Matthias Mielke

Design and evaluation of a smartphone application for non-speech sound awareness for people with hearing loss.

Auditory cues provide people with information about events outside of their field of view and can so help detecting potential hazards. People with severe hearing loss, i.e. hard of hearing, deafened, and deaf people, often cannot or can only partially benefit from auditory cues, which can lead to a lowered quality of life. Even though hearing aids are available, not everyone can benefit from them. To provide deaf people (i.e. deaf, deafened, and hard of hearing) with auditory cues from environmental sounds different assistive devices have been introduced, usually for use at home. A flexible and mobile assistive device basing on a smartphone is presented in this contribution. It detects and recognizes acoustic events by analysing the acoustic environment of the user. By using pattern recognition algorithms the user can define the sounds that should be recognised by the device. Warning sounds occurring in road traffic were chosen as demonstrator. Interviews were conducted with deaf people to evaluate the concept and to gain more insights into the user needs and expectations.

An assistive technology for hearing-impaired persons: Analysis, requirements and architecture

In this contribution, a concept of an assistive technology for hearing-impaired and deaf persons is presented. The concept applies pattern recognition algorithms and makes use of modern communication technology to analyze the acoustic environment around a user, identify critical acoustic signatures and give an alert to the user when an event of interest happened. A detailed analysis of the needs of deaf and hearing-impaired people has been performed. Requirements for an adequate assisting device have been derived from the results of the analysis, and have been turned into an architecture for its implementation that will be presented in this article. The presented concept is the basis for an assistive system which is now under development at the Institute of Microsystem Engineering at the University of Siegen.

A Pilot Study about the Smartwatch as Assistive Device for Deaf People

In the last years the smartphone became an important tool for deaf and hard of hearing people. Its no wonder that many different smartphone based assistive tools were introduced recently, among them tools for environmental sound awareness. Even though smartphones seem to be a good way to implement such tools, with the smartwatch a new class of mobile computing devices became available. In this paper results from interviews with six deaf people about the use of a smartwatch as environmental sound alert are presented. The interviews showed that a smartwatch based environmental sound alert is promising as the participants were highly interested in using such a device.

A decentralized charge management for electric vehicles using a genetic algorithm: Case study and proof-of-concept in Java and FPGA

Genetic algorithms are a common option to solve optimization problems. In this paper a decentralized approach to calculate a charging schedule for electric vehicles based on a genetic algorithm is presented. It is predicted, that the number of battery electric vehicles (BEV) and plug-in hybrid electric vehicles (PHEV) will increase to 5 million vehicles by the year of 2020. The increase of electric vehicles will have an impact on the existing power infrastructure, especially at specific times of day. Equipping all electric vehicles with a power controlling unit (PCU) in a so-called consumer grid, and connect the PCUs to each other, will allow to calculate an optimized schedule. This schedule ensures that all electric vehicles are charged and that a given maximum power peak will not be exceeded. First, the proposed approach was implemented in a Java program and its performance was evaluated for different scenarios. Afterwards, a VHDL (Very High Speed Integrated Circuit Hardware Description Language) implementation was created and verified by using simulation and FPGAs (Field Programmable Gate Array).

Design of innovative integrated circuits in education

Teaching practical ASIC design, one faces a lot of problems, such as high manufacturing costs, long workflow, and heterogeneous previous knowledge of the students. On one hand, it is difficult to find topics that motivate students and, at the same time, are not too complex. On the other hand, the industry requires students who are trained not only theoretically, but also have practical experience in team work and project management. We regard these problems as a challenge and are going to create a concept of a project-oriented ASIC design course that focuses on teaching hard and soft skills. In this paper, we describe our concept for a student project work, which leaves to the students a lot of degrees of freedom in the design process and offers the possibility to realize an own idea as integrated circuit.

A modular framework for efficient sound recognition using a smartphone

The identification of sounds is an important tool in ubiquitous and context aware applications. Todays smartphones are capable of performing even computational intensive tasks, like digital signal processing and pattern recognition. In this contribution an implementation scheme and a framework for sound recognition for smartphones are presented. A basic sound recognition flow consists of preprocessing, feature extraction, feature selection, classiication, and action trigger. A flow is not hard coded but described in a JSON file and build dynamically by the framework. The framework itself is implemented in Java for the Android operating system. But specific algorithms can be realized in Java, C(++), and Renderscript for execution on the CPU, or in Filterscript for execution on a GPU. An example flow is presented and benchmark results are shown for Java-, C-, and Filterscript-implementations of Mel Frequency Cepstral Coefficients (MFCC). Recommendations for technology selection are made.

Use of silicon photomultipliers for detection of Cherenkov light from Compton scattered electrons for medical imaging

Radioactive isotopes with energies up to 0.5 MeV are used in nuclear medicine for imaging. However several isotopes with energies up to 10 MeV exist that have interesting properties for medical applications, but conventional detectors are inefficient for these energies. A Compton camera setup, consisting of a radiator and an absorption layer, can be used to detect such high energy gamma radiation. In a Compton camera an incident gamma ray undergoes a Compton scattering in the radiator creating a high energetic Compton electron e. By determining the point of interaction and measuring the energy and the direction of the scattered gamma ray it is possible to confine the origin of the incident gamma ray to the surface of a cone. The greatest challenge lies in the coincident detection of electron and scattered gamma. Previous research proposed the use of Silicon Photomultipliers arrays (SiPM) to detect Cherenkov Light (CL) produced by e for determining es properties based on the directional properties of CL. Since only few photons of CL are produced, the high noise floor of the SiPM affects the detection negatively. In this contribution an estimation of SiPMs noise floor is presented, that bases on a behavioural simulation of noise processes in the SiPM. With the simulation it is possible to determine properties of the SiPM, to assess the effectiveness of filter and to build stimuli for other simulations.

A home automation based environmental sound alert for people experiencing hearing loss

Different assistive technologies are available for deaf people (i.e. deaf, deafened, and hard of hearing). Besides the well-known hearing aid, devices for detection of sound events that occur at home or at work (e.g. doorbell, telephone) are available. Despite the technological progress in the last years and resulting new possibilities, the basic functions and concepts of such devices have not changed. The user still needs special assistive technology that is bound to the home or work environment. In this contribution a new concept for awareness of events in buildings is presented. In contrast to state-of-the-art assistive devices, it makes use of modern Information and Communication and home automation technology, and thus offers the prospect of cheap implementation and higher comfort for the user. In this concept events are indicated by notifications that are send over a Bluetooth Low Energy mesh network from a source to the user. The notifications are received by the users smartwatch and the event is indicated by vibration and an icon representing its source.

AUDIS wear: A smartwatch based assistive device for ubiquitous awareness of environmental sounds

A multitude of assistive devices is available for deaf people (i.e. deaf, deafened, and hard of hearing). Besides hearing and communication aids, devices to access environmental sounds are available commercially. But the devices have two major drawbacks: 1. they are targeted at indoor environments (e.g. home or work), and 2. only specific events are supported (e.g. the doorbell or telephone). Recent research shows that important sounds can occur in all contexts and that the interests in sounds are diverse. These drawbacks can be tackled by using modern information and communication technology that enables the development of new and improved assistive devices. The smartwatch, a new computing platform in the form of a wristwatch, offers new potential for assistive technology. Its design promises a perfect integration into various different social contexts and thus blends perfectly into the users life. Based on a smartwatch and algorithms from pattern recognition, a prototype for awareness of environmental sounds is presented here. It observes the acoustic environment of the user and detects environmental sounds. A vibration is triggered when a sound is detected and the type of sound is shown on the display. The design of the prototype was discussed with deaf people in semi-structured interviews, leading to a set of implications for the design of such a device.

Best practices for time-management of student groups with heterogeneous effort

The daily work of an engineer in industry is affected by project work; often more than one project at a time. Consequently, time and self-management is an important part of the education of future engineers and scientists. Students of electrical engineering and computer science at the University of Siegen have a student project work in their curricula to deepen hard skills and to learn soft skills, like teamwork, organization and time-management. Often these groups consist of students with heterogeneous requirements in terms of working hours. In this contribution, the authors present a good practice for time-management of groups with heterogeneous working-time.