-and-right direction, respectively. With these considerations, we introduce the innovative design of our second generation assist robotic walker (JARoW-II) for elderly people in need of supervision. And, this paper proposes a pelvic based walking-support control technique employing JARoW-II. By facilitating pelvic movements while walking, we try to enhance and/or maintain ambulatory performances such as stride length. As another important feature, the scheme is realized without use of specific manual controls or additional equipment. In detail, JARoW-II allows to accurately generate both the direction and location of walking movement and the pelvic movement in a way that corresponds to the user's walking steps. In this paper, the implementation details based on the walking-support scheme are explained, and the effectiveness of the scheme by using JARoW-II is verified through extensive experiments in everyday environments.

Design and implementation of an intelligent belt system using accelerometer.

Activity monitor systems are increasing used recently. They are important for athletes and casual users to manage physical activity during daily exercises. In this paper, we use a triaxial accelerometer to design and implement an intelligent belt system, which can detect the user's step and flapping motion. In our system, a wearable intelligent belt is worn on the user's waist to collect activity acceleration signals. We present a step detection algorithm to detect real-time human step, which has high accuracy and low complexity. In our system, an Android App is developed to manage the intelligent belt. We also propose a protocol, which can guarantee data transmission between smartphones and wearable belt effectively and efficiently. In addition, when users flap the belt in emergency, the smartphone will receive alarm signal sending by the belt, and then notifies the emergency contact person, which can be really helpful for users in danger. Our experiment results show our system can detect physical activities with high accuracy (overall accuracy of our algorithm is above 95%) and has an effective alarm subsystem, which is significant for the practical use.

Using smart-phones and floor plans for indoor location tracking

We implement pedestrian dead reckoning (PDR) for indoor localization. With a waist-mounted PDR based system on a smart-phone, we estimate the user's step length that utilizes the height change of the waist based on the Pythagorean Theorem. We propose a zero velocity update (ZUPT) method to address sensor drift error: Simple harmonic motion and a low-pass filtering mechanism combined with the analysis of gait characteristics. This method does not require training to develop the step length model. Exploiting the geometric similarity between the user trajectory and the floor map, our map matching algorithm includes three different filters to calibrate the direction errors from the gyro using building floor plans. A sliding-window-based algorithm detects corners. The system achieved 98% accuracy in estimating user walking distance with a waist-mounted phone and 97% accuracy when the phone is in the user's pocket. ZUPT improves sensor drift error (the accuracy drops from 98% to 84% without ZUPT) using 8 Hz as the cut-off frequency to filter out sensor noise. Corner length impacted the corner detection algorithm. In our experiments, the overall location error is about 0.48 meter.

Integrated online localization and navigation for people with visual impairments using smart phones

Indoor localization and navigation systems for individuals with Visual Impairments (VIs) typically rely upon extensive augmentation of the physical space, significant computational resources, or heavy and expensive sensors; thus, few systems have been implemented on a large scale. This work describes a system able to guide people with VIs through indoor environments using inexpensive sensors, such as accelerometers and compasses, which are available in portable devices like smart phones. The method takes advantage of feedback from the human user, who confirms the presence of landmarks, something that users with VIs already do when navigating in a building. The system calculates the user's location in real time and uses it to provide audio instructions on how to reach the desired destination. Initial early experiments suggested that the accuracy of the localization depends on the type of directions and the availability of an appropriate transition model for the user. A critical parameter for the transition model is the user's step length. Consequently, this work also investigates different schemes for automatically computing the user's step length and reducing the dependence of the approach on the definition of an accurate transition model. In this way, the direction provision method is able to use the localization estimate and adapt to failed executions of paths by the users. Experiments are presented that evaluate the accuracy of the overall integrated system, which is executed online on a smart phone. Both people with VIs and blindfolded sighted people participated in the experiments, which included paths along multiple floors that required the use of stairs and elevators.

A Pilot Study of the VirtuSphere as a Virtual Reality Enhancement

This pilot study assessed the utility and acceptability of the VirtuSphere, a cutting edge navigation platform designed to enhance presence in virtual environments. The VirtuSphere includes a 12-ft hollow sphere within which the user stands, and it rolls within a wheeled platform, in any direction, according to the user's steps. The pilot was a within-subject crossover design comparing the VirtuSphere to standard game controller navigation. The comparison was based on locomotion in Virtual Iraq, a virtual world resembling Iraqi war zones. Participants were 10 active duty soldiers not suffering from posttraumatic stress disorder. Results indicated that there were negligible differences in sense of presence, simulator sickness, and satisfaction across the two navigation systems. Although the VirtuSphere may provide entertainment value, these results do not provide initial support for the use of the VirtuSphere to improve constructs thought to be important to behavioral health applications of virtual reality. Potential improvements to the design of the VirtuSphere are discussed.

Step length estimation using handheld inertial sensors.

In this paper a novel step length model using a handheld Micro Electrical Mechanical System (MEMS) is presented. It combines the user's step frequency and height with a set of three parameters for estimating step length. The model has been developed and trained using 12 different subjects: six men and six women. For reliable estimation of the step frequency with a handheld device, the frequency content of the handheld sensor's signal is extracted by applying the Short Time Fourier Transform (STFT) independently from the step detection process. The relationship between step and hand frequencies is analyzed for different hand's motions and sensor carrying modes. For this purpose, the frequency content of synchronized signals collected with two sensors placed in the hand and on the foot of a pedestrian has been extracted. Performance of the proposed step length model is assessed with several field tests involving 10 test subjects different from the above 12. The percentages of error over the travelled distance using universal parameters and a set of parameters calibrated for each subject are compared. The fitted solutions show an error between 2.5 and 5% of the travelled distance, which is comparable with that achieved by models proposed in the literature for body fixed sensors only.

A self-adaptive foot-drop corrector using functional electrical stimulation (FES) modulated by tibialis anterior electromyography (EMG) dataset

We developed a functional electrical stimulator for correcting the gait patterns of patients with foot-drop problem. The stimulating electrical pulses of the system are modulated to evoke contractions of the tibialis anterior muscle, by emulating the normal patterns. The modulation is adaptive, i.e. the system can predict the user's step frequency and the generated stimulation can match each step in real-time. In this study, step data from 11 young healthy volunteers were acquired, and five prediction algorithms were evaluated by the acquired data, including the average of Previous N steps (P-N), the Previous Nth step (P-Nth), General Regression Neural Network (GRNN), Autoregressive (AR) and Kalman filter (KF). The algorithm with the best efficiency-accuracy trade-off (P-N, when N=5) was implemented in the FES system. System evaluation results obtained from a post-stroke patient with foot-drop showed that the system of this study demonstrated better performance on gait pattern correction than the methods widely adopted in commercial products.

RAFIV: A Method for Cognitive Usability Analysis

RAFIV is a cognitive usability method that is based on the label-following heuristic found in the exploratory learning literature. This paper describes the empirical evidence and theoretical foundation for the RAFIV method, a five-stage model that describes a user's cognitive steps as they perform a task. The contributions of this method to the usability literature are discussed, as well as a comparison between RAFIV and other methods such as GOMS and the Cognitive Walkthrough.

Why a Consumer Electronic Device is Difficult to Use

This paper describes a cognitive usability analysis of a home stereo as well as an experiment that tests the predictions borne out of that analysis using the RAFIV method of cognitive usability analysis (Sherry, Polson, Fennell, & Feary, 2002). At the heart of this method is a five-stage model that describes a user's cognitive steps as they perform a task. This model provides a framework for analyzing an interface by asking whether or not each stage can be accomplished purely through label-following. The results suggest that the RAFIV technique can be used to predict which tasks might prove difficult for users. Furthermore, it suggests that the number of recall steps within a task can play a negative role in a user's ability to complete that task.

"The Nerve Garden": Plant a Seed in Cyberspace

When as children we were presented with the gift of a terrarium, aquarium, ant farm or chemical garden, we were given much more than a toy. We were given dresser-top universes that gave us admiration and passion for the natural world. Cyberspace is becoming an increasingly rich space for the evolution of form. Nerve Garden seeks to express natural forms by allowing people to plant a seed in cyberspace and populate a virtual terrarium (Fig. 1). Nerve Gardeners use aJava applet to germinate compelling models of plants from L-systems, a kind of fractal genetic algorithm. Users can mutate their plants' forms and even generate animals that possess branching or segmented body plans (such as arthropods). The user's final step is to place their virtual organisms into a collective garden, expressed in a three-dimensional Virtual Reality Modeling Language (VRML) scene. The next version of Nerve Garden will

Over-friendly software

A user friendly system which incorporates full screen edit, controlled data entry points and explicitly stated data entry formats, guides a user's data entry and processing steps W the narrowest limits. This specification is, however, the antithesis of sub sequent flexibility. Also, too much prompting can become a tortuous path for the experienced user. The article discusses the nature of a truly user friendly system, one which affords both distance as well as intimacy.