One-dimensional CNN Model of Network Traffic Classification based on Transfer Learning

Lingyun Yang,Yuning Dong,Zaijian Wang,Feifei Gao 한국인터넷정보학회 2024 KSII Transactions on Internet and Information Syst Vol.18 No.2

There are some problems in network traffic classification (NTC), such as complicated statistical features and insufficient training samples, which may cause poor classification effect. A NTC architecture based on one-dimensional Convolutional Neural Network (CNN) and transfer learning is proposed to tackle these problems and improve the fine-grained classification performance. The key points of the proposed architecture include: (1) Model classification--by extracting normalized rate feature set from original data, plus existing statistical features to optimize the CNN NTC model. (2) To apply transfer learning in the classification to improve NTC performance. We collect two typical network flows data from Youku and YouTube, and verify the proposed method through extensive experiments. The results show that compared with existing methods, our method could improve the classification accuracy by around 3-5%for Youku, and by about 7 to 27% for YouTube.

m6A-mediated upregulation of AC008 promotes osteoarthritis progression through the miR-328-3p‒AQP1/ANKH axis

Yang Jiashu,Zhang Ming,Yang Dawei,Ma Yunfei,Tang Yuting,Xing Mengying,Li Lingyun,Chen Li,Jin Yucui,Ma Changyan 생화학분자생물학회 2021 Experimental and molecular medicine Vol.53 No.-

Long noncoding RNAs (lncRNAs) have emerged as important regulators of osteoarthritis (OA), but the biological roles and clinical significance of most lncRNAs in OA are not fully understood. Microarray analysis was performed to identify differentially expressed lncRNAs, mRNAs, and miRNAs between normal and osteoarthritic cartilage. We found that AC008440.5 (abbreviated AC008), as well as AQP1 and ANKH, were highly expressed in osteoarthritic cartilage, whereas miR-328-3p was expressed at a low level in osteoarthritic cartilage. Functional assays showed that ectopic expression of AC008, AQP1, and ANKH significantly decreased chondrocyte viability and promoted chondrocyte apoptosis and extracellular matrix (ECM) degradation, whereas knockdown of AC008, AQP1, and ANKH resulted in the opposite effects. Moreover, miR-328-3p overexpression increased chondrocyte viability and attenuated chondrocyte apoptosis and ECM degradation, whereas inhibition of miR-328-3p resulted in the opposite effects. Bioinformatics analysis, RNA immunoprecipitation (RIP), and luciferase assays revealed that AC008 functioned as a competing endogenous RNA (ceRNA) to regulate miR-328-3p, which specifically targeted the AQP1 and ANKH genes. In addition, miR-328-3p significantly ameliorated MIA-induced OA, whereas AC008 accelerated OA progression in vivo. Furthermore, fat mass and obesity-associated (FTO)-mediated N6-methyladenosine demethylation downregulated AC008 transcription, while lower FTO expression led to upregulation of AC008 transcription in OA. In conclusion, our data reveal that AC008 plays a critical role in OA pathogenesis via the miR-328-3p‒AQP1/ANKH pathway, suggesting that AC008 may be a potential therapeutic target for OA.

A real-time sorting algorithm for in-beam PET of heavy-ion cancer therapy device

Ke, Lingyun,Yan, Junwei,Chen, Jinda,Wang, Changxin,Zhang, Xiuling,Du, Chengming,Hu, Minchi,Yang, Zuoqiao,Xu, Jiapeng,Qian, Yi,She, Qianshun,Yang, Haibo,Zhao, Hongyun,Pu, Tianlei,Pei, Changxu,Su, Hong Korean Nuclear Society 2021 Nuclear Engineering and Technology Vol.53 No.10

A real-time digital time-stamp sorting algorithm used in the In-Beam positron emission tomography (In-Beam PET) is presented. The algorithm is operated in the field programmable gate array (FPGA) and a small amount of registers, MUX and memory cells are used. It is developed for sorting the data of annihilation event from front-end circuits, so as to identify the coincidence events efficiently in a large amount of data. In the In-Beam PET, each annihilation event is detected by the detector array and digitized by the analog to digital converter (ADC) in Data Acquisition Unit (DAQU), with a resolution of 14 bits and sampling rate of 50 MS/s. Test and preliminary operation have been implemented, it can perform a sorting operation under the event count rate up to 1 MHz per channel, and support four channels in total, count rate up to 4 MHz. The performance of this algorithm has been verified by pulse generator and ²²Na radiation source, which can sort the events with chaotic order into chronological order completely. The application of this algorithm provides not only an efficient solution for selection of coincidence events, but also a design of electronic circuit with a small-scale structure.

A Hybrid Strategy for Fine-Grained Sentiment of Microblog

Ouyang Chunping,Luo Lingyun,Zhang Shuqing,Yang Xiaohua 보안공학연구지원센터 2014 International Journal of Database Theory and Appli Vol.7 No.6

Currently, most sentiment analysis of microblog has been focused on coarse-grained sentiment analysis, but fine-grained sentiment is better for reflecting the opinion of the public when they are facing the social focus. Therefore, a hybrid strategy which is a combination of Naïve Bayesian and two-layer CRFs is put forward, which has been applied to the fine-grained sentiment analysis of Chinese microblog. First, microblog is classified into two types: sentiment and non-sentiment by using Naïve Bayesian classification algorithm. And then the first-layer CRFs model is built for the topic emotional sentence. Finally CRFs algorithm is used again to do multi-classification to assign a specific sentiment category. Experimental results show that a good result in sentiment identification based on the combination of Naïve Bayesian and CRFs, and also show the advantage of the combination of Naïve Bayesian and CRFs interrelated with emotional sentence extraction based on CRFs.

Study on flexible Ga-In liquid metal-air battery with high performance

Lingyun Xiong,Jung Woo Lee,Nguyen Thuy Hang,Hankyu Lee,Manxiang Wang,Guicheng Liu,Woochul Yang 한국진공학회 2020 한국진공학회 학술발표회초록집 Vol.2020 No.2

Crashworthiness design of bionic-shell thin-walled tube under axial impact

Lingyun Qin,Shuyi Yang,Hongzhou Li,Juchuan Dai,Guosheng Wang,Qihui Ling,Zhewu Chen 대한기계학회 2023 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.37 No.7

Bionic structures have been widely utilized in the crashworthiness design of thin-walled structures due to their superior energy absorption capabilities. This study constructed a bionic-shell thin-walled tube (BST) with excellent crashworthiness based on the structural bionic principle using the shell shape cross-section as the prototype. First, the theoretical model of the mean crushing force (MCF) for BST under axial compression was developed. An experiment was conducted and the reliability of the finite element model was verified. Then, the effects of structural parameters, such as the number of ribs, wall thickness, and inner tube diameter on the crashworthiness of the BST were investigated using the finite element method. Finally, to obtain the ideal configuration of structural parameters, the BST was optimized using the response surface method (RSM) with specific energy absorption (SEA) and crushing force efficiency (CFE) as the optimization objectives and peak crushing force (PCF) as the constraint condition. The results showed that the BST with six ribs exhibited the best crashworthiness under the same mass. The optimized BST-6 was found to have better energy absorption performance than the double circular tube (DCT) and the bionic-horsetail thin-walled tube (BHT). Compared with the DCT, the SEA and CFE increased by 35.15 % and 32.23 %, respectively.

Generative Linguistic Steganography: A Comprehensive Review

Lingyun Xiang,Rong Wang,Zhongliang Yang,Yuling Liu 한국인터넷정보학회 2022 KSII Transactions on Internet and Information Syst Vol.16 No.3

Text steganography is one of the most imminent and promising research interests in the information security field. With the unprecedented success of the neural network and natural language processing (NLP), the last years have seen a surge of research on generative linguistic steganography (GLS). This paper provides a thorough and comprehensive review to summarize the existing key contributions, and creates a novel taxonomy for GLS according to NLP techniques and steganographic encoding algorithm, then summarizes the characteristics of generative linguistic steganographic methods properly to analyze the relationship and difference between each type of them. Meanwhile, this paper also comprehensively introduces and analyzes several evaluation metrics to evaluate the performance of GLS from diverse perspective. Finally, this paper concludes the future research work, which is more conducive to the follow-up research and innovation of researchers.

Identification and Functional Analysis of Acyl-Acyl Carrier Protein Δ9 Desaturase from Nannochloropsis oceanica

Yang Ruigang,Wang Hui,Zhu Lingyun,Zhu Lvyun,Liu Tianzhong,Zhang Dongyi 한국미생물학회 2023 The journal of microbiology Vol.61 No.1

The oleaginous marine microalga Nannochloropsis oceanica strain IMET1 has attracted increasing attention as a promising photosynthetic cell factory due to its unique excellent capacity to accumulate large amounts of triacylglycerols and eicosapentaenoic acid. To complete the genomic annotation for genes in the fatty acid biosynthesis pathway of N. oceanica, we conducted the present study to identify a novel candidate gene encoding the archetypical chloroplast stromal acyl-acyl carrier protein Δ9 desaturase. The full-length cDNA was generated using rapid-amplification of cDNA ends, and the structure of the coding region interrupted by four introns was determined. The RT-qPCR results demonstrated the upregulated transcriptional abundance of this gene under nitrogen starvation condition. Fluorescence localization studies using EGFP-fused protein revealed that the translated protein was localized in chloroplast stroma. The catalytic activity of the translated protein was characterized by inducible expression in Escherichia coli and a mutant yeast strain BY4389, indicating its potential desaturated capacity for palmitoyl-ACP (C16:0-ACP) and stearoyl-ACP (C18:0-ACP). Further functional complementation assay using BY4839 on plate demonstrated that the expressed enzyme restored the biosynthesis of oleic acid. These results support the desaturated activity of the expressed protein in chloroplast stroma to fulfill the biosynthesis and accumulation of monounsaturated fatty acids in N. oceanica strain IMET1.

The Application of Radiolabeled Targeted Molecular Probes for the Diagnosis and Treatment of Prostate Cancer

Cheng Luyi,Yang Tianshuo,Zhang Jun,Gao Feng,Yang Lingyun,Tao Weijing 대한영상의학회 2023 Korean Journal of Radiology Vol.24 No.6

Radiopharmaceuticals targeting prostate-specific membrane antigens (PSMA) are essential for the diagnosis, evaluation, and treatment of prostate cancer (PCa), particularly metastatic castration-resistant PCa, for which conventional treatment is ineffective. These molecular probes include [68Ga]PSMA, [18F]PSMA, [Al18F]PSMA, [99mTc]PSMA, and [89Zr]PSMA, which are widely used for diagnosis, and [177Lu]PSMA and [225Ac]PSMA, which are used for treatment. There are also new types of radiopharmaceuticals. Due to the differentiation and heterogeneity of tumor cells, a subtype of PCa with an extremely poor prognosis, referred to as neuroendocrine prostate cancer (NEPC), has emerged, and its diagnosis and treatment present great challenges. To improve the detection rate of NEPC and prolong patient survival, many researchers have investigated the use of relevant radiopharmaceuticals as targeted molecular probes for the detection and treatment of NEPC lesions, including DOTA-TOC and DOTA-TATE for somatostatin receptors, 4A06 for CUB domain-containing protein 1, and FDG. This review focused on the specific molecular targets and various radionuclides that have been developed for PCa in recent years, including those mentioned above and several others, and aimed to provide valuable up-to-date information and research ideas for future studies.

TFPI inhibits breast cancer progression by suppressing ERK/p38 MAPK signaling pathway

Xing Mengying,Yang Ying,Huang Jiaxue,Fang Yaqun,Jin Yucui,Li Lingyun,Chen Xiang,Zhu Xiaoxia,Ma Changyan 한국유전학회 2022 Genes & Genomics Vol.44 No.7

Background: Tissue factor pathway inhibitor-1 (TFPI) is a serine protease inhibitor, which is responsible for inactivating TF-induced coagulation. Recently, increasing studies revealed that TFPI was lowly expressed in tumor cells and exhibited the antitumor activity. Objective: The aim of this study was to explore the role and underlying molecular mechanisms of TFPI in breast cancer. Methods: The expression and prognostic value of TFPI were analyzed using UALCAN and Kaplan-Meier plotter website. The expression level of TFPI in breast cancer tissues and cells was examined by immunohistochemistry (IHC) and western blot analysis, respectively. Cellular proliferation was evaluated by CCK-8 and colony formation assays. Cell migration and invasion were determined by transwell assay. The methylation level of TFPI promoter was determined by methylation-specific PCR. Results: TFPI expression was significantly lower in breast cancer tissues and cells compared to normal breast tissues and normal breast cells. Patients with low TFPI levels showed worse overall survival (OS). Furthermore, overexpression of TFPI significantly inhibited the proliferation, migration and invasion of breast cancer cells. Conversely, knockdown of TFPI promoted the proliferation, migration and invasion of breast cancer cells. Mechanistically, TFPI inhibited the ERK/p38 MAPK signaling pathway in breast cancer. Moreover, DNA hypermethylation of TFPI promoter was responsible for the downregulation of TFPI in breast cancer cells. Conclusion: TFPI inhibited breast cancer cell proliferation, migration and invasion through inhibition of the ERK/p38 MAPK signaling pathway, suggesting that TFPI may serve as a novel prognostic biomarker and therapeutic target for breast cancer.