Search

With the wide deployment of digital image capturing equipment, the need of denoising to produce a crystal clear image from noisy capture environment has become indispensable. In this work, a novel type-2 fuzzy-based filter is proposed for denoising images corrupted by impulse noise, especially for the high-density salt-and-pepper noise. It operates two stages, namely, type-2 fuzzy identifier and matrix completion denoiser. In the proposed method, the type-2 fuzzy identifier is first employed to identify and trim the entries contaminated by impulse noise in the data matrix from fuzzy system. Then, the trimmed data matrix is utilized to retrieve the noiseless data matrix with the matrix completion technology. Herein, a novel matrix completion technique is developed without $a priori$ rank information compared with its counterparts. Simulation results are presented which vividly show the denoised images obtained by the proposed method can achieve crystal clear image with strong structural integrity, and are showing good performance in terms of peak signal-to-noise ratio (PSNR).

Speech emotion recognition plays an important role in many applications, but the task is challenging due to various factors such as background noise, different speaker speech characteristics, etc. The well known speech emotion recognition system ACRNN uses CNN to extract local features of speech signals and attention mechanism focuses on the parts with prominent emotions. However, it has no ability to capture long-term global information and it also has no ability to jointly attend to the information from different representation subspaces at different positions because only one single attention module is used. In order to settle out the drawbacks of ACRNN, CoRNN is proposed in this letter by applying Conformer to replace the modules of CNN and attention module. The experimental results on IEMOCAP dataset demonstrate the unweighted average recall of the proposed CoRNN can achieve 65.53%, which improves 0.79% comparing with ACRNN.

Propose: Autophagy plays a complicated role in cancer progression. This study aims at assessing the function of ATG5-induced autophagy in progression of lung squamous cell carcinoma and its upstream mechanism. Method: TCGA database of lung squamous cell carcinoma was analyzed to explore the differentially expressed miRNAs and mRNAs and relative prognosis. RT-PCR and Western blot were performed to evaluate autophagy relative gene expression level in human lung squamous cell carcinoma cell Lines. Autophagy flux was observed using transmission electron microscopy and immunofluorescence. Meanwhile, binding relationship of potential target miRNA and mRNAs were also confirmed using Dual-luciferase reporter gene assay. Lung metastatic model was established to evaluated the effect of targeting protein and miRNA. Result: High level expression of ATG5 was detected in LUSC patients. Relative experiments confirmed that ATG5 silencing could decrease the autophagy flux in LUSC. In addition, our research revealed that there is a binding sites between hsa-mir-30a-5p and 3′-UTR of ATG5. Mimic miR-30a-5p suppresses ATG5-mediated autophagy in lung squamous cell carcinoma cells. The in vivo experiments confirmed that miR-30a-5p could attenuate lung squamous cell carcinoma progression through the autophagy pathway. Conclusion: Accordingly, the in vivo and in vitro study in our research have demonstrated that miR-30a-5p inhibits lung squamous cell carcinoma progression via ATG5-mediated autophagy.

ImportanceAn accurate and robust artificial intelligence (AI) algorithm for detecting cancer in digital breast tomosynthesis (DBT) could significantly improve detection accuracy and reduce health care costs worldwide.ObjectivesTo make training and evaluation data for the development of AI algorithms for DBT analysis available, to develop well-defined benchmarks, and to create publicly available code for existing methods.Design, Setting, and ParticipantsThis diagnostic study is based on a multi-institutional international grand challenge in which research teams developed algorithms to detect lesions in DBT. A data set of 22 032 reconstructed DBT volumes was made available to research teams. Phase 1, in which teams were provided 700 scans from the training set, 120 from the validation set, and 180 from the test set, took place from December 2020 to January 2021, and phase 2, in which teams were given the full data set, took place from May to July 2021.Main Outcomes and MeasuresThe overall performance was evaluated by mean sensitivity for biopsied lesions using only DBT volumes with biopsied lesions; ties were broken by including all DBT volumes.ResultsA total of 8 teams participated in the challenge. The team with the highest mean sensitivity for biopsied lesions was the NYU B-Team, with 0.957 (95% CI, 0.924-0.984), and the second-place team, ZeDuS, had a mean sensitivity of 0.926 (95% CI, 0.881-0.964). When the results were aggregated, the mean sensitivity for all submitted algorithms was 0.879; for only those who participated in phase 2, it was 0.926.Conclusions and RelevanceIn this diagnostic study, an international competition produced algorithms with high sensitivity for using AI to detect lesions on DBT images. A standardized performance benchmark for the detection task using publicly available clinical imaging data was released, with detailed descriptions and analyses of submitted algorithms accompanied by a public release of their predictions and code for selected methods. These resources will serve as a foundation for future research on computer-assisted diagnosis methods for DBT, significantly lowering the barrier of entry for new researchers.

Prosodic phrasing is an important factor that affects naturalness and intelligibility in text-to-speech synthesis. Studies show that deep learning techniques improve prosodic phrasing when large text and speech corpus are available. However, for low-resource languages, such as Mongolian, prosodic phrasing remains a challenge for various reasons. First, the database suitable for system training is limited. Second, word composition knowledge that is prosody-informing has not been used in prosodic phrase modeling. To address these problems, in this article, we propose a feature augmentation method in conjunction with a self-attention neural classifier. We augment input text with morphological and phonological decompositions of words to enhance the text encoder. We study the use of self-attention classifier, that makes use of global context of a sentence, as a decoder for phrase break prediction. Both objective and subjective evaluations validate the effectiveness of the proposed phrase break prediction framework, that consistently improves voice quality in a Mongolian text-to-speech synthesis system.

Most of the existing feature representations for spoofing countermeasures consider information either from the magnitude or phase spectrum. We hypothesize that both magnitude and phase spectra can be beneficial for spoofing detection (SD) when collectively used to capture the signal artifacts. In this work, we propose a novel feature referred to as modified magnitude-phase spectrum (MMPS) to capture both magnitude and phase information from the speech signal. The constant-Q transform is used to obtain the magnitude and phase information in terms of MMPS, which can be denoted as CQT-MMPS. We then use this information for the proposal of a handcrafted feature, namely, constant-Q modified octave coefficients (CQMOC). To evaluate the proposed CQT-MMPS and CQMOC features, three classic anti-spoofing models are adopted, including the Gaussian mixture model (GMM), the light CNN (LCNN) and the ResNet. Additionally, since there is usually no prior knowledge about the spoofing kind in real-world applications, two novel methods referred to as three-class classifiers with maximum spoofing-score (TCMS) and multi-task learning (MTL) are designed for unknown-kind SD (UKSD). The experimental results on ASVspoof 2019 corpus show that CQMOC outperforms most of the commonly-used handcrafted features, and the CQT-based MMPS performs better than the magnitude-phase spectrum and the commonly-used log power spectrum. Further, the MMPS-based systems can achieve comparable or even better performance when compared with the state-of-the-art systems. We find that the newly-designed TCMS and MTL methods outperform the combination-based method for UKSD and meanwhile, generalize much better than the respective-kind-based methods in cross-spoofing-kind evaluation scenarios.

Sediments are the major sink for selenium (Se) in aquatic environments. Se speciation in sediments is crucial for its bioavailability and the toxicity in benthos but this is relatively understudied. In this study, selenite (Se(IV)) and seleno-L-methionine (Se-Met) were respectively added to sediments for 90 and 7 days, and the accumulation and depuration of Se in the oligochaete Lumbriculus variegatus was investigated. The background levels of Se in the river sediments, fish flakes, and L. variegatus were also detected. Without the presence of worms, the levels of Se(IV) in the sediments were relatively stable within 7 d but showed a decreasing trend during the 90 d of aging. In contrast, Se-Met in the sediments showed a sharp decrease within 3 d of aging. The LC50-96h values of Se(IV) and Se-Met in L. variegatus were 372.6 and 9.4 µg/g. Interestingly, the dominant Se species in Se(IV)- or Se-Met-treated L. variegatus was Se-Met, whose levels were increased with time in 7 days of exposure. Se was barely depurated from L. variegatus during the 8 d of depuration period. This study has provided indispensable data on the levels of total Se in the abiotic and biotic matrices and the biodynamics of Se in a representative benthos, which could better understand the ecological risk of Se to the freshwater benthic communities.

Sediments are the major sink for selenium (Se) in aquatic environments. Se speciation in sediments is crucial for its bioavailability and toxicity in benthos, but this is relatively understudied. In this study, the background levels of Se in the river sediments, fish flakes, and Lumbriculus variegatus were also detected. Then, the dynamic changes of selenium speciation and concentrations in sediments were investigated after adding selenite (Se(IV)) and seleno-L-methionine (Se-Met) in the sediments for 90 and 7 days, and the accumulation and depuration of Se(IV) and Se-Met for 7 days in the oligochaete L. variegatus were also explored. Without the presence of worms, the levels of Se(IV) in the sediments were relatively stable within 7 days but showed a decreasing trend during the 90 days of aging. In contrast, Se-Met in the sediments showed a sharp decrease within 3 days of aging. The LC

Previous works in synthetic speech detection have focused on features based on magnitude or phase spectrum. In this study, to extract useful discriminative information for synthetic speech detection, the authors propose a feature based on magnitude-phase spectrum (MPS), combining magnitude- and phase-spectra information. The proposed feature is termed as constant-Q magnitude-phase coefficient (CMPC), which is obtained by combining constant-Q transform (CQT), MPS, uniform resampling, and discrete cosine transform. The CQT used in this study is a long-term window transform, which can provide the basis for CMPC to capture important artefacts of synthetic speech. Such artefacts are obtained using a unit selection algorithm, which have difficulties when based on the short-term window transform. Uniform resampling aims to convert MPS from the octave domain into the linear domain. The discrete cosine transform is used when extracting principal components to remove correlations among the feature dimensions. The experimental results on AVspoof and ASVspoof 2015 corpora show that CMPC performs better than some commonly used features based on magnitude or phase spectrum alone. Their system based on CMPC outperforms many known systems.

In text-to-speech or voice conversion based synthetic speech detection, it is a common practice that spectral information over the entire frequency band is used for feature representation. We propose a new method, referred to as subband transform, that characterizes the signals by subband. It is found that subband transform captures the artifacts in synthetic speech more effectively than full band transform. We propose equal subband transform, octave subband transform, and mel subband transform for three novel features, namely, constant-Q equal subband transform (CQ-EST), constant-Q octave subband transform (CQ-OST) and discrete Fourier mel subband transform (DF-MST). We evaluate the three features on the ASVspoof 2015, noisy ASVspoof 2015 and ASVspoof 2019 logical access corpora. The experiments show that the proposed CQ-EST feature achieves an average equal error rate of 0.056% on ASVspoof 2015 evaluation set. The study observes that the features based on subband transform outperform those based on full band transform under both clean and noisy conditions. In addition, the tandem detection cost function of CQ-OST can reach 0.188 on ASVspoof 2019 logical access evaluation set.

Conventional speaker verification systems become frail or incompetent while facing attack from spoofed speech. Presently many anti-spoofing countermeasures have been studied for automatic speaker verification. It has been known that the salient feature is of a more important role rather than the selection of classifiers in the current research field of spoofing detection. The effectiveness of constant-Q transform (CQT) has been demonstrated for anti-spoofing feature analysis in many research literatures on automatic speaker verification. On the basis of CQT-based information sub-features, i.e. octave-band principal information (OPI), full-band principal information (FPI), short-term spectral statistics information (STSSI) and magnitude-phase energy information (MPEI), three concatenated features are proposed by investigating their information complementarity in this paper, the first one is constant-Q statistics-plus-principal information coefficients (CQSPIC) by combining OPI, FPI and STSSI; the second one is constant-Q energy-plus-principal information coefficients (CQEPIC) by combining OPI, FPI and MPEI and the third one is constant-Q energy-statistics-principal information coefficients (CESPIC) by combining OPI, FPI, MPEI and STSSI. In this paper, we set up deep neural network (DNN) classifiers for evaluation of the proposed features. Experiments show that the proposed features can outperform some commonly used features meanwhile the proposed systems give better or comparable performance comparing with state-of-the-art performance on ASVspoof 2019 logical access and physical access corpus.

A fully-automated deep learning algorithm matched performance of radiologists in assessment of knee osteoarthritis severity in radiographs using the Kellgren-Lawrence grading system. Purpose To develop an automated deep learning-based algorithm that jointly uses Posterior-Anterior (PA) and Lateral (LAT) views of knee radiographs to assess knee osteoarthritis severity according to the Kellgren-Lawrence grading system. Materials and methods We used a dataset of 9739 exams from 2802 patients from Multicenter Osteoarthritis Study (MOST). The dataset was divided into a training set of 2040 patients, a validation set of 259 patients and a test set of 503 patients. A novel deep learning-based method was utilized for assessment of knee OA in two steps: (1) localization of knee joints in the images, (2) classification according to the KL grading system. Our method used both PA and LAT views as the input to the model. The scores generated by the algorithm were compared to the grades provided in the MOST dataset for the entire test set as well as grades provided by 5 radiologists at our institution for a subset of the test set. Results The model obtained a multi-class accuracy of 71.90% on the entire test set when compared to the ratings provided in the MOST dataset. The quadratic weighted Kappa coefficient for this set was 0.9066. The average quadratic weighted Kappa between all pairs of radiologists from our institution who took part in the study was 0.748. The average quadratic-weighted Kappa between the algorithm and the radiologists at our institution was 0.769. Conclusion The proposed model performed demonstrated equivalency of KL classification to MSK radiologists, but clearly superior reproducibility. Our model also agreed with radiologists at our institution to the same extent as the radiologists with each other. The algorithm could be used to provide reproducible assessment of knee osteoarthritis severity.

This article focuses on extracting information from the octave power spectra of long-term constant-Q transform (CQT) for spoofing attack detection. A novel framework based on multi-level transform (MLT) is proposed that can capture the relevant information from octave power spectra using level by level in a multi-level manner. We then derive a novel feature referred to as constant-Q multi-level coefficient (CMC) based on proposed MLT. The proposed feature is evaluated on synthetic as well as replay speech detection studies on ASVspoof 2015 and ASVspoof 2017 version 2.0 database, respectively. We find the proposed CMC feature outperforms the conventional constant-Q cepstral coefficient based long-term feature obtained from linear power spectrum after uniform resampling. This depicts the usefulness of MLT to extract salient artifacts from octave power spectrum. Further, the proposed CMC feature performs better than the existing the well known other state-of-the-art systems for spoofing attack detection that showcases its importance.

As a natural flavonolignan, silibinin is reported to possess multiple biological activities, while the inhibitory potential of silibinin on carbohydrate-hydrolyzing enzymes is still unclear. Therefore, in this study, the inhibitory effect and underlying mechanism of silibinin against α-amylase/α-glucosidase were investigated. The results indicated that silibinin showed a strong inhibitory efficiency against α-amylase/α-glucosidase in noncompetitive manners and exhibited synergistic inhibition against α-glucosidase with acarbose. However, interestingly, the inhibitory effect of silibinin was significantly hindered in various milk protein-rich environments, but this phenomenon disappeared after simulated gastrointestinal digestion of milk proteins in vitro. Furthermore, silibinin could combine with the inactive site of α-amylase/α-glucosidase and change the microenvironment and secondary structure of the enzymes, thereby influencing the catalytic efficiency of enzymes. This research suggested that silibinin could be used as a novel carbohydrate-hydrolyzing enzyme inhibitor, and milk beverages rich in silibinin had the potential for further application in antidiabetic dietary or medicine.

The pathophysiology of cardiac hypertrophy is complex and multifactorial. Both the store-operated Ca2+ entry (SOCE) and excessive autophagy are the major causative factors for pathological cardiac hypertrophy. However, it is unclear whether these two causative factors are interdependent. In this study, we examined the functional role of SOCE and Orai1 in angiotensin II (Ang II)-induced autophagy and hypertrophy using in vitro neonatal rat cardiomyocytes (NRCMs) and in vivo mouse model, respectively. We show that YM-58483 or SKF-96365 mediated pharmacological inhibition of SOCE, or silencing of Orai1 with Orail-siRNA inhibited Ang II-induced cardiomyocyte autophagy both in vitro and in vivo. Also, the knockdown of Orai1 attenuated Ang II-induced pathological cardiac hypertrophy. Together, these data suggest that Ang II promotes excessive cardiomyocyte autophagy through SOCE/Orai1 which can be the prime contributing factors in cardiac hypertrophy.

Background: Persisters make biofilm infections difficult to cure, the low content of persisters in biofilm and the difficulty of obtaining them are outstanding problems in research, finding a reliable method to obtain a sufficient amount of persisters is the key to research. Methods: In this study, C.albicans strain ATCC10231 and S.epidermidis ATCC35984 were used to culture mixed biofilms on the surface of a titanium metal coupon. Tetracycline, gentamicin, 5-fluorocytosine(5-Fc), caspofungin, rifampicin, fluconazole and carbonyl cyanide m-chlorophenylhydrazone (CCCP) were used to induce the dormancy of biofilms to produce persisters. Ciprofloxacin and amphotericin B were used to kill the non dormant bacteria, and then the persisters were screened. Results:The study showed that dormancy induced by tetracycline and 5-Fc could significantly increase the persister levels of S.epidermidis and C.albicans, respectively. After the induced persisters were re-cultured, there was no significant change in antibiotic sensitivity compared with before induction.Scanning electron microscope(SEM) observations showed that after dormancy induction, the surface morphology of C.albicans in the mixed biofilm showed convex changes, and the volume of S.epidermidis decreased. Confocal laser scanning microscope (CLSM)observation showed that the mixed biofilm with high content of persisters did not dissolve under the killing of antibiotics, and the biofilm with low content of persisters dissolved in large area. Conclusions: Induction of dormancy is a reliable method for the formation of persistent bacteria in C.albicans-S.epidermidis mixed biofilm.

In this study, we propose a method for acoustic event diarization based on a feature of deep embedding and a clustering algorithm of integer linear programming. The deep embedding learned by deep auto-encoder network is used to represent the properties of different classes of acoustic events, and then the integer linear programming is adopted for merging audio segments belonging to the same class of acoustic events. Four kinds of TV/movie audios (21.5 h in total) are used as experimental data, including Sport, Situation comedy, Award ceremony, and Action movie. We compare the deep embedding with state-of-the-art features. Further, the clustering algorithm of integer linear programming is compared with other clustering algorithms adopted in previous works. Finally, the proposed method is compared to both supervised and unsupervised methods on four kinds of TV/movie audios. The results show that the proposed method is superior to other unsupervised methods based on agglomerative information bottleneck, Bayesian information criterion and spectral clustering, and is little inferior to the supervised method based on deep neural network in terms of acoustic event error.

A discriminative feature extraction method for playback speech detection is proposed, it relies on the finding that frame-wise magnitude-spectrum weight (FWMW) can enlarge the difference between genuine speech and playback speech. The proposed FWMW is obtained by supplying the sum of every frame magnitude spectrum frequency bin as the weight on the frame magnitude spectrum. Then, a new feature based on FWMW is proposed, namely constant-Q weight segmentation coefficients (CQWSCs). The experimental result on ASVspoof 2017 version 2.0 evaluation set using CQWSC indicates that: (i) FWMW can make the proposed feature has more discriminative ability and the equal error rate can decline 15.53 and 19.18% under Gaussian mixture model and deep neural network, respectively, and (ii) CQWSC performs better than some commonly used features.

The playback speech contains information from the environment, playback and recorder used. This work focuses on proposal of a novel normalization scheme, namely, low frequency frame-wise normalization (LFFN) as one of the modules in feature extraction process that is hypothesized to help in capturing the artifacts from the playback speech. It is based on low frequency bin processing that is performed frame-wise and hence its name. The constant-Q transform (CQT) based features are found to provide the benchmark results for detection of spoofing attacks. In this work, LFFN is combined with CQT to extract two new features from octave and linear power spectra, respectively. The first one is obtained by CQT, LFFN and octave segmentation that is referred to as constant-Q normalization segmentation coefficients (CQNSC). The latter uses conventional constant-Q cepstral coefficient (CQCC) and LFFN to obtain constant-Q normalization cepstral coefficients (CQNCC). The studies are performed on ASVspoof 2017 version 2.0 corpus that is designed for studying playback speech detection. The experimental results show the effectiveness of proposed LFFN with CQT based features. We obtain equal error rate of 10.63% and 10.31% for CQNSC and CQNCC features on the evaluation set of ASVspoof 2017 version 2.0 corpus, respectively.

Automatic speaker verification systems are prone to various spoofing attacks. The convolutional neural networks are found to be effective for detection of spoofing attacks. However, they lack spatial information and relationship of low-level features with the pooling layer. On the other hand, capsule networks use vectors to record spatial information and the probability of presence simultaneously. They are known to be effective for detection of forged images and videos. In this work, we study capsule networks for replay attack detection. We consider different input features to capsule network and study on recent ASVspoof 2019 physical access corpus. The studies suggest the proposed capsule network based system performs effectively and the performance is comparable to state-of-the-art single systems for replay attack detection.

Energy system information valuable for electricity access planning such as the locations and connectivity of electricity transmission and distribution towers, termed the power grid, is often incomplete, outdated, or altogether unavailable. Furthermore, conventional means for collecting this information is costly and limited. We propose to automatically map the grid in overhead remotely sensed imagery using deep learning. Towards this goal, we develop and publicly-release a large dataset ($263km^2$) of overhead imagery with ground truth for the power grid, to our knowledge this is the first dataset of its kind in the public domain. Additionally, we propose scoring metrics and baseline algorithms for two grid mapping tasks: (1) tower recognition and (2) power line interconnection (i.e., estimating a graph representation of the grid). We hope the availability of the training data, scoring metrics, and baselines will facilitate rapid progress on this important problem to help decision-makers address the energy needs of societies around the world.

The recent advances in voice conversion (VC) and text-to-speech (TTS) make it possible to produce natural sounding speech that poses threat to automatic speaker verification (ASV) systems. To this end, research on spoofing countermeasures has gained attention to protect ASV systems from such attacks. While the advanced spoofing countermeasures are able to detect known nature of spoofing attacks, they are not that effective under unknown attacks. In this work, we propose a novel data augmentation technique using a-law and mu-law based signal companding. We believe that the proposed method has an edge over traditional data augmentation by adding small perturbation or quantization noise. The studies are conducted on ASVspoof 2019 logical access corpus using light convolutional neural network based system. We find that the proposed data augmentation technique based on signal companding outperforms the state-of-the-art spoofing countermeasures showing ability to handle unknown nature of attacks., Comment: 5 pages, Accepted for publication in International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2021

MDD (major depressive disorder) is a serious, often chronic, and disabling mental disorder, which affects various brain areas. MDD is characterized by at least two weeks of pervasive low mood, low self-esteem, and loss of interest or pleasure in normally enjoyable activities. Stress model including chronic stress and early life stress could be the trigger for MDD and neurotransmitter disorder theory is the mainstream explanation of the disease. MDD would cause disfunction of the brain from different aspects. The MDD mainly affect the brain structure by neurotoxic progress, which includes multiple pathways and neurotransmitter causing the brain structural changes. Hippocampus and mPFC are the most common brain areas could be affected by the MDD, the structural changes could be found by fMRI. The review would focus on introducing mainstream models and how they affect the brain structure. At the end, this review would also involve the regular antidepressants and aspects of future study.

In order to improve the performance of hand-crafted features to detect playback speech, two discriminative features, constant-Q variance-based octave coefficients and constant-Q mean-based octave coefficients, are proposed for playback speech detection in this work. They rely on our findings that variance-based modified log magnitude spectrum and mean-based modified log magnitude spectrum can enhance the discriminative power between genuine speech and playback speech. Then constant-Q variance-based octave coefficients (constant-Q mean-based octave coefficients) can be obtained by combining variance-based modified log magnitude spectrum (mean-based modified log magnitude spectrum), octave segmentation, and discrete cosine transform. Finally, constant-Q variance-based octave coefficients and constant-Q mean-based octave coefficients are evaluated on ASVspoof 2017 corpus version 2.0 and ASVspoof 2019 physical access, respectively. Experimental results show that variance-based modified log magnitude spectrum and mean-based modified log magnitude spectrum can produce discriminative features toward playback speech. Further results on the two databases show that constant-Q variance-based octave coefficients and constant-Q mean-based octave coefficients can perform better than some common features, such as mel frequency cepstral coefficients and constant-Q cepstral coefficients.