A network traffic classification method based on random forest and improved convolutional neural network by Bensheng YUN, Xiaoya GAN, Yaguan QIAN

“…In order to improve the efficiency and reduce the complexity of network traffic classification model, a classification method based on random forest and improved convolutional neural network was proposed.Firstly, the random forest was used to evaluate the importance of each feature of network traffic, and the feature was selected according to the importance ranking.Secondly, AdamW optimizer and triangular cyclic learning rate were adopted to optimize the convolutional neural network classification model.Then, the model was built on Spark cluster to realize the parallelization of model training.Adopting triangular cyclic learning rate with constant cycle amplitude, the experimental results of selecting 1 024, 400, 256 and 100 most important features as input show that the model accuracy is improved to 97.68%, 95.84%, 95.03% and 94.22%, respectively.The 256 most important features were selected and the experimental results based on adopting different learning rates show that the learning rate with half the cycle amplitude works best, the accuracy of the model is improved to 95.25%, and training time of the model is reduced by nearly half.…”
Get full text

A Copula-based Method for River Ecological Flow Quantification and Algal Bloom Risk Assessment in the Hanjiang River by NONG Xi-zhi, LAI Cheng, JING Zheng, YE Ye

“…It provides an efficient tool for analyzing ecological flow during a single algal bloom outbreak.(2) The multi-scenario conditional probability analysis demonstrates that risk probabilities of algal density differed significantly across different flow ranges, offering refined flow thresholds for reservoir operations and bloom prevention.(3) In complex hydro-ecological systems, it is necessary to integrate multi-factor models like Copula to avoid risk underestimation. …”
Get full text

Chromosome-Level Genome Assembly and Comparative Transcriptome Analyses Identified Energy Conservation as a Key Strategy for Anadromous Adaptation of the Hilsa Shad, <i>Tenualosa i... by Kishor Kumar Sarker, Liang Lu, Roland Nathan Mandal, Md Rashedur Rahman, Anirban Sarker, Mohammad Abdul Baki, Chenhong Li

“…We observed rapid expansion of gene families to facilitate efficient signaling and osmotic balance, as well as a substantial selection pressure in metabolism regulatory genes, potentially relevant to a highly anadromous fish. …”
Get full text

Deep Learning Approaches for Morphological Classification of Intestinal Organoids by Giovanni Cicceri, Sebastiano Di Bella, Simone Di Franco, Giorgio Stassi, Matilde Todaro, Salvatore Vitabile

“…The use of deep learning (DL) in organoid image analysis becomes crucial to handle complexity, variability, and large amounts of data efficiently and accurately, overcoming the limitations of traditional image processing approaches. …”
Get full text

Robust Network Traffic Classification Based on Information Bottleneck Neural Network by Wei Lin, Yu Chen

“…Recent advances in machine learning have improved NTC but often struggle with data labeling, encrypted traffic, and model complexity. This paper introduces a novel Information Bottleneck Neural Network (IBNN) to address these challenges by efficiently extracting essential features from raw traffic data while minimizing irrelevant information. …”
Get full text

Improved SLM algorithm for PAPR reduction in OFDM system by Ce JI, Wenjing ZHU, Ying WEI, Dianxia JIA

“…In order to reduce the peak to average power ratio (PAPR) of the conventional selective mapping (SLM) algorithm,decrease the transmission of side-band information,and improve the spectral efficiency in the orthogonal frequency division multiplexing (OFDM) system,the TL-SLM algorithm based on the conversion matrix and the chaotic sequence was proposed firstly.Although the TL-SLM algorithm could effectively decrease the transmission of side-band information,the reduction of PA P R was limited.To solve this problem,an improved TL-SLM algorithm based on the rotation vector was proposed,which was the TR-SLM algorithm.TR-SLM algorithm introduced the rotation vector to generate more time-domain alternative signals to further reducing the PA P R.The performance analysis shows that although the TL-SLM algorithm and the TR-SLM algorithm increase the complexity a little,the PA P R performance is effectively improved and the transmission of side-band information is greatly reduced.…”
Get full text

Spatial ratio of two fungal genotypes content of Naematelia aurantialba and Stereum hirsutum in nutritional growth substrate and fruiting bodies reveals their potential parasitic l... by Jianqiong Lan, Yongkang Zhang, Yingli Cai, Xiaofei Shi, Kaixuan Zhang, Jiacheng Huang, Chengmo Yang, Xinhua He, Fuqiang Yu, Wei Liu

“…Nine species-specific fragments were selected, with four primer pairs validated after evaluating amplification efficiency and melting curves. …”
Get full text

An energy-balanced multi-sensor scheduling scheme for collaborative target tracking in wireless sensor networks by Pengcheng Fu, Hongying Tang, Yongbo Cheng, Baoqing Li, Hanwang Qian, Xiaobing Yuan

“…More specifically, with regard to practical circumstances, we perform analysis on the target detection probability, as well as residual energy of sensor nodes, when selecting a suitable set of candidate sensor nodes. …”
Get full text

Recombinant HMG1 Protein Produced in Pichia pastoris: A Nonviral Gene Delivery Agent by A.R. Mistry, L. Falciola, L. Monaco, R. Tagliabue, G. Acerbis, A. Knight, R.P. Harbottle, M. Soria, M.E. Bianchi, C. Coutelle, S.L. Hart

“…HMG1 transfection complexes were not toxic to cultured cells, even at high concentrations.…”
Get full text

Recent Advances in Understanding the Keys Factors Influencing Pressurized Liquid Extraction of Secondary Metabolites: A Comprehensive Review by Pauline Donn, Sepidar Seyyedi-Mansour, Franklin Chamorro, Paula Garcia-Oliveira, Javier Echave, Ana Perez-Vazquez, Paula Barciela, Lucia Cassani, Miguel Angel Prieto

“…This communication provides an overview of recent advancements in understanding the key factors influencing the efficiency and selectivity of the PLE of these bioactive compounds. …”
Get full text

Application of multi-objective neural network algorithm in industrial polymerization reactors for reducing energy cost and maximising productivity by Fakhrony Sholahudin Rohman, Sharifah Rafidah Wan Alwi, Dinie Muhammad, Ashraf Azmi, Zainuddin Abd Manan, Jeng Shiun Lim, Hong An Er, Siti Nor Azreen Ahmad Termizi

“…Optimization on an industrial scale is a complex task that involves fine-tuning the performance of large-scale systems and applications to make them more efficient and effective. …”
Get full text

Design of nonlinear gradient sheet-based TPMS-lattice using artificial neural networks by Zhou Li, Junhao Li, Jiahao Tian, Shiqi Xia, Kai Li, Guanqiao Su, Yao Lu, Mengyuan Ren, Zhengyi Jiang

“…A new design methodology for the nonlinear gradient structure was proposed in this study, with the aim of achieving efficient and accurate modeling of complex and gradient sheet-based TPMS structures under specific performance objectives. …”
Get full text

A Validation Tool (VaPCE) for Postcoordinated SNOMED CT Expressions: Development and Usability Study by Tessa Ohlsen, Viola Hofer, Josef Ingenerf

“… Abstract BackgroundThe digitalization of health care has increased the demand for efficient data exchange, emphasizing semantic interoperability. …”
Get full text

Presenting a model for the establishment and maintenance of expert human resources in the government organizations of Sistan and Baluchestan province by Majid Reza Dahmardeh, Vahid pourshahabi, Amin Reza Kamalian, Habibollah Salaerzehi

“…Because maintenance measures are complementary to other human resource management measures and processes; even if the recruitment, selection, appointment and improvement operations are done properly, the results of management actions will not be very impressive without paying enough attention to maintenance. …”
Get full text

Typical characteristics of deep coal seams with high outburst risk, outburst inducing mechanism and prevention measures by Baiquan LIN, Wei YANG, Tong LIU

“…With the continuous increase in mining depth, the outburst risk of coal seam has significantly increased, with both the frequency and intensity of outbursts rising noticeably, posing huge challenges to the safe and efficient development of deep coal resources. This paper first analyzes the complex stress environment faced by coal seams at different depths in deep areas, then systematically studies the typical characteristics of high-risk coal seams in deep regions, elucidates the mechanisms of outburst induction in deep mining, and finally proposes countermeasures for preventing outburst disasters in deep mining. …”
Get full text

Integrative review of artificial intelligence applications in nursing: education, clinical practice, workload management, and professional perceptions by Rabie Adel El Arab, Omayma Abdulaziz Al Moosa, Mette Sagbakken, Ahmed Ghannam, Fuad H. Abuadas, Joel Somerville, Joel Somerville, Abbas Al Mutair, Abbas Al Mutair, Abbas Al Mutair, Abbas Al Mutair, Abbas Al Mutair

“…Learners also reported an increased cognitive load and heightened stress levels when navigating these more complex, AI-driven activities.Clinical decision support and monitoringAI-enabled alert algorithms and wearable sensors enabled nurses to detect subtle signs of patient deterioration and fever significantly earlier than conventional methods, supporting timelier clinical interventions. …”
Get full text

Ruthenium-based MOF catalysts for methanation of CO2 derivatives by Itziar Arnaiz, Carlos Márquez-Álvarez, Marcos Zubimendi, M. Asunción Molina, Andrew M. Beale, Manuel Sánchez-Sánchez, Joaquín Pérez-Pariente

“…Ru-BTC was particularly efficient: 67 % conversion and 96 % selectivity to CH4 at 150 ºC and 30 bars of H2 using a Ru/dimethylurea weight ratio of 1 %. …”
Get full text

Compressive Single-Pixel Read-Out of Single-Photon Quantum Walks on a Polymer Photonic Chip by Aveek Chandra, Shuin Jian Wu, Angelina Frank, James A. Grieve

“…Quantum photonic devices operating in the single photon regime require the detection and characterization of quantum states of light. …”
Get full text

Container Liner Shipping System Design Considering Methanol-Powered Vessels by Zhaokun Li, Xinke Yu, Jianning Shang, Kang Chen, Xu Xin, Wei Zhang, Shaoqiang Yu

“…While methanol, including both green and gray methanol, offers environmental benefits, its lower energy density introduces operational complexities. Motivated by the aforementioned background, we establish a bi-level programming model. …”
Get full text

Construction and Application of Monitoring System for Green Tarpaulin Cover Net in Mega Cities by Yang SUN, Dawei GAO, Haoye JIANG, Wanguang DU

“…Subsequently, representative samples of tarpaulin cover are selected for annotation, and a training dataset is constructed. …”
Get full text