Search

The convergence of systems neuroscience and open science arouses great interest in the current brain big data era, highlighting the thinking capability of intelligent agents in handling multi-source knowledge, information and data across various levels of granularity. To realize such thinking-inspired brain computing during a brain investigation process, one of the major challenges is to find a holistic brain map that can model multi-dimensional variables of brain investigations across brain functions, experimental tasks, brain data and analytical methods synthetically. In this paper, we propose a context-enhanced graph learning method to fuse open knowledge from different sources, including: contextual information enrichment, structural knowledge fusion, and holistic graph learning. Such a method can enhance contextual learning of abstract concepts and relational learning between two concepts that have large gap from different dimensions. As a result, an extensible space, namely Thinking Space, is generated to represent holistic variables and their relations in a map, which currently contributes to the field of brain research for systematic brain computing. In the future, the Thinking Space coupled with the rapid development and spread of artificial intelligence generated content will be developed in more scenarios so as to promote global interactions of intelligence in the connected world.

Learning based credit prediction has attracted great interest from academia and industry. Different institutions hold a certain amount of credit data with limited users to build model. An institution has the requirement to obtain data from other institutions for improving model performance. However, due to the privacy protection and subject to legal restrictions, they encounter difficulties in data exchange. This affects the performance of credit prediction. In order to solve the above problem, this paper proposes a federated learning based semi-supervised credit prediction approach enhanced by multi-layer label mean, which can aggregate parameters of each institution via joint training while protecting the data privacy of each institution. Moreover, in actual production and life, there are usually more unlabeled credit data than labeled ones, and the distribution of their feature space presents multiple data-dense divisions. To deal with these, local meanNet model is proposed with a multi-layer label mean based semi-supervised deep learning network. In addition, this paper introduces a cost-sensitive loss function in the supervised part of the local mean model. Conducted on two public credit datasets, experimental results show that our proposed federated learning based approach has achieved promising credit prediction performance in terms of Accuracy and F1 measures. At the same time, the framework design mode that splits data aggregation and keys uniformly can improve the security of data privacy and enhance the flexibility of model training.

Topic models have been widely used for learning the latent explainable representation of documents, but most of the existing approaches discover topics in a flat structure. In this study, we propose an effective hierarchical neural topic model with strong interpretability. Unlike the previous neural topic models, we explicitly model the dependency between layers of a network, and then combine latent variables of different layers to reconstruct documents. Utilizing this network structure, our model can extract a tree-shaped topic hierarchy with low redundancy and good explainability by exploiting dependency matrices. Furthermore, we introduce manifold regularization into the proposed method to improve the robustness of topic modeling. Experiments on real-world datasets validate that our model outperforms other topic models in several widely used metrics with much fewer computation costs.

Exploiting hand-crafted lexicon knowledge to enhance emotional or sentimental features at word-level has become a widely adopted method in emotion-relevant classification studies. However, few attempts have been made to explore the emotion construction in the classification task, which provides insights to how a sentence’s emotion is constructed. The major challenge of exploring emotion construction is that the current studies assume the dataset labels as relatively independent emotions, which overlooks the connections among different emotions. This work aims to understand the coarse-grained emotion construction and their dependency by incorporating fine-grained emotions from domain knowledge. Incorporating domain knowledge and dimensional sentiment lexicons, our previous work proposes a novel method namedEmoChannelto capture the intensity variation of a particular emotion in time series. We utilize the resultant knowledge of 151 available fine-grained emotions to comprise the representation of sentence-level emotion construction. Furthermore, this work explicitly employs a self-attention module to extract the dependency relationship within all emotions and proposeEmoChannel-SANetwork to enhance emotion classification performance. We conducted experiments to demonstrate that the proposed method produces competitive performances against the state-of-the-art baselines on both multi-class datasets and sentiment analysis datasets.

With the rapid development of artificial intelligence and the increasing demand for legal intelligence, using AI methods to predict legal judgments has become a hot spot in recent years. Charge prediction is one of the core tasks of Legal Judgment Prediction (LJP). It aims to predict charge from complicated legal facts, so as to help the court make judgments or provide legal professional guidance to non-professionals. In the field of legalAI, interpretability is crucial compared to others. Reasonable interpretability can eliminate hidden dangers such as gender discrimination and provide support for judges’ decisions. However, how to add the legal theory framework to the modeling to improve the interpretability is a challenge, which has few researches at present. To address this problem, we use Double-layer Criminal System as a guide to build Charge Prediction modeling called DCSCP which aims to predict charges in the criminal law of China. In general, our characteristic is to achieve multi-granularity inference of legal charges by obtaining the subjective and objective elements from the fact descriptions of legal cases. Specifically, our approach is performed in two steps: (1) extract the objective elements from the fact description and use them to generate candidate charges to achieve coarse-grained prediction; (2) extract the subjective elements from the fact description, and design the first-order predicate logic inference to realize the fine-grained charge inference in combination with the candidate charges. Experimental results show that our DCSCP can provide interpretable predictions, and it can maintain performance compared to other state-of-the-art charge prediction models.

Secure deduplication aims to efficiently eliminate redundant data in cloud storage system, where convergent encryption (CE) is widely-used to provide the data confidentiality. As the number of convergent keys (CKs) in CE will increase dramatically with enlarging data, there is a critical issue that how to safely manage the CKs. Previous works usually introduce a fully-trusted key management server (KS) to ensure the CKs security, resulting in data leakage by KS in reality. In this paper, we propose a blockchain-based secure deduplication scheme with reliable CK management, denoted as BDKM, which introduces different secret information to CE to enhance the data confidentiality in different level deduplications. To realize secure and reliable CK management, the CK will be divided into key segments by using secret sharing scheme and distributed on blockchain as transactions. Therefore, only the valid data owner can recover the CK from the blockchain and the original data will be protected even if the adversaries have colluded with cloud service provider. Security analysis and performance evaluation demonstrate that our proposed scheme can remain secure under the proposed security models with a limited overhead.

The application of artificial intelligence (AI) technologies in assisting human electroencephalogram (EEG) analysis has become an active scientific field. This study aims to present a comprehensive review of the research field of AI-enhanced human EEG analysis. Using bibliometrics and topic modeling, research articles concerning AI-enhanced human EEG analysis collected from the Web of Science database during the period 2009–2018 were analyzed. After examining 2053 research articles published around the world, it was found that the annual number of articles had significantly grown from 78 to 468, with the USA and China being the most influential and prolific. The results of the keyword analysis showed that “electroencephalogram,” “brain–computer interface,” “classification,” “support vector machine,” “electroencephalography,” and “signal” were the most frequently used. The results of topic modeling and evolution analyses highlighted several important issues, including epileptic seizure detection, brain–machine interface, EEG classification, mental disorders, emotion, and alcoholism and anesthesia. The findings suggest that such visualization and analysis of the research articles could provide a comprehensive overview of the field for communities of practice and inquiry worldwide.

Hard interaction learning between source sequences and their next targets is challenging, which exists in a myriad of sequential prediction tasks. During the training process, most existing methods focus on explicitly hard interactions caused by wrong responses. However, a model might conduct correct responses by capturing a subset of learnable patterns, which results in implicitly hard interactions with some unlearned patterns. As such, its generalization performance is weakened. The problem gets more serious in sequential prediction due to the interference of substantial similar candidate targets. To this end, we propose a Hardness Aware Interaction Learning framework (HAIL) that mainly consists of two base sequential learning networks and mutual exclusivity distillation (MED). The base networks are initialized differently to learn distinctive view patterns, thus gaining different training experiences. The experiences in the form of the unlikelihood of correct responses are drawn from each other by MED, which provides mutual exclusivity knowledge to figure out implicitly hard interactions. Moreover, we deduce that the unlikelihood essentially introduces additional gradients to push the pattern learning of correct responses. Our framework can be easily extended to more peer base networks. Evaluation is conducted on four datasets covering cyber and physical spaces. The experimental results demonstrate that our framework outperforms several state-of-the-art methods in terms of top-k based metrics., 10 pages; 4 figures; Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM '21), November 1--5, 2021, Virtual Event, QLD, Australia

Text classification (a.k.a text categorisation) is an effective and efficient technology for information organisation and management. With the explosion of information resources on the Web and corporate intranets continues to increase, it has being become more and more important and has attracted wide attention from many different research fields. In the literature, many feature selection methods and classification algorithms have been proposed. It also has important applications in the real world. However, the dramatic increase in the availability of massive text data from various sources is creating a number of issues and challenges for text classification such as scalability issues. The purpose of this report is to give an overview of existing text classification technologies for building more reliable text classification applications, to propose a research direction for addressing the challenging problems in text mining.

Banking and Financial Services Corporations need to update information systems with logic and data of various applications on everyday basis to remain consistent with change in economy and business activity. This helps to work with latest information included in information system available in current economic and business scenario. This enables information systems and empowers work force to complete tasks in rapidly changing flow of monetary resources. With several employees in Banking and Financial Services Corporations using cloud infrastructure and reporting incidents arising in using cloud infrastructure, it is of prime importance to fix incidents reported within specific timelines. IT change management process is followed in order to adhere to IT governance & compliance framework and reduce risk of failure while performing changes in cloud infrastructure. With incident management and change management processes are aligned to keep cloud infrastructure available and secure, they become integral part of IT operations everyday activity. To make ITIL processes efficient, further organization specific policies are developed. With global standards and organization level controls in place, there are failures in IT incident and change management processes and implementation. In this paper, we have identified the risk arising due to incident management and change management processes that lead to emergency changes being implemented on cloud infrastructure architecture and discussed the steps to mitigate risks to bring greater responsibility and accountability for cloud services providers.

With the advances and development of imaging and computer technologies, the application of artificial intelligence (AI) in the processing of magnetic resonance imaging (MRI) data has become a significant research field. Based on 2572 research articles concerning AI-enhanced brain MRI processing, this study provides a latent Dirichlet allocation based bibliometric analysis for the exploration of the status, trends, major research issues, and potential future directions of the research field. The trend analyses of articles and citations demonstrate a flourishing and increasing impact of the research. Neuroimage is the most prolific and influential journal. The USA and University College London have contributed the most to the research. The collaboration between European countries is very close. Essential research issues such as Image segmentation, Mental disorder, Functional network connectivity, and Alzheimer’s disease have been uncovered. Potential inter-topic research directions such as Functional network connectivity and Mental disorder, Image segmentation and Image classification, Cognitive impairment and Diffusion imaging, as well as Sense and memory and Emotion and feedback, have been highlighted.

Nowadays, breast cancer is reported as one of most common cancers amongst women. Early detection of this cancer is an essential to aid in informing subsequent treatments. This study investigates automated breast cancer prediction using machine learning and data mining techniques. We proposed the nested ensemble approach which used the Stacking and Vote (Voting) as the classifiers combination techniques in our ensemble methods for detecting the benign breast tumors from malignant cancers. Each nested ensemble classifier contains “Classifiers” and “MetaClassifiers”. MetaClassifiers can have more than two different classification algorithms. In this research, we developed the two-layer nested ensemble classifiers. In our two-layer nested ensemble classifiers the MetaClassifiers have two or three different classification algorithms. We conducted the experiments on Wisconsin Diagnostic Breast Cancer (WDBC) dataset and K-fold Cross Validation technique are used for the model evaluation. We compared the proposed two-layer nested ensemble classifiers with single classifiers (i.e., BayesNet and Naive Bayes) in terms of the classification accuracy, precision, recall, F1 measure, ROC and computational times of training single and nested ensemble classifiers. We also compared our best model with previous works reported in the literatures in terms of accuracy. The results demonstrate that the proposed two-layer nested ensemble models outperformance the single classifiers and most of the previous works. Both SV-BayesNet-3-MetaClassifier and SV-Naive Bayes-3-MetaClassifier achieved accuracy 98.07% ( K = 10 ). However, SV-Naive Bayes-3-MetaClassifier is more efficiency as it needs less time to build the model.

Simile, a special type of metaphor, can help people to express their ideas more clearly. Simile component extraction is to extract tenors and vehicles from sentences. This task has a realistic significance since it is useful for building cognitive knowledge base. With the development of deep neural networks, researchers begin to apply neural models to component extraction. Simile components should be in cross-domain. According to our observations, words in cross-domain always have different concepts. Thus, concept is important when identifying whether two words are simile components or not. However, existing models do not integrate concept into their models. It is difficult for these models to identify the concept of a word. What’s more, corpus about simile component extraction is limited. There are a number of rare words or unseen words, and the representations of these words are always not proper enough. Exiting models can hardly extract simile components accurately when there are low-frequency words in sentences. To solve these problems, we propose a hybrid representation-based component extraction (HRCE) model. Each word in HRCE is represented in three different levels: word level, concept level and character level. Concept representations (representations in concept level) can help HRCE to identify the words in cross-domain more accurately. Moreover, with the help of character representations (representations in character levels), HRCE can represent the meaning of a word more properly since words are consisted of characters and these characters can partly represent the meaning of words. We conduct experiments to compare the performance between HRCE and existing models. The experiment results show that HRCE significantly outperforms current models.

Recent advances in remote patient monitoring (RPM) systems can recognize various human activities to measure vital signs, including subtle motions from superficial vessels. There is a growing interest in applying artificial intelligence (AI) to this area of healthcare by addressing known limitations and challenges such as predicting and classifying vital signs and physical movements, which are considered crucial tasks. Federated learning is a relatively new AI technique designed to enhance data privacy by decentralizing traditional machine learning modeling. However, traditional federated learning requires identical architectural models to be trained across the local clients and global servers. This limits global model architecture due to the lack of local models heterogeneity. To overcome this, a novel federated learning architecture, FedStack, which supports ensembling heterogeneous architectural client models was proposed in this study. This work offers a protected privacy system for hospitalized in-patients in a decentralized approach and identifies optimum sensor placement. The proposed architecture was applied to a mobile health sensor benchmark dataset from 10 different subjects to classify 12 routine activities. Three AI models, ANN, CNN, and Bi-LSTM were trained on individual subject data. The federated learning architecture was applied to these models to build local and global models capable of state of the art performances. The local CNN model outperformed ANN and Bi-LSTM models on each subject data. Our proposed work has demonstrated better performance for heterogeneous stacking of the local models compared to homogeneous stacking. This work sets the stage to build an enhanced RPM system that incorporates client privacy to assist with clinical observations for patients in an acute mental health facility and ultimately help to prevent unexpected death., 47 Pages, Journal Article. Knowledge-Based Systems (2022)

Streamflow (Qflow) prediction is one of the essential steps for the reliable and robust water resources planning and management. It is highly vital for hydropower operation, agricultural planning, and flood control. In this study, the convolution neural network (CNN) and Long-Short-term Memory network (LSTM) are combined to make a new integrated model called CNN-LSTM to predict the hourly Qflow (short-term) at Brisbane River and Teewah Creek, Australia. The CNN layers were used to extract the features of Qflow time-series, while the LSTM networks use these features from CNN for Qflow time series prediction. The proposed CNN-LSTM model is benchmarked against the standalone model CNN, LSTM, and Deep Neural Network models and several conventional artificial intelligence (AI) models. Qflow prediction is conducted for different time intervals with the length of 1-Week, 2-Weeks, 4-Weeks, and 9-Months, respectively. With the help of different performance metrics and graphical analysis visualization, the experimental results reveal that with small residual error between the actual and predicted Qflow, the CNN-LSTM model outperforms all the benchmarked conventional AI models as well as ensemble models for all the time intervals. With 84% of Qflow prediction error below the range of 0.05 m3 s−1, CNN-LSTM demonstrates a better performance compared to 80% and 66% for LSTM and DNN, respectively. In summary, the results reveal that the proposed CNN-LSTM model based on the novel framework yields more accurate predictions. Thus, CNN-LSTM has significant practical value in Qflow prediction.

Deep clustering aims to cluster unlabeled real-world samples by mining deep feature representation. Most of existing methods remain challenging when handling high -dimensional data and simultaneously exploring the complementarity of deep feature representation and clustering. In this paper, we propose a novel Deep Variational Attention Encoder-decoder for Clustering (DVAEC). Our DVAEC improves the representation learning ability by fusing variational attention. Specifically, we design a feature-aware automatic clustering module to mitigate the unreliability of similarity calculation and guide network learning. Besides, to further boost the performance of deep clustering from a global perspective, we define a joint optimization objective to promote feature representation learning and automatic clustering synergistically. Extensive experimental results show the promising performance achieved by our DVAEC on six datasets comparing with several popular baseline clustering methods.

Traffic signal control problems are critical in urban intersections. Recently, deep reinforcement learning demonstrates impressive performance in the control of traffic signals. The design of state and reward function is often heuristic, which leads to highly vulnerable performance. To solve this problem, some studies introduce transportation theory into deep reinforcement learning to support the design of reward function e.g., max-pressure control, which have yielded promising performance. We argue that the constant changes of intersections’ pressure can be better represented with the consideration of downstream neighboring intersections. In this paper, we propose CMPLight, a deep reinforcement learning traffic signal control approach with a novel cooperative max-pressure-based reward function to leverage the vehicle queue information of neighborhoods. The approach employs cooperative max-pressure to guide the design of reward function in deep reinforcement learning. We theoretically prove that it is stabilizing when the average traffic demand is admissible and traffic flow is stable in road network. The state of deep reinforcement learning is enhanced by neighboring information, which helps to learn a detailed representation of traffic environment. Extensive experiments are conducted on synthetic and real-world datasets. The experimental results demonstrate that our approach outperforms traditional heuristic transportation control approaches and the state-of-the-arts learning-based approaches in terms of average travel time of all vehicles in road network.

Remote Patient Monitoring (RPM) has gained great popularity with an aim to measure vital signs and gain patient related information in clinics. RPM can be achieved with noninvasive digital technology without hindering a patient&rsquo, s daily activities and can enhance the efficiency of healthcare delivery in acute clinical settings. In this study, an RPM system was built using radio frequency identification (RFID) technology for early detection of suicidal behaviour in a hospital-based mental health facility. A range of machine learning models such as Linear Regression, Decision Tree, Random Forest, and XGBoost were investigated to help determine the optimum fixed positions of RFID reader&ndash, antennas in a simulated hospital ward. Empirical experiments showed that Decision Tree had the best performance compared to Random Forest and XGBoost models. An Ensemble Learning model was also developed, took advantage of these machine learning models based on their individual performance. The research set a path to analyse dynamic moving RFID tags and builds an RPM system to help retrieve patient vital signs such as heart rate, pulse rate, respiration rate and subtle motions to make this research state-of-the-art in terms of managing acute suicidal and self-harm behaviour in a mental health ward.

The current multi-class emotion classification studies mainly focus on enhancing word-level and sentence-level semantical and sentimental features by exploiting hand-crafted lexicon dictionaries. In comparison, very limited studies attempt to achieve emotion classification task from the emotion-level perspectives, which are to understand how the emotion of a sentence is constructed. Another limitation of existing works is that they assumed that emotion labels are relatively independent, neglecting the possible relations among different types of emotions. Therefore, in this work, we aim to explore various fine-grained emotions based on domain knowledge to understand the construction details of emotions and the interconnection among emotions. To address the first issue, we propose a novel method named EmoChannel to capture the intensity variation of a particular emotion in time series by incorporating domain knowledge and dimensional sentiment lexicons. The resulting information of 151 available fine-grained emotions is utilized to comprise the sentence-level emotion construction. As for the second issue, we introduce the EmoChannelAttn Network to identify the dependency relationship within all emotions via attention mechanism to enhance emotion classification performance. Our experiments demonstrate that the proposed method gains significant improvements compared with baseline models on several multi-class datasets.

breast cancer is reported as one of most common malignancy amongst women in the world. Early detection of this cancer is critical to clinical and epidemiologic for aiding in informing subsequent treatments. This study investigates automated breast cancer prediction using deep learning techniques. A new 19-layer deep convolutional neural network (CNN) model for detecting the benign breast tumors from malignant cancers was proposed and implemented. The experiments on BreaKHis dataset was conducted and K-fold Cross Validation technique are used for the model evaluation. The proposed 19-layer deep CNN based classifiers compared with conventional machine learning classifier, namely Support Vector Machine (SVM) and a state-of-the-art deep learning model, namely GoogLeNet in terms of Accuracy, Area under the Receiver Operating Characteristic (ROC) Curve (AUC), the Classification Mean Absolute Error (MAE), Mean Squared Error (MSE) metrics. The results demonstrate that the proposed new model outperformed the other classifiers. The proposed model achieved an accuracy, AUC, MAE and MSE of 84.5%, 85.7%, 0.082, and 0.043, respectively.

Forecasting the traffic flow is a critical issue for researchers and practitioners in the field of transportation. Using the graph convolutional network (GCN) is widespread in traffic flow forecasting. Existing GCN-based methods mostly rely on undirected spatial correlations to represent the features of spatial-temporal graph. What's more, the traffic flow renders two types of spatial correlations, including the stable correlation constrained by the fixed road structure and the dynamic correlation influenced by the traffic fluctuation. In this paper, we propose a two-stream graph convolutional network by considering stable and dynamic correlations in parallel, which is an end-to-end deep learning framework for dynamic traffic forecasting. We present an auto-decomposing layer to decompose real-time traffic flow data into a stable component and a dynamic component with different spatial correlations. Specifically, the stable component is constrained by the physical road network, and the dynamic component represents fluctuations caused by changes in traffic conditions such as congestion and bad weather. Moreover, we extract stable and dynamic spatial correlations through our two-stream graph convolutional layer. Finally, we use parameterized skip connection to fuse spatial-temporal correlations as the input of output layer for forecasting. Extensive experiments are conducted on two real-world traffic datasets, and experimental results show that our proposed model is better than several popular baselines.

Major depressive disorder (MDD) is an issue that affects 350 million people worldwide. Traditional approaches have been to identify depressive symptoms in datasets, but recently, research is beginning to explore the association between psychosocial factors such as those on the quality of life scale and mental well-being, which will lead to earlier diagnosis and prediction of MDD. In this research, an ensemble binary classifier is proposed to analyse health survey data against ground truth from the SF-20 Quality of Life scales. The classifier aims to improve the performance of machine learning techniques on large datasets and identify depressed cases based on associations between items on the QoL scale and mental illness by increasing predictive performance. On the experimental evaluation on the National Health and Nutrition Examination Survey (NHANES), the classifier demonstrated an F1 score of 0.976 in the prediction, without any incorrectly identified depression instances. Only about 4% of instances had been mistakenly classified into depressed cases, with a significant accuracy of 95.4% comparing to the result from PHQ-9 mental screen inventory. The presented ensemble binary classifier performed comparably better than each baseline algorithm in all measures and all experiments. We trained the ensemble model on the processed NHANES dataset, tested and evaluated the results of its performance against mental screen inventory and discussed the comparable predictions. Finally, we provided future research directions.

Predicting workplace injury using automated techniques opens newer possibilities in evidence-based research. This paper presents our preliminary research in a PhD project in predicting workplace incidents using machine learning algorithms. The analysis on the model performance using several mainstream machine learning algorithms including random forest, k-nearest neighbor and decision tree indicated that the general performance of the decision tree model was found to be statistically higher than that of the other two algorithms.

Evolutionary behavior of Online Social Networks (OSNs) has not been well understood in many different aspects. Although there have been many developments around social applications like recommendation, prediction, detection and identification which take advantage of past observations of structural patterns, they lack the necessary representative power to adequately account for the sophistication contained within relationships between actors of a social network in real life. In this demo, we extend the innovative developments of SLIND [17] (Stable LINk Detection) to include a novel generative adversarial architecture and the Relational Turbulence Model (RTM) [15] using relational features extracted from real-time twitter streaming data. Test results show that SLIND\(^+\) is capable of detecting relational turbulence profiles learned from prior feature evolutionary patterns in the social data stream. Representing turbulence profiles as a pivotal set of relational features improves detection accuracy and performance of well-known application approaches in this area of research.

The social networking scene has evolved tremendously over the years. It has grown in relational complexities that extend a vast presence onto popular social media platforms on the internet. With the advance of sentimental computing and social complexity, relationships which were once thought to be simple have now become multi-dimensional and widespread in the online scene. This explosion in the online social scene has attracted much research attention. The main aims of this work revolve around the knowledge discovery and datamining processes of these feature-rich relations. In this paper, we provide a survey of relational learning and discovery through popular social analysis of different structure types which are integral to applications within the emerging field of sentimental and affective computing. It is hoped that this contribution will add to the clarity of how social networks are analyzed with the latest groundbreaking methods and provide certain directions for future improvements.

Sentiment analysis classification models trained using neural networks require large amounts of data, but collecting these datasets requires significant time and resources. Although artificial data has been used successfully in computer vision, there are few effective and generalizable methods for creating artificial augmented text data. In this paper, a text based data augmentation method is proposed called back-and-forth translation that can be used to artificially increase the size of any natural language dataset. By creating augmented text data and adding it to the original dataset, it is demonstrated by empirical experiments that back-and-forth translation data augmentation can reduce the error rate in binary sentiment classification models by up to 3.4%. These results are shown to be statistically significant.

Multi-view graph clustering is an attentional research topic in recent years due to its wide applications. According to recent surveys, most existing works focus on incorporating comprehensive information among multiple views to achieve the clustering task. However, these studies pay less attention to explore the collaborative relationship between fusion-view features and independence-view features. To make full use of view relationships and enhance the complementary benefits of different views in graphs, we propose a trio-based collaborative learning framework for multi-view graph representation clustering (TCMGC) that drives the multiple auto-clustering constraints. We utilize the triplet operations (trio-based) to guarantee the independence and complementarity between each view and complete clustering tasks collaboratively. Meanwhile, we propose a joint optimization objective to improve the overall performance of representation learning and clustering. Experimental results on four real-world benchmark datasets show that the proposed TCMGC has promising performance compared with state-of-the-art baseline methods.

Recently, the use of intelligent technologies in clinical decision making in the telehealth environment has begun to play a vital role in improving the quality of patients' lives and helping reduce the costs and workload involved in their daily healthcare. In this paper, an effective medical recommendation system that uses a fast Fourier transformation-coupled machine learning ensemble model is proposed for short-term disease risk prediction to provide chronic heart disease patients with appropriate recommendations about the need to take a medical test or not on the coming day based on analysing their medical data. The input sequence of sliding windows based on the patient's time series data are decomposed by using the fast Fourier transformation in order to extract the frequency information. A bagging-based ensemble model is utilized to predict the patient's condition one day in advance for producing the final recommendation. A combination of three classifiers-artificial neural network, least squares-support vector machine, and naive bayes-are used to construct an ensemble framework. A real-life time series telehealth data collected from chronic heart disease patients are utilized for experimental evaluation. The experimental results show that the proposed system yields a very good recommendation accuracy and offers an effective way to reduce the risk of incorrect recommendations as well as reduce the workload for heart disease patients in conducting body tests every day. The results conclusively ascertain that the proposed system is a promising tool for analyzing time series medical data and providing accurate and reliable recommendations to patients suffering from chronic heart diseases.

The use of intelligent technologies for providing useful recommendations to patients suffering chronic diseases may play a positive role in improving the general life quality of patients and help reduce the workload and cost involved in their daily healthcare. The objective of this study is to develop an intelligent recommender system based on predictive analysis for advising patients in the telehealth environment concerning whether they need to take the body test one day in advance by analyzing medical measurements of a patient for the past k days. The proposed algorithms supporting the recommender system have been validated using a time series telehealth data recorded from heart disease patients which were collected from May to January 2012, from our industry collaborator Tunstall. The experimental results show that the proposed system yields satisfactory recommendation accuracy and offer a promising way for saving the workload for patients to conduct body tests every day. This study highlights the possible usefulness of the computerized analysis of time series telehealth data in providing appropriate recommendations to patients suffering chronic diseases such as heart diseases patients.

Technology plays an important role in helping organizations control quality and costs, and take advantage of opportunities in a highly competitive and increasingly complex business environment. Cloud computing offers greater access to computing power, storage, software, and remote data centres through the web. This research aims to confirm the factors to be considered for cloud computing adoption in Australian regional municipal governments. The research involved data from interviews with IT managers from selected regional municipal governments, and survey data from 480 IT staff across 47 regional municipal governments. The major factors to be considered for the adoption of cloud computing in regional municipal governments were identified as Internet connectivity, Internet speed, availability, reliability, data storage location, security, data sovereignty, cost, integration, data backup, provider dependability, employees’ knowledge, and transportability. The findings of this research may help managers increase their awareness about factors to be considered when regional municipal governments planning to adopt cloud computing.

Detecting words that express negativity in a social media message is one step towards detecting depressive moods. To understand if a Twitter user could exhibit depression over a period of time, we applied techniques in stages to discover words that are negative in expression. Existing methods either use a single step or a data subset, whereas we applied a multi-step approach which allowed us to identify potential users and then discover the words that expressed negativity by these users. We address some Twitter specific characteristics in our research. One of which is that Twitter data can be very large, hence our desire to be able to process the data efficiently. The other is that due to its enforced character limitation, the style of writing makes interpreting and obtaining the semantic meaning of the words more challenging. Results show that the sentiment of these words can be obtained and scored efficiently as the computation on these dataset were narrowed to only these selected users. We also obtained the stress scores which correlated well with negative sentiment expressed in the content. This work shows that by first identifying users and then using methods to discover words can be a very effective technique.

Applying Pearson correlation and semantic relations in building a heterogeneous information graph (HIG) to develop a classification model has achieved a notable performance in improving the accuracy of predicting the status of health risks. In this study, the approach that was used, integrated knowledge of the medical domain as well as taking advantage of applying Pearson correlation and semantic relations in building a classification model for diagnosis. The research mined knowledge which was extracted from titles and abstracts of MEDLINE to discover how to assess the links between objects relating to medical concepts. A knowledge-base HIG model then was developed for the prediction of a patient’s health status. The results of the experiment showed that the knowledge-base model was superior to the baseline model and has demonstrated that the knowledge-base could help improve the performance of the classification model. The contribution of this study has been to provide a framework for applying a knowledge-base in the classification model which helps these models achieve the best performance of predictions. This study has also contributed a model to medical practice to help practitioners become more confident in making final decisions in diagnosing illness. Moreover, this study affirmed that biomedical literature could assist in building a classification model. This contribution will be advantageous for future researchers in mining the knowledge-base to develop different kinds of classification models.

Knowledge Graphs (KGs) have deep and impactful applications in a wide-array of information networks such as natural language processing, recommendation systems, predictive analysis, recognition, classification, etc. Embedding real-life relational representations in KGs is an essential process of abstracting facts for many important data mining tasks like information retrieval, privacy and control, enrichment and so on. In this paper, we investigate the embedding of the relational fractals which are learned from the Relational Turbulence profiles in the transactions of Online Social Networks (OSNs) into KGs. These relational fractals have the capability of building both compositional-depth hierarchies and shallow-wide continuous vector spaces for more efficient computations on devices with limited resources. The results from our RFT model show accurate predictions of relational turbulence patterns in OSNs which can be used to evolve facts in KGs for more accurate and timely information representations.

Inaccurate assessment may lead to inaccurate levels of dosage given to the patients that may lead to intraoperative awareness that is caused by under dosage during surgery or prolonged recovery in patients that is caused by over dosage after the surgery is done. Previous research and evidence show that assessing anesthetic levels with the help of electroencephalography (EEG) signals gives an overall better aspect of the patient’s anesthetic state. This paper presents a new method to assess the depth of anesthesia (DoA) using Independent Component Analysis (ICA) and permutation entropy analysis. ICA is performed on two-channel EEG to reduce the noise then Wavelet and permutation entropy are applied on these channels to extract the features. A linear regression model was used to build the new DoA index using the selected features. The new index designed by proposed methods performs well under low signal quality and it was overall consistent in most of the cases where Bispectral index (BIS) may fail to provide any valid value.

With more patients taking multiple medications and the increasing digital availability of diagnostic data such as treatment notes and x-ray images, the importance of decision support systems to help dentists in their treatment planning cannot be over emphasised. Based on the hypothesis that a higher similarity ratio between drugs in a drug-pair indicates that the combination of the drug-pair has a higher chance of an adverse interaction, this paper describes an efficient approach in extracting feature vectors from the drugs in a drug-pair to compute the similarity ratio between them. The feature vectors are obtained through a network model where the information of the drugs are represented as nodes and the relationships between them represented as edges. Experimental evaluation of our model yielded a superior F score of 74%. The use of a network model will drive research efforts into more efficient data-mining algorithms for information retrieval, similarity search and machine learning. Since it is important to avoid drug allergies when prescribing drugs, our work when integrated within the clinical work-flow will reduce prescription errors thereby increasing health outcomes for patients.

The currency exchange rate is the rate that is using one currency to another exchange. Under the classical economic analysis method, fluctuations in exchange rates significantly impacted the real economy. Using the well-being transformer/generator inspection network, the device parts, and the program executed single-chip instructions so far in the previous method. Track temperature, current or transformers, generators, machines, or self-generated and load voltage self-sold, direct information that connects this section or gadgets to this work. From this point on, in this implementation, change direction and a uniform temperature water momentum sensor, information of the voltage sensor, and a sensor for detecting that the data is being converted into a mechanical structure simple structure via the interface voltage and temperature sensors and flow sensor using machine learning and embedded system. The sensor information is then used by the microcontroller to display the display information obtained in the microcontroller and transmit it to the Wi-Fi module. Information, such a current will have three distinct patterns displayed on a particular website, e.g., voltage and temperature.

While most dental clinicians use some sort of information system, they are involved with administrative functions, despite the advisory potential of some of these systems. This paper outlines some current decision support systems (DSS) and the common barriers facing dentists in adopting them within their workflow. These barriers include lack of perceived usefulness, complicated social and economic factors, and the difficulty for users to interpret the advice given by the system. A survey of current systems found that although there are systems that suggest treatment options, there is no real-time integration with other knowledge bases. Additionally, advice on drug prescription at point-of-care is absent from such systems, which is a significant omission, in consideration of the fact that disease management and drug prescription are common in the workflow of a dentist. This paper also addresses future trends in the research and development of dental clinical DSS, with specific emphasis on big data, standards and privacy issues to fulfil the vision of a robust, user-friendly and scalable personalised DSS for dentists. The findings of this study will offer strategies in design, research and development of a DSS with sufficient perceived usefulness to attract adoption and integration by dentists within their routine clinical workflow, thus resulting in better health outcomes for patients and increased productivity for the clinic.

The use of intelligent and sophistic technologies in evidence-based clinical decision making support have been playing an important role in improving the quality of patients’ life and helping to reduce cost and workload involved in their daily healthcare. In this paper, an effective medical recommendation system that uses a structural graph approach with advanced machine learning ensemble model is proposed for short-term disease risk prediction to provide chronic heart disease patients with appropriate recommendations about the need to take a medical test or not on the coming day based on analysing their medical data. A time series telehealth data recorded from patients is used for experimentations, evaluation and validation. The Tunstall dataset were collected from May to October 2012, from industry collaborator Tunstall. A time series data is segmented into slide windows and then mapped into undirect graph. The size of slide window was empirically determined. The structural properties of graph enter as the features set to the machine learning ensemble classifier to predict the patient’s condition one day in advance. A combination of three classifiers—Least Squares-Support Vector Machine, Artificial Neural Network, and Naive Bayes—are used to construct an ensemble framework to classify the graph features. To investigate the predictive ability of the graph with the ensemble classifier, the extracted statistical features were also forwarded to the individual classifiers for comparison. The findings of this study shows that the recommendation system yields a satisfactory recommendation accuracy, offers a effective way for reducing the risk of incorrect recommendations as well as reducing the workload for heart disease patients in conducting body tests every day. A 94% average prediction accuracy is achieved by using the proposed recommendation system. The results conclusively ascertain that the proposed system is a promising tool for analyzing time series medical data and providing accurate and reliable recommendations to patients suffering from chronic heart diseases.

Intelligent technologies are enjoying growing popularity in a telehealth environment for helping improve the quality of chronic patients’ lives and provide better clinical decision-making to reduce the costs and workload involved in their daily healthcare. Obtaining a short-term disease risk prediction and thereby offering medical recommendations reliably and accurately are challenging in teleheath systems. In this work, a novel medical recommender system is proposed based upon time series data analysis for diabetes patients. It uses three decomposition methods, i.e., dual-tree complex wavelet transform (DTCWT), fast Fourier transformation (FFT) and dual-tree complex wavelet transform-coupled fast Fourier transform (DWCWT-FFT), with least square-support vector machine (LS-SVM) for short-term disease risk prediction for diabetes disease patients which then generates appropriate recommendations on their need to take a medical test or not on the coming day based on the analysis of their medical data. A real-life time series dataset is used for experimental evaluation. The experimental results show that the proposed system yields very good recommendation accuracy and can effectively reduce the workload for diabetes disease patients in conducting daily body tests.