Code vulnerability detection method based on graph neural network by Hao CHEN, Ping YI

“…The schemes of using neural networks for vulnerability detection are mostly based on traditional natural language processing ideas, processing the code as array samples and ignoring the structural features in the code, which may omit possible vulnerabilities.A code vulnerability detection method based on graph neural network was proposed, which realized function-level code vulnerability detection through the control flow graph feature of the intermediate language.Firstly, the source code was compiled into an intermediate representation, and then the control flow graph containing structural information was extracted.At the same time, the word vector embedding algorithm was used to initialize the vector of basic block to extract the code semantic information.Then both of above were spliced to generate the graph structure sample data.The multilayer graph neural network model was trained and tested on graph structure data features.The open source vulnerability sample data set was used to generate test data to evaluate the method proposed.The results show that the method effectively improves the vulnerability detection ability.…”
Get full text

A seed-epidermis-feature-recognition-based lightweight peanut seed selection method for embedded systems by Dehao Li, Jinlong Huang, Xincheng Li, Zhaolei Yang, Xueke An, Pengfei Xu, Yuliang Yun

“…The transfer learning method was used to use four pre-trained models, EfficientNet_b0, EfficientNetv2-b0, MobileNet_v2_35_224, and NasNet_Mobile, as feature extraction layers, the input layer was added before the feature extraction layer, and the dropout and dense layers were added after the feature extraction layer to construct a classifier. …”
Get full text

Modern architectures convolutional neural networks in human activity recognition by H. Mahmoud

“…Convolutional networks indeed derive more relevant and complex features with every additional layer. …”
Get full text

Analysis of Cardiac Arrhythmias Based on ResNet-ICBAM-2DCNN Dual-Channel Feature Fusion by Chuanjiang Wang, Junhao Ma, Guohui Wei, Xiujuan Sun

“…Subsequently, in the primary channel, region of interest features are emphasized using a ResNet-ICBAM network model for feature extraction. …”
Get full text

A Lightweight Network with Domain Adaptation for Motor Imagery Recognition by Xinmin Ding, Zenghui Zhang, Kun Wang, Xiaolin Xiao, Minpeng Xu

“…This paper proposes an innovative method that combines a lightweight convolutional neural network (CNN) with domain adaptation. A lightweight feature extraction module is designed to extract key features from both the source and target domains, effectively reducing the model’s parameters and improving the real-time performance and computational efficiency. …”
Get full text

SECNN: Squeeze-and-Excitation Convolutional Neural Network for Sentence Classification by Shandong Yuan, Zili Zou, Han Zhou, Yun Ren, Jianping Wu, Kai Yan

“…Convolutional Neural Networks (CNNs) have gained prominence in this domain due to their capacity to extract n-gram features through parallel convolutional filters, effectively capturing local lexical correlations. …”
Get full text

A novel hybrid convolutional and transformer network for lymphoma classification by Mohamed Yacin Sikkandar, Sankar Ganesh Sundaram, Muteb Nasser Almeshari, S. Sabarunisha Begum, E. Siva Sankari, Yousef A. Alduraywish, Waeal J. Obidallah, Fahad Mansour Alotaibi

“…A Feature Fusion and Enhancement Module (FFEM) is introduced to dynamically integrate features from both pathways. …”
Get full text

Advancing student outcome predictions through generative adversarial networks by Helia Farhood, Ibrahim Joudah, Amin Beheshti, Samuel Muller

“…The ‘Math dataset’ has 395 observations and 33 features, whereas the ‘Exam dataset’ has 1000 observations and 8 features. …”
Get full text

Interaction based on method for spam detection in online social networks by Kan CHEN, Liang CHEN, Pei-dong ZHU, Yue-shan XIONG

“…In online social networks,advertisements,rumors and malicious links are propagated by spammers arbitrarily.They not only disturb users’usualaccess,but also bring about network security threats and social panics.In an attempt to deal with the spam problems,an information diffusion model was proposed to capture the features of spam propagation.Propagation behaviors are quantitatively analyzed to detect spam messages with a decision tree-based method.The effectiveness of proposed detection model is evaluated with real data from the micro-bloggingnetwork of Sina.The experimental results show that proposed model can effectively detect spams in Sina micro-bloggingnetwork.…”
Get full text

Automated essay scoring with SBERT embeddings and LSTM-Attention networks by Yuzhe Nie

“…Automated essay scoring (AES) is essential in the field of educational technology, providing rapid and accurate evaluations of student writing. This study presents an innovative AES method that integrates Sentence-BERT (SBERT) with Long Short-Term Memory (LSTM) networks and attention mechanisms to improve the scoring process. …”
Get full text

Prediction of Banks Efficiency Using Feature Selection Method: Comparison between Selected Machine Learning Models by Hamzeh F. Assous

“…Subsequently, 4 prediction models (i.e., SVM, CHAID, linear regression, and a neural network) were developed to choose the best fit. The performance metrics have also been evaluated. …”
Get full text

Improving deep convolutional neural networks with mixed maxout units by Hui-zhen ZHAO, Fu-xian LIU, Long-yue LI, Chang LUO

“…The maxout units have the problem of not delivering non-max features， resulting in the insufficient of pooling operation over a subspace that is composed of several linear feature mappings,when they are applied in deep convolutional neural networks.The mixed maxout (mixout) units were proposed to deal with this constrain.Firstly,the exponential probability of the feature mappings getting from different linear transformations was computed.Then,the averaging of a subspace of different feature mappings by the exponential probability was computed.Finally,the output was randomly sampled from the max feature and the mean value by the Bernoulli distribution,leading to the better utilizing of model averaging ability of dropout.The simple models and network in network models was built to evaluate the performance of mixout units.The results show that mixout units based models have better performance.…”
Get full text

Enhancing ECG disease detection accuracy through deep learning models and P-QRS-T waveform features. by Rida Nayyab, Asim Waris, Iqra Zaheer, Muhammad Jawad Khan, Fawwaz Hazzazi, Muhammad Adeel Ijaz, Hassan Ashraf, Syed Omer Gilani

“…The R-peaks of the clean signal were used to detect the subsequent morphological features, i.e., P-QRS-T intervals and amplitudes. The feature set was balanced using the Synthetic Minority Oversampling Technique for Nominal and Continuous (SMOTE-NC) and fed into Convolutional Neural Network (CNN) and Deep Neural Network (DNN) with 5-fold cross-validation. …”
Get full text

Towards edge-collaborative,lightweight and secure region proposal network by Jinbo XIONG, Renwan BI, Qianxin CHEN, Ximeng LIU

“…Aiming at the problem of image privacy leakage and computing efficiency in edge environment,a lightweight and secure region proposal network (SecRPN) was proposed.A series of secure computing protocols were designed based on the additive secret sharing scheme.Two non-collusive edge servers cooperate to perform calculation modules such as secure feature processing,secure anchor transformation,secure bounding-box correction,and secure non-maximum suppression.Theoretical analysis guarantees the correctness and security of SecRPN.The actual performance evaluation shows that SecRPN is outstanding in the computational cost and communication overhead compared with the existing works.…”
Get full text

An Energy-Efficient Broadcast MAC Protocol for Hybrid Vehicular Networks by DaeHun Yoo, WoongChul Choi

“…Then, we show our protocol's performance evaluation using ns-2.…”
Get full text

Hybrid Macroprogramming Wireless Networks of Embedded Systems with Declarative Naming by Chalermek Intanagonwiwat

“…DRN provides programming simplicity, expressiveness, tunability, on-the-fly reprogrammability, and in-network data aggregation for energy savings. None of existing macroprogramming paradigms supports all of the mentioned features. …”
Get full text

Bipolar disorder at mixed states and major depressive disorder with mixed features differ in peripheral biochemical parameters by Xiaohui Wu, Shuo Wang, Zhiang Niu, Yuncheng Zhu, Ping Sun, Wenxi Sun, Jun Chen, Yiru Fang

“…Network analysis and Principal Component Analysis (PCA) was also performed to investigate the relationships among these parameters. …”
Get full text

A novel early stage drip irrigation system cost estimation model based on management and environmental variables by Masoud Pourgholam-Amiji, Khaled Ahmadaali, Abdolmajid Liaghat

“…The two LCA and FOA algorithms produced the best estimation, according to the evaluation criteria results. Their RMSE for all features was 0.0020 and 0.0018, respectively, and their R2 was 0.94 and 0.94. …”
Get full text

Hyperspectral target detection based on graph sampling and aggregation network. by Tie Li, Hongfeng Jin, Zhiqiu Li

“…Upon reconstructing the image, the target data is extracted using residuals, and target detection is accomplished by minimizing the constraint energy. The model was evaluated on seven hyperspectral image datasets, and the experimental results demonstrated that the proposed graph sampling aggregation network model could proficiently detect targets with an average detection accuracy exceeding 99 . 8%, outperforming other comparative models. …”
Get full text

Websites and social networks of communes in Slovakia: development and current state by Bačík Vladimír, Klobučník Michal

“…One of the main features of today’s information society is the availability of data of various kinds provided by various companies and organisations. …”
Get full text