scholarly journals Identifying User Profile by Incorporating Self-Attention Mechanism based on CSDN Data Set

2019 ◽  
Vol 1 (2) ◽  
pp. 160-175 ◽  
Author(s):  
Junru Lu ◽  
Le Chen ◽  
Kongming Meng ◽  
Fengyi Wang ◽  
Jun Xiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Neural Network Model ◽  
User Profile ◽  
User Profiling ◽  
Technology Evaluation ◽  
Data Set ◽  
Value Prediction ◽  
User Interests ◽  
Evaluation Scores

With the popularity of social media, there has been an increasing interest in user profiling and its applications nowadays. This paper presents our system named UIR-SIST for User Profiling Technology Evaluation Campaign in SMP CUP 2017. UIR-SIST aims to complete three tasks, including keywords extraction from blogs, user interests labeling and user growth value prediction. To this end, we first extract keywords from a user's blog, including the blog itself, blogs on the same topic and other blogs published by the same user. Then a unified neural network model is constructed based on a convolutional neural network (CNN) for user interests tagging. Finally, we adopt a stacking model for predicting user growth value. We eventually receive the sixth place with evaluation scores of 0.563, 0.378 and 0.751 on the three tasks, respectively.

scholarly journals RISC-V Virtual Platform-Based Convolutional Neural Network Accelerator Implemented in SystemC

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1514
Author(s):  
Seung-Ho Lim ◽  
WoonSik William Suh ◽  
Jin-Young Kim ◽  
Sang-Young Cho
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
System Level ◽  
Neural Network Models ◽  
Data Set ◽  
Embedded Device ◽  
Virtual Platform

The optimization for hardware processor and system for performing deep learning operations such as Convolutional Neural Networks (CNN) in resource limited embedded devices are recent active research area. In order to perform an optimized deep neural network model using the limited computational unit and memory of an embedded device, it is necessary to quickly apply various configurations of hardware modules to various deep neural network models and find the optimal combination. The Electronic System Level (ESL) Simulator based on SystemC is very useful for rapid hardware modeling and verification. In this paper, we designed and implemented a Deep Learning Accelerator (DLA) that performs Deep Neural Network (DNN) operation based on the RISC-V Virtual Platform implemented in SystemC in order to enable rapid and diverse analysis of deep learning operations in an embedded device based on the RISC-V processor, which is a recently emerging embedded processor. The developed RISC-V based DLA prototype can analyze the hardware requirements according to the CNN data set through the configuration of the CNN DLA architecture, and it is possible to run RISC-V compiled software on the platform, can perform a real neural network model like Darknet. We performed the Darknet CNN model on the developed DLA prototype, and confirmed that computational overhead and inference errors can be analyzed with the DLA prototype developed by analyzing the DLA architecture for various data sets.

An Experimental Study of Spammer Detection on Chinese Microblogs

2020 ◽  
Vol 30 (11n12) ◽  
pp. 1759-1777
Author(s):  
Jialing Liang ◽  
Peiquan Jin ◽  
Lin Mu ◽  
Jie Zhao
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
User Behavior ◽  
Real Data ◽  
User Profile ◽  
Data Set ◽  
Sina Weibo ◽  
Factors Affecting ◽  
The Government ◽  
Hot Event

With the development of Web 2.0, social media such as Twitter and Sina Weibo have become an essential platform for disseminating hot events. Simultaneously, due to the free policy of microblogging services, users can post user-generated content freely on microblogging platforms. Accordingly, more and more hot events on microblogging platforms have been labeled as spammers. Spammers will not only hurt the healthy development of social media but also introduce many economic and social problems. Therefore, the government and enterprises must distinguish whether a hot event on microblogging platforms is a spammer or is a naturally-developing event. In this paper, we focus on the hot event list on Sina Weibo and collect the relevant microblogs of each hot event to study the detecting methods of spammers. Notably, we develop an integral feature set consisting of user profile, user behavior, and user relationships to reflect various factors affecting the detection of spammers. Then, we employ typical machine learning methods to conduct extensive experiments on detecting spammers. We use a real data set crawled from the most prominent Chinese microblogging platform, Sina Weibo, and evaluate the performance of 10 machine learning models with five sampling methods. The results in terms of various metrics show that the Random Forest model and the over-sampling method achieve the best accuracy in detecting spammers and non-spammers.

scholarly journals Exploiting the Relationship between Pruning Ratio and Compression Effect for Neural Network Model Based on TensorFlow

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Bo Liu ◽  
Qilin Wu ◽  
Yiwen Zhang ◽  
Qian Cao
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Prediction Accuracy ◽  
Computing Time ◽  
Experimental Results ◽  
Data Set ◽  
Compression Effect ◽  
Model Based ◽  
The Relationship

Pruning is a method of compressing the size of a neural network model, which affects the accuracy and computing time when the model makes a prediction. In this paper, the hypothesis that the pruning proportion is positively correlated with the compression scale of the model but not with the prediction accuracy and calculation time is put forward. For testing the hypothesis, a group of experiments are designed, and MNIST is used as the data set to train a neural network model based on TensorFlow. Based on this model, pruning experiments are carried out to investigate the relationship between pruning proportion and compression effect. For comparison, six different pruning proportions are set, and the experimental results confirm the above hypothesis.

An explicit methodology for manufacturing cost–tolerance modeling and optimization using the neural network integrated with the genetic algorithm

2020 ◽  
Vol 34 (3) ◽  
pp. 430-443
Author(s):  
A. Saravanan ◽  
J. Jerald ◽  
A. Delphin Carolina Rani
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Network Model ◽  
Neural Network Model ◽  
Network Models ◽  
Manufacturing Cost ◽  
Genetic Operators ◽  
Neural Network Models ◽  
Data Set ◽  
The Neural Network

AbstractThe objective of the paper is to develop a new method to model the manufacturing cost–tolerance and to optimize the tolerance values along with its manufacturing cost. A cost–tolerance relation has a complex nonlinear correlation among them. The property of a neural network makes it possible to model the complex correlation, and the genetic algorithm (GA) is integrated with the best neural network model to optimize the tolerance values. The proposed method used three types of neural network models (multilayer perceptron, backpropagation network, and radial basis function). These network models were developed separately for prismatic and rotational parts. For the construction of network models, part size and tolerance values were used as input neurons. The reference manufacturing cost was assigned as the output neuron. The qualitative production data set was gathered in a workshop and partitioned into three files for training, testing, and validation, respectively. The architecture of the network model was identified based on the best regression coefficient and the root-mean-square-error value. The best network model was integrated into the GA, and the role of genetic operators was also studied. Finally, two case studies from the literature were demonstrated in order to validate the proposed method. A new methodology based on the neural network model enables the design and process planning engineers to propose an intelligent decision irrespective of their experience.

scholarly journals Anticipating the Compressive Strength of Hydrated Lime Cement Concrete Using Artificial Neural Network Model

2018 ◽  
Vol 4 (12) ◽  
pp. 3005 ◽  
Author(s):  
Chioma Temitope Gloria Awodiji ◽  
Davis Ogbonnaya Onwuka ◽  
Chinenye Okere ◽  
Owus Ibearugbulem
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Compressive Strength ◽  
Portland Cement ◽  
Neural Network Model ◽  
Artificial Neural Network Model ◽  
Ordinary Portland Cement ◽  
Hydrated Lime ◽  
Cement Concrete ◽  
Data Set

In this research work, the levernberg Marquardt back propagation neural network was adequately trained to understand the relationship between the 28th day compressive strength values of hydrated lime cement concrete and their corresponding mix ratios with respect to curing age. Data used for the study were generated experimentally. A total of a hundred and fourteen (114) training data set were presented to the network. Eighty (80) of these were used for training the network, seventeen (17) were used for validation, and another seventeen (17) were used for testing the network's performance. Six (6) data set were left out and later used to test the adequacy of the network predictions. The outcome of results of the created network was close to that of the experimental efforts. The lowest and highest correlation coefficient recorded for all data samples used for developing the network were 0.901 and 0.984 for the test and training samples respectively. These values were close to 1. T-value obtained from the adequacy test carried out between experimental and model generated data was 1.437. This is less than 2.064, which is the T values from statistical table at 95% confidence limit. These results proved that the network made reliable predictions. Maximum compressive strength achieved from experimental works was 30.83N/mm2 at a water-cement ratio of 0.562 and a percentage replacement of ordinary portland cement with hydrated lime of 18.75%. Generally, for hydrated lime to be used in making structural concrete, ordinary portland cement percentage replacement with hydrated lime must not be up to 30%. With the use of the developed artificial neural network model, mix design procedure for hydrated lime cement concrete can be carried out with lesser time and energy requirements, when compared to the traditional method. This is because, the need to prepare trial mixes that will be cured, and tested in the laboratory, will no longer be required.

scholarly journals Prediction Model of Hot Metal Silicon Content Based on Improved GA-BPNN

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Zeqian Cui ◽  
Yang Han ◽  
Chaomeng Lu ◽  
Yafeng Wu ◽  
Mansheng Chu
Keyword(s):  
Neural Network ◽  
Blast Furnace ◽  
Time Delay ◽  
Network Model ◽  
Neural Network Model ◽  
Silicon Content ◽  
Large Time ◽  
Hot Metal ◽  
Multiple Control ◽  
Data Set

The inconsistency of the detection period of blast furnace data and the large time delay of key parameters make the prediction of the hot metal silicon content face huge challenges. Aiming at the problem that the hot metal silicon content is not consistent with the detection period of time series of multiple control parameters, the cubic spline interpolation fitting model was used to realize the data integration of multiple detection periods. The large time delay of the blast furnace iron making process was analyzed. Moreover, Spearman analysis was combined with the weighted moving average method to optimize the data set of silicon content prediction. Aiming at the problem of low prediction accuracy of the ordinary neural network model, genetic algorithm was used to optimize parameters on the BP neural network model to improve the convergence speed of the model to achieve global optimization. Combined with the autocorrelation analysis of the hot metal silicon content, a modified model for the prediction of hot metal silicon content based on error analysis was proposed to further improve the accuracy of the prediction. The model comprehensively considers problems such as data detection inconsistency, large time delay, and inaccuracy of prediction results. Its average absolute error is 0.05009, which can be used in actual production.

scholarly journals Identification of a Typical CSTR Using Optimal Focused Time Lagged Recurrent Neural Network Model with Gamma Memory Filter

2009 ◽  
Vol 2009 ◽  
pp. 1-7
Author(s):  
S. N. Naikwad ◽  
S. V. Dudul
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Recurrent Neural Network ◽  
Neural Network Model ◽  
Learning Rule ◽  
Continuous Stirred Tank Reactor ◽  
Back Propagation Algorithm ◽  
Data Set ◽  
Highly Nonlinear ◽  
Time Lagged

A focused time lagged recurrent neural network (FTLR NN) with gamma memory filter is designed to learn the subtle complex dynamics of a typical CSTR process. Continuous stirred tank reactor exhibits complex nonlinear operations where reaction is exothermic. It is noticed from literature review that process control of CSTR using neuro-fuzzy systems was attempted by many, but optimal neural network model for identification of CSTR process is not yet available. As CSTR process includes temporal relationship in the input-output mappings, time lagged recurrent neural network is particularly used for identification purpose. The standard back propagation algorithm with momentum term has been proposed in this model. The various parameters like number of processing elements, number of hidden layers, training and testing percentage, learning rule and transfer function in hidden and output layer are investigated on the basis of performance measures like MSE, NMSE, and correlation coefficient on testing data set. Finally effects of different norms are tested along with variation in gamma memory filter. It is demonstrated that dynamic NN model has a remarkable system identification capability for the problems considered in this paper. Thus FTLR NN with gamma memory filter can be used to learn underlying highly nonlinear dynamics of the system, which is a major contribution of this paper.

Phát hiện mã độc IoT botnet dựa trên đồ thị PSI với mô hình Skip-gram

2020 ◽  
Vol 7 (1) ◽  
pp. 29-36
Author(s):  
Ngô Quốc Dũng ◽  
Lê Văn Hoàng ◽  
Nguyễn Huy Trung
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Experimental Results ◽  
Data Set ◽  
Iot Devices

 Tóm tắt— Trong bài báo này, nhóm tác giả đề xuất một phương pháp phát hiện mã độc IoT botnet dựa trên đồ thị PSI (Printable String Information)  sử dụng mạng nơ-ron tích chập (Convolutional Neural Network - CNN). Thông qua việc phân tích đặc tính của Botnet trên các thiết bị IoT, phương pháp đề xuất xây dựng đồ thị để thể hiện các mối liên kết giữa các PSI, làm đầu vào cho mô hình mạng nơ-ron CNN phân lớp. Kết quả thực nghiệm trên bộ dữ liệu 10033 tập tin ELF gồm 4002 mẫu mã độc IoT botnet và 6031 tập tin lành tính cho thấy phương pháp đề xuất đạt độ chính xác (accuracy) và độ đo F1 lên tới 98,1%. Abstract— In this paper, the authors propose a method for detecting IoT botnet malware based on PSI graphs using Convolutional Neural Network (CNN). Through analyzing the characteristics of Botnet on IoT devices, the proposed method construct the graph to show the relations between PSIs, as input for the CNN neural network model. Experimental results on the 10033 data set of ELF files including 4002 IoT botnet malware samples and 6031 benign files show Accuracy and F1-score up to 98.1%. 

Exploring Visual Representation of #ShoutYourAbortion Hashtag Movement and the Public’s Responses on Instagram: Descriptive and Infodemiology Study (Preprint)

2021 ◽  
Author(s):  
Sunmi ‍Lee ◽  
Yunhwan Kim
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Social Media ◽  
Neural Network Model ◽  
Predictive Analytics ◽  
Visual Representation ◽  
Point Of View ◽  
The Public ◽  
Intelligence Services ◽  
Human Faces

BACKGROUND Hashtag movement has become one of the major ways of online movement, but few studies have examined how social media photos were used for the movement. Also, it has not been actively investigated how photo features were related to the public’s responses in hashtag movements. OBJECTIVE The aim of the present research was to explore Instagram photos with #ShoutYourAbortion hashtag, as an example of hashtag movements via photos, in terms of their visual representation and the relationships between photo features and the public’s responses to the photos. METHODS Instagram photos with #ShoutYourAbortion hashtag, 11,176 in total, were downloaded, and their content and embedded texts were analyzed using online artificial intelligence services. The photos were clustered into subgroups based on the features extracted using a pretrained convolutional neural network model. The resulting clusters were compared in terms of their content tags, embedded texts, and photo features which were manually extracted at the content and pixel levels. The public’s responses were measured by engagement and comment sentiment. Correlational analysis and predictive analytics were conducted to examine the relationships between photo features and the public’s responses. RESULTS It was found that the photos in the text category took the largest share (57.19%), and the embedded texts were mainly about stories told in first person point of view as a woman. A possible evidence of hashtag hijacking was observed. The photos were grouped into two clusters; the first cluster comprised photos which exhibit text materials on them, while the second cluster consisted of photos which contain human faces with texts. The photos in the first cluster were brighter, while the photos in the second cluster were more colorful than the others. And public responses were found to be related to photo features such as size of faces, happy emotion, and share of warm colors. Engagement was predicted from the photo features with an acceptable level of accuracy, while comment sentiment was not. CONCLUSIONS This This study has shown the visual representation of #ShoutYourAbortion hashtag movement. It has also shown how photo features at content and pixel levels were related to the public’s responses to the photos. The results are expected to contribute to the understanding of hashtag movements via photos and making photos in hashtag movements more appealing to the public. CLINICALTRIAL Not Applicable

Sign in / Sign up

Export Citation Format

Share Document