Ergonomics improvement in a harsh environment using an audio feedback system

Speech is a natural form of interaction for people, and smart environments offer good possibilities for experimenting with new kinds of interaction with users and devices. Speech control can offer more intuitive and easy forms of interaction with the environment compared to traditional graphical or physical user interfaces. This paper describes the development, implementation and current ongoing work on a location-aware speech control and audio feedback user interface.

In our society, blind people consist a wide number of individuals. In order to improve the quality of life of a blind person, the smart cane was therefore created. This project aims to develop a smart cane for the blind with an ultrasonic sensor and an audio feedback system. This embedded system will mainly have two parts; the system of mobility and feedback. It was been fitted with an ultrasonic sensor for the mobility system, while the vibrating motor and audio input will provide input from the ultrasonic and the vibrating module. An Ultrasonic sensor was used to send the signal to the vibrating motor as soon as an obstacle is detected, which in turn triggers it. With audio feedback alerting the user of the presence of the obstacle, the vibrating motor vibrates with various strengths according to the distance of the obstacle. One major component incorporated into this embedded system is an ATmega328 single-chip microcontroller which was programed in the c language of which the original programing was written with Matlab. It involves the use of a convolution neural network which was trained on the CIFAR 10 dataset. This dataset was chosen because of its composition of images of objects likely to be found as obstacles on a blind man's path. A 93.8% accuracy was obtained from an unsupervised learning on the data set, after which the C Matlab coder was used to translate the source code into C language for effective embedding into the ATmega328 microcontroller.

In this paper, we explore human-centered interaction design aspects that determine the realisation and appreciation of musical works (installations, composition and performance), interfaces for sound design and musical expression, augmented instruments, sonic aspects of virtual environments and interactive audiovisual performances. In this first work, with the human at the centre of the design, we started sketching modes of interaction with sound that could result direct, engaging, natural and embodied in a collaborative, interactive, inclusive and diverse music environment. We define this as Human-Sound Interaction (HSI). To facilitate the exploration of HSIs, we prototyped SoundSculpt, a cross-modal audio, holographic projection and mid-air haptic feedback system. During an informal half-day workshop, we observed that HSIs through SoundSculpt have the potential to foster new ways of interaction with sound and to make them accessible to diverse musicians, sound artists and audience.

Audio feedback is a method that can provide rich, personal and detailed feedback that can convey more than the written word. This is particularly achieved through the capturing of the expressive quality of the speaker’s voice. Audio feedback has the potential to promote student engagement in the feedback process, as it is not associated with the negative connotations of written feedback. This chapter will draw upon the growing literature base and recent research. It will indicate how different approaches to using audio technology can enhance the learning experience and the feedback process through its personal and timely qualities. The chapter will conclude with guidelines for best practice for implementation of audio feedback.

This paper offers a survey of my musical collaboration (2010–2013) with Italian composer Agostino Di Scipio on Modes of Interference n.2 (2006), for audio feedback system with saxophone and live-electronics, and builds on my PhD research on participative musical performance on mixed music for saxophones. Di Scipio composes a network of interactions: he does not compose the sounding structure itself of the piece, but rather a set of possibilities for a performer to experiment in sound. All the elements of the piece (such as the live-electronics equipment, the saxophone, and the environment) are mutually connected and influence each other. They constitute a dynamical system, as implemented by the composer. The saxophone is not expected only to produce a variety of noise materials, but also to act both as a control device and as a filter inside an audio feedback loop. This systemic approach requires from the player a new attitude towards the instrument, as well as new manners of listening to and reacting to the sound events emerging in the performance.

Introductory programming is challenging for many students, requiring them to engage with a deep approach to learning concepts in order to succeed. These challenges compound for online students who do not have direct face-to-face interactions with teaching staff. With the growing demand for online education, we need to examine approaches that assist in building supportive learning environments for these students. A growing body of work from other education disciplines indicates that audio feedback provides an opportunity for developing stronger relationships with students. Further studies recommend an integrated implementation of audio recording into the virtual learning environment. To evaluate audio feedback for use in programming education, we developed an integrated, cross-browser audio feedback feature into the open-source Doubtfire learning management system. Doubtfire is used to support and scale a task-oriented teaching and learning system built upon the principles of constructive alignment and has been shown to help students engage with programming concepts in campus-only units. Our findings from experimental and observational activities indicate that programming tutors can use a blended approach of audio and text feedback via the learning management system to better support student learning. The blended approach provides more nuanced feedback, conveying personality and feelings of connectedness to students, while retaining the benefits of specificity for code-specific issues.

Assistive navigation systems for the blind commonly use speech to convey directions to their users. However, this is problematic for short range navigation systems that need to provide fine but diligent guidance in order to avoid obstacles. For this task, we have compared haptic and audio feedback systems under the NASA-TLX protocol to analyze the additional cognitive load that they place on users. Both systems are able to guide the users through a test obstacle course. However, for white cane users, auditory feedback results in a 22 times higher cognitive load than haptic feedback. This discrepancy in cognitive load was not found on blindfolded users, thus we argue against evaluating navigation systems solely with blindfolded users.

Indoor audio feedback is a common problem in many audio amplification systems. The audio feedback can be out of control in some indoor conditions, which results in howling. Also, the howling frequency is subject to variation by the changes of indoor environments. Most conventional methods attempt to eliminate the howling, but they do not provide a way to predict the occurrence of howling. This paper presents a novel method to predict the howling frequency using temporal variations in power spectrum.

This chapter aims to create a real-time object detection and audio output system for blind users using the YOLOv3 algorithm and a 360-degree camera sensor. The system is designed to detect a wide range of objects, including people, vehicles, and other objects in the environment, and provide audio feedback to the user. The system architecture consists of a 360-degree camera sensor, a processing unit, and an audio output system. The camera sensor captures the environment, which is processed by the processing unit, which uses the YOLOv3 algorithm to detect and classify objects. The audio output system provides audio feedback to the user based on the objects detected by the system. The project has significant importance for blind users as it can help them navigate their environment and recognize objects in real time and can serve as a foundation for future research in the field of object detection systems for blind users.

Simulation supports are intermediary objects that help in anticipating the behavior of production systems are important in designs that involve Ergonomics Work Analysis (EWA) method and Future Activity Analysis (FAA) approach. The objective is to describe the process of transformation design of a productive situation using three areas of study: Ergonomics, Simulation and Plant Layout Design. The focus is on the application of intermediary objects during the design process. This article involves a reflective practice of a single case study in which the activity-centered ergonomics approach was employed in the design of productive situations. The described case took place at a plastic film roll manufacturing plant. In this work were used the computational techniques and tools for the design of productive situations: Computer Aided Design, Digital Human Modeling and Simulation, Discrete Event Simulation and Game Engine. The use of these intermediary objects potentially reduces the time spent on design, makes better use of investment resources, contributes to an understanding of current and future capacity, and provides ergonomic improvements of the work situation for future users. The integration of different intermediate objects at the perspective of ergonomics, like digital human simulation, discrete event simulation and game engine can contribute to simulate future work in the design process.

In this paper we present results of a study where perception of dynamic audiotactile feedback to gesture input was examined. Our main motivation was to investigate how users' active input and different modality conditions effect the perception of the feedback. The experimental prototype in the study was a handheld sensor-actuator device that responds dynamically to user's hand movements creating an impression of a virtual texture. The feedback was designed so that the amplitude and frequency of texture were proportional to the overall angular velocity of the device. We used four different textures with different velocity responses. The feedback was presented to the user by the tactile actuator in the device, by audio through headphones, or by both. During the experiments, textures were switched in random intervals and the task of the user was to detect the changes while moving the device freely. The performances of the users with audio or audiotactile feedback were quite equal while tactile feedback alone yielded poorer performance. The texture design didn't influence the movement velocity or periodicity but tactile feedback induced most and audio feedback the least energetic motion. In addition, significantly better performance was achieved with slower motion. We also found that significant learning happened over time; detection accuracy increased significantly during and between the experiments. The masking noise used in tactile modality condition did not significantly influence the detection accuracy when compared to acoustic blocking but it increased the average detection time.

This paper describes a multidisciplinary method which permits, both the analysis of the usefulness of an assistive aid by a quantitative evaluation method as well as introducing a newly developed audio feedback system. A 3D recording system allowed one to provide a bio-feedback environment based on the audition to help the user during the learning period when using an arm robot. We present the quantitative evaluation method when using a Manus robot at home of the disabled people involved in this experimentation. The auditory biofeedback generates sounds with tone and intensity vary according to movements of the hand, or in the case of the robot end effector, according to the position of the target.

Previous clinical studies have reported that gait retraining is an effective non-invasive intervention for patients with medial compartment knee osteoarthritis. These gait retraining programs often target a reduction in the knee adduction moment (KAM), which is a commonly used surrogate marker to estimate the loading in the medial compartment of the tibiofemoral joint. However, conventional evaluation of KAM requires complex and costly equipment for motion capture and force measurement. Gait retraining programs, therefore, are usually confined to a laboratory environment. In this study, machine learning techniques were applied to estimate KAM during walking with data collected from two low-cost wearable sensors. When compared to the traditional laboratory-based measurement, our mobile solution using artificial neural network (ANN) and XGBoost achieved an excellent agreement with R2 of 0.956 and 0.947 respectively. With the implementation of a real-time audio feedback system, the present algorithm may provide a viable solution for gait retraining outside laboratory. Clinical treatment strategies can be developed using the continuous feedback provided by our system.

We discuss an experimental audio feedback system and method for positional guidance in real-time surgical instrument placement tasks. This system is intended for future usability testing in order to ascertain the efficacy of the use of the aural modality for assisting surgical placement tasks in the operating room. The method is based on translating spatial parameters of a surgical instrument or device, such as its position or velocity with respect to some coordinate system, into a set of audio feedback parameters along the coordinates of a generalised audio space. Error signals that correspond to deviations of the actual instrument trajectory from an optimal trajectory are transformed into a set of audio signals that indicate to the user whether correction is necessary. An experimental hardware platform was assembled using commercially available hardware. A system for 3-D modelling, surgical procedure planning, real-time instrument tracking and audio generation was developed. Prototype software algorithms for generating audio feedback as a function of instrument navigation were designed and implemented. The system is sufficient for future usability testing. This technology is still in an early stage of development, with formal usability and performance testing yet to be done. However, informal usability experiments in the course of the basic engineering process indicate the use of audio is a promising alternative to, or redundancy measure in support of visual display technology for intra-operative navigation.

The long‐standing debate around the processes involved in species assembly has generated a conceptual gradient from deterministic to stochastic postulates. Environment selects traits to determine the species that ultimately participate in realised assemblages. However, neutral ecological processes (e.g. random seed dispersal, demographic stochasticity) can also lead to species co‐occurrence in the community. Despite the current consensus that both filtering and unpredictable events drive the organisation of communities, little information is available regarding the actual contribution of each. We experimentally analysed the contributions of both functional filtering and stochasticity (i.e. lack of trait selection) to assembly processes at a fine spatial scale in a dryland gypsum annual plant‐dominated community by evaluating the effects of seed availability (natural soil seed banks vs. seed‐free soil) and main biotic filters (biocrusts vs. perennial tussocks) on realised assemblages. Species richness, cover, diversity and functional properties were measured based on major plant traits defining fundamental life strategies in assemblages during four consecutive years. Biotic scenarios decisively affected community features. Biocrusts substantially promoted richness and productivity, whereas perennial tussocks restrained assemblage complexity in their vicinity. However, other than some weak filtering effects on maximum plant height and leaf dry matter content, the experimental treatments did not clearly select for either functional or compositional patterns in the community during four consecutive annual assembly events, which matched an unusual spring rainy period. Synthesis . Stochastic processes linked to active secondary, horizontal seed movements may play a prominent role in driving local species assembly at a fine spatial scale. Dryland gypsum soil systems have been described as harsh environments that impose strong deterministic filtering effects during plant assembly. However, even in restrictive, environmentally unpredictable habitats, the weightings of deterministic versus stochastic processes can shift, making stochasticity an eventual force of species coexistence contributing to the maintenance of diversity in the regional pool. Importantly, our results suggest that environmental filters would operate not only through a spatial but also through an intensity hierarchy, in which the intensity of the local biotic filtering depends on that of the regional abiotic one.