Automatic Depression Detection Using Smartphone-Based Text-Dependent Speech Signals: Deep Convolutional Neural Network Approach.

BACKGROUND: Automatic diagnosis of depression based on speech can complement mental health treatment methods in the future. Previous studies have reported that acoustic properties can be used to identify depression. However, few studies have attempted a large-scale differential diagnosis of patients with depressive disorders using acoustic characteristics of non-English speakers. OBJECTIVE: This study proposes a framework for automatic depression detection using large-scale acoustic characteristics based on the Korean language. METHODS: We recruited 153 patients who met the criteria for major depressive disorder and 165 healthy controls without current or past mental illness. Participants' voices were recorded on a smartphone while performing the task of reading predefined text-based sentences. Three approaches were evaluated and compared to detect depression using data sets with text-dependent read speech tasks: conventional machine learning models based on acoustic features, a proposed model that trains and classifies log-Mel spectrograms by applying a deep convolutional neural network (CNN) with a relatively small number of parameters, and models that train and classify log-Mel spectrograms by applying well-known pretrained networks. RESULTS: The acoustic characteristics of the predefined text-based sentence reading automatically detected depression using the proposed CNN model. The highest accuracy achieved with the proposed CNN on the speech data was 78.14%. Our results show that the deep-learned acoustic characteristics lead to better performance than those obtained using the conventional approach and pretrained models. CONCLUSIONS: Checking the mood of patients with major depressive disorder and detecting the consistency of objective descriptions are very important research topics. This study suggests that the analysis of speech data recorded while reading text-dependent sentences could help predict depression status automatically by capturing the characteristics of depression. Our method is smartphone based, is easily accessible, and can contribute to the automatic identification of depressive states.

Single-Channel FMCW-Radar-Based Multi-Passenger Occupancy Detection Inside Vehicle.

In this paper, we provide the results of multi-passenger occupancy detection inside a vehicle obtained using a single-channel frequency-modulated continuous-wave radar. The physiological characteristics of the radar signal are analyzed in a time-frequency spectrum, and features are proposed based on these characteristics for multi-passenger occupancy detection. After clutter removal is applied, the spectral power and Wiener entropy are proposed as features to quantify physiological movements arising from breathing and heartbeat. Using the average means of both the power and Wiener entropy at seats 1 and 2, the feature distributions are expressed, and classification is performed. The multi-passenger occupancy detection performance is evaluated using linear discriminant analysis and maximum likelihood estimation. The results indicate that the proposed power and Wiener entropy are effective features for multi-passenger occupancy detection.

CD117⁺ CD3⁻ CD56⁻ OX40Lhigh cells express IL-22 and display an LTi phenotype in human secondary lymphoid tissues.

Here, we identify cells within human adult secondary lymphoid tissues that are comparable in phenotype and location to the lymphoid tissue inducer (LTi) cells that persist in the adult mouse. Identified as CD117(+) CD3(-) CD56(-) cells, like murine LTi cells, they lack expression of many common lineage markers and express CD127, OX40L and TRANCE. These cells were detected at the interface between the B- and T- zones, as well as at the subcapsular sinus in LNs, the location where LTi cells reside in murine spleen and LNs. Furthermore, like murine LTi cells, these cells expressed high levels of IL-22 and upregulated IL-22 expression upon IL-23 stimulation. Importantly, these cells were not an NK cell subset since they showed no expression of IFN-γ and perforin. Interestingly, a subset of the CD117(+) CD3(-) CD56(-) OX40L(+) population expressed NKp46, again similar to recent findings in mice. Finally, these cells supported memory CD4(+) T-cell survival in an OX40L-dependent manner. Combined, these data indicate that the CD117(+) CD3(-) CD56(-) OX40L(+) cells in human secondary lymphoid tissues are comparable in phenotype, location and function to the LTi cells that persist within adult murine secondary lymphoid tissues.

Ecotoxicological evaluation of tributyltin toxicity to the equilateral venus clam, Gomphina veneriformis (Bivalvia: Veneridae).

Tributyltin (TBT) is the most common pesticide in marine and freshwater environments. To evaluate the potential ecological risk posed by TBT, we measured biological responses such as growth rate, gonad index, sex ratio, the percentage of intersex gonads, filtration rate, and gill abnormalities in the equilateral venus clam (Gomphina veneriformis). Additionally, the biochemical and molecular responses were evaluated in G. veneriformis exposed to various concentrations of TBT. The growth of G. veneriformis was significantly delayed in a dose-dependent manner after exposure to all tested TBT concentrations. After TBT was administered to G. veneriformis, the gonad index decreased and the sex balance was altered. The percentage of intersex gonads also increased significantly in treated females, whereas no intersex gonads were detected in the solvent control group. Additionally, intersex gonads were detected in male G. veneriformis specimens exposed to relatively high TBT concentrations (20 µg L⁻¹). The filtration rate was also reduced in a dose-dependent manner in TBT-exposed G. veneriformis. We also noted abnormal gill morphology in TBT-exposed G. veneriformis. Furthermore, increases in antioxidant enzyme activities were observed in TBT-exposed G. veneriformis clams, regardless of dosage. Vitellogenin gene expression also increased significantly in a dose-dependent manner in G. veneriformis exposed to TBT. These results provide valuable information regarding our understanding of the toxicology of TBT in G. veneriformis. Moreover, the responses of biological and molecular factors could be utilized as information for risk assessments and marine monitoring of TBT toxicity.

Asynchronous decoding of dexterous finger movements using M1 neurons.

Previous efforts in brain-machine interfaces (BMI) have looked at decoding movement intent or hand and arm trajectory, but current cortical control strategies have not focused on the decoding of dexterous [corrected] actions such as finger movements. The present work demonstrates the asynchronous decoding (i.e., where cues indicating the onset of movement are not known) of individual and combined finger movements. Single-unit activities were recorded sequentially from a population of neurons in the M1 hand area of trained rhesus monkeys during flexion and extension movements of each finger and the wrist. Nonlinear filters were designed to detect the onset of movement and decode the movement type from randomly selected neuronal ensembles (assembled from individually recorded single-unit activities). Average asynchronous decoding accuracies as high as 99.8%, 96.2%, and 90.5%, were achieved for individuated finger and wrist movements with three monkeys. Average decoding accuracy was still 92.5% when combined movements of two fingers were included. These results demonstrate that it is possible to asynchronously decode dexterous finger movements from a neuronal ensemble with high accuracy. This work takes an important step towards the development of a BMI for direct neural control of a state-of-the-art, multifingered hand prosthesis.

Improving neurological outcomes post-cardiac arrest in a rat model: immediate hypothermia and quantitative EEG monitoring.

OBJECTIVES: Therapeutic hypothermia (TH) after cardiac arrest (CA) improves outcomes in a fraction of patients. To enhance the administration of TH, we studied brain electrophysiological monitoring in determining the benefit of early initiation of TH compared to conventional administration in a rat model. METHODS: Using an asphyxial CA model, we compared the benefit of immediate hypothermia (IH, T=33 degrees C, immediately post-resuscitation, maintained 6h) to conventional hypothermia (CH, T=33 degrees C, starting 1h post-resuscitation, maintained 12h) via surface cooling. We tracked quantitative EEG using relative entropy (qEEG) with outcome verification by serial Neurological Deficit Score (NDS) and quantitative brain histopathological damage scoring (HDS). Thirty-two rats were divided into 4 groups based on CH/IH and 7/9-min duration of asphyxial CA. Four sham rats were included for evaluation of the effect of hypothermia on qEEG. RESULTS: The 72-h NDS of the IH group was significantly better than the CH group for both 7-min (74/63; median, IH/CH, p<0.001) and 9-min (54/47, p=0.022) groups. qEEG showed greater recovery with IH (p<0.001) and significantly less neuronal cortical injury by HDS (IH: 18.9+/-2.5% versus CH: 33.2+/-4.4%, p=0.006). The 1-h post-resuscitation qEEG correlated well with 72-h NDS (p<0.05) and 72-h behavioral subgroup of NDS (p<0.01). No differences in qEEG were noted in the sham group. CONCLUSIONS: Immediate but shorter hypothermia compared to CH leads to better functional outcome in rats after 7- and 9-min CA. The beneficial effect of IH was readily detected by neuro-electrophysiological monitoring and histological changes supported the value of this observation.

Development of Electrical Neural Stimulator Generating Periodic and Non-periodic Signals and Supporting Closed-loop Experimental System.

It is essential to build a system to generate proper neural stimulus signals with adjusting parameters. We developed a stimulator with up to four channels for separate settings in periodic and non-periodic modes. The device can support a closed-loop experimental system which utilizes neural information in real time as a feedback for controlling stimuli. To confirm whether stimulating signals are properly produced and delivered inside the brain, two experiments with rats were conducted. We observed that the change of firing rates and the cross-power spectral density increased after stimulation which meant that electric signals were transferred well and that they affected the neurons' activities. Thus, it is expected that the stimulator can be utilized to produce appropriate stimulation signals in accordance with various objectives.

Single-Finger Neural Basis Information-Based Neural Decoder for Multi-Finger Movements.

In this paper, we investigate the relationship between single and multi-finger movements. By exploiting the neural correlation between the temporal firing patterns between movements, we show that the Pearson's correlation coefficient for the physically related movement pairs are greater than those of others; the firing rates of the neurons that are tuned to a single-finger movements also increases when the corresponding multi-finger movements are instructed. We also use a hierarchical cluster analysis to verify not only the relationship between the single and multi-finger movements, but also the relationship between the flexion and extension movements. Furthermore, we propose a novel decoding method of modeling neural firing patterns while omitting the training process of the multi-finger movements. For the decoding, the Skellam and Gaussian probability distributions are used as mathematical models. The probabilistic distribution model of the multi-finger movements was estimated using the neural activity that was acquired during single-finger movements. As a result, the proposed neural decoding accuracy comparable with that of the supervised neural decoding accuracy when all of the neurons were used for the multi-finger movements. These results suggest that only the neural activities of single-finger movements can be exploited for the control of dexterous multi-finger neuroprosthetics.

Novel Methods for Measuring Depth of Anesthesia by Quantifying Dominant Information Flow in Multichannel EEGs.

In this paper, we propose novel methods for measuring depth of anesthesia (DOA) by quantifying dominant information flow in multichannel EEGs. Conventional methods mainly use few EEG channels independently and most of multichannel EEG based studies are limited to specific regions of the brain. Therefore the function of the cerebral cortex over wide brain regions is hardly reflected in DOA measurement. Here, DOA is measured by the quantification of dominant information flow obtained from principle bipartition. Three bipartitioning methods are used to detect the dominant information flow in entire EEG channels and the dominant information flow is quantified by calculating information entropy. High correlation between the proposed measures and the plasma concentration of propofol is confirmed from the experimental results of clinical data in 39 subjects. To illustrate the performance of the proposed methods more easily we present the results for multichannel EEG on a two-dimensional (2D) brain map.

Quantitative EEG and neurological recovery with therapeutic hypothermia after asphyxial cardiac arrest in rats.

We test the hypothesis that quantitative electroencephalogram (qEEG) can be used to objectively assess functional electrophysiological recovery of brain after hypothermia in an asphyxial cardiac arrest rodent model. Twenty-eight rats were randomly subjected to 7-min (n = 14) and 9-min (n = 14) asphyxia times. One half of each group (n = 7) was randomly subjected to hypothermia (T = 33 degrees C for 12 h) and the other half (n = 7) to normothermia (T = 37 degrees C). Continuous physiologic monitoring of blood pressure, EEG, and core body temperature monitoring and intermittent arterial blood gas (ABG) analysis was undertaken. Neurological recovery after resuscitation was monitored using serial Neurological Deficit Score (NDS) calculation and qEEG analysis. Information Quantity (IQ), a previously validated measure of relative EEG entropy, was employed to monitor electrical recovery. The experiment demonstrated greater recovery of IQ in rats treated with hypothermia compared to normothermic controls in both injury groups (P < 0.05). The 72-h NDS of the hypothermia group was also significantly improved compared to the normothermia group (P < 0.05). IQ values measured at 4 h had a strong correlation with the primary neurological outcome measure, 72-h NDS score (Pearson correlation 0.746, 2-tailed significance <0.001). IQ is sensitive to the acceleration of neurological recovery as measured NDS after asphyxial cardiac arrest known to occur with induced hypothermia. These results demonstrate the potential utility of qEEG-IQ to track the response to neuroprotective hypothermia during the early phase of recovery from cardiac arrest.

Quantitative EEG and effect of hypothermia on brain recovery after cardiac arrest.

In this paper, we provide a quantitative electroencephalogram (EEG) analysis to study the effect of hypothermia on the neurological recovery of brain after cardiac arrest. We hypothesize that the brain injury results in a reduction in information of the brain rhythm. To measure the information content of the EEG a new measure called information quantity (IQ), which is the Shannon entropy of decorrelated EEG signals, is developed. For decorrelating EEG signals, we use the discrete wavelet transform (DWT) which is known to have good decorrelating properties and to show a good match to the standard clinical bands in EEG. In measuring the amount of information, IQ shows better tracking capability for dynamic amplitude change and frequency component change than conventional entropy-based measures. Experiments are carried out in rodents (n = 30) to monitor the neurological recovery after cardiac arrest. In addition, EEG signal recovery under normothermic (37 degrees C) and hypothermic (33 degrees C) resuscitation following 5, 7, and 9 min of cardiac arrest is recorded and analyzed. Experimental results show that the IQ is greater for hypothermic than normothermic rats, with an IQ difference of more than 0.20 (0.20 +/- 0.11 is 95% condidence interval). The results quantitatively support the hypothesis that hypothermia accelerates the electrical recovery from brain injury after cardiac arrest.

Spectral Gini Index for Quantifying the Depth of Consciousness.

We propose indices that describe the depth of consciousness (DOC) based on electroencephalograms (EEGs) acquired during anesthesia. The spectral Gini index (SpG) is a novel index utilizing the inequality in the powers of the EEG spectral components; a similar index is the binarized spectral Gini index (BSpG), which has low computational complexity. A set of EEG data from 15 subjects was obtained during the induction and recovery periods of general anesthesia with propofol. The efficacy of the indices as indicators of the DOC was demonstrated by examining Spearman's correlation coefficients between the indices and the effect-site concentration of propofol. A higher correlation was observed for SpG and BSpG (0.633 and 0.770, resp., p < 0.001) compared to the conventional indices. These results show that the proposed indices can achieve a reliable quantification of the DOC with simplified calculations.

Novel Burst Suppression Segmentation in the Joint Time-Frequency Domain for EEG in Treatment of Status Epilepticus.

We developed a method to distinguish bursts and suppressions for EEG burst suppression from the treatments of status epilepticus, employing the joint time-frequency domain. We obtained the feature used in the proposed method from the joint use of the time and frequency domains, and we estimated the decision as to whether the measured EEG was a burst segment or suppression segment by the maximum likelihood estimation. We evaluated the performance of the proposed method in terms of its accordance with the visual scores and estimation of the burst suppression ratio. The accuracy was higher than the sole use of the time or frequency domains, as well as conventional methods conducted in the time domain. In addition, probabilistic modeling provided a more simplified optimization than conventional methods. Burst suppression quantification necessitated precise burst suppression segmentation with an easy optimization; therefore, the excellent discrimination and the easy optimization of burst suppression by the proposed method appear to be beneficial.

Neuron Selection by Relative Importance for Neural Decoding of Dexterous Finger Prosthesis Control Application.

Future generations of upper limb prosthesis will have dexterous hand with individual fingers and will be controlled directly by neural signals. Neurons from the primary motor (M1) cortex code for finger movements and provide the source for neural control of dexterous prosthesis. Each neuron's activation can be quantified by the change in firing rate before and after finger movement, and the quantified value is then represented by the neural activity over each trial for the intended movement. Since this neural activity varies with the intended movement, we define the relative importance of each neuron independent of specific intended movements. The relative importance of each neuron is determined by the inter-movement variance of the neural activities for respective intended movements. Neurons are ranked by the relative importance and then a subpopulation of rank-ordered neurons is selected for the neural decoding. The use of the proposed neuron selection method in individual finger movements improved decoding accuracy by 21.5% in the case of decoding with only 5 neurons and by 9.2% in the case of decoding with only 10 neurons. With only 15 highly-ranked neurons, a decoding accuracy of 99.5% was achieved. The performance improvement is still maintained when combined movements of two fingers were included though the decoding accuracy fell to 95.7%. Since the proposed neuron selection method can achieve the targeting accuracy of decoding algorithms with less number of input neurons, it can be significant for developing brain-machine interfaces for direct neural control of hand prostheses.

Odor discrimination using neural decoding of the main olfactory bulb in rats.

This paper presents a novel method for inferring the odor based on neural activities observed from rats' main olfactory bulbs. Multichannel extracellular single unit recordings were done by microwire electrodes (tungsten, 50 µm, 32 channels) implanted in the mitral/tufted cell layers of the main olfactory bulb of anesthetized rats to obtain neural responses to various odors. Neural response as a key feature was measured by subtraction of neural firing rate before stimulus from after. For odor inference, we have developed a decoding method based on the maximum likelihood estimation. The results have shown that the average decoding accuracy is about 100.0%, 96.0%, 84.0%, and 100.0% with four rats, respectively.

Finger Motion Decoding Using EMG Signals Corresponding Various Arm Postures.

We provide a novel method to infer finger flexing motions using a four-channel surface electromyogram (EMG). Surface EMG signals can be recorded from the human body non-invasively and easily. Surface EMG signals in this study were obtained from four channel electrodes placed around the forearm. The motions consist of the flexion of five single fingers (thumb, index finger, middle finger, ring finger, and little finger) and three multi.finger motions. The maximum likelihood estimation was used to infer the finger motions. Experimental results have shown that this method can successfully infer the finger flexing motions. The average accuracy was as high as 97.75%. In addition, we examined the influence of inference accuracies with the various arm postures.

Neural decoding of finger movements using Skellam-based maximum-likelihood decoding.

We present an optimal method for decoding the activity of primary motor cortex (M1) neurons in a nonhuman primate during single finger movements. The method is based on the maximum-likelihood (ML) inference, which assuming the probability of finger movements is uniform, is equivalent to the maximum a posteriori (MAP) inference. Each neuron's activation is first quantified by the change in firing rate before and after finger movement. We then estimate the probability density function of this activation given finger movement, i.e., Pr(neuronal activation (x) | finger movements (m)). Based on the ML criterion, we choose finger movements to maximize Pr(x |m). Experimentally, data were collected from 115 task-related neurons in M1 as the monkey performed flexion and extension of each finger and the wrist (12 movements). With as few as 20--25 randomly selected neurons, the proposed method decoded single-finger movements with 99% accuracy. Since the training and decoding procedures in the proposed method are simple and computationally efficient, the method can be extended for real-time neuroprosthetic control of a dexterous hand.

A subband-based information measure of EEG during brain injury and recovery after cardiac arrest.

We propose an improved quantitative measure of EEG during brain injury and recovery after cardiac arrest. In our previous studies, we proposed a measure, information quantity (IQ), to detect the early effects of temperature manipulation on the EEG signals recorded from the scalp. IQ incorporates the wavelet transform and the Shannon entropy in full bands from delta to gamma. Unlike IQ, here we separately calculate IQ in each subband, i.e., the new measure is IQ in each subband. We will call it subband IQ (SIQ). We demonstrate the performance of the proposed method by comparing SIQ with IQ in terms of how well the meausres predict actual neurological outcomes. Thirteen rats, based on 7-min cardiac arrest were used. The experimental results show that the proposed measure was more highly correlated to neurological outcome than IQ.

Quantitative EEG assessment of brain injury and hypothermic neuroprotection after cardiac arrest.

In this paper we provide a quantitative electroencephalogram (EEG) analysis to study the effect of hypothermia on the neurological recovery of brain after cardiac arrest. We hypothesize that the brain injury results in a reduction in information of the brain rhythm. To measure the information content of the EEG a new measure called information quantity (IQ), which is the Shannon entropy of decorrelated EEG signals, is developed. For decorrelating EEG signals, we use the discrete wavelet transform (DWT) which is known to have good decorrelating properties and to show a good match to the standard clinical bands in EEG. In simulation for measuring the amount of information, the IQ shows better tracking capability for dynamic amplitude change and frequency component change than conventional entropy-based measures. Experiments are carried out in rodents to monitor the neurological recovery after cardiac arrest. In addition, EEG signal recovery under normothermic (37 degrees C) and hypothermic (33 degrees C) resuscitation following 5, 7 and 9 minutes of cardiac arrest is recorded and analyzed. Experimental results show that the IQ is higher for hypothermic than normothermic rats. The results quantitatively support the hypothesis that hypothermia accelerates the recovery of brain injury after cardiac arrest.