•Over 40 models for aspect-based sentiment analysis are summarized and classified.•Deep learning methods use fewer parameters but achieved comparative performance.•Deep learning is still in infancy, ...given challenges in data, domains and languages.•A task-combined and concept-centric approach should be considered in future studies.
The increasing volume of user-generated content on the web has made sentiment analysis an important tool for the extraction of information about the human emotional state. A current research focus for sentiment analysis is the improvement of granularity at aspect level, representing two distinct aims: aspect extraction and sentiment classification of product reviews and sentiment classification of target-dependent tweets. Deep learning approaches have emerged as a prospect for achieving these aims with their ability to capture both syntactic and semantic features of text without requirements for high-level feature engineering, as is the case in earlier methods. In this article, we aim to provide a comparative review of deep learning for aspect-based sentiment analysis to place different approaches in context.
Equipment for the correct identification of living objects entrapped under heavy debris is generally purpose-built, is costly, must be operated by highly trained professionals and is not readily ...available in a catastrophic event. A more readily available solution for improving the time-to-rescue ratio and logistics issues can be provided with smartphones which, equipped with software to find signs of life, are readily available at any disaster scene. This paper examines whether cardiac and pulmonary-related activities of living objects can provide acceptably accurate readings from a non-contact detection method. Laboratory experiments were conducted with Doppler radar at a 2.4 GHz frequency spectrum similar to smartphone-like devices, with empirical results demonstrating that human vital signs can be clearly identified when using smartphones for non-contact detection of living objects entrapped under debris. Experiments also simulated the psychogenic tremors likely to be experienced by individuals while operating the sensor-equipped devices under crisis conditions. The results show a clear relationship between the wavelength of pulmonary and blood vessel activities and the distance between the trapped human and the sensor in various conditions. The article also reports the design of a pseudo learning algorithm for model-based anomaly detection in time series to detect vital signs during normal and abnormal ventilation based on cardiopulmonary clinical records and datasets. This work significantly contributes to the existing body of research on timely rescue during disaster events.
Medical diagnosis through classification is often critical as the medical datasets are multilabel in nature, that is, a patient may have more than one health condition: high blood pressure, obesity, ...and diabetes. The aim of this article is to improve the accuracy and performance of multilabel classification using multilabel feature selection and improved overlapping clustering method. The proposed system consists of Optimized Initial Cluster Centers and Enhanced Objective Function technique to reduce the number of iterations in the clustering process thereby improving the clustering performance and to improve the clustering accuracy which will result in improving the accuracy and performance of multilabel classification. Ratios of clustering distance to class distance and execution time are used as the evaluation metric for accuracy and total execution time is used as the evaluation metric for performance. Based on the different combination with the number of labels, attributes, instances, and number of clusters, different values of accuracy and performance are obtained. The results on all 10 datasets show that the proposed technique is superior to the current technique. Furthermore, on average, the proposed technique has improved the classification accuracy by 5%-7%. Furthermore, the performance of new technique is improved by decreasing the processing time by 0.5-1 s on average. The proposed system targets on improving the accuracy and performance of the multilabel classification for medical diagnosis, which consists of multilabel feature selection and enhanced overlapping clustering technique. This study provides an acceptable range of accuracy with improved processing time, which assists the doctors in medical diagnosis (high blood pressure, obesity, and diabetes) of patients.
The purpose of this article is to identify and assess service delivery issues within a hospital emergency department and propose an improved model to address them. Possible solutions and options to ...these issues are explored to determine the one that best fits the context. In this article, we have analysed the emergency department’s organizational models through i* strategic dependency and rational modelling technique before proposing updated models that could potentially drive business process efficiencies. The results produced by the models, framework and improved patient journey in the emergency department were evaluated against the statistical data revealed from a reputed government organization related to health, to ensure that the key elements of the issues such as wait time, stay time/throughput, workload and human resource are resolved. The result of the evaluation was taken as a basis to determine the success of the project. Based on these results, the article recommends implementing the concept on actual scenario, where a positive result is achievable.
The constantly growing offering of online learning materials to students is making it more difficult to locate specific information from data pools. Personalization systems attempt to reduce this ...complexity through adaptive e-learning and recommendation systems. The latter are, generally, based on machine learning techniques and algorithms and there has been progress. However, challenges remain in the form of data-scarcity, cold-start, scalability, time consumption and accuracy. In this article, we provide an overview of recommendation systems in the e-learning context following four strands: Content-Based, Collaborative Filtering, Knowledge-Based and Hybrid Systems. We developed a taxonomy that accounts for components required to develop an effective recommendation system. It was found that machine learning techniques, algorithms, datasets, evaluation, valuation and output are necessary components. This paper makes a significant contribution to the field by providing a much-needed overview of the current state of research and remaining challenges.
Deep learning (DL) is a type of machine learning capable of processing large quantities of data to provide analytic results based on a particular framework’s parameters and aims. DL is widely used in ...a variety of fields, including medicine. Currently, there are various DL-based prediction models for predicting cancer probability and survival. However, the specific problem is that no integrated system can predict cancer survival, probability, and presence in the medical patient’s samples. Therefore, this research investigates the latest literature in the field of DL-based cancer prediction models for predicting the cancer probability and the patient survival rate. The name of this proposed model is Multimodal Incremental Recurrent Deep Neural Network; it can perform the analysis, prediction, and diagnosis of cancer using multi-dimensional data processing. It can also predict the cancer possibility and survival using incremental recurrent neural networks. The components of the proposed taxonomy are Data, Prediction technique, and View (DPV). This research’s contribution is the critical analysis of the latest literature on the DL-based systems that can predict cancer and its outcomes. It provides a theoretical model that can predict the possibility, presence, and survival of cancer by processing multi-dimensional medical samples of the patient to make accurate predictions. We also highlight the importance of the proposed taxonomy.
Background and Aim: deep learning has not been successfully implemented in liver tumour feature extraction and classification using computer-aided diagnosis. This study aims to enhance classification ...accuracy and improves the processing time to better differentiate tumour types. Methodology: This study proposed a hybrid model, which combines the regularization function with the current loss function for the support vector machine (SVM) classifier. Regularization function is used for prioritizing image classes before feeding it to the linear mapping. The proposed model consists of the region growing algorithm to get the region-of-interest (ROI), and Weiner filtering algorithm for image enhancement and noise removal. The gray level co-occurrence matrix (GLCM) was performed to extract the feature from the image. The extracted feature then fed to SVM classifier using selected feature vectors to classify the affected region and neglecting the unwanted areas. Results: classification accuracy was calculated using probability score, and the processing time was calculated based on the total execution time. The proposed system was able to achieve an average classification accuracy of 98.9%, which is about 2–3% higher than the current system. The results showed that 12 ms reduced the processing time on average. Conclusion: The proposed system focused on improving feature extraction and classification for different types of tumours from the MRI images. The study solved the problem in linear mapping of support vector machine and enhanced the classification accuracy and the processing time of early diagnosis of three different types of tumours in liver MRI images.
Accurate classification of Magnetic Resonance Images (MRI) is essential to accurately predict Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD) conversion. Meanwhile, deep learning has been ...successfully implemented to classify and predict dementia disease. However, the accuracy of MRI image classification is low. This paper aims to increase the accuracy and reduce the processing time of classification through Deep Learning Architecture by using Elastic Net Regularisation in Feature Selection. The proposed system consists of Convolutional Neural Network (CNN) to enhance the accuracy of classification and prediction by using Elastic Net Regularisation. Initially, the MRI images are fed into CNN for features extraction through convolutional layers alternate with pooling layers, and then through a fully connected layer. After that, the features extracted are subjected to Principle Component Analysis (PCA) and Elastic Net Regularisation for feature selection. Finally, the selected features are used as an input to Extreme Machine Learning (EML) for the classification of MRI images. The result shows that the accuracy of the proposed solution is better than the current system. In addition to that, the proposed method has improved the classification accuracy by 5% on average and reduced the processing time by 30 ~ 40 seconds on average. The proposed system is focused on improving the accuracy and processing time of MCI converters/non-converters classification. It consists of features extraction, feature selection, and classification using CNN, FreeSurfer, PCA, Elastic Net, and Extreme Machine Learning. Finally, this study enhances the accuracy and the processing time by using Elastic Net Regularisation, which provides important selected features for classification.