An Indoor Scene Classification Method for Service Robot Based on CNN Feature by Shaopeng Liu, Guohui Tian

“…To solve this problem, an indoor scene classification method is proposed in this paper, which utilizes CNN feature of scene images to generate scene category features to classify scenes by a novel feature matching algorithm. …”
Get full text

Advancing EEG based stress detection using spiking neural networks and convolutional spiking neural networks by Aaditya Joshi, Paramveer Singh Matharu, Lokesh Malviya, Manoj Kumar, Akshay Jadhav

“…We apply Discrete Wavelet Transform (DWT) for feature extraction and evaluate CSNN performance on the Physionet EEG dataset, benchmarking it against traditional deep learning and machine learning methods. …”
Get full text

A pilot study of Telco’s next generation IT architecture evolution: business function virtualization (BFV) by Wen QIAO, Xiaozheng WANG, Zhenqiang SUN, Gan REN, Yunxin LIU, Aidong YANG, Peng WANG, Da WANG, Xiaozhou YE, Ye OUYANG

“…With the development of information and communication technologies, traditional telecom business support systems (BSS) are facing the challenge of agilely meeting the flexible needs from business.Application scenarization, service standardization, technology componentization and resource sharing have gradually become the consensual features among the evolution of telecom BSS architectures.A business function virtualization (BFV)-based BSS architecture, which is based on cloud-native, micro-services, containers, and DevOps technologies, was proposed.By embedding four components into the architecture, including standardized virtual network functions, modular design orchestrator, micro-service management framework, and multi-plane elastic computing controller, the system is able to deploy unitized system and distributed cloud.Therefore, the requirements of flexible telecom business development and frequent evolution of the system could be satisfied by the proposed BFV-based BSS architecture.In other words, the lightweight delivery of IT technologies and agile business support could be fulfilled by using the proposed BFV-based BSS architecture, and the proposed architecture will eventually become the standard architecture of next generation telecom BSS.…”
Get full text

A pilot study of Telco’s next generation IT architecture evolution: business function virtualization (BFV) by Wen QIAO, Xiaozheng WANG, Zhenqiang SUN, Gan REN, Yunxin LIU, Aidong YANG, Peng WANG, Da WANG, Xiaozhou YE, Ye OUYANG

“…With the development of information and communication technologies, traditional telecom business support systems (BSS) are facing the challenge of agilely meeting the flexible needs from business.Application scenarization, service standardization, technology componentization and resource sharing have gradually become the consensual features among the evolution of telecom BSS architectures.A business function virtualization (BFV)-based BSS architecture, which is based on cloud-native, micro-services, containers, and DevOps technologies, was proposed.By embedding four components into the architecture, including standardized virtual network functions, modular design orchestrator, micro-service management framework, and multi-plane elastic computing controller, the system is able to deploy unitized system and distributed cloud.Therefore, the requirements of flexible telecom business development and frequent evolution of the system could be satisfied by the proposed BFV-based BSS architecture.In other words, the lightweight delivery of IT technologies and agile business support could be fulfilled by using the proposed BFV-based BSS architecture, and the proposed architecture will eventually become the standard architecture of next generation telecom BSS.…”
Get full text

Thyroid disease classification using generative adversarial networks and Kolmogorov-Arnold network for three-class classification by Aysel Topşir, Ferdi Güler, Ecesu Çetin, Mehmet Furkan Burak, Melih Ağraz

“…This study introduces an advanced machine learning approach that integrates generative adversarial networks (GANs) for data augmentation and Kolmogorov-Arnold networks (KANs) for classification. …”
Get full text

A Spatio-Temporal Tensor Graph Neural Network-Based Method for Node-Link Prediction in Port Networks by Zhixin Xia, Zhangqi Zheng, Feiyang Wei, Yongshan Liu, Lu Yu

“…Therefore, to effectively utilize the information of the dynamic network and improve the prediction efficiency as well as the prediction accuracy, this paper proposes a spatio-temporal tensor graph neural network model, which learns graph structural features from both spatial and temporal aspects to capture the evolution of the dynamic network. …”
Get full text

Efficient Intrusion Detection System Data Preprocessing Using Deep Sparse Autoencoder with Differential Evolution by Saranya N., Anandakumar Haldorai

“…The efficiency of the transformation methods is evaluated with recursive Pearson correlation-based feature selection and graphical convolution neural network (G-CNN) methods.…”
Get full text

Differentiating biomarker features and familial characteristics of B-SNIP psychosis Biotypes by David A. Parker, Rebekah L. Trotti, Jennifer E. McDowell, Sarah K. Keedy, Matcheri S. Keshavan, Godfrey D. Pearlson, Elliot S. Gershon, Elena I. Ivleva, Ling-Yu Huang, Kodiak Sauer, S. Kristian Hill, John A. Sweeney, Carol A. Tamminga, Brett A. Clementz

Get full text

Comparative analysis of convolutional neural networks and traditional machine learning models for IVF live birth prediction: a retrospective analysis of 48514 IVF cycles and an eva... by Yu Liu, Yi Wang, Kai Huang, Hao Shi, Hang Xin, Shanjun Dai, Jinhao Liu, Xinhong Yang, Jianyuan Song, Fuli Zhang, Yihong Guo

“…The study also explores the feasibility of deploying such models in resource-limited clinical settings.DesignRetrospective cohort study based on EMR data using five models: CNN, Naïve Bayes, Random Forest, Decision Tree, and Feedforward Neural Network. Feature importance and model interpretability were evaluated using SHAP.SettingFirst Hospital of Zhengzhou University.Population48,514 fresh IVF cycles from August 2009 to May 2018.MethodsPreprocessed EMR data were used to train and evaluate five classification models predicting live birth outcomes. …”
Get full text

An efficient supervised framework for music mood recognition using autoencoder‐based optimised support vector regression model by Gaurav Agarwal, Hari Om

“…The experimental results are evaluated and compared with the existing classifiers including SVR, deep belief network (DBN) and Recurrent neural network (RNN). …”
Get full text

Challenges and Perspectives in Interpretable Music Auto-Tagging Using Perceptual Features by Vassilis Lyberatos, Spyridon Kantarelis, Edmund Dervakos, Giorgos Stamou

“…We developed a pipeline incorporating three types of information extraction procedures: 1) symbolic knowledge, 2) auxiliary deep neural networks, and 3) signal processing, to extract perceptual features of audio files, which were then used to train an explainable machine learning model to predict tags. …”
Get full text

Posterior-Based Analysis of Spatio-Temporal Features for Sign Language Assessment by Neha Tarigopula, Sandrine Tornay, Ozge Mercanoglu Sincan, Richard Bowden, Mathew Magimai.-Doss

“…Existing methods rely on handcrafted skeleton-based features for hand movement within a KL-HMM framework to identify errors in manual components. …”
Get full text

Self-Assembling Peptide–Co-PPIX Complex Catalyzes Photocatalytic Hydrogen Evolution and Forms Hydrogels by Nicholas Ryan Halloran, Abesh Banerjee, Giovanna Ghirlanda

“…Herein, we report a peptide-based system for light-driven hydrogen evolution from water under neutral conditions. The M1 peptide is an ABC triblock polymer featuring two coiled-coil alpha-helical regions flanking a water-soluble, polyanionic, intrinsically disordered region. …”
Get full text

Unveiling reductant chemistry in fabricating noble metal aerogels for superior oxygen evolution and ethanol oxidation by Ran Du, Jinying Wang, Ying Wang, René Hübner, Xuelin Fan, Irena Senkovska, Yue Hu, Stefan Kaskel, Alexander Eychmüller

Get full text

ADFCNN-BiLSTM: A Deep Neural Network Based on Attention and Deformable Convolution for Network Intrusion Detection by Bin Li, Jie Li, Mingyu Jia

“…Many existing intrusion detection studies often fail to fully extract the spatial features of network traffic and make reasonable use of temporal features. …”
Get full text

Adaptive evolution and functional significance of the PPARGC1A gene across diverse animal species by Seyed Mahdi Hosseini, Farman Ullah, Muhammad Zulfiqar Ahmad, Majid Pasandideh, Aixin Liang, Guohua Hua, Liguo Yang

Get full text

User-Independent Activity Recognition via Three-Stage GA-Based Feature Selection by Theresia Ratih Dewi Saputri, Adil Mehmood Khan, Seok-Won Lee

“…The proposed system uses simple time domain features with a single neural network and a three-stage genetic algorithm-based feature selection method for accurate user-independent activity recognition. …”
Get full text

Impact of agricultural industry transformation based on deep learning model evaluation and metaheuristic algorithms under dual carbon strategy by Xuan Zhao, Weiyun Tang, Qiuyan Liu, Hongtao Cao, Fei Chen

“…A hybrid deep learning model—combining Convolutional Neural Networks and Long Short-Term Memory networks—is developed to evaluate the effects of agricultural industry transformation. …”
Get full text

An optimized approach for predicting water quality features and a performance evaluation for mapping surface water potential zones based on Discriminant Analysis (DA), Geographical... by Abhijeet Das

Get full text

Bee‐Mediated Pollen Transport Across Five Urban Landscape Features: Buildings Are Important Barriers by Olivér I. Roper, Elsa Youngsteadt

Get full text