Search

This work aims to explore the utility of wearable inertial measurement units (IMUs) for quantifying movement in Romberg tests and investigate the extent of movement in adults with vestibular hypofunction (VH). A cross-sectional study was conducted at an academic tertiary medical center between March 2021 and April 2022. Adults diagnosed with unilateral vestibular hypofunction (UVH) or bilateral vestibular hypofunction (BVH) were enrolled in the VH group. Healthy controls (HCs) were recruited from community or outpatient clinics. The IMU-based instrumented Romberg and tandem Romberg tests on the floor were applied to both groups. The primary outcomes were kinematic body metrics (maximum acceleration [ACC], mean ACC, root mean square [RMS] of ACC, and mean sway velocity [MV]) along the medio-lateral (ML), cranio-caudal (CC), and antero-posterior (AP) axes. A total of 31 VH participants (mean age, 33.48 [SD 7.68] years; 19 [61%] female) and 31 HCs (mean age, 30.65 [SD 5.89] years; 18 [58%] female) were recruited. During the eyes-closed portion of the Romberg test, VH participants demonstrated significantly higher maximum ACC and increased RMS of ACC in head movement, as well as higher maximum ACC in pelvic movement along the ML axis. In the same test condition, individuals with BVH exhibited notably higher maximum ACC and RMS of ACC along the ML axis in head and pelvic movements compared with HCs. Additionally, BVH participants exhibited markedly increased maximum ACC along the ML axis in head movement during the eyes-open portion of the tandem Romberg test. Conversely, no significant differences were found between UVH participants and HCs in the assessed parameters. The instrumented Romberg and tandem Romberg tests characterized the kinematic differences in head, pelvis, and ankle movement between VH and healthy adults. The findings suggest that these kinematic body metrics can be useful for screening BVH and can provide goals for vestibular rehabilitation.

Objective: Leveraging patient data through machine learning techniques in disease care offers a multitude of substantial benefits. Nonetheless, the inherent nature of patient data poses several challenges. Prevalent cases amass substantial longitudinal data owing to their patient volume and consistent follow-ups, however, longitudinal laboratory data are renowned for their irregularity, temporality, absenteeism, and sparsity; In contrast, recruitment for rare or specific cases is often constrained due to their limited patient size and episodic observations. This study employed self-supervised learning (SSL) to pretrain a generalized laboratory progress (GLP) model that captures the overall progression of six common laboratory markers in prevalent cardiovascular cases, with the intention of transferring this knowledge to aid in the detection of specific cardiovascular event. Methods and procedures: GLP implemented a two-stage training approach, leveraging the information embedded within interpolated data and amplify the performance of SSL. After GLP pretraining, it is transferred for target vessel revascularization (TVR) detection. Results: The proposed two-stage training improved the performance of pure SSL, and the transferability of GLP exhibited distinctiveness. After GLP processing, the classification exhibited a notable enhancement, with averaged accuracy rising from 0.63 to 0.90. All evaluated metrics demonstrated substantial superiority ( ${p} < 0.01$ ) compared to prior GLP processing. Conclusion: Our study effectively engages in translational engineering by transferring patient progression of cardiovascular laboratory parameters from one patient group to another, transcending the limitations of data availability. The transferability of disease progression optimized the strategies of examinations and treatments, and improves patient prognosis while using commonly available laboratory parameters. The potential for expanding this approach to encompass other diseases holds great promise. Clinical impact: Our study effectively transposes patient progression from one cohort to another, surpassing the constraints of episodic observation. The transferability of disease progression contributed to cardiovascular event assessment.

Objective: To investigate the feasibility and accuracy of artificial intelligence (AI) methods of facial deidentification in hospital-recorded epileptic seizure videos, for improved patient privacy protection while preserving clinically important features of seizure semiology. Patients and Methods: Videos of epileptic seizures displaying seizure-related involuntary facial changes were selected from recordings at Taipei Veterans General Hospital Epilepsy Unit (between August 1, 2020 and February 28, 2023), and a single representative video frame was prepared per seizure. We tested 3 AI transformation models: (1) morphing the original facial image with a different male face; (2) substitution with a female face; and (3) cartoonization. Facial deidentification and preservation of clinically relevant facial detail were calculated based on: (1) scoring by 5 independent expert clinicians and (2) objective computation. Results: According to the clinician scoring of 26 facial frames in 16 patients, the best compromise between deidentification and preservation of facial semiology was the cartoonization model. A male facial morphing model was superior to the cartoonization model for deidentification, but clinical detail was sacrificed. Objective similarity testing of video data reported deidentification scores in agreement with the clinicians’ scores; however, preservation of semiology gave mixed results likely due to inadequate existing comparative databases. Conclusion: Artificial intelligence-based face transformation of medical seizure videos is feasible and may be useful for patient privacy protection. In our study, the cartoonization approach provided the best compromise between deidentification and preservation of seizure semiology.

Abstract Electroencephalography (EEG) measures changes in neuronal activity and can reveal significant changes from infancy to adulthood concomitant with brain maturation, making it a potential physiological marker of brain maturation and cognition. To investigate a promising deep learning tool for EEG classification, we applied the bidirectional long short-term memory (BLSTM) algorithm to analyze EEG data from the pediatric EEG laboratory of Taipei Tzu Chi Hospital. The trained BLSTM model was 86% accurate when identifying EEGs from young children (8 months–6 years) and adolescents (12–20 years). However, there was only a modest classification accuracy (69.3%) when categorizing EEG samples into three age groups (8 months–6 years, 6–12 years, and 12–20 years). For EEG samples from patients with intellectual disability, the prediction accuracy of the trained BLSTM model was 46.4%, which was significantly lower than its accuracy for EEGs from neurotypical patients, indicating that the individual’s intelligence plays a major role in the age prediction. This study confirmed that scalp EEG can reflect brain maturation and the BLSTM algorithm is a feasible deep learning tool for the identification of cognitive age. The trained model can potentially be applied to clinical services as a supportive measurement of neurodevelopmental status.

Objective: Improving geographical access remains a key issue in determining the sufficiency of regional medical resources during health policy design. However, patient choices can be the result of the complex interactivity of various factors. The aim of this study is to propose a deep neural network approach to model the complex decision of patient choice in travel distance to access care, which is an important indicator for policymaking in allocating resources. Method: We used the 4-year nationwide insurance data of Taiwan and accumulated the possible features discussed in earlier literature. This study proposes the use of a convolutional neural network (CNN)-based framework to make predictions. The model performance was tested against other machine learning methods. The proposed framework was further interpreted using Integrated Gradients (IG) to analyze the feature weights. Results: We successfully demonstrated the effectiveness of using a CNN-based framework to predict the travel distance of patients, achieving an accuracy of 0.968, AUC of 0.969, sensitivity of 0.960, and specificity of 0.989. The CNN-based framework outperformed all other methods. In this research, the IG weights are potentially explainable; however, the relationship does not correspond to known indicators in public health. Conclusions: Our results demonstrate the feasibility of the deep learning-based travel distance prediction model. It has the potential to guide policymaking in resource allocation. Clinical and Translational Impact Statement— Deep learning technology is feasible in investigating the distance that patients would travel while accessing care. It is a tool that integrates complex interactive variables with highly imbalanced data distributions.

Goal: Numerous studies had successfully differentiated normal and abnormal voice samples. Nevertheless, further classification had rarely been attempted. This study proposes a novel approach, using continuous Mandarin speech instead of a single vowel, to classify four common voice disorders (i.e. functional dysphonia, neoplasm, phonotrauma, and vocal palsy). Methods: In the proposed framework, acoustic signals are transformed into mel-frequency cepstral coefficients, and a bi-directional long-short term memory network (BiLSTM) is adopted to model the sequential features. The experiments were conducted on a large-scale database, wherein 1,045 continuous speech were collected by the speech clinic of a hospital from 2012 to 2019. Results: Experimental results demonstrated that the proposed framework yields significant accuracy and unweighted average recall improvements of 78.12–89.27% and 50.92–80.68%, respectively, compared with systems that use a single vowel. Conclusions: The results are consistent with other machine learning algorithms, including gated recurrent units, random forest, deep neural networks, and LSTM.The sensitivities for each disorder were also analyzed, and the model capabilities were visualized via principal component analysis. An alternative experiment based on a balanced dataset again confirms the advantages of using continuous speech for learning voice disorders.

This study presents a deep learning-based speech signal-processing mobile application known as CITISEN. The CITISEN can perform three functions: speech enhancement (SE), model adaptation (MA), and background noise conversion (BNC), which allow CITISEN to be used as a platform for utilizing and evaluating SE models and flexibly extend the models to address various noise environments and users. For SE, CITISEN downloads pretrained SE models on the cloud server and then uses these models to effectively reduce noise components from prerecordings or instant recordings provided by users. When it encounters noisy speech signals with unknown speakers or noise types, the MA function allows CITISEN to improve the SE performance effectively. A few audio files of unseen speakers or noise types are recorded and uploaded to the cloud server and then used to adapt the pretrained SE model. Finally, for BNC, CITISEN removes the original background noise using an SE model and then mixes the processed speech signal with new background noise. The novel BNC function can evaluate SE performance under specific conditions, cover people’s tracks, and provide entertainment. The experimental results confirmed the effectiveness of SE, MA, and BNC functions. Compared with the noisy speech signals, the enhanced speech signals by SE achieved about 6% and 33% of improvements, respectively, in terms of short-time objective intelligibility (STOI) and perceptual evaluation of speech quality (PESQ). With MA, the STOI and PESQ could be further improved by approximately 6% and 11%, respectively. Note that the SE model and MA method are not limited to the ones described in this study and can be replaced with any SE model and MA method. Finally, the BNC experiment results indicated that the speech signals of original and converted backgrounds have a close scene identification accuracy and similar embeddings in an acoustic scene classification model. Therefore, the proposed BNC can effectively convert the background noise of a speech signal and be a data augmentation method when clean speech signals are unavailable.

Objective: With the rapid growth of high-speed deep-tissue imaging in biomedical research, there is an urgent need to develop a robust and effective denoising method to retain morphological features for further texture analysis and segmentation. Conventional denoising filters and models can easily suppress the perturbative noise in high-contrast images; however, for low photon budget multiphoton images, a high detector gain will not only boost the signals but also bring significant background noise. In such a stochastic resonance imaging regime, subthreshold signals may be detectable with the help of noise, meaning that a denoising filter capable of removing noise without sacrificing important cellular features, such as cell boundaries, is desirable. Method: We propose a convolutional neural network-based denoising autoencoder method — a fully convolutional deep denoising autoencoder (DDAE) — to improve the quality of three-photon fluorescence (3PF) and third-harmonic generation (THG) microscopy images. Results: The average of 200 acquired images of a given location served as the low-noise answer for the DDAE training. Compared with other conventional denoising methods, our DDAE model shows a better signal-to-noise ratio (28.86 and 21.66 for 3PF and THG, respectively), structural similarity (0.89 and 0.70 for 3PF and THG, respectively), and preservation of the nuclear or cellular boundaries (F1-score of 0.662 and 0.736 for 3PF and THG, respectively). It shows that DDAE is a better trade-off approach between structural similarity and preserving signal regions. Conclusions: The results of this study validate the effectiveness of the DDAE system in boundary-preserved image denoising. Clinical Impact: The proposed deep denoising system can enhance the quality of microscopic images and effectively support clinical evaluation and assessment.

This study investigated brain activation during auditory processing as a biomarker for the prediction of future perceptual learning performance. Cochlear implant simulated sounds (vocoded sounds) are degraded signals. Participants with normal hearing who were trained with these ambiguous sounds showed varied speech comprehension levels. We discovered that the neuronal signatures from untrained participants forecasted their future ambiguous speech comprehension levels. Participants’ brain activations for auditory information processing were measured before (t1) they underwent a five-day vocoded sounds training session. We showed that the pre-training (t1) activities in the inferior frontal gyrus (IFG) correlate with the fifth-day (t2) vocoded sound comprehension performance. To further predict participants' future (t2) performances, we split the participants into two groups (i.e., good and bad learners) based on their fifth-day performance; a linear support vector machine (SVM) was trained to classify (predict) the remaining participants’ groups. We found that pre-training (t1) fMRI activities in the bilateral IFG, angular gyrus (AG), and supramarginal gyrus (SMG) showed discriminability between future (t2) good and bad learners. These findings suggest that neural correlates of individual differences in auditory processing can potentially be used to predict participants’ future cognition and behaviors.

Abstract Recognizing specific heart sound patterns is important for the diagnosis of structural heart diseases. However, the correct recognition of heart murmur depends largely on clinical experience. Accurately identifying abnormal heart sound patterns is challenging for young and inexperienced clinicians. This study is aimed at the development of a novel algorithm that can automatically recognize systolic murmurs in patients with ventricular septal defects (VSDs). Heart sounds from 51 subjects with VSDs and 25 subjects without a significant heart malformation were obtained in this study. Subsequently, the soundtracks were divided into different training and testing sets to establish the recognition system and evaluate the performance. The automatic murmur recognition system was based on a novel temporal attentive pooling-convolutional recurrent neural network (TAP-CRNN) model. On analyzing the performance using the test data that comprised 178 VSD heart sounds and 60 normal heart sounds, a sensitivity rate of 96.0% was obtained along with a specificity of 96.7%. When analyzing the heart sounds recorded in the second aortic and tricuspid areas, both the sensitivity and specificity were 100%. We demonstrated that the proposed TAP-CRNN system can accurately recognize the systolic murmurs of VSD patients, showing promising potential for the development of software for classifying the heart murmurs of several other structural heart diseases.

Abstract A comprehensive assessment of ecosystem dynamics requires the monitoring of biological, physical and social changes. Changes that cannot be observed visually may be trackable acoustically through soundscape analysis. Soundscapes vary greatly depending on geophysical events, biodiversity and human activities. However, retrieving source‐specific information from geophony, biophony and anthropophony remains a challenging task, due to interference by simultaneous sound sources. Audio source separation is a technique that aims to recover individual sound sources when only mixtures are accessible. Here, we review techniques of monoaural audio source separation with the fundamental theories and assumptions behind them. Depending on the availability of prior information about the source signals, the task can be approached as a blind source separation or a model‐based source separation. Most blind source separation techniques depend on assumptions about the behaviour of the source signals, and their performance may deteriorate when the assumptions fail. Model‐based techniques generally do not require specific assumptions, and the models are directly learned from labelled data. With the recent advances of deep learning, the model‐based techniques can yield state‐of‐the‐art separation performance, accordingly facilitate content‐based audio information retrieval. Source separation techniques have been adopted in several ecoacoustic applications to evaluate the contributions from biodiversity and anthropogenic disturbance to soundscape dynamics. They can also be employed as nonlinear filters to improve the recognition of bioacoustic signals. To effectively retrieve ecological information from soundscapes, source separation is a crucial tool. We believe that the future integrations of ecological hypotheses and deep learning can realize a high‐performance source separation for ecoacoustics, and accordingly improve soundscape‐based ecosystem monitoring. Therefore, we outline a roadmap for applying source separation to assist in soundscape information retrieval and hope to promote cross‐disciplinary collaboration.

IPIN 2019 Competition, sixth in a series of IPIN competitions, was held at the CNR Research Area of Pisa (IT), integrated into the program of the IPIN 2019 Conference. It included two on-site real-time Tracks and three off-site Tracks. The four Tracks presented in this paper were set in the same environment, made of two buildings close together for a total usable area of 1000 m2 outdoors and and 6000 m2 indoors over three floors, with a total path length exceeding 500 m. IPIN competitions, based on the EvAAL framework, have aimed at comparing the accuracy performance of personal positioning systems in fair and realistic conditions: past editions of the competition were carried in big conference settings, university campuses and a shopping mall. Positioning accuracy is computed while the person carrying the system under test walks at normal walking speed, uses lifts and goes up and down stairs or briefly stops at given points. Results presented here are a showcase of state-of-the-art systems tested side by side in real-world settings as part of the on-site real-time competition Tracks. Results for off-site Tracks allow a detailed and reproducible comparison of the most recent positioning and tracking algorithms in the same environment as the on-site Tracks.

The electrocardiogram (ECG) is an efficient and noninvasive indicator for arrhythmia detection and prevention. In real-world scenarios, ECG signals are prone to be contaminated with various noises, which may lead to wrong interpretation. Therefore, significant attention has been paid on denoising of ECG for accurate diagnosis and analysis. A denoising autoencoder (DAE) can be applied to reconstruct the clean data from its noisy version. In this paper, a DAE using the fully convolutional network (FCN) is proposed for ECG signal denoising. Meanwhile, the proposed FCN-based DAE can perform compression with regard to the DAE architecture. The proposed approach is applied to ECG signals from the MIT-BIH Arrhythmia database and the added noise signals are obtained from the MIT-BIH Noise Stress Test database. The denoising performance is evaluated using the root-mean-square error (RMSE), percentage-root-mean-square difference (PRD), and improvement in signal-to-noise ratio (SNRimp). The results of the experiments conducted on noisy ECG signals of different levels of input SNR show that the FCN acquires better performance as compared to the deep fully connected neural network- and convolutional neural network-based denoising models. Moreover, the proposed FCN-based DAE reduces the size of the input ECG signals, where the compressed data is 32 times smaller than the original. The results of the study demonstrate the superiority of FCN in denoising, with lower RMSE and PRD, as well as higher SNRimp. According to the results, we believe that the proposed FCN-based DAE has a good application prospect in clinical practice.

The Indoor Positioning and Indoor Navigation (IPIN) conference holds an annual competition in which indoor localization systems from different research groups worldwide are evaluated empirically. The objective of this competition is to establish a systematic evaluation methodology with rigorous metrics both for real-time (on-site) and post-processing (off-site) situations, in a realistic environment unfamiliar to the prototype developers. For the IPIN 2018 conference, this competition was held on September 22nd, 2018, in Atlantis, a large shopping mall in Nantes (France). Four competition tracks (two on-site and two off-site) were designed. They consisted of several 1 km routes traversing several floors of the mall. Along these paths, 180 points were topographically surveyed with a 10 cm accuracy, to serve as ground truth landmarks, combining theodolite measurements, differential global navigation satellite system (GNSS) and 3D scanner systems. 34 teams effectively competed. The accuracy score corresponds to the third quartile (75th percentile) of an error metric that combines the horizontal positioning error and the floor detection. The best results for the on-site tracks showed an accuracy score of 11.70 m (Track 1) and 5.50 m (Track 2), while the best results for the off-site tracks showed an accuracy score of 0.90 m (Track 3) and 1.30 m (Track 4). These results showed that it is possible to obtain high accuracy indoor positioning solutions in large, realistic environments using wearable light-weight sensors without deploying any beacon. This paper describes the organization work of the tracks, analyzes the methodology used to quantify the results, reviews the lessons learned from the competition and discusses its future.

Toona sinensis (TS) is a medicinal herb possessing anti-apoptotic, anti-oxidant, and anti-inflammatory properties and is used to treat diabetes, cancer, and inflammatory diseases. In traditional Chinese medicine theory, TS clears dampness and heat, strengthens the stomach function, and regulates vital energy flow. TS is also used as an astringent and a pesticide. In this study, we aimed to evaluate how TS influences autophagy and cytokines during the inflammatory process in RAW 264.7 macrophages. The treatment groups were pre-supplemented with TS leaf extract; rapamycin was used to enhance autophagy and lipopolysaccharide (LPS) was used to induce inflammation. The expression of autophagy-related proteins was analyzed by western blotting. The survival rate of, and chemokine expression and oxidative stress in the cells were also assessed. TS leaf extract inhibited mammalian target of rapamycin (mTOR) phosphorylation at site S2448 in the macrophages. At relatively higher concentrations (50 and 75 μg/mL), TS elevated the expression of light chain 3 II (LC3-II), which further modulated autophagy. Pre-supplementation with TS leaf extract elevated the total glutathione (GSH) level and GSH/oxidized GSH (GSSG) ratio, but it decreased the GSSG, total nitric oxide, nitrate, nitrite, malondialdehyde, and superoxide anion levels. TS reversed the effects of LPS-induced cytokines, including interleukin (IL)-6 and IL-10. TS did not induce significant toxicity at the studied concentrations. In conclusion, TS leaf extract may modulate autophagy during inflammation. Furthermore, it may prevent cell damage via anti-inflammation and anti-oxidation. Thus, this study supports the ethnomedical use of TS in the prevention of inflammation-related diseases.

Chinese lexical tones determine word meaning and are crucial in reading development. Reduced tone awareness is widely reported in children with reading difficulties (RD). Lexical-tone processing requires sensitivity to frequency-modulated sound changes. The present study investigates whether reduced tone awareness in children with RD is reflected in basic auditory processing and the level at which the breakdown occurs. Magnetoencephalographic techniques and an oddball paradigm were used to elicit auditory-related neural responses. Five frequency sweep conditions were established to mirror the frequency fluctuation in Chinese lexical tones, including one standard (level) sweep and four deviant sweeps (fast-up, fast-down, slow-up, and slow-down). A total of 14 Chinese-speaking children aged 9–12 years with RD and 13 age-matched typically developing children were recruited. The participants completed a magnetoencephalographic data acquisition session, during which they watched a silent cartoon and the auditory stimuli were presented in a pseudorandomized order. The results revealed that the significant between-group difference was caused by differences in the level of auditory sensory processing, reflected by the P1m component elicited by the slow-up frequency sweep. This finding indicated that auditory sensory processing was affected by both the duration and the direction of a frequency sweep. Sensitivity to changes in duration and frequency is crucial for the processing of suprasegmental features. Therefore, this sensory deficit might be associated with difficulties discriminating two tones with an upward frequency contour in Chinese.

Abstract Investigating the dynamics of biodiversity via passive acoustic monitoring is a challenging task, owing to the difficulty of identifying different animal vocalizations. Several indices have been proposed to measure acoustic complexity and to predict biodiversity. Although these indices perform well under low-noise conditions, they may be biased when environmental and anthropogenic noises are involved. In this paper, we propose a periodicity coded non-negative matrix factorization (PC-NMF) for separating different sound sources from a spectrogram of long-term recordings. The PC-NMF first decomposes a spectrogram into two matrices: spectral basis matrix and encoding matrix. Next, on the basis of the periodicity of the encoding information, the spectral bases belonging to the same source are grouped together. Finally, distinct sources are reconstructed on the basis of the cluster of the basis matrix and the corresponding encoding information, and the noise components are then removed to facilitate more accurate monitoring of biological sounds. Our results show that the PC-NMF precisely enhances biological choruses, effectively suppressing environmental and anthropogenic noises in marine and terrestrial recordings without a need for training data. The results may improve behaviour assessment of calling animals and facilitate the investigation of the interactions between different sound sources within an ecosystem.

In wireless telephony and audio data mining applications, it is desirable that noise suppression can be made robust against changing noise conditions and operates in real time (or faster). The learning effectiveness and speed of artificial neural networks are therefore critical factors in applications for speech enhancement tasks. To address these issues, we present an extreme learning machine (ELM) framework, aimed at the effective and fast removal of background noise from a single-channel speech signal, based on a set of randomly chosen hidden units and analytically determined output weights. Because feature learning with shallow ELM may not be effective for natural signals, such as speech, even with a large number of hidden nodes, hierarchical ELM (H-ELM) architectures are deployed by leveraging sparse autoencoders. In this manner, we not only keep all the advantages of deep models in approximating complicated functions and maintaining strong regression capabilities, but we also overcome the cumbersome and time-consuming features of both greedy layer-wise pre-training and back-propagation (BP)-based fine tuning schemes, which are typically adopted for training deep neural architectures. The proposed ELM framework was evaluated on the Aurora-4 speech database. The Aurora-4 task provides relatively limited training data, and test speech data corrupted with both additive noise and convolutive distortions for matched and mismatched channels and signal-to-noise ratio (SNR) conditions. In addition, the task includes a subset of testing data involving noise types and SNR levels that are not seen in the training data. The experimental results indicate that when the amount of training data is limited, both ELMand H-ELM-based speech enhancement techniques consistently outperform the conventional BP-based shallow and deep learning algorithms, in terms of standardized objective evaluations, under various testing conditions.

In this paper, we propose a smartphone-based hearing assistive system (termed SmartHear) to facilitate speech recognition for various target users, who could benefit from enhanced listening clarity in the classroom. The SmartHear system consists of transmitter and receiver devices (e.g., smartphone and Bluetooth headset) for voice transmission, and an Android mobile application that controls and connects the different devices via Bluetooth or WiFi technology. The wireless transmission of voice signals between devices overcomes the reverberation and ambient noise effects in the classroom. The main functionalities of SmartHear include: 1) configurable transmitter/receiver assignment, to allow flexible designation of transmitter/receiver roles; 2) advanced noise-reduction techniques; 3) audio recording; and 4) voice-to-text conversion, to give students visual text aid. All the functions are implemented as a mobile application with an easy-to-navigate user interface. Experiments show the effectiveness of the noise-reduction schemes at low signal-to-noise ratios in terms of standard speech perception and quality indices, and show the effectiveness of SmartHear in maintaining voice-to-text conversion accuracy regardless of the distance between the speaker and listener. Future applications of SmartHear are also discussed.

The popularity of Internet has made advertisement marketing gone virtualized and location-based mobile advertising successful in recent years. Adlocus, an APP developed by HyXen Technology, is one good example to achieve this. This advertising software can tailor to the campaign needs and target users within a diameter of 1 km. However, the question is that is it possible to predict whether the user is willing to click on the advertisement. This paper adopts many ways to analyze how these relations influence in different kinds of mobile advertisement. A comprehensive performance comparison of different models is provided, and the analysis of different factors is also discussed, including click time, advertisement category, language, and mobile phone manufacturers.

The development of indoor positioning solutions using smartphones is a growing activity with an enormous potential for everyday life and professional applications. The research activities on this topic concentrate on the development of new positioning solutions that are tested in specific environments under their own evaluation metrics. To explore the real positioning quality of smartphone-based solutions and their capabilities for seamlessly adapting to different scenarios, it is needed to find fair evaluation frameworks. The design of competitions using extensive pre-recorded datasets is a valid way to generate open data for comparing the different solutions created by research teams. In this paper, we discuss the details of the 2017 IPIN indoor localization competition, the different datasets created, the teams participating in the event, and the results they obtained. We compare these results with other competition-based approaches (Microsoft and Perf-loc) and on-line evaluation web sites. The lessons learned by organising these competitions and the benefits for the community are addressed along the paper. Our analysis paves the way for future developments on the standardization of evaluations and for creating a widely-adopted benchmark strategy for researchers and companies in the field.

Temporal envelope is the primary acoustic cue used in most cochlear implant (CI) speech processors to elicit speech perception for patients fitted with CI devices. Envelope compression narrows down envelope dynamic range and accordingly degrades speech understanding abilities of CI users, especially under challenging listening conditions (e.g., in noise). A new adaptive envelope compression (AEC) strategy was proposed recently, which in contrast to the traditional static envelope compression, is effective at enhancing the modulation depth of envelope waveform by making best use of its dynamic range and thus improving the intelligibility of envelope-based speech. The present study further explored the effect of adaptation rate in envelope compression on the intelligibility of compressed-envelope based speech. Moreover, since noise reduction is another essential unit in modern CI systems, the compatibility of AEC and noise reduction was also investigated. In this study, listening experiments were carried out by presenting vocoded sentences to normal hearing listeners for recognition. Experimental results demonstrated that the adaptation rate in envelope compression had a notable effect on the speech intelligibility performance of the AEC strategy. By specifying a suitable adaptation rate, speech intelligibility could be enhanced significantly in noise compared to when using static envelope compression. Moreover, results confirmed that the AEC strategy was suitable for combining with noise reduction to improve the intelligibility of envelope-based speech in noise.

This paper investigates the transportation and vehicular modes classification by using big data from smartphone sensors. The three types of sensors used in this paper include the accelerometer, magnetometer, and gyroscope. This study proposes improved features and uses three machine learning algorithms including decision trees, K-nearest neighbor, and support vector machine to classify the user’s transportation and vehicular modes. In the experiments, we discussed and compared the performance from different perspectives including the accuracy for both modes, the executive time, and the model size. Results show that the proposed features enhance the accuracy, in which the support vector machine provides the best performance in classification accuracy whereas it consumes the largest prediction time. This paper also investigates the vehicle classification mode and compares the results with that of the transportation modes.

Conventionally, the maximum likelihood (ML) criterion is applied to train a deep belief network (DBN). We present a maximum entropy (ME) learning algorithm for DBNs, designed specifically to handle limited training data. Maximizing only the entropy of parameters in the DBN allows more effective generalization capability, less bias towards data distributions, and robustness to over-fitting compared to ML learning. Results of text classification and object recognition tasks demonstrate ME-trained DBN outperforms ML-trained DBN when training data is limited.