1D-CNN-based audio tampering detection using ENF signals.

The extensive adoption of digital audio recording has revolutionized its application in digital forensics, particularly in civil litigation and criminal prosecution. Electric network frequency (ENF) has emerged as a reliable technique in the field of audio forensics. However, the absence of comprehensive ENF reference datasets limits current ENF-based methods. To address this, this study introduces ATD, a blind audio forensics framework based on a one-dimensional convolutional neural network (1D-CNN) model. ATD can identify phase mutations and waveform discontinuities within the tampered ENF signal, without relying on an ENF reference database. To enhance feature extraction, the framework incorporates characteristics of the fundamental harmonics of ENF signals. In addition, a denoising method termed ENF noise reduction (ENR) based on the variational mode decomposition (VMD) and robust filtering algorithm (RFA) is proposed to reduce the impact of external noise on embedded electric network frequency signals. This study investigates three distinct types of audio tampering-deletion, insertion, and replacement-culminating in the design of binary-class tampering detection scenarios and four-class tampering detection scenarios tailored to these tampering types. ATD achieves a tampering detection accuracy of over 93% in the four-class scenario and exceeds 96% in the binary-class scenario. The effectiveness, efficiency, adaptability, and robustness of ATD in the two and four classification scenarios have been confirmed by extensive experiments.

Identifying key bird species and geographical hotspots of avian influenza A (H7N9) virus in China.

BACKGROUND: In China since the first human infection of avian influenza A (H7N9) virus was identified in 2013, it has caused serious public health concerns due to its wide spread and high mortality rate. Evidence shows that bird migration plays an essential role in global spread of avian influenza viruses. Accordingly, in this paper, we aim to identify key bird species and geographical hotspots that are relevant to the transmission of avian influenza A (H7N9) virus in China. METHODS: We first conducted phylogenetic analysis on 626 viral sequences of avian influenza A (H7N9) virus isolated in chicken, which were collected from the Global Initiative on Sharing All Influenza Data (GISAID), to reveal geographical spread and molecular evolution of the virus in China. Then, we adopted the cross correlation function (CCF) to explore the relationship between the identified influenza A (H7N9) cases and the spatiotemporal distribution of migratory birds. Here, the spatiotemporal distribution of bird species was generated based on bird observation data collected from China Bird Reports, which consists of 157 272 observation records about 1145 bird species. Finally, we employed a kernel density estimator to identify geographical hotspots of bird habitat/stopover that are relevant to the influenza A (H7N9) infections. RESULTS: Phylogenetic analysis reveals the evolutionary and geographical patterns of influenza A (H7N9) infections, where cases in the same or nearby municipality/provinces are clustered together with small evolutionary differences. Moreover, three epidemic waves in chicken along the East Asian-Australasian flyway in China are distinguished from the phylogenetic tree. The CCF analysis identifies possible migratory bird species that are relevant to the influenza A(H7N9) infections in Shanghai, Jiangsu, Zhejiang, Fujian, Jiangxi, and Guangdong in China, where the six municipality/provinces account for 91.2% of the total number of isolated H7N9 cases in chicken in GISAID. Based on the spatial distribution of identified bird species, geographical hotspots are further estimated and illustrated within these typical municipality/provinces. CONCLUSIONS: In this paper, we have identified key bird species and geographical hotspots that are relevant to the spread of influenza A (H7N9) virus. The results and findings could provide sentinel signal and evidence for active surveillance, as well as strategic control of influenza A (H7N9) transmission in China.

Social network supported process recommender system.

Process recommendation technologies have gained more and more attention in the field of intelligent business process modeling to assist the process modeling. However, most of the existing technologies only use the process structure analysis and do not take the social features of processes into account, while the process modeling is complex and comprehensive in most situations. This paper studies the feasibility of social network research technologies on process recommendation and builds a social network system of processes based on the features similarities. Then, three process matching degree measurements are presented and the system implementation is discussed subsequently. Finally, experimental evaluations and future works are introduced.

[Clinical observation of fluorescence endoscopy in medical diagnosis].

It's difficult to diagnose precancerous lesion and early cancer for a long time, because both of them haven't typical morphological characteristics. As a novel diagnostic modality, fluorescence endoscopy can accurately reflect minimal changes in human's tissue, thus making a meaningful progress for cancer diagnosing. 200 patients were examined by fluorescence endoscopy to evaluate the diagnostic value. The overall accuracy, sensitivity and specificity for detecting malignant gastrointestinal tumor was 94.0%, 94.6% and 93.5%, respectively. Thus, fluorescence endoscopy can be used to diagnose malignant gastrointestinal tumors with high validity and reliability, and is advantageous over conventional white light endoscopy especially in detecting the atypical and suspicious lesions. Furthermore, fluorescence endoscopy can also guide target biopsy, is significant to improve the early cancer detection rate, has a broad development prospect.