scholarly journals Joint Extraction of Multiple Relations and Entities from Building Code Clauses

2020 ◽  
Vol 10 (20) ◽  
pp. 7103
Author(s):  
Fulin Li ◽  
Yuanbin Song ◽  
Yongwei Shan
Keyword(s):  
Learning Algorithm ◽  
Semantic Relations ◽  
Named Entities ◽  
Domain Specific ◽  
Deep Learning Algorithm ◽  
Proposed Model ◽  
Compliance Checking ◽  
Extraction Model ◽  
Code Compliance ◽  
Engineering Constraints

The extraction of regulatory information is a prerequisite for automated code compliance checking. Although a number of machine learning models have been explored for extracting computer-understandable engineering constraints from code clauses written in natural language, most are inadequate to address the complexity of the semantic relations between named entities. In particular, the existence of two or more overlapping relations involving the same entity greatly exacerbates the difficulty of information extraction. In this paper, a joint extraction model is proposed to extract the relations among entities in the form of triplets. In the proposed model, a hybrid deep learning algorithm combined with a decomposition strategy is applied. First, all candidate subject entities are identified, and then, the associated object entities and predicate relations are simultaneously detected. In this way, multiple relations, especially overlapping relations, can be extracted. Furthermore, nonrelated pairs are excluded through the judicious recognition of subject entities. Moreover, a collection of domain-specific entity and relation types is investigated for model implementation. The experimental results indicate that the proposed model is promising for extracting multiple relations and entities from building codes.

scholarly journals An Investigation into the Application of Deep Learning in the Detection and Mitigation of DDOS Attack on SDN Controllers

Technologies ◽  
2021 ◽  
Vol 9 (1) ◽  
pp. 14
Author(s):  
James Dzisi Gadze ◽  
Akua Acheampomaa Bamfo-Asante ◽  
Justice Owusu Agyemang ◽  
Henry Nunoo-Mensah ◽  
Kwasi Adu-Boahen Opare
Keyword(s):  
Deep Learning ◽  
Network Architecture ◽  
Learning Algorithm ◽  
Single Point ◽  
Denial Of Service ◽  
Specific Work ◽  
Learning Models ◽  
Ddos Attack ◽  
Deep Learning Algorithm ◽  
Proposed Model

Software-Defined Networking (SDN) is a new paradigm that revolutionizes the idea of a software-driven network through the separation of control and data planes. It addresses the problems of traditional network architecture. Nevertheless, this brilliant architecture is exposed to several security threats, e.g., the distributed denial of service (DDoS) attack, which is hard to contain in such software-based networks. The concept of a centralized controller in SDN makes it a single point of attack as well as a single point of failure. In this paper, deep learning-based models, long-short term memory (LSTM) and convolutional neural network (CNN), are investigated. It illustrates their possibility and efficiency in being used in detecting and mitigating DDoS attack. The paper focuses on TCP, UDP, and ICMP flood attacks that target the controller. The performance of the models was evaluated based on the accuracy, recall, and true negative rate. We compared the performance of the deep learning models with classical machine learning models. We further provide details on the time taken to detect and mitigate the attack. Our results show that RNN LSTM is a viable deep learning algorithm that can be applied in the detection and mitigation of DDoS in the SDN controller. Our proposed model produced an accuracy of 89.63%, which outperformed linear-based models such as SVM (86.85%) and Naive Bayes (82.61%). Although KNN, which is a linear-based model, outperformed our proposed model (achieving an accuracy of 99.4%), our proposed model provides a good trade-off between precision and recall, which makes it suitable for DDoS classification. In addition, it was realized that the split ratio of the training and testing datasets can give different results in the performance of a deep learning algorithm used in a specific work. The model achieved the best performance when a split of 70/30 was used in comparison to 80/20 and 60/40 split ratios.

scholarly journals Development of Deep Learning Algorithm for Brain Tumor Segmentation

2019 ◽  
Vol 9 (1) ◽  
pp. 2800-2803
Keyword(s):  
Deep Learning ◽  
Brain Tumor ◽  
Brain Tumors ◽  
Learning Algorithm ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Human Errors ◽  
Deep Learning Algorithm ◽  
Proposed Model ◽  
A New Technique

Medical imaging is an emerging field in engineering. As traditional way of brain tumor analysis, MRI scanning is the way to identify brain tumor. The core drawback of manual MRI studies conducted by surgeons is getting manual visual errorswhich can lead toofa false identification of tumor boundaries. To avoid such human errors, ultra age engineering adopted deep learning as a new technique for brain tumor segmentation. Deep learning convolution network can be further developed by means of various deep learning models for better performance. Hence, we proposed a new deep learning algorithm development which can more efficiently identifies the types of brain tumors in terms of level of tumor like T1, T2, and T1ce etc. The proposed system can identify tumors using convolution neural network(CNN) which works with the proposed algorithm “Sculptor DeepCNet”. The proposed model can be used by surgeons to identify post-surgical remains (if any) of brain tumors and thus proposed research can be useful for ultra-age neural surgical image assessments. This paper discusses newly developed algorithm and its testing results.

An Efficient Approach to Predict COVID-19 Infected Patient Applying Deep learning Algorithm on Chest X-ray Images with Analyzing the Patient Symptoms (Preprint)

2020 ◽  
Author(s):  
Mohammad Helal Uddin ◽  
Mohammad Nahid Hossain ◽  
K. Thapa ◽  
S.-H Yang
Keyword(s):  
Learning Algorithm ◽  
Early Stage ◽  
Low Cost ◽  
Research Work ◽  
Lung Infection ◽  
X Ray ◽  
Deep Learning Algorithm ◽  
Proposed Model ◽  
Life Threatening ◽  
Chest X Ray

BACKGROUND COVID-19 is a life-threatening infectious disease that has become a pandemic for the time being. The virus grows within the lower respiratory tract where early-stage symptoms(like- cough, fever, sore throat, etc.) develop and then it causes lung infection(pneumonia) OBJECTIVE This paper proposed a new methodology of artificial testing whether a patient has been infected by COVID-19 or not METHODS We have presented a prediction model based on, Convolutional Neural Networks(CNN) and our own developed mathematical equation based algorithm named SymptomNet. The CNN algorithm classifies the lung infection(pneumonia) from frontal chest X-ray images, while the symptoms analyzing algorithm(SymptomNet) predicts the possibility of COVID-19 infection from developed symptoms in a patient RESULTS The model has the accuracy of 96% while predicting COVID-19 patients. In this Model, the CNN classifier has the accuracy of around 96% and the SymptomNet algorithm has the accuracy of 97%. CONCLUSIONS This research work obtained a promising accuracy while predicting COVID-19 infected patients. The proposed model can be ubiquitously used at a low cost with high accuracy.

AUTOMATIC SEGMENTATION AND INDICATORS MEASUREMENT OF THE VOCAL FOLDS AND GLOTTAL IN LARYNGEAL ENDOSCOPY IMAGES USING MASK R-CNN

2021 ◽  
pp. 2150027
Author(s):  
Chiun-Li Chin ◽  
Chun-Lung Chang ◽  
Yu-Chieh Liu ◽  
Yong-Long Lin
Keyword(s):  
Clinical Practice ◽  
Medical Information ◽  
Learning Algorithm ◽  
Automatic Segmentation ◽  
Vocal Folds ◽  
Positive Influence ◽  
High Rate ◽  
Deep Learning Algorithm ◽  
Proposed Model ◽  
Clinic Practice

In present clinic practice of otolaryngology, otolaryngologists utilized laryngoscopy to diagnose the larynx lesion of patients preliminarily. Nevertheless, it was challenging for otolaryngologists to interpret the detailed information from laryngoscopy videos comprehensively. In this paper, we proposed Mask R-CNN deep learning algorithm to segment the regions of the vocal folds and glottal from laryngoscopy videos, and self-built algorithm to calculate measured indicators including the length and curvature of vocal folds, the angle of glottal, the area of vocal folds and glottal, and the triangle type composed of vocal folds and glottal. Moreover, in order to provide otolaryngologists critical and immediate medical information during diagnosis, we also provided visualized information, which is labeled on the laryngoscopy images to meet all the needs in clinical practice. From the result of this research, the precision of segmentation has reached a high rate of 90.4% on average. It shows that the model not only achieves great performance in segmentation, but also further proved the indicators are accurate enough to be considered in practical diagnosis. In the future, it is possible for the proposed model to be applied in more kinds of laryngoscopy analyses for more comprehensive diagnosis, which would make a positive influence toward the clinical practice of otolaryngology.

scholarly journals Identification and Classification of Cataract Stages in Old Age People Using Deep Learning Algorithm

2019 ◽  
Vol 8 (10) ◽  
pp. 2767-2772
Keyword(s):  
Old Age ◽  
Learning Algorithm ◽  
Image Feature ◽  
Learning Technology ◽  
Model Accuracy ◽  
Data Set ◽  
Deep Learning Algorithm ◽  
Clear Vision ◽  
Extraction Model

Cataract is a dense cloudy area that forms in a lens of the eye because of which many people are going blind. More than 50% of people in old age suffer due to cataract and will not have a clear vision. In the convolutional neural network, there are many trained models which help in the classification of the object. We use transfer learning technology to train the model for the data set we have. The image feature extraction model with the inception V3 architecture trained on image net. Cataract and normal image dataset are collected. A cataract is further divided into a mature and immature cataract. The result shows whether the image is either a normal eye or cataract eye with the model accuracy being 87.5%. If in the presence of cataract, the model will identify the stage of cataract

scholarly journals Application of deep learning algorithm to detect and visualize vertebral fractures on plain frontal radiographs

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0245992
Author(s):  
Hsuan-Yu Chen ◽  
Benny Wei-Yun Hsu ◽  
Yu-Kai Yin ◽  
Feng-Huei Lin ◽  
Tsung-Han Yang ◽  
...  
Keyword(s):  
Vertebral Fractures ◽  
Learning Algorithm ◽  
Characteristic Curve ◽  
Fracture Prevention ◽  
Secondary Fracture ◽  
Model Interpretation ◽  
Deep Learning Algorithm ◽  
Proposed Model ◽  
Sensitivity Specificity ◽  
Detection And Localization

Background Identification of vertebral fractures (VFs) is critical for effective secondary fracture prevention owing to their association with the increasing risks of future fractures. Plain abdominal frontal radiographs (PARs) are a common investigation method performed for a variety of clinical indications and provide an ideal platform for the opportunistic identification of VF. This study uses a deep convolutional neural network (DCNN) to identify the feasibility for the screening, detection, and localization of VFs using PARs. Methods A DCNN was pretrained using ImageNet and retrained with 1306 images from the PARs database obtained between August 2015 and December 2018. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were evaluated. The visualization algorithm gradient-weighted class activation mapping (Grad-CAM) was used for model interpretation. Results Only 46.6% (204/438) of the VFs were diagnosed in the original PARs reports. The algorithm achieved 73.59% accuracy, 73.81% sensitivity, 73.02% specificity, and an AUC of 0.72 in the VF identification. Conclusion Computer driven solutions integrated with the DCNN have the potential to identify VFs with good accuracy when used opportunistically on PARs taken for a variety of clinical purposes. The proposed model can help clinicians become more efficient and economical in the current clinical pathway of fragile fracture treatment.

Answer Extraction Model Based on Named Entity Recognition

2014 ◽  
Vol 571-572 ◽  
pp. 339-344
Author(s):  
Yong He Lu ◽  
Ming Hui Liang
Keyword(s):  
Question Answering ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Named Entities ◽  
Named Entity ◽  
Model Based ◽  
Answer Extraction ◽  
Proposed Model ◽  
Final Answer ◽  
Extraction Model

The answer extraction model has a direct impact on the performance of the Automatic Question Answering System (QA System). In this paper, an answer extraction model based on named entity recognition was presented. It mainly answers specific questions whose answers are related with the named entity. Firstly, it classified the questions according to answer types. And then it identified named entities with suitable types in the fragmented information. Finally, it got the final answer based on scores. The experiments in the paper proved that the model could accurately answer the questions provided by Text REtrieval Conference (TREC). Thus, the proposed model is easy to implement and its performance is good for specific questions.

scholarly journals Effective Soil Type Classification Using Convolutional Neural Network

2021 ◽  
Vol 3 (1) ◽  
pp. 20
Author(s):  
Antomy David Ronaldo
Keyword(s):  
Learning Algorithm ◽  
Soil Classification ◽  
Research Area ◽  
Traditional Learning ◽  
Accuracy Rate ◽  
Classification Result ◽  
Novel Technique ◽  
Deep Learning Algorithm ◽  
Proposed Model ◽  
Type Classification

Soil classification is a growing research area in the current era. Various studies have proposed different techniques to deal with the issues, including rule-based, statistical, and traditional learning methods. However, the plans remain drawbacks to producing an accurate classification result. Therefore, we propose a novel technique to address soil classification by implementing a deep learning algorithm to construct an effective model. Based on the experiment result, the proposed model can obtain classification results with an accuracy rate of 97% and a loss of 0.1606. Furthermore, we also received an F1-score of 98%.

scholarly journals Research on Basketball Teaching Network Course Resource Recommendation Method Based on Deep Learning Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Kai Ma
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Three Dimensional ◽  
Computation Time ◽  
Personalized Learning ◽  
Learning Resource ◽  
Recognition Error ◽  
Deep Learning Algorithm ◽  
Proposed Model ◽  
Resource Data

To solve the problem of invalid resource recommendation data and poor recommendation effect in basketball teaching network course resource recommendation, a basketball teaching network course resource recommendation method based on a deep learning algorithm is proposed. The objective function is applied to eliminate the noise in the basketball teaching network course resource data. The prominent characteristics of basketball teaching network curriculum resources are extracted using a kernel function and combined into a feature set. A convolution neural network (CNN) was employed to realize the basketball teaching network curriculum resources recommendation model. The model was assessed in terms of computation time and recognition error. To validate the performance, the proposed model was compared with two well-known recommendation models such as the learning resource recommendation method based on transfer learning and the personalized learning resource recommendation method based on three-dimensional feature collaborative domination. Experimental results show that the proposed model achieved the lowest computation time of 15 s and recommendation error less than 0.4% as compared with the existing model.

scholarly journals A deep learning algorithm to detect coronavirus (COVID-19) disease using CT images

2021 ◽  
Vol 7 ◽  
pp. e345
Author(s):  
Mojtaba Mohammadpoor ◽  
Mehran Sheikhi karizaki ◽  
Mina Sheikhi karizaki
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Screening Method ◽  
Ct Scans ◽  
X Rays ◽  
Deep Learning Algorithm ◽  
Fast Screening ◽  
Proposed Model ◽  
Deep Learning Neural Network ◽  
Lung Ct

Background COVID-19 pandemic imposed a lockdown situation to the world these past months. Researchers and scientists around the globe faced serious efforts from its detection to its treatment. Methods Pathogenic laboratory testing is the gold standard but it is time-consuming. Lung CT-scans and X-rays are other common methods applied by researchers to detect COVID-19 positive cases. In this paper, we propose a deep learning neural network-based model as an alternative fast screening method that can be used for detecting the COVID-19 cases by analyzing CT-scans. Results Applying the proposed method on a publicly available dataset collected of positive and negative cases showed its ability on distinguishing them by analyzing each individual CT image. The effect of different parameters on the performance of the proposed model was studied and tabulated. By selecting random train and test images, the overall accuracy and ROC-AUC of the proposed model can easily exceed 95% and 90%, respectively, without any image pre-selecting or preprocessing.

Sign in / Sign up

Export Citation Format

Share Document