Web of students : class-level friendship network discovery from educational big data
- Guo, Teng, Tang, Tang, Zhang, Dongyu, Li, Jianxin, Xia, Feng
- Authors: Guo, Teng , Tang, Tang , Zhang, Dongyu , Li, Jianxin , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 22nd International Conference on Web Information Systems Engineering, WISE 2021 p. 497-511
- Full Text: false
- Reviewed:
- Description: Classmate friendships are a major aspect of university social experience. Taking classes together is one of the main ways for students to build friendships. Consequently, class-level friendship networks have attracted tremendous attention from researchers. They are also very useful in student support and early intervention. However, these networks are normally invisible for educators. Discovering such an important web of students effectively is a pressing problem. Against this background, we propose a data-driven framework called CANDY which automatically discovers the class-level friendship networks based on educational big data. We first represent features through representation learning methods. Secondly, the data is augmented with the randomly shuffling method. Thirdly, a conditional generative adversarial network model is used to mine the class-level friendship networks. A deep adversarial optimization strategy is proposed here for problems caused by network sparsity. To evaluate the performance of the proposed approach, we build a real-world dataset that contains rich student information. Extensive experiments have been conducted and the results demonstrate the effectiveness of our framework. © 2021, Springer Nature Switzerland AG.
Expressing metaphorically, writing creatively: Metaphor identification for creativity assessment
- Zhang, Dongyu, Zhang, Minghao, Peng, Ciyuan, Xia, Feng
- Authors: Zhang, Dongyu , Zhang, Minghao , Peng, Ciyuan , Xia, Feng
- Date: 2022
- Type: Text , Conference proceedings
- Relation: WWW '22: Companion Proceedings of the Web Conference , Virtual event , April 2022 p. 1198-
- Full Text:
- Reviewed:
- Description: Metaphor, which can implicitly express profound meanings and emotions, is a unique writing technique frequently used in human language. In writing, meaningful metaphorical expressions can enhance the literariness and creativity of texts. Therefore, the usage of metaphor is a significant impact factor when assessing the creativity and literariness of writing. However, little to no automatic writing assessment system considers metaphorical expressions when giving the score of creativity. For improving the accuracy of automatic writing assessment, this paper proposes a novel creativity assessment model that imports a token-level metaphor identification method to extract metaphors as the indicators for creativity scoring. The experimental results show that our model can accurately assess the creativity of different texts with precise metaphor identification. To the best of our knowledge, we are the first to apply automatic metaphor identification to assess writing creativity. Moreover, identifying features (e.g., metaphors) that influence writing creativity using computational approaches can offer fair and reliable assessment methods for educational settings.
- Authors: Zhang, Dongyu , Zhang, Minghao , Peng, Ciyuan , Xia, Feng
- Date: 2022
- Type: Text , Conference proceedings
- Relation: WWW '22: Companion Proceedings of the Web Conference , Virtual event , April 2022 p. 1198-
- Full Text:
- Reviewed:
- Description: Metaphor, which can implicitly express profound meanings and emotions, is a unique writing technique frequently used in human language. In writing, meaningful metaphorical expressions can enhance the literariness and creativity of texts. Therefore, the usage of metaphor is a significant impact factor when assessing the creativity and literariness of writing. However, little to no automatic writing assessment system considers metaphorical expressions when giving the score of creativity. For improving the accuracy of automatic writing assessment, this paper proposes a novel creativity assessment model that imports a token-level metaphor identification method to extract metaphors as the indicators for creativity scoring. The experimental results show that our model can accurately assess the creativity of different texts with precise metaphor identification. To the best of our knowledge, we are the first to apply automatic metaphor identification to assess writing creativity. Moreover, identifying features (e.g., metaphors) that influence writing creativity using computational approaches can offer fair and reliable assessment methods for educational settings.
Soil moisture, organic carbon, and nitrogen content prediction with hyperspectral data using regression models
- Datta, Dristi, Paul, Manoranjan, Murshed, Manzur, Teng, Shyh Wei, Schmidtke, Leigh
- Authors: Datta, Dristi , Paul, Manoranjan , Murshed, Manzur , Teng, Shyh Wei , Schmidtke, Leigh
- Date: 2022
- Type: Text , Journal article
- Relation: Sensors (Basel, Switzerland) Vol. 22, no. 20 (2022), p.
- Full Text:
- Reviewed:
- Description: Soil moisture, soil organic carbon, and nitrogen content prediction are considered significant fields of study as they are directly related to plant health and food production. Direct estimation of these soil properties with traditional methods, for example, the oven-drying technique and chemical analysis, is a time and resource-consuming approach and can predict only smaller areas. With the significant development of remote sensing and hyperspectral (HS) imaging technologies, soil moisture, carbon, and nitrogen can be estimated over vast areas. This paper presents a generalized approach to predicting three different essential soil contents using a comprehensive study of various machine learning (ML) models by considering the dimensional reduction in feature spaces. In this study, we have used three popular benchmark HS datasets captured in Germany and Sweden. The efficacy of different ML algorithms is evaluated to predict soil content, and significant improvement is obtained when a specific range of bands is selected. The performance of ML models is further improved by applying principal component analysis (PCA), a dimensional reduction method that works with an unsupervised learning method. The effect of soil temperature on soil moisture prediction is evaluated in this study, and the results show that when the soil temperature is considered with the HS band, the soil moisture prediction accuracy does not improve. However, the combined effect of band selection and feature transformation using PCA significantly enhances the prediction accuracy for soil moisture, carbon, and nitrogen content. This study represents a comprehensive analysis of a wide range of established ML regression models using data preprocessing, effective band selection, and data dimension reduction and attempt to understand which feature combinations provide the best accuracy. The outcomes of several ML models are verified with validation techniques and the best- and worst-case scenarios in terms of soil content are noted. The proposed approach outperforms existing estimation techniques.
- Authors: Datta, Dristi , Paul, Manoranjan , Murshed, Manzur , Teng, Shyh Wei , Schmidtke, Leigh
- Date: 2022
- Type: Text , Journal article
- Relation: Sensors (Basel, Switzerland) Vol. 22, no. 20 (2022), p.
- Full Text:
- Reviewed:
- Description: Soil moisture, soil organic carbon, and nitrogen content prediction are considered significant fields of study as they are directly related to plant health and food production. Direct estimation of these soil properties with traditional methods, for example, the oven-drying technique and chemical analysis, is a time and resource-consuming approach and can predict only smaller areas. With the significant development of remote sensing and hyperspectral (HS) imaging technologies, soil moisture, carbon, and nitrogen can be estimated over vast areas. This paper presents a generalized approach to predicting three different essential soil contents using a comprehensive study of various machine learning (ML) models by considering the dimensional reduction in feature spaces. In this study, we have used three popular benchmark HS datasets captured in Germany and Sweden. The efficacy of different ML algorithms is evaluated to predict soil content, and significant improvement is obtained when a specific range of bands is selected. The performance of ML models is further improved by applying principal component analysis (PCA), a dimensional reduction method that works with an unsupervised learning method. The effect of soil temperature on soil moisture prediction is evaluated in this study, and the results show that when the soil temperature is considered with the HS band, the soil moisture prediction accuracy does not improve. However, the combined effect of band selection and feature transformation using PCA significantly enhances the prediction accuracy for soil moisture, carbon, and nitrogen content. This study represents a comprehensive analysis of a wide range of established ML regression models using data preprocessing, effective band selection, and data dimension reduction and attempt to understand which feature combinations provide the best accuracy. The outcomes of several ML models are verified with validation techniques and the best- and worst-case scenarios in terms of soil content are noted. The proposed approach outperforms existing estimation techniques.
DEFINE: friendship detection based on node enhancement
- Pan, Hanxiao, Guo, Teng, Bedru, Hayat, Qing, Qing, Zhang, Dongyu, Xia, Feng
- Authors: Pan, Hanxiao , Guo, Teng , Bedru, Hayat , Qing, Qing , Zhang, Dongyu , Xia, Feng
- Date: 2020
- Type: Text , Conference paper
- Relation: 31st Australasian Database Conference, ADC 2019 Vol. 12008 LNCS, p. 81-92
- Full Text:
- Reviewed:
- Description: Network representation learning (NRL) is a matter of importance to a variety of tasks such as link prediction. Learning low-dimensional vector representations for node enhancement based on nodes attributes and network structures can improve link prediction performance. Node attributes are important factors in forming networks, like psychological factors and appearance features affecting friendship networks. However, little to no work has detected friendship using the NRL technique, which combines students’ psychological features and perceived traits based on facial appearance. In this paper, we propose a framework named DEFINE (No enhancement based r e dship D tection) to detect students’ friend relationships, which combines with students’ psychological factors and facial perception information. To detect friend relationships accurately, DEFINE uses the NRL technique, which considers network structure and the additional attributes information for nodes. DEFINE transforms them into low-dimensional vector spaces while preserving the inherent properties of the friendship network. Experimental results on real-world friendship network datasets illustrate that DEFINE outperforms other state-of-art methods. © 2020, Springer Nature Switzerland AG.
- Description: E1
- Authors: Pan, Hanxiao , Guo, Teng , Bedru, Hayat , Qing, Qing , Zhang, Dongyu , Xia, Feng
- Date: 2020
- Type: Text , Conference paper
- Relation: 31st Australasian Database Conference, ADC 2019 Vol. 12008 LNCS, p. 81-92
- Full Text:
- Reviewed:
- Description: Network representation learning (NRL) is a matter of importance to a variety of tasks such as link prediction. Learning low-dimensional vector representations for node enhancement based on nodes attributes and network structures can improve link prediction performance. Node attributes are important factors in forming networks, like psychological factors and appearance features affecting friendship networks. However, little to no work has detected friendship using the NRL technique, which combines students’ psychological features and perceived traits based on facial appearance. In this paper, we propose a framework named DEFINE (No enhancement based r e dship D tection) to detect students’ friend relationships, which combines with students’ psychological factors and facial perception information. To detect friend relationships accurately, DEFINE uses the NRL technique, which considers network structure and the additional attributes information for nodes. DEFINE transforms them into low-dimensional vector spaces while preserving the inherent properties of the friendship network. Experimental results on real-world friendship network datasets illustrate that DEFINE outperforms other state-of-art methods. © 2020, Springer Nature Switzerland AG.
- Description: E1
GraphLearning’22: 1st International Workshop on Graph Learning
- Xia, Feng, Lambiotte, Renaud, Aggarwal, Charu
- Authors: Xia, Feng , Lambiotte, Renaud , Aggarwal, Charu
- Date: 2022
- Type: Text , Conference proceedings
- Relation: WWW '22: Companion Proceedings of the Web Conference 2022, Virtual Event, Lyon France April 25 - 29, 2022 p. 1004-1005
- Full Text:
- Reviewed:
- Description: The First Workshop on Graph Learning aims to bring together researchers and practitioners from academia and industry to discuss recent advances and core challenges of graph learning. This workshop will be established as a platform for multiple disciplines such as computer science, applied mathematics, physics, social sciences, data science, complex networks, and systems engineering. Core challenges in regard to theory, methodology, and applications of graph learning will be the main center of discussions at the workshop.
- Authors: Xia, Feng , Lambiotte, Renaud , Aggarwal, Charu
- Date: 2022
- Type: Text , Conference proceedings
- Relation: WWW '22: Companion Proceedings of the Web Conference 2022, Virtual Event, Lyon France April 25 - 29, 2022 p. 1004-1005
- Full Text:
- Reviewed:
- Description: The First Workshop on Graph Learning aims to bring together researchers and practitioners from academia and industry to discuss recent advances and core challenges of graph learning. This workshop will be established as a platform for multiple disciplines such as computer science, applied mathematics, physics, social sciences, data science, complex networks, and systems engineering. Core challenges in regard to theory, methodology, and applications of graph learning will be the main center of discussions at the workshop.
Metaphor research in the 21st century : a bibliographic analysis
- Zhang, Dongyu, Zhang, Minghao, Peng, Ciyuan, Jung, Jason, Xia, Feng
- Authors: Zhang, Dongyu , Zhang, Minghao , Peng, Ciyuan , Jung, Jason , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: Computer Science and Information Systems Vol. 18, no. 1 (2020), p. 303-322
- Full Text:
- Reviewed:
- Description: Metaphor is widely used in human communication. The cohort of scholars studying metaphor in various fields is continuously growing, but very few work has been done in bibliographical analysis of metaphor research. This paper examines the advancements in metaphor research from 2000 to 2017. Using data retrieved from Microsoft Academic Graph and Web of Science, this paper makes a macro analysis of metaphor research, and expounds the underlying patterns of its development. Taking into consideration sub-fields of metaphor research, the internal analysis of metaphor research is carried out from a micro perspective to reveal the evolution of research topics and the inherent relationships among them. This paper provides novel insights into the current state of the art of metaphor research as well as future trends in this field, which may spark new research interests in metaphor from both linguistic and interdisciplinary perspectives. © 2020, ComSIS Consortium. All rights reserved.
- Authors: Zhang, Dongyu , Zhang, Minghao , Peng, Ciyuan , Jung, Jason , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: Computer Science and Information Systems Vol. 18, no. 1 (2020), p. 303-322
- Full Text:
- Reviewed:
- Description: Metaphor is widely used in human communication. The cohort of scholars studying metaphor in various fields is continuously growing, but very few work has been done in bibliographical analysis of metaphor research. This paper examines the advancements in metaphor research from 2000 to 2017. Using data retrieved from Microsoft Academic Graph and Web of Science, this paper makes a macro analysis of metaphor research, and expounds the underlying patterns of its development. Taking into consideration sub-fields of metaphor research, the internal analysis of metaphor research is carried out from a micro perspective to reveal the evolution of research topics and the inherent relationships among them. This paper provides novel insights into the current state of the art of metaphor research as well as future trends in this field, which may spark new research interests in metaphor from both linguistic and interdisciplinary perspectives. © 2020, ComSIS Consortium. All rights reserved.
Graduate employment prediction with bias
- Guo, Teng, Xia, Feng, Zhen, Shihao, Bai, Xiaomei, Zhang, Dongyu
- Authors: Guo, Teng , Xia, Feng , Zhen, Shihao , Bai, Xiaomei , Zhang, Dongyu
- Date: 2020
- Type: Text , Conference paper
- Relation: AAAI 2020 - 34th AAAI Conference on Artificial Intelligence p. 670-677
- Full Text:
- Reviewed:
- Description: The failure of landing a job for college students could cause serious social consequences such as drunkenness and suicide. In addition to academic performance, unconscious biases can become one key obstacle for hunting jobs for graduating students. Thus, it is necessary to understand these unconscious biases so that we can help these students at an early stage with more personalized intervention. In this paper, we develop a framework, i.e., MAYA (Multi-mAjor emploYment stAtus) to predict students’ employment status while considering biases. The framework consists of four major components. Firstly, we solve the heterogeneity of student courses by embedding academic performance into a unified space. Then, we apply a generative adversarial network (GAN) to overcome the class imbalance problem. Thirdly, we adopt Long Short-Term Memory (LSTM) with a novel dropout mechanism to comprehensively capture sequential information among semesters. Finally, we design a bias-based regularization to capture the job market biases. We conduct extensive experiments on a large-scale educational dataset and the results demonstrate the effectiveness of our prediction framework. Copyright © 2020, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Feng Xia” is provided in this record**
- Authors: Guo, Teng , Xia, Feng , Zhen, Shihao , Bai, Xiaomei , Zhang, Dongyu
- Date: 2020
- Type: Text , Conference paper
- Relation: AAAI 2020 - 34th AAAI Conference on Artificial Intelligence p. 670-677
- Full Text:
- Reviewed:
- Description: The failure of landing a job for college students could cause serious social consequences such as drunkenness and suicide. In addition to academic performance, unconscious biases can become one key obstacle for hunting jobs for graduating students. Thus, it is necessary to understand these unconscious biases so that we can help these students at an early stage with more personalized intervention. In this paper, we develop a framework, i.e., MAYA (Multi-mAjor emploYment stAtus) to predict students’ employment status while considering biases. The framework consists of four major components. Firstly, we solve the heterogeneity of student courses by embedding academic performance into a unified space. Then, we apply a generative adversarial network (GAN) to overcome the class imbalance problem. Thirdly, we adopt Long Short-Term Memory (LSTM) with a novel dropout mechanism to comprehensively capture sequential information among semesters. Finally, we design a bias-based regularization to capture the job market biases. We conduct extensive experiments on a large-scale educational dataset and the results demonstrate the effectiveness of our prediction framework. Copyright © 2020, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Feng Xia” is provided in this record**
ANSWER : generating information dissemination network on campus
- Qing, Qing, Guo, Teng, Zhang, Dongyu, Xia, Feng
- Authors: Qing, Qing , Guo, Teng , Zhang, Dongyu , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 32nd Australasian Database Conference, ADC 2021 Vol. 12610 LNCS, p. 74-86
- Full Text:
- Reviewed:
- Description: Information dissemination matters, both on an individual and group level. For college students who are physically and mentally immature, they are more sensitive and susceptible to unnormal information like rumors. However, current researches focus on large-scale online message sharing networks like Facebook and Twitter, rather than profile the information dissemination on campus, which fail to provide any references for daily campus management. Against this background, we propose a framework to generate the information dissemination network on campus, named ANSWER (cAmpus iNformation diSsemination netWork gEneRation), based on multimodal data including behavior data, appearance data, and psychological data. The construction of the ANSWER is listed as four steps. First, we use a convolutional autoencoder to extract the students’ facial features. Second, we process the behavior data to construct a friendship network. Third, heterogeneous information is embedded in the low-dimensional vector space by using network representation learning to obtain embedding vectors. Fourth, we use the deep learning model to predict. The experiment results show that ANSWER outperforms other methods in multiple feature fusion and prediction of information dissemination relationship performance. © 2021, Springer Nature Switzerland AG.
- Authors: Qing, Qing , Guo, Teng , Zhang, Dongyu , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 32nd Australasian Database Conference, ADC 2021 Vol. 12610 LNCS, p. 74-86
- Full Text:
- Reviewed:
- Description: Information dissemination matters, both on an individual and group level. For college students who are physically and mentally immature, they are more sensitive and susceptible to unnormal information like rumors. However, current researches focus on large-scale online message sharing networks like Facebook and Twitter, rather than profile the information dissemination on campus, which fail to provide any references for daily campus management. Against this background, we propose a framework to generate the information dissemination network on campus, named ANSWER (cAmpus iNformation diSsemination netWork gEneRation), based on multimodal data including behavior data, appearance data, and psychological data. The construction of the ANSWER is listed as four steps. First, we use a convolutional autoencoder to extract the students’ facial features. Second, we process the behavior data to construct a friendship network. Third, heterogeneous information is embedded in the low-dimensional vector space by using network representation learning to obtain embedding vectors. Fourth, we use the deep learning model to predict. The experiment results show that ANSWER outperforms other methods in multiple feature fusion and prediction of information dissemination relationship performance. © 2021, Springer Nature Switzerland AG.
In your face : sentiment analysis of metaphor with facial expressive features
- Zhang, Dongyu, Zhang, Minghao, Guo, Teng, Peng, Ciyuan, Saikrishna, Vidya, Xia, Feng
- Authors: Zhang, Dongyu , Zhang, Minghao , Guo, Teng , Peng, Ciyuan , Saikrishna, Vidya , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Joint Conference on Neural Networks, IJCNN 2021 Vol. 2021-July
- Full Text:
- Reviewed:
- Description: Metaphor plays an important role in human communication, which often conveys and evokes sentiments. Numerous approaches to sentiment analysis of metaphors have thus gained attention in natural language processing (NLP). The primary focus of these approaches is on linguistic features and text rather than other modal information and data. However, visual features such as facial expressions also play an important role in expressing sentiments. In this paper, we present a novel neural network approach to sentiment analysis of metaphorical expressions that combines both linguistic and visual features and refer to it as the multimodal model approach. For this, we create a Chinese dataset, containing textual data from metaphorical sentences along with visual data on synchronized facial images. The experimental results indicate that our multimodal model outperforms several other linguistic and visual models, and also outperforms the state-of-the-art methods. The contribution is realized in terms of novelty of the approach and creation of a new, sizeable, and scarce dataset with linguistic and synchronized facial expressive image data. The dataset is particularly useful in languages other than English and the approach addresses one of the most challenging NLP issue: sentiment analysis in metaphor. © 2021 IEEE.
- Authors: Zhang, Dongyu , Zhang, Minghao , Guo, Teng , Peng, Ciyuan , Saikrishna, Vidya , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Joint Conference on Neural Networks, IJCNN 2021 Vol. 2021-July
- Full Text:
- Reviewed:
- Description: Metaphor plays an important role in human communication, which often conveys and evokes sentiments. Numerous approaches to sentiment analysis of metaphors have thus gained attention in natural language processing (NLP). The primary focus of these approaches is on linguistic features and text rather than other modal information and data. However, visual features such as facial expressions also play an important role in expressing sentiments. In this paper, we present a novel neural network approach to sentiment analysis of metaphorical expressions that combines both linguistic and visual features and refer to it as the multimodal model approach. For this, we create a Chinese dataset, containing textual data from metaphorical sentences along with visual data on synchronized facial images. The experimental results indicate that our multimodal model outperforms several other linguistic and visual models, and also outperforms the state-of-the-art methods. The contribution is realized in terms of novelty of the approach and creation of a new, sizeable, and scarce dataset with linguistic and synchronized facial expressive image data. The dataset is particularly useful in languages other than English and the approach addresses one of the most challenging NLP issue: sentiment analysis in metaphor. © 2021 IEEE.
Comparative analysis of machine and deep learning models for soil properties prediction from hyperspectral visual band
- Datta, Dristi, Paul, Manoranjan, Murshed, Manzur, Teng, Shyh Wei, Schmidtke, Leigh
- Authors: Datta, Dristi , Paul, Manoranjan , Murshed, Manzur , Teng, Shyh Wei , Schmidtke, Leigh
- Date: 2023
- Type: Text , Journal article
- Relation: Environments Vol. 10, no. 5 (2023), p. 77
- Full Text:
- Reviewed:
- Description: Estimating various properties of soil, including moisture, carbon, and nitrogen, is crucial for studying their correlation with plant health and food production. However, conventional methods such as oven-drying and chemical analysis are laborious, expensive, and only feasible for a limited land area. With the advent of remote sensing technologies like multi/hyperspectral imaging, it is now possible to predict soil properties non-invasive and cost-effectively for a large expanse of bare land. Recent research shows the possibility of predicting those soil contents from a wide range of hyperspectral data using good prediction algorithms. However, these kinds of hyperspectral sensors are expensive and not widely available. Therefore, this paper investigates different machine and deep learning techniques to predict soil nutrient properties using only the red (R), green (G), and blue (B) bands data to propose a suitable machine/deep learning model that can be used as a rapid soil test. Another objective of this research is to observe and compare the prediction accuracy in three cases i. hyperspectral band ii. full spectrum of the visual band, and iii. three-channel of RGB band and provide a guideline to the user on which spectrum information they should use to predict those soil properties. The outcome of this research helps to develop a mobile application that is easy to use for a quick soil test. This research also explores learning-based algorithms with significant feature combinations and their performance comparisons in predicting soil properties from visual band data. For this, we also explore the impact of dimensional reduction (i.e., principal component analysis) and transformations (i.e., empirical mode decomposition) of features. The results show that the proposed model can comparably predict the soil contents from the three-channel RGB data.
- Authors: Datta, Dristi , Paul, Manoranjan , Murshed, Manzur , Teng, Shyh Wei , Schmidtke, Leigh
- Date: 2023
- Type: Text , Journal article
- Relation: Environments Vol. 10, no. 5 (2023), p. 77
- Full Text:
- Reviewed:
- Description: Estimating various properties of soil, including moisture, carbon, and nitrogen, is crucial for studying their correlation with plant health and food production. However, conventional methods such as oven-drying and chemical analysis are laborious, expensive, and only feasible for a limited land area. With the advent of remote sensing technologies like multi/hyperspectral imaging, it is now possible to predict soil properties non-invasive and cost-effectively for a large expanse of bare land. Recent research shows the possibility of predicting those soil contents from a wide range of hyperspectral data using good prediction algorithms. However, these kinds of hyperspectral sensors are expensive and not widely available. Therefore, this paper investigates different machine and deep learning techniques to predict soil nutrient properties using only the red (R), green (G), and blue (B) bands data to propose a suitable machine/deep learning model that can be used as a rapid soil test. Another objective of this research is to observe and compare the prediction accuracy in three cases i. hyperspectral band ii. full spectrum of the visual band, and iii. three-channel of RGB band and provide a guideline to the user on which spectrum information they should use to predict those soil properties. The outcome of this research helps to develop a mobile application that is easy to use for a quick soil test. This research also explores learning-based algorithms with significant feature combinations and their performance comparisons in predicting soil properties from visual band data. For this, we also explore the impact of dimensional reduction (i.e., principal component analysis) and transformations (i.e., empirical mode decomposition) of features. The results show that the proposed model can comparably predict the soil contents from the three-channel RGB data.
- Authors: Mestrom, Sanne
- Date: 2012
- Type: Text , Visual art work
- Full Text:
Efficient data gathering in 3D linear underwater wireless sensor networks using sink mobility
- Akbar, Mariam, Javaid, Nadeem, Khan, Ayesha, Imran, Muhammad, Shoaib, Muhammad, Vasilakos, Athanasios
- Authors: Akbar, Mariam , Javaid, Nadeem , Khan, Ayesha , Imran, Muhammad , Shoaib, Muhammad , Vasilakos, Athanasios
- Date: 2016
- Type: Text , Journal article
- Relation: Sensors (Switzerland) Vol. 16, no. 3 (2016), p.
- Full Text:
- Reviewed:
- Description: Due to the unpleasant and unpredictable underwater environment, designing an energy-efficient routing protocol for underwater wireless sensor networks (UWSNs) demands more accuracy and extra computations. In the proposed scheme, we introduce a mobile sink (MS), i.e., an autonomous underwater vehicle (AUV), and also courier nodes (CNs), to minimize the energy consumption of nodes. MS and CNs stop at specific stops for data gathering; later on, CNs forward the received data to the MS for further transmission. By the mobility of CNs and MS, the overall energy consumption of nodes is minimized. We perform simulations to investigate the performance of the proposed scheme and compare it to preexisting techniques. Simulation results are compared in terms of network lifetime, throughput, path loss, transmission loss and packet drop ratio. The results show that the proposed technique performs better in terms of network lifetime, throughput, path loss and scalability. © 2016 by the authors; licensee MDPI, Basel, Switzerland.
- Authors: Akbar, Mariam , Javaid, Nadeem , Khan, Ayesha , Imran, Muhammad , Shoaib, Muhammad , Vasilakos, Athanasios
- Date: 2016
- Type: Text , Journal article
- Relation: Sensors (Switzerland) Vol. 16, no. 3 (2016), p.
- Full Text:
- Reviewed:
- Description: Due to the unpleasant and unpredictable underwater environment, designing an energy-efficient routing protocol for underwater wireless sensor networks (UWSNs) demands more accuracy and extra computations. In the proposed scheme, we introduce a mobile sink (MS), i.e., an autonomous underwater vehicle (AUV), and also courier nodes (CNs), to minimize the energy consumption of nodes. MS and CNs stop at specific stops for data gathering; later on, CNs forward the received data to the MS for further transmission. By the mobility of CNs and MS, the overall energy consumption of nodes is minimized. We perform simulations to investigate the performance of the proposed scheme and compare it to preexisting techniques. Simulation results are compared in terms of network lifetime, throughput, path loss, transmission loss and packet drop ratio. The results show that the proposed technique performs better in terms of network lifetime, throughput, path loss and scalability. © 2016 by the authors; licensee MDPI, Basel, Switzerland.
A3Graph : adversarial attributed autoencoder for graph representation learning
- Hou, Mingliang, Wang, Lei, Liu, Jiaying, Kong, Xiangjie, Xia, Feng
- Authors: Hou, Mingliang , Wang, Lei , Liu, Jiaying , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 36th Annual ACM Symposium on Applied Computing, SAC 2021 p. 1697-1704
- Full Text:
- Reviewed:
- Description: Recent years have witnessed a proliferation of graph representation techniques in social network analysis. Graph representation aims to map nodes in the graph into low-dimensional vector space while preserving as much information as possible. However, most existing methods ignore the robustness of learned latent vectors, which leads to inferior representation results due to sparse and noisy data in graphs. In this paper, we propose a novel framework, named A3Graph, which aims to improve the robustness and stability of graph representations. Specifically, we first construct an aggregation matrix by the combining positive point-wise mutual information matrix with the attribute matrix. Then, we enforce the autoencoder to reconstruct the aggregation matrix instead of the input attribute matrix. The enhancement autoencoder can incorporate structural and attributed information in a joint learning way to improve the noise-resilient during the learning process. Furthermore, an adversarial learning component is leveraged in our framework to impose a prior distribution on learned representations has been demonstrated as an effective mechanism in improving the robustness and stability in representation learning. Experimental studies on real-world datasets have demonstrated the effectiveness of the proposed A3Graph. © 2021 ACM.
- Authors: Hou, Mingliang , Wang, Lei , Liu, Jiaying , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 36th Annual ACM Symposium on Applied Computing, SAC 2021 p. 1697-1704
- Full Text:
- Reviewed:
- Description: Recent years have witnessed a proliferation of graph representation techniques in social network analysis. Graph representation aims to map nodes in the graph into low-dimensional vector space while preserving as much information as possible. However, most existing methods ignore the robustness of learned latent vectors, which leads to inferior representation results due to sparse and noisy data in graphs. In this paper, we propose a novel framework, named A3Graph, which aims to improve the robustness and stability of graph representations. Specifically, we first construct an aggregation matrix by the combining positive point-wise mutual information matrix with the attribute matrix. Then, we enforce the autoencoder to reconstruct the aggregation matrix instead of the input attribute matrix. The enhancement autoencoder can incorporate structural and attributed information in a joint learning way to improve the noise-resilient during the learning process. Furthermore, an adversarial learning component is leveraged in our framework to impose a prior distribution on learned representations has been demonstrated as an effective mechanism in improving the robustness and stability in representation learning. Experimental studies on real-world datasets have demonstrated the effectiveness of the proposed A3Graph. © 2021 ACM.
Attractiveness based conference ranking
- Zhang, Chen, Febrinanto, Falih, Liu, Mujie, Kong, Xiangjie, Zhang, Dongyu, Islam, Sardar
- Authors: Zhang, Chen , Febrinanto, Falih , Liu, Mujie , Kong, Xiangjie , Zhang, Dongyu , Islam, Sardar
- Date: 2022
- Type: Text , Conference paper
- Relation: 37th ACM/SIGAPP Symposium on Applied Computing, SAC 2022, Virtual, online, 25-29 April 2022, Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing p. 803-806
- Full Text: false
- Reviewed:
- Description: Conferences have a significant impact on the academic world. Academic conferences aim to exchange information about research results with others. The quality of the conference is highly considered because it involves the credibility of the research papers produced. Creating a ranking system is an effective way to measure conference quality and compare it with other venues. The existing conference ranking systems do not have a unified index or are still manually evaluated by humans, so there is a gap to create an academic conference evaluation system that is objective, comprehensive, and universal. To further improve the ranking system, we propose two new indicators in this work. In these two indicators, we quantify the attractiveness of conferences and combine them with the traditional three indicators to calculate the scores of 10 conferences in the field of data science through the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) model. The proposed new evaluation system can help authors understand conferences more comprehensively and screen conferences more sensibly. © 2022 ACM.
Predicting mental health problems with personality, behavior, and social networks
- Zhang, Dongyu, Guo, Teng, Han, Shiyu, Vahabli, Sadaf, Naseriparsa, Mehdi, Xia, Feng
- Authors: Zhang, Dongyu , Guo, Teng , Han, Shiyu , Vahabli, Sadaf , Naseriparsa, Mehdi , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Big Data, Big Data 2021, virtual online, 15-18 December 2021, Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 p. 4537-4546
- Full Text:
- Reviewed:
- Description: Mental health is an integral part of human health and well-being. Unhealthy mentality leads to serious consequences such as self-mutilation and suicide, especially for college students. While the literature focused on analysing the relationship between mental health and a single factor such as personality or behavior, accurate prediction is yet to be achieved due to the lack of cross-dimensional analysis and multi-dimensional joint prediction. To this end, this work proposes leveraging multiple factors from three crucial dimensions of mental health: behaviors, personality, and social networks. We recruited 490 college students, and collected their behavioral records from smart cards. In addition, we extracted their psychological traits from questionnaires, and social networks by conducting the survey on the nominating community members. We created a neural network-based model to integrate behavioral, psychological, and social network factors to predict mental health problems. The experimental results verify the efficacy of the proposed model, and demonstrate that the classification model of various factors effectively predicts the students' mental issues. © 2021 IEEE.
- Authors: Zhang, Dongyu , Guo, Teng , Han, Shiyu , Vahabli, Sadaf , Naseriparsa, Mehdi , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Big Data, Big Data 2021, virtual online, 15-18 December 2021, Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 p. 4537-4546
- Full Text:
- Reviewed:
- Description: Mental health is an integral part of human health and well-being. Unhealthy mentality leads to serious consequences such as self-mutilation and suicide, especially for college students. While the literature focused on analysing the relationship between mental health and a single factor such as personality or behavior, accurate prediction is yet to be achieved due to the lack of cross-dimensional analysis and multi-dimensional joint prediction. To this end, this work proposes leveraging multiple factors from three crucial dimensions of mental health: behaviors, personality, and social networks. We recruited 490 college students, and collected their behavioral records from smart cards. In addition, we extracted their psychological traits from questionnaires, and social networks by conducting the survey on the nominating community members. We created a neural network-based model to integrate behavioral, psychological, and social network factors to predict mental health problems. The experimental results verify the efficacy of the proposed model, and demonstrate that the classification model of various factors effectively predicts the students' mental issues. © 2021 IEEE.
MAM : a metaphor-based approach for mental illness detection
- Zhang, Dongyu, Shi, Nan, Peng, Ciyuan, Aziz, Abdul, Zhao, Wenhong, Xia, Feng
- Authors: Zhang, Dongyu , Shi, Nan , Peng, Ciyuan , Aziz, Abdul , Zhao, Wenhong , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 21st International Conference on Computational Science, ICCS 2021 Vol. 12744 LNCS, p. 570-583
- Full Text:
- Reviewed:
- Description: Among the most disabling disorders, mental illness is one that affects millions of people across the world. Although a great deal of research has been done to prevent mental disorders, detecting mental illness in potential patients remains a considerable challenge. This paper proposes a novel metaphor-based approach (MAM) to determine whether a social media user has a mental disorder or not by classifying social media texts. We observe that the social media texts posted by people with mental illness often contain many implicit emotions that metaphors can express. Therefore, we extract these texts’ metaphor features as the primary indicator for the text classification task. Our approach firstly proposes a CNN-RNN (Convolution Neural Network - Recurrent Neural Network) framework to enable the representations of long texts. The metaphor features are then applied to the attention mechanism for achieving the metaphorical emotions-based mental illness detection. Subsequently, compared with other works, our approach achieves creative results in the detection of mental illnesses. The recall scores of MAM on depression, anorexia, and suicide detection are the highest, with 0.50, 0.70, and 0.65, respectively. Furthermore, MAM has the best F1 scores on depression and anorexia detection tasks, with 0.51 and 0.71. © 2021, Springer Nature Switzerland AG.
- Authors: Zhang, Dongyu , Shi, Nan , Peng, Ciyuan , Aziz, Abdul , Zhao, Wenhong , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 21st International Conference on Computational Science, ICCS 2021 Vol. 12744 LNCS, p. 570-583
- Full Text:
- Reviewed:
- Description: Among the most disabling disorders, mental illness is one that affects millions of people across the world. Although a great deal of research has been done to prevent mental disorders, detecting mental illness in potential patients remains a considerable challenge. This paper proposes a novel metaphor-based approach (MAM) to determine whether a social media user has a mental disorder or not by classifying social media texts. We observe that the social media texts posted by people with mental illness often contain many implicit emotions that metaphors can express. Therefore, we extract these texts’ metaphor features as the primary indicator for the text classification task. Our approach firstly proposes a CNN-RNN (Convolution Neural Network - Recurrent Neural Network) framework to enable the representations of long texts. The metaphor features are then applied to the attention mechanism for achieving the metaphorical emotions-based mental illness detection. Subsequently, compared with other works, our approach achieves creative results in the detection of mental illnesses. The recall scores of MAM on depression, anorexia, and suicide detection are the highest, with 0.50, 0.70, and 0.65, respectively. Furthermore, MAM has the best F1 scores on depression and anorexia detection tasks, with 0.51 and 0.71. © 2021, Springer Nature Switzerland AG.
Heterogeneous graph learning for explainable recommendation over academic networks
- Chen, Xiangtai, Tang, Tao, Ren, Jing, Lee, Ivan, Chen, Honglong, Xia, Feng
- Authors: Chen, Xiangtai , Tang, Tao , Ren, Jing , Lee, Ivan , Chen, Honglong , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021, Virtual, Online, 14-17 December 2021, ACM International Conference Proceeding Series p. 29-36
- Full Text:
- Reviewed:
- Description: With the explosive growth of new graduates with research degrees every year, unprecedented challenges arise for early-career researchers to find a job at a suitable institution. This study aims to understand the behavior of academic job transition and hence recommend suitable institutions for PhD graduates. Specifically, we design a deep learning model to predict the career move of early-career researchers and provide suggestions. The design is built on top of scholarly/academic networks, which contains abundant information about scientific collaboration among scholars and institutions. We construct a heterogeneous scholarly network to facilitate the exploring of the behavior of career moves and the recommendation of institutions for scholars. We devise an unsupervised learning model called HAI (Heterogeneous graph Attention InfoMax) which aggregates attention mechanism and mutual information for institution recommendation. Moreover, we propose scholar attention and meta-path attention to discover the hidden relationships between several meta-paths. With these mechanisms, HAI provides ordered recommendations with explainability. We evaluate HAI upon a real-world dataset against baseline methods. Experimental results verify the effectiveness and efficiency of our approach. © 2021 ACM.
- Authors: Chen, Xiangtai , Tang, Tao , Ren, Jing , Lee, Ivan , Chen, Honglong , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021, Virtual, Online, 14-17 December 2021, ACM International Conference Proceeding Series p. 29-36
- Full Text:
- Reviewed:
- Description: With the explosive growth of new graduates with research degrees every year, unprecedented challenges arise for early-career researchers to find a job at a suitable institution. This study aims to understand the behavior of academic job transition and hence recommend suitable institutions for PhD graduates. Specifically, we design a deep learning model to predict the career move of early-career researchers and provide suggestions. The design is built on top of scholarly/academic networks, which contains abundant information about scientific collaboration among scholars and institutions. We construct a heterogeneous scholarly network to facilitate the exploring of the behavior of career moves and the recommendation of institutions for scholars. We devise an unsupervised learning model called HAI (Heterogeneous graph Attention InfoMax) which aggregates attention mechanism and mutual information for institution recommendation. Moreover, we propose scholar attention and meta-path attention to discover the hidden relationships between several meta-paths. With these mechanisms, HAI provides ordered recommendations with explainability. We evaluate HAI upon a real-world dataset against baseline methods. Experimental results verify the effectiveness and efficiency of our approach. © 2021 ACM.
On the regularity of weak solutions of the boussinesq equations in besov spaces
- Barbagallo, Annamaria, Gala, Sadek, Ragusa, Maria, Théra, Michel
- Authors: Barbagallo, Annamaria , Gala, Sadek , Ragusa, Maria , Théra, Michel
- Date: 2021
- Type: Text , Journal article
- Relation: Vietnam Journal of Mathematics Vol. 49, no. 3 (2021), p. 637-649
- Relation: http://purl.org/au-research/grants/arc/DP160100854
- Full Text:
- Reviewed:
- Description: The main issue addressed in this paper concerns an extension of a result by Z. Zhang who proved, in the context of the homogeneous Besov space Ḃ
- Authors: Barbagallo, Annamaria , Gala, Sadek , Ragusa, Maria , Théra, Michel
- Date: 2021
- Type: Text , Journal article
- Relation: Vietnam Journal of Mathematics Vol. 49, no. 3 (2021), p. 637-649
- Relation: http://purl.org/au-research/grants/arc/DP160100854
- Full Text:
- Reviewed:
- Description: The main issue addressed in this paper concerns an extension of a result by Z. Zhang who proved, in the context of the homogeneous Besov space Ḃ
Mandarin DP1-he-DP2 in the subject position
- Authors: Han, Weifeng , Shi, Dingxu
- Date: 2022
- Type: Text , Journal article
- Relation: SKASE Journal of Theoretical Linguistics Vol. 19, no. 1 (2022), p. 43-62
- Full Text:
- Reviewed:
- Description: Recent studies claim that, syntactically, he in DP1-he-DP2 can only be analyzed as a conjunction or as a preposition, but not both, in the subject position in Mandarin. This paper presents both empirical and theoretical arguments against such singular analyses of he. Drawn upon cross-linguistic evidence, we argue that he is open to both a conjunction and a proposition analyses. Under the Merge theory, it is argued that the prepositional phrase (PP) is derived through only EXTERNAL MERGE (EM), while the conjunction phrase (&P) is yielded through EM and then INTERNAL MERGE (IM). Therefore, PP and &P undergo different processes of labelling. The Phase Impenetrability Condition helps explain the topicalization and focus marking issues by the singular analysis of he as a preposition only. This paper illustrates how the same lexical item of he is used for both the conjunction and the comitative structures in Mandarin, and how both structures differ syntactically under the Merge theory. © 2022 Slovak Association for the Study of English. All rights reserved.
- Authors: Han, Weifeng , Shi, Dingxu
- Date: 2022
- Type: Text , Journal article
- Relation: SKASE Journal of Theoretical Linguistics Vol. 19, no. 1 (2022), p. 43-62
- Full Text:
- Reviewed:
- Description: Recent studies claim that, syntactically, he in DP1-he-DP2 can only be analyzed as a conjunction or as a preposition, but not both, in the subject position in Mandarin. This paper presents both empirical and theoretical arguments against such singular analyses of he. Drawn upon cross-linguistic evidence, we argue that he is open to both a conjunction and a proposition analyses. Under the Merge theory, it is argued that the prepositional phrase (PP) is derived through only EXTERNAL MERGE (EM), while the conjunction phrase (&P) is yielded through EM and then INTERNAL MERGE (IM). Therefore, PP and &P undergo different processes of labelling. The Phase Impenetrability Condition helps explain the topicalization and focus marking issues by the singular analysis of he as a preposition only. This paper illustrates how the same lexical item of he is used for both the conjunction and the comitative structures in Mandarin, and how both structures differ syntactically under the Merge theory. © 2022 Slovak Association for the Study of English. All rights reserved.
The Zinc Transporter, Slc39a7 (Zip7) Is Implicated in Glycaemic Control in Skeletal Muscle Cells
- Myers, Stephen, Nield, Alex, Chew, Guatsiew, Myers, Mark
- Authors: Myers, Stephen , Nield, Alex , Chew, Guatsiew , Myers, Mark
- Date: 2013
- Type: Text , Journal article
- Relation: Plos One Vol. 8, no. 11 (November 2013 2013), p. 15
- Full Text:
- Reviewed:
- Description: Dysfunctional zinc signaling is implicated in disease processes including cardiovascular disease, Alzheimer's disease and diabetes. Of the twenty-four mammalian zinc transporters, ZIP7 has been identified as an important mediator of the 'zinc wave' and in cellular signaling. Utilizing siRNA targeting Zip7 mRNA we have identified that Zip7 regulates glucose metabolism in skeletal muscle cells. An siRNA targeting Zip7 mRNA down regulated Zip7 mRNA 4.6-fold (p = 0.0006) when compared to a scramble control. This was concomitant with a reduction in the expression of genes involved in glucose metabolism including Agl, Dlst, Galm, Gbe1, Idh3g, Pck2, Pgam2, Pgm2, Phkb, Pygm, Tpi1, Gusb and Glut4. Glut4 protein expression was also reduced and insulin-stimulated glycogen synthesis was decreased. This was associated with a reduction in the mRNA expression of Insr, Irs1 and Irs2, and the phosphorylation of Akt. These studies provide a novel role for Zip7 in glucose metabolism in skeletal muscle and highlight the importance of this transporter in contributing to glycaemic control in this tissue.
- Authors: Myers, Stephen , Nield, Alex , Chew, Guatsiew , Myers, Mark
- Date: 2013
- Type: Text , Journal article
- Relation: Plos One Vol. 8, no. 11 (November 2013 2013), p. 15
- Full Text:
- Reviewed:
- Description: Dysfunctional zinc signaling is implicated in disease processes including cardiovascular disease, Alzheimer's disease and diabetes. Of the twenty-four mammalian zinc transporters, ZIP7 has been identified as an important mediator of the 'zinc wave' and in cellular signaling. Utilizing siRNA targeting Zip7 mRNA we have identified that Zip7 regulates glucose metabolism in skeletal muscle cells. An siRNA targeting Zip7 mRNA down regulated Zip7 mRNA 4.6-fold (p = 0.0006) when compared to a scramble control. This was concomitant with a reduction in the expression of genes involved in glucose metabolism including Agl, Dlst, Galm, Gbe1, Idh3g, Pck2, Pgam2, Pgm2, Phkb, Pygm, Tpi1, Gusb and Glut4. Glut4 protein expression was also reduced and insulin-stimulated glycogen synthesis was decreased. This was associated with a reduction in the mRNA expression of Insr, Irs1 and Irs2, and the phosphorylation of Akt. These studies provide a novel role for Zip7 in glucose metabolism in skeletal muscle and highlight the importance of this transporter in contributing to glycaemic control in this tissue.