Smartphone Recordings Research Articles

Effects of cranial electrotherapy stimulation with novel in-ear electrodes on anxiety and resting-state brain activity: A randomized double-blind placebo-controlled trial

BackgroundCranial Electrotherapy Stimulation (CES) is a promising non-invasive brain stimulation technique with the potential to alleviate anxiety. We examined the effectiveness of home-based CES with novel, headphone-like, in-ear electrodes on anxiety-related symptoms and resting-state brain activity. MethodsThis study spanned 3-weeks, with randomized, double blind, and active-controlled design. Nonclinical volunteers experiencing daily anxiety were randomly assigned to either the active or the sham groups. CES provides an alternating current (10 Hz frequency, 500 μA intensity), connected to smartphone recording treatment logs. Participants treated themselves with 20 trials of CES at home. We evaluated the effectiveness using State-Trait Anxiety Inventory (STAI), Beck Depression Inventory (BDI), Wisconsin Card Sort Test (WCST), and resting-state electroencephalography (EEG). ResultsThe active group showed a significant improvement in state-anxiety compared to sham, while there was a statistical trend in the WCST-Category Completed (p = .061) and no change in depression. In EEG analysis, the active group showed significantly increased relative power for theta in the left frontal region compared with the sham, and this significantly correlated with the changes in state-anxiety. The active group exhibited significantly increased high-beta source activity in cuneus and middle occipital gyrus after intervention compared with the baseline. LimitationsThis study had a relatively short treatment period and small sample size. ConclusionsOur findings provide the first electrophysiological evidence for CES for novel in-ear electrodes to improve anxiety. The modulatory effects of CES on resting-state oscillations of EEG imply that CES could beneficially affect functional brain activity.

COVID-19 cough classification using machine learning and global smartphone recordings

We present a machine learning based COVID-19 cough classifier which can discriminate COVID-19 positive coughs from both COVID-19 negative and healthy coughs recorded on a smartphone. This type of screening is non-contact, easy to apply, and can reduce the workload in testing centres as well as limit transmission by recommending early self-isolation to those who have a cough suggestive of COVID-19. The datasets used in this study include subjects from all six continents and contain both forced and natural coughs, indicating that the approach is widely applicable. The publicly available Coswara dataset contains 92 COVID-19 positive and 1079 healthy subjects, while the second smaller dataset was collected mostly in South Africa and contains 18 COVID-19 positive and 26 COVID-19 negative subjects who have undergone a SARS-CoV laboratory test. Both datasets indicate that COVID-19 positive coughs are 15%–20% shorter than non-COVID coughs. Dataset skew was addressed by applying the synthetic minority oversampling technique (SMOTE). A leave-p-out cross-validation scheme was used to train and evaluate seven machine learning classifiers: logistic regression (LR), k-nearest neighbour (KNN), support vector machine (SVM), multilayer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM) and a residual-based neural network architecture (Resnet50). Our results show that although all classifiers were able to identify COVID-19 coughs, the best performance was exhibited by the Resnet50 classifier, which was best able to discriminate between the COVID-19 positive and the healthy coughs with an area under the ROC curve (AUC) of 0.98. An LSTM classifier was best able to discriminate between the COVID-19 positive and COVID-19 negative coughs, with an AUC of 0.94 after selecting the best 13 features from a sequential forward selection (SFS). Since this type of cough audio classification is cost-effective and easy to deploy, it is potentially a useful and viable means of non-contact COVID-19 screening.

TEACHER-STUDENT VERBAL INTERACTION PATTERN IN READING CLASSROOM SMP PARULIAN 2 MEDAN

TEACHER-STUDENT VERBAL INTERACTION PATTERN INREADING CLASSROOM SMP PARULIAN 2 MEDAN*Nurcahaya Sinaga** Dr. Siti Aisah Ginting M.Pd.** Farida Hanim Saragih, S.Pd., M.HumABSTRACTNurcahaya Sinaga. Registration Number: 2153321022. Teacher-StudentVerbal Interaction Pattern in Reading Classroom at SMP Parulian 2 Medan.A Thesis. English and Literature Department. Faculty of Languages andArts. State University of Medan, 2020.This research was intended to examine the verbal interaction features used by twoteachers in teaching reading comprehension through virtual classroom with zoomapplication. This virtual class was chosen since the offline classroom was changedinto online classroom during the covid 19 pandemic. This research was conductedto answer the research problems; 1. How are the teachers and the students verbalinteraction patterns used in reading classroom of SMP Parulian 2 Medan. 2 Whydo the teachers interact in the way they do? It covers the analysis on thetranscripts of teachers-student verbal interaction and the interview. The analysiscovers the steps of data condensation. In the process of data condensing, allrecorded utterances were selected to focus on the utterances used by the teachersand students during the virtual classroom. Then, the utterances were simplified inorder to be easier to understand. The abstracting process was done to focus on theintention of answering the research problems. The final step was transforming theutterances and interview into transcription. The design of this research is a casequalitative study. The subjects were two English teachers and twenty students ofParulian Junior High School. The data to answer the problems were transcripts ofverbal interaction used by the teachers and students and interview to find thereasons of the teachers to use certain patterns students during the virtualclassroom. The data were collected by using recording tools; smart phonerecording and observational notes. The findings show that the teachers’ verbalclassroom interaction did not cover all types of interactional features by Walsh.The verbal interactions through zoom virtual classroom by the first teacher consistof seven types of interactional features. They are Display questions (0,53%),Seeking clarification (0,21%), Extended wait-time (0,125%), Scaffolding(0,003%), Direct repair (0,003%), Confirmation checks (0,003%), Teacher echo(0,003%). While. The verbal interactions through zoom virtual classroom by thesecond teacher consist of seven types of interactional features. They are Display questions (0,29%), Scaffolding (0,023%), Extended wait-time (0,23%), Seekingclarification(0,12%), Confirmation checks (0,032%), Teacher interruptions(0,032%), Direct repair (0,016%), Content feedback ( 0,016%), Extended learnerturn (0,016%), Teacher echo (0,016 %). The most frequently used of interactionalfeature is display questions. The reason to use display questions is material focus.The teachers wanted the students to focus on the material.Keywords: Classroom Verbal Interaction, Pedagogical goal, ReadingClassroom.

Evaluating the Accuracy and Reliability of Bicycle GPS Devices

<div class="section abstract"><div class="htmlview paragraph">Every day in the United States, an average of approximately two cyclists die in bicycle accidents. Sometimes, forensic engineers are asked to reconstruct these accidents. These cyclists may use bicycle GPS devices to record important data, which they use to monitor their riding activities. By analyzing this data, many questions can be answered regarding various parameters such as speed, position, and riding behavior of the bicyclist.</div><div class="htmlview paragraph">The goal of this study was to analyze the accuracy of the GPS position and speed data. For this study, four different bicycle GPS devices (one of which was paired with a magnetometer Garmin Bicycle Speed Sensor), a GoPro camera equipped with GPS, and a smartphone recording to Strava, were mounted on a bicycle. The bicycle was ridden in an approximately straight line (back and forth), and then around a building, to measure positional and speed accuracy. Additionally, the bicycle was ridden in a straight line, then decelerated to a complete stop for varied durations, and then accelerated forward. This was done to see if the retrieved data showed the bicycle coming to a complete stop, or if the GPS averaged a few data points showing that the rider never came to a stop. Furthermore, the bicycle was stopped at a specific location for a certain duration and the GPS drift of each device was studied. </div><div class="htmlview paragraph">Using VBOX 3i RTK DGPS positional data as the reference, test data revealed that all six bicycle test devices had relative error in positional and speed data. The Garmin Edge 530 had an average speed error of 10.83% and positional error of 21.78 ft. The Garmin Edge 1000 (BSS) had an average speed error of 4.71% and positional error of 15.2 ft. The Lezyne Mega XL had an average speed error of 3.5% and positional error of 4.82 ft. The Wahoo ELEMNT Bolt had an average speed error of 3.53% and a positional error of 10.46 ft. The Strava app had a positional error of 11.45 ft. The GoPro Hero5 had an average speed error of 5.05% and a positional error of 4.79 ft.</div></div>

Using Crowd-Sourced Speech Data to Study Socially Constrained Variation in Nonmodal Phonation.

This study examines the status of nonmodal phonation (e.g. breathy and creaky voice) in British English using smartphone recordings from over 2,500 speakers. With this novel data collection method, it uncovers effects that have not been reported in past work, such as a relationship between speakers’ education and their production of nonmodal phonation. The results also confirm that previous findings on nonmodal phonation, including the greater use of creaky voice by male speakers than female speakers, extend to a much larger and more diverse sample than has been considered previously. This confirmation supports the validity of using crowd-sourced data for phonetic analyses. The acoustic correlates that were examined include fundamental frequency, H1*-H2*, cepstral peak prominence, and harmonic-to-noise ratio.

The diagnosis of respiratory disease in children using a phone-based cough and symptom analysis algorithm: The smartphone recordings of cough sounds 2 (SMARTCOUGH-C 2) trial design

The diagnosis of acute respiratory diseases in children can be challenging, and no single objective diagnostic test exists for common pediatric respiratory diseases. Previous research has demonstrated that ResAppDx, a cough sound and symptom-based analysis algorithm, can identify common respiratory diseases at the point of care. We present the study protocol for SMARTCOUGH-C 2, a prospective diagnostic accuracy trial of a cough and symptom-based algorithm in a cohort of children presenting with acute respiratory diseases. The objective of the study is to assess the performance characteristics of the ResAppDx algorithm in the diagnosis of common pediatric acute respiratory diseases.

Analysis of Smartphone Recordings in Time, Frequency, and Cepstral Domains to Classify Parkinson's Disease.

ObjectivesParkinson’s disease (PD) is the second most common neurodegenerative disorder; it affects more than 10 million people worldwide. Detecting PD usually requires a professional assessment by an expert, and investigation of the voice as a biomarker of the disease could be effective in speeding up the diagnostic process.MethodsWe present our methodology in which we distinguish PD patients from healthy controls (HC) using a large sample of 18,210 smartphone recordings. Those recordings were processed by an audio processing technique to create a final dataset of 80,594 instances and 138 features from the time, frequency, and cepstral domains. This dataset was preprocessed and normalized to create baseline machine-learning models using four classifiers, namely, linear support vector machine, K-nearest neighbor, random forest, and extreme gradient boosting (XGBoost). We divided our dataset into training and held-out test sets. Then we used stratified 5-fold cross-validation and four performance measures: accuracy, sensitivity, specificity, and F1-score to assess the performance of the models. We applied two feature selection methods, analysis of variance (ANOVA) and least absolute shrinkage and selection operator (LASSO), to reduce the dimensionality of the dataset by selecting the best subset of features that maximizes the performance of the classifiers.ResultsLASSO outperformed ANOVA with almost the same number of features. With 33 features, XGBoost achieved a maximum accuracy of 95.31% on training data, and 95.78% by predicting unseen data.ConclusionsDeveloping a smartphone-based system that implements machine-learning techniques is an effective way to diagnose PD using the voice as a biomarker.

Linguistic fieldwork in a pandemic: Supervised data collection combining smartphone recordings and videoconferencing

Abstract Linguistic data collection typically involves conducting interviews with participants in close proximity. The safety precautions related to the COVID-19 pandemic brought such data collection to an abrupt halt: Social distancing forced linguistic fieldwork into involuntary hibernation in many parts of the world. Such hardship, however, can inspire innovation. In this contribution, we present an approach that – we believe – enables a reliable switch from in-person, face-to-face interviews to virtual, online data collection. In this approach, participants remain at home and navigate a smartphone application, enabling high-quality audio recordings and multisensory presentation of linguistic material, while they are being supervised via videoconferencing (Zoom 2020https://zoom.us/ (accessed 11 August 2020)). The smartphone app and the infrastructure presented are open source, accessible, and adaptable to researchers’ specific needs. To explore whether participants’ experiences of in-person data collection are different from participation in a virtual setting, we conducted a study with 36 participants. Overall, findings revealed a substantial degree of overlap in interview experience, setting a methodological baseline for future work. We end this contribution by discussing the benefits and pitfalls of this new approach.

Abstract PO-011: CiRCL: A psychosocial program facilitating communication and care to patients, families, and frontline health care teams during COVID-19

Abstract The need for strict social distancing measures preventing visitors on inpatient oncology, ICU, and COVID units during the COVID-19 pandemic has had the unintended consequence of leading to significant psychological and spiritual distress for patients and families and “moral distress” for frontline health care teams tasked with supporting patients who are suffering or dying alone without the support of their loved ones. The trauma of these deaths is sometimes further compounded for families by their inability to provide the final rituals of patients’ faith communities in their last moments, leading to complicated and ongoing grief after the loss. To address these complex psychosocial needs among COVID-19 and advanced cancer oncology patients, and the health care teams caring for them, the Simms/Mann UCLA Center for Integrative Oncology, in collaboration with colleagues at the UCLA Anderson School of Business and a team of diverse faith leaders, developed an innovative digitally mediated program for connection, communication, and care. This program, CiRCL (Caring in Remote Communities of Love), leveraged ZOOM and smartphone recording technology to accomplish the following goals: 1) provide psychological support to family members and friends to facilitate the recording of meaningful personal messages to the patient, including curated playlists of evocative songs from the patient’s life to be played at the bedside; 2) facilitate more meaningful communication between loved ones and frontline workers, including messages of gratitude and support to reduce feelings of isolation and moral distress for frontline workers; and 3) create a liturgical library of recorded ecumenical and faith-based blessings from various traditions, available during illness and at time of dying. Blessings include and encompass the health care teams as well as patients. This program, recently developed and being piloted at UCLA, is intended to extend compassion to all within the health care system during the unique challenges of COVID-19 and, by facilitating connection and support among patients, families, and frontline teams, extend the definition of healing and mitigate the impact of loss and grief for all during the many phases of this pandemic. Citation Format: Kauser Ahmed, Peter Phung, Noah Goldstein, John Glaspy. CiRCL: A psychosocial program facilitating communication and care to patients, families, and frontline health care teams during COVID-19 [abstract]. In: Proceedings of the AACR Virtual Meeting: COVID-19 and Cancer; 2020 Jul 20-22. Philadelphia (PA): AACR; Clin Cancer Res 2020;26(18_Suppl):Abstract nr PO-011.

CONVOLUTIONAL RECURRENT NEURAL NETWORK BASED DIRECTION OF ARRIVAL ESTIMATION METHOD USING TWO MICROPHONES FOR HEARING STUDIES.

This work proposes a convolutional recurrent neural network (CRNN) based direction of arrival (DOA) angle estimation method, implemented on the Android smartphone for hearing aid applications. The proposed app provides a 'visual' indication of the direction of a talker on the screen of Android smartphones for improving the hearing of people with hearing disorders. We use real and imaginary parts of short-time Fourier transform (STFT) as a feature set for the proposed CRNN architecture for DOA angle estimation. Real smartphone recordings are utilized for assessing performance of the proposed method. The accuracy of the proposed method reaches 87.33% for unseen (untrained) environments. This work also presents real-time inference of the proposed method, which is done on an Android smartphone using only its two built-in microphones and no additional component or external hardware. The real-time implementation also proves the generalization and robustness of the proposed CRNN based model.

Point-of-care semen analysis of patients with infertility via smartphone and colorimetric paper-based diagnostic device.

Male infertility affects millions of males worldwide and is rising in prevalence due to social and environmental conditions. However, men often feel too embarrassed to receive a semen analysis in the hospital due to social stigmas. To overcome this problem, we developed a 3‐(4,5‐Dimethyl‐2‐thiazolyl)‐2,5‐diphenyl‐2H‐tetrazolium bromide test strip to distinguish semen samples with low total motile sperm concentration from those with normal motile sperm concentration. This is a point‐of‐care colorimetric semen analytical method with a one‐step, inexpensive, equipment‐free evaluation process, and adequate accuracy validated in a 42‐sample clinical trial. In this study, results were evaluated visually and with a smartphone application. Using visual observation methods, the area under the curve (AUC) was 0.71 (95% of confidence interval = 0.55–0.86; p = 0.021), sensitivity was 41%, specificity was 95%, positive predictive value was 90%, negative predictive value (NPV) was 59.4%, and accuracy was 67%. Using a smartphone recording and analytical system, AUC was 0.766 (95% of confidence interval = 0.612–0.92; p = 0.003), sensitivity was 96%, specificity was 65%, PPV was 75%, NPV was 92.9%, and accuracy was 80.9%. This work demonstrated a screening tool that could elevate semen analysis to the level of routine healthcare and provide for private, in‐home self‐assessment.

Pilot study of the influence of self-coding on empathy within an introductory motivational interviewing training

BackgroundMotivational interviewing (MI) is a framework for addressing behavior change that is often used by healthcare professionals. Expression of empathy during MI is associated with positive client outcomes, while absence of empathy may produce iatrogenic effects. Although training in MI is linked to increased therapeutic empathy in learners, no research has investigated individual training components’ contribution to this increase. The objective of this study was to test whether a self-coding MI exercise using smartphones completed at hour 6 of an 8-h MI training was superior in engendering empathy to training as usual (watching an MI expert perform in a video clip for the same duration at the same point in the training).MethodsThis was a pilot study at two sites using randomization and control groups with 1:1 allocation. Allocation was achieved via computerized assignment (site 1, United Kingdom) or facedown playing card distribution (site 2, United States). Participants were 58 students attending a university class at one of two universities, of which an 8-h segment was dedicated to a standardized MI training. Fifty-five students consented to participate and were randomized. The intervention was an MI self-coding exercise using smartphone recording and a standardized scoring sheet. Students were encouraged to reflect on areas of potential improvement based on their self-coding results. The main outcome measure was score on the Helpful Responses Questionnaire, a measure of therapeutic empathy, collected prior to and immediately following the 8-h training. Questionnaire coding was completed by 2 blinded external reviewers and assessed for interrater reliability, and students were assigned averaged empathy scores from 6 to 30. Analyses were conducted via repeated-measures ANOVA using the general linear model.ResultsFifty-five students were randomized, and 2 were subsequently excluded from analysis at site 2 due to incomplete questionnaires. The study itself was feasible, and overall therapeutic empathy increased significantly and substantially among students. However, the intervention was not superior to the control condition in this study.ConclusionsReplacing a single passive learning exercise with an active learning exercise in an MI training did not result in a substantive boost to therapeutic empathy. However, consistently with prior research, this study identified significant overall increases in empathy following introductory MI training. A much larger study examining the impact of selected exercises and approaches would likely be useful and informative.

Smartphone Screen Recording Apps: An Effective Tool to Enhance Fluency in the English Language

This investigation intended to assess the effectiveness of smartphone video recording applications in increasing the speaking fluency of students of English as a foreign language (EFL). The study was conducted on a group of thirty-one 7th grade students aged between 12 and 13 years and enrolled in a subsidised school in Chile. The convenience sampling method was employed to select the participating students and the participants’ manner of communication was analysed through several English speaking sessions in which they used their smartphone video recording applications. Data collection was undertaken through pre- and post-speaking tasks used in this action research. The collected data were examined using a specific analytic rubric and a focus group interview. Data analysis was accomplished via two techniques: a simple percentage analysis and a thematic examination. The findings revealed an increase in the speaking fluency of the participating students, specifically with regard to the ‘pace’ criterion identified in the analytic rubric used to assess improvement in the speaking performance of students as evidenced by video recordings. Also, the results of the focus group interview conducted with the students evidenced the participants’ positive response to the use of smartphone recording video applications in ameliorating their English communication fluency.

Natural Language Processing Methods for Acoustic and Landmark Event-Based Features in Speech-Based Depression Detection

The processing of speech as an explicit sequence of events is common in automatic speech recognition (linguistic events), but has received relatively little attention in paralinguistic speech classification despite its potential for characterizing broad acoustic event sequences. This paper proposes a framework for analyzing speech as a sequence of acoustic events, and investigates its application to depression detection. In this framework, acoustic space regions are tokenized to ‘words’ representing speech events at fixed or irregular intervals. This tokenization allows the exploitation of acoustic word features using proven natural language processing methods. A key advantage of this framework is its ability to accommodate heterogeneous event types: herein we combine acoustic words and speech landmarks, which are articulation-related speech events. Another advantage is the option to fuse such heterogeneous events at various levels, including the embedding level. Evaluation of the proposed framework on both controlled laboratory-grade supervised audio recordings as well as unsupervised self-administered smartphone recordings highlight the merits of the proposed framework across both datasets, with the proposed landmark-dependent acoustic words achieving improvements in F1(depressed) of up to 15% and 13% for SH2-FS and DAIC-WOZ respectively, relative to acoustic speech baseline approaches.

Phone Sensor Data in the Mathematics Classroom

Recently, a new source of data with great potential for use in the mathematics classroom has become available. The smartphones in our pockets are packed with sensors. Most phones have at a minimum global positioning, accelerometer, magnetometer, and gyroscope sensors. We give an example of the collection and analysis of global positioning sensor (GPS) data. Specifically, we find the fastest mile in a smartphone recording of an ordinary jogging workout. All of the analysis is done with the free Jupyter/Python computing environment. This example can be used by an instructor knowledgeable in the use of Jupyter/Python to scaffold a GPS project for students in a laboratory calculus classroom. More broadly, via this example, we provide a framework for instructors to incorporate these kinds of easily accessible data projects into the mathematics classroom. We also encourage the collaborative development of other phone sensor projects via a github repository.

Predicting motor, cognitive & functional impairment in Parkinson's.

ObjectiveWe recently demonstrated that 998 features derived from a simple 7‐minute smartphone test could distinguish between controls, people with Parkinson's and people with idiopathic Rapid Eye Movement sleep behavior disorder, with mean sensitivity/specificity values of 84.6‐91.9%. Here, we investigate whether the same smartphone features can be used to predict future clinically relevant outcomes in early Parkinson's.MethodsA total of 237 participants with Parkinson's (mean (SD) disease duration 3.5 (2.2) years) in the Oxford Discovery cohort performed smartphone tests in clinic and at home. Each test assessed voice, balance, gait, reaction time, dexterity, rest, and postural tremor. In addition, standard motor, cognitive and functional assessments and questionnaires were administered in clinic. Machine learning algorithms were trained to predict the onset of clinical outcomes provided at the next 18‐month follow‐up visit using baseline smartphone recordings alone. The accuracy of model predictions was assessed using 10‐fold and subject‐wise cross validation schemes.ResultsBaseline smartphone tests predicted the new onset of falls, freezing, postural instability, cognitive impairment, and functional impairment at 18 months. For all outcome predictions AUC values were greater than 0.90 for 10‐fold cross validation using all smartphone features. Using only the 30 most salient features, AUC values greater than 0.75 were obtained.InterpretationWe demonstrate the ability to predict key future clinical outcomes using a simple smartphone test. This work has the potential to introduce individualized predictions to routine care, helping to target interventions to those most likely to benefit, with the aim of improving their outcome.

Public exposure to ultrasound and very high-frequency sound in air.

Recent work showing the presence of a new generation of ultrasound (US) sources in public places has reopened the debate about whether there are adverse effects of US on humans, and has identified weaknesses in standards and exposure guidelines. Systems that rely on very high-frequency sound (VHFS) and US include public-address voice-alarm (PAVA) systems (whose operational status is often monitored using tones at ∼20 kHz) and pest deterrents. In this study, sound pressure levels (SPLs) produced by 16 sources that were either publically available or installed in busy public spaces were measured. These sources were identified through a citizen science project, wherein members of the public were asked to provide smartphone recordings of VHFS/US sources. With measurements made in realistic listening positions, pest deterrents were found that produced levels of up to 100 dB SPL at ∼20 kHz, and a hand dryer was found to produce 84 dB SPL at 40 kHz. PAVA systems were found to emit lower levels of up to 76 dB SPL at ∼20 kHz. Pest deterrents measured breach recommended safe listening limits for public exposure for people who are nearby even for relatively short periods.

Smartphone motor testing to distinguish idiopathic REM sleep behavior disorder, controls, and PD.

ObjectiveWe sought to identify motor features that would allow the delineation of individuals with sleep study-confirmed idiopathic REM sleep behavior disorder (iRBD) from controls and Parkinson disease (PD) using a customized smartphone application.MethodsA total of 334 PD, 104 iRBD, and 84 control participants performed 7 tasks to evaluate voice, balance, gait, finger tapping, reaction time, rest tremor, and postural tremor. Smartphone recordings were collected both in clinic and at home under noncontrolled conditions over several days. All participants underwent detailed parallel in-clinic assessments. Using only the smartphone sensor recordings, we sought to (1) discriminate whether the participant had iRBD or PD and (2) identify which of the above 7 motor tasks were most salient in distinguishing groups.ResultsStatistically significant differences based on these 7 tasks were observed between the 3 groups. For the 3 pairwise discriminatory comparisons, (1) controls vs iRBD, (2) controls vs PD, and (3) iRBD vs PD, the mean sensitivity and specificity values ranged from 84.6% to 91.9%. Postural tremor, rest tremor, and voice were the most discriminatory tasks overall, whereas the reaction time was least discriminatory.ConclusionsProdromal forms of PD include the sleep disorder iRBD, where subtle motor impairment can be detected using clinician-based rating scales (e.g., Unified Parkinson's Disease Rating Scale), which may lack the sensitivity to detect and track granular change. Consumer grade smartphones can be used to accurately separate not only iRBD from controls but also iRBD from PD participants, providing a growing consensus for the utility of digital biomarkers in early and prodromal PD.

Legal Responses to Non-Consensual Smartphone Recordings in the Context of Domestic and Family Violence

The increasingly ubiquitous use of smartphones is further complicating the legal response to domestic and family violence (‘DFV’). Perpetrators can now use smartphone recording facilities to record private conversations and activities of their (ex-)partners. Such behaviour may be a criminal offence of breach of a domestic and family violence protection order or stalking. On the other hand, those who have experienced DFV can record perpetrators and use the recordings in legal proceedings. The use of non-consensual smartphone recordings as evidence in DFV related cases is increasing and courts must determine when recordings are admissible. A key factor in making such determinations is whether the recording contravenes state-based criminal laws and listening and surveillance devices law. Drawing on reported experiences of the use of smartphone recordings in the context of DFV we show why further consideration and legal reform is needed if the law is to keep pace with this issue.

Estimating Parameters of Nonlinear Systems Using the Elitist Particle Filter Based on Evolutionary Strategies

In this paper, we present the elitist particle filter based on evolutionary strategies EPFES as an efficient approach to estimate the statistics of a latent state vector capturing the relevant information of a nonlinear system. Similar to classical particle filtering, the EPFES consists of a set of particles and respective weights which represent different realizations of the latent state vector and their likelihood of being the solution of the optimization problem. As main innovation, the EPFES includes an evolutionary elitist-particle selection scheme which combines long-term information with instantaneous sampling from an approximated continuous posterior distribution. In this paper, we propose two advancements of the previously published elitist-particle selection process. Further, the EPFES is shown to be a generalization of the widely-used Gaussian particle filter and thus evaluated with respect to the latter: First, we consider the univariate nonstationary growth model with time-variant latent state variable to evaluate the tracking capabilities of the EPFES for instantaneously calculated particle weights. This is followed by addressing the problem of single-channel nonlinear acoustic echo cancellation as a challenging benchmark task for identifying an unknown system of large search space: the nonlinear acoustic echo path is modeled by a cascade of a parameterized preprocessor to model the loudspeaker signal distortions and a linear FIR filter to model the sound wave propagation and the microphone. By using long-term information, we highlight the efficacy of the well-generalizing EPFES in estimating the preprocessor parameters for a simulated scenario and a real smartphone recording. Finally, we illustrate similarities between the EPFES and evolutionary algorithms to outline future improvements by fusing the achievements of both fields of research.