With the continuous development of artiticial intelligence techniques, many new solutions have emerged for acoustic echo cancellation. Acoustic echo cancellation, a key problem in contemporary audio communication, is gradually being replaced by traditional filter algorithms with deep learning-based approaches. In this paper, traditional filter algorithms and neural network models based on deep learning theory are used to solve the task of acoustic echo cancellation respectively. Comparative experiments are performed on popular models using the dataset from the 2021 Acoustic Echo Cancellation Challenge. The experimental results demonstrate the good results and importance of neural networks in acoustic echo cancellation tasks.
Gaze estimation based on electrooculograms (EOGs) has been widely explored. However, the inter-subject variability of EOGs still leaves a significant challenge for practical applications. It contributes to performance degradation when handling inter-subject issues. In this paper, an unsupervised transfer learning approach with an adaptive reweighting and resampling (ARR) strategy to fully consider individual variability is proposed for EOG-based gaze angle estimation. It allows quantifying domain shifts by leveraging the source-target similarities, reweighting and resampling the source data to retain relevant instances and disregard irrelevant instances during adaptation. Specifically, our proposed methodology first assesses the domain shifts via decomposing transformation matrices, which are estimated between the training subjects (denoted as multi-source domains) and the test subject (denoted as target domain). Then, the multi-domain shifts are assigned as weighted indicators to resample the multi-source domains for model training. Comparative experiments with several prevailing transfer learning methods including CORrelation ALignment (CORAL), Geodesic Flow Kernel (GFK), Joint Distribution Adaptation (JDA), Transfer component analysis (TCA), and Balanced distribution adaption (BDA) using two different normalization processes were conducted on a realistic scenario across 18 subjects. Experimental results demonstrate that the ARR strategy can significantly improve performance (mean absolute error (MAE) reduction: 7.0%, root mean square error (RMSE) reduction: 6.3%), outperforming the prevailing methods. Besides, the impacts of data diversity and data size on ARR strategy are further investigated. It exhibits that data size is more important than data diversity for EOG-based gaze angle estimation, and also presents the benefits of the ARR strategy for dealing with practical scenarios.
Sleep staging is a fundamental step in diagnosis and treatment of sleep disorders. In current sleep staging systems, normally a set of thresholds should be set up to determine the boundaries in differentiating different linguistic or symbolic features. However, as far as we know, there are no fully satisfying automatic method to do this task. Thresholds are mostly set up manually. In this paper, an automatic thresholds setting-up method based on Cross Entropy is proposed. Person-dependent thresholds can be provided automatically by using Cross Entropy and used in personalized sleep staging analysis while considering individual variability. The feasibility of Cross Entropy has also been evaluated, computational results exhibit that the Cross Entropy-based method is an efficient, convenient and applicable stochastic method for automatically setting-up thresholds in sleep staging system. Compared with manual method, average F-Measures are improved more than 10% for all the stages and up-to 74% for stage N3 by using proposed method.
Tactile sensors are among the most important devices used in industrial and biomedical fields. Sensors’ profiles are significantly affected by their structures and material used. This article presents a robust, low-cost, low noise, accurate and simple fabrication capacitive tactile sensor as a single taxel fabricated on foam. This highly scalable design provides excellent noise immunity, accuracy, and due to a unique printable elastic conductor, it is flexible and stretchable with more than 200% strain. Furthermore, the taxel is based on the capacitive Wheatstone bridge. As a result, noise immunity and stability in case of temperature fluctuation is accomplished. Additionally, the sensor’s innovative, simple fabrication, made of Polyurethane foam and printable elastic conductor, allows the system to adapt and achieve relevant results necessary for the purpose of the sensor’s application. Therefore, the proposed sensor has potential applications in industrial and biomedical contexts, such as sleep monitoring, etc.
The electroencephalogram (EEG) is a weak electrical signal generated by the activity of neurons located in the cerebral cortex or scalp surface neurons which is very important to brain disease diagnosis, rehabilitation and so on. However, the traditional acquisition equipment is usually large in size, difficult to configure, and complicated to use. To overcome these problems, a novel 8-channel EEG acquisition system based on the analog front end ADS1299, which can be also extended to 32-channel is proposed. A novel flexible and replaceable electrode based on felt material without the requirement of the conductive paste is designed. The proposed system is able to adjust the sampling rate from 250 Hz to 16 kHz. Moreover, with the advantage of a programmable gain amplifier, the proposed system can be applied not only for EEG signal acquisition, but also for most of the physiological signals acquisition like the electrocardiogram (ECG), electromyogram (EMG) and so on. In order to evaluate the performance of the EEG acquisition system, input noise level experiment and comparison experiment with the commercial product are performed. Moreover, spontaneous EEG signals (open-closed eyes) and evoked EEG signals (the steady-state visual evoked potentials, SSVEP) tasks are conducted. Experimental results indicate that the system satisfies the requirements of multi-channel EEG acquisition with high signal quality. And the system could provide a comfortable portable, function-rich, reconfigurable and low power-consumption way for the EEG related applications such as clinical diseases diagnosis and brain-computer interface (BCI).
Feline chronic gingivostomatitis (FCGS) is an ulcerative and/or proliferative disease that typically affects the palatoglossal folds. Because of its unknown pathogenesis and long disease course, it is difficult to treat and has a high recurrence rate. Most of the bacteria in the oral microbiota exist in the mouth symbiotically and maintain a dynamic balance, and when the balance is disrupted, they may cause disease. Disturbance of the oral microbiota may play an important role in the development of FCGS. In this study, the medical records of 3109 cats in three general pet hospitals in Xi ‘an were collected. Sixty-one cats with FCGS were investigated via questionnaires, routine oral examinations and laboratory examinations. Oral microbiota samples were collected from 16 FCGS-affected cats, and microbial species were identified by 16S rDNA sequencing. The results showed that the incidence of FCGS had no significant correlation with age, sex or breed. However, the incidence of FCGS was associated with immunization, a history of homelessness and multicat rearing environments. The number of neutrophils and the serum amyloid A concentration were increased, and the percentage of cells positive for calicivirus antigen was high in all cases. All the cats had different degrees of dental calculus, and there were problems such as loss of alveolar bone or tooth resorption. Compared with those in healthy cats, the bacterial diversity and the abundance of anaerobic bacteria were significantly increased in cats with FCGS. Porphyromonas , Treponemas and Fusobacterium were abundant in the mouths of the affected cats and may be potential pathogens of FCGS. After tooth extraction, a shift could be seen in the composition of the oral microbiota in cats with FCGS. An isolated bacteria obtained from the mouths of the affected cats was homologous to P. gulae . Both the identified oral microbiota and the isolated strain of the cats with FCGS had high sensitivity to enrofloxacin and low sensitivity to metronidazole. This study provides support to current clinical criteria in diagnosing FCGS and proposes a more suitable antibiotic therapy.
Facial cosmetic conditions can manifest as post-inflammatory erythema, scars, pigmentation, enlarged pores, skin laxity, and photoaging. The microneedle fractional radiofrequency system (MFRS) is a new device that combines radiofrequency and microneedles and has been widely used for skin rejuvenation. Since MFRS is an invasive technique, this study aimed to evaluate whether the skin barrier functions might be impaired by this treatment, revealed by skin sensitivity and exacerbation of melasma.Twenty patients with Fitzpatrick grades III-IV facial conditions (skin laxity with melasma, n = 9; post-inflammatory erythema and scars, n = 5; and enlarged pores, n = 6) and treated with MFRS were enrolled. Transepidermal water loss (TEWL, using Ultrascan UC22), skin sensitivity (ten-item Sensitive Scale, SS-10), melanin index (MI), melasma area and severity index (MASI), red areas (VISIA), and thickness and density of the epidermis and dermis on ultrasonography were compared between baseline and 6 months after all treatment sessions.Twenty patients completed a 6-month follow-up after two MFRS treatments. During days 1-3 post-treatment, the TEWL values gradually increased to the peak and decreased to baseline levels (BD) on day 7. There was no significant difference in TEWL compared with baseline in month (M) 1, M3, and M6. There were no significant changes in the thickness and density of the epidermis. Although the thickness and density of the dermis increased, there was no significant difference compared to baseline. There was no significant difference in the MI, MASI, and SS-10 score before and after MFRS treatment. After treatment with MFRS, the red area and scarring reduced significantly (p < .01), and no significant difference was observed in other patients.MFRS is a safe and effective treatment for facial cosmetic conditions. The skin barrier function is not impaired by MFRS treatment, since it does not cause skin sensitivity or melasma exacerbation.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)