Context-Free Word Importance Scores for Attacking Neural Networks

Shakeel, Nimrah; Shakeel, Saifullah

doi:10.47852/bonviewjcce2202406

Cited by 39 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The self-adaptive BP network structure can ensure that the model has better practical analysis effect in the process of analyzing teaching evaluation index. However, due to large data scale in colleges and universities, a single hidden layer in the adaptive BP will limit calculation and prediction ability of model [16] . Based on this, this paper introduces the deep denoising auto encoder (DDAE) to enhance the robustness of adaptive BP, and uses support vector regression (SVR) as model predictor output layer to predict influencing evaluation factors.…”

Section: Iei Teaching Quality Evaluation Model Construction By Adapti...mentioning

confidence: 99%

Teaching quality evaluation model construction of university industry and education integration by adaptive BP and DDAE-SVR

Zhang,

Weng

2024

Preprint

View full text Add to dashboard Cite

To adapt to changing teaching modes in colleges and universities, and better predict and analyze the students' learning situation, this study aims at a series of deficiencies existing in the traditional teaching quality evaluation index system. By leveraging deep learning, the evaluation model is enhanced and constructed. Firstly, the system is refined by integrating the concept of integrating industry and education. Secondly, the traditional back propagation neural network is improved, and the model is built by incorporating deep noise reduction auto-encoder and support vector regression technology. Model test showed that model used in this study had good iterative performance. When the number of iterations was 62, the model started to enter a stable state, and the optimal fitness value in the stable state was 0.25. In addition, the detection accuracy was up to 0.98, and prediction effect can be satisfied by most teachers and students. To sum up, the quality evaluation model can accurately evaluate teaching quality, provide a reliable reference for colleges and enterprises, and promote the in-depth integration development of industry and education.

show abstract

Section: Iei Teaching Quality Evaluation Model Construction By Adapti...mentioning

confidence: 99%

Teaching quality evaluation model construction of university industry and education integration by adaptive BP and DDAE-SVR

Zhang,

Weng

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Convolutional Neural Network (CNN) is one of the most important models in DL, playing a significant role in promoting the development of image classification, recognition, and understanding technologies. It adopts convolutional kernel weight sharing mode, reduces network model parameters, achieves deep network structure, obtains more abstract and deep level features, and accelerates model training speed [16,17]. Figure 1 shows the main structure of CNN.…”

Section: Based Fuzzy Logic Constructionmentioning

confidence: 99%

Automatic Quality Inspection and Intelligent Prevention of Prefabricated Building Construction Based on BIM and Fuzzy Logic

2024

Decis. Mak. Appl. Manag. Eng.

View full text Add to dashboard Cite

The construction industry plays an important role in China's economy. However, traditional construction quality inspection methods have problems such as low efficiency, high leakage rate, and poor real-time performance. Therefore, taking the appearance quality defects of reinforced concrete engineering as an example, this study combines building information models and computer vision technology. By this way, it can achieve automatic quality inspection and intelligent quality problem prevention, to improve the quality management level during the construction process. In this study, ResNet50 network was pre-trained and classified using a self-made defect image database. After transfer learning, the accuracy values of the training and testing sets remained stable at around 0.95 and the loss value remained stable at around 0.10 after 10 epochs, indicating a significant improvement in learning performance. In the defect area quantification experiment, four corner coordinates of the defect image were calculated. These corner coordinates are simultaneously obtained and saved during on-site image acquisition. According to the calculation results, the defect area of honeycomb is approximately 67.67 square centimetres. These results confirm that this method improves the efficiency and accuracy of quality inspection and has potential application in quality inspection of prefabricated building construction.

show abstract

“…Decision trees, being weak learners, are combined to create a strong model [57]. RF can be used for predicting either class variables or regression variables [58,59]. In the GEE platform, there are six parameters related to RF that can be adjusted.…”

Section: Random Forest (Rf)mentioning

confidence: 99%

Monitoring the Spatio-Temporal Distribution of Soil Salinity Using Google Earth Engine for Detecting the Saline Areas Susceptible to Salt Storm Occurrence

Kazemi Garajeh

2024

Pollutants

View full text Add to dashboard Cite

Recent droughts worldwide have significantly affected ecosystems in various regions. Among these affected areas, the Lake Urmia Basin (LUB) has experienced substantial effects from both drought and human activity in recent years. Lake Urmia, known as one of the hypersaline lakes globally, has been particularly influenced by these activities. The extraction of water since 1995 has resulted in an increase in the extent of salty land, leading to the frequent occurrence of salt storms. To address this issue, the current study utilized various machine learning algorithms within the Google Earth Engine (GEE) platform to map the probability of saline storm occurrences. Landsat time-series images spanning from 2000 to 2022 were employed. Soil salinity indices, Ground Points (GPs), and Moderate Resolution Imaging Spectroradiometer (MODIS) aerosol products were utilized to prepare the training data, which served as input for constructing and running the models. The results demonstrated that the Support Vector Machine (SVM) performed effectively in identifying the probability of saline storm occurrence areas, achieving high R2 values of 91.12%, 90.45%, 91.78%, and 91.65% for the years 2000, 2010, 2015, and 2022, respectively. Additionally, the findings reveal an increase in areas exhibiting a very high probability of saline storm occurrences from 2000 to 2022. In summary, the results of this study indicate that the frequency of salt storms is expected to rise in the near future, owing to the increasing levels of soil salinity resources within the Lake Urmia Basin.

show abstract

Context-Free Word Importance Scores for Attacking Neural Networks

Cited by 39 publications

References 20 publications

Teaching quality evaluation model construction of university industry and education integration by adaptive BP and DDAE-SVR

Teaching quality evaluation model construction of university industry and education integration by adaptive BP and DDAE-SVR

Automatic Quality Inspection and Intelligent Prevention of Prefabricated Building Construction Based on BIM and Fuzzy Logic

Monitoring the Spatio-Temporal Distribution of Soil Salinity Using Google Earth Engine for Detecting the Saline Areas Susceptible to Salt Storm Occurrence

Contact Info

Product

Resources

About