1. |
- Feigin, Valery L., et al.
(författare)
-
Global, regional, and national burden of neurological disorders, 1990–2016 : a systematic analysis for the Global Burden of Disease Study 2016
- 2019
-
Ingår i: Lancet Neurology. - : Elsevier. - 1474-4422 .- 1474-4465. ; 18:5, s. 459-480
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Neurological disorders are increasingly recognised as major causes of death and disability worldwide. The aim of this analysis from the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2016 is to provide the most comprehensive and up-to-date estimates of the global, regional, and national burden from neurological disorders.Methods: We estimated prevalence, incidence, deaths, and disability-adjusted life-years (DALYs; the sum of years of life lost [YLLs] and years lived with disability [YLDs]) by age and sex for 15 neurological disorder categories (tetanus, meningitis, encephalitis, stroke, brain and other CNS cancers, traumatic brain injury, spinal cord injury, Alzheimer's disease and other dementias, Parkinson's disease, multiple sclerosis, motor neuron diseases, idiopathic epilepsy, migraine, tension-type headache, and a residual category for other less common neurological disorders) in 195 countries from 1990 to 2016. DisMod-MR 2.1, a Bayesian meta-regression tool, was the main method of estimation of prevalence and incidence, and the Cause of Death Ensemble model (CODEm) was used for mortality estimation. We quantified the contribution of 84 risks and combinations of risk to the disease estimates for the 15 neurological disorder categories using the GBD comparative risk assessment approach.Findings: Globally, in 2016, neurological disorders were the leading cause of DALYs (276 million [95% UI 247–308]) and second leading cause of deaths (9·0 million [8·8–9·4]). The absolute number of deaths and DALYs from all neurological disorders combined increased (deaths by 39% [34–44] and DALYs by 15% [9–21]) whereas their age-standardised rates decreased (deaths by 28% [26–30] and DALYs by 27% [24–31]) between 1990 and 2016. The only neurological disorders that had a decrease in rates and absolute numbers of deaths and DALYs were tetanus, meningitis, and encephalitis. The four largest contributors of neurological DALYs were stroke (42·2% [38·6–46·1]), migraine (16·3% [11·7–20·8]), Alzheimer's and other dementias (10·4% [9·0–12·1]), and meningitis (7·9% [6·6–10·4]). For the combined neurological disorders, age-standardised DALY rates were significantly higher in males than in females (male-to-female ratio 1·12 [1·05–1·20]), but migraine, multiple sclerosis, and tension-type headache were more common and caused more burden in females, with male-to-female ratios of less than 0·7. The 84 risks quantified in GBD explain less than 10% of neurological disorder DALY burdens, except stroke, for which 88·8% (86·5–90·9) of DALYs are attributable to risk factors, and to a lesser extent Alzheimer's disease and other dementias (22·3% [11·8–35·1] of DALYs are risk attributable) and idiopathic epilepsy (14·1% [10·8–17·5] of DALYs are risk attributable).Interpretation: Globally, the burden of neurological disorders, as measured by the absolute number of DALYs, continues to increase. As populations are growing and ageing, and the prevalence of major disabling neurological disorders steeply increases with age, governments will face increasing demand for treatment, rehabilitation, and support services for neurological disorders. The scarcity of established modifiable risks for most of the neurological burden demonstrates that new knowledge is required to develop effective prevention and treatment strategies.Funding: Bill & Melinda Gates Foundation.
|
|
2. |
- Imran, Ali Shariq, et al.
(författare)
-
Predicting Student Dropout in a MOOC : An Evaluation of a Deep Neural Network Model
- 2019
-
Ingår i: Proceedings of the 2019 5th International Conference on Computing and Artificial Intelligence. - New York, NY, USA : ACM Publications. - 9781450361064 ; , s. 190-195
-
Konferensbidrag (refereegranskat)abstract
- Massive Open Online Courses (MOOCs) have transformed the way educational institutions deliver high-quality educational material to the onsite and distance learners across the globe. As a result, a new paradigm shifts as to how learners acquire and benefit from the wealth of knowledge provided by a MOOC at their doorstep nowadays in contrast to the brick and mortar settings is visible. Learners are therefore showing a profound interest in the MOOCs offered by top universities and industry giants. They have also attracted a vast number of students from far-flung areas of the world. The massive number of registered students in MOOCs, however, pose one major challenge, i.e., 'the dropouts'. Course planners and content providers are struggling to retain the registered students, which give rise to a new research agenda focusing on predicting and explaining student dropout and low completion rates in a MOOC. Machine learning techniques utilizing deep learning approaches can efficiently predict the potential dropouts and can raise an alert well before time. In this paper, we have focused our study on the application of feed-forward deep neural network architectures to address this problem. Our model achieves not only high accuracy, but also low false negative rate while predicting dropouts on the MOOC data. Moreover, we also provide an in-depth comparison of the proposed architectures concerning precision, recall, and F1 measure.
|
|
3. |
- Imran, Ali Shariq, et al.
(författare)
-
Text-Independent Speaker ID Employing 2D-CNN for Automatic Video Lecture Categorization in a MOOC Setting
- 2019
-
Ingår i: 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI). - : IEEE Press. - 9781728137988 - 9781728137995 ; , s. 273-277
-
Konferensbidrag (refereegranskat)abstract
- A new form of distance and blended education has hit the market in recent years with the advent of massive open online courses (MOOCs) which have brought many opportunities to the educational sector. Consequently, the availability of learning content to vast demographics of people and across locations has opened up a plethora of possibilities for everyone to gain new knowledge through MOOCs. This poses an immense issue to the content providers as the amount of manual effort required to structure properly and to organize the content automatically for millions of video lectures daily become incredibly challenging. This paper, therefore, addresses this issue as a small part of our proposed personalized content management system by exploiting the voice pattern of the lecturer for identification and for classifying video lectures to the right speaker category. The use of Mel frequency Cepstral coefficients (MFCC) as 2D input features maps to 2D-CNN has shown promising results in contrast to machine learning and deep learning classifiers - making text-independent speaker identification plausible in MOOC setting for automatic video lecture categorization. It will not only help categorize educational videos efficiently for easy search and retrieval but will also promote effective utilization of micro-lectures and multimedia video learning objects (MLO).
|
|
4. |
- Imran, Ali Shariq, et al.
(författare)
-
Text-Independent Speaker ID for Automatic Video Lecture Classification Using Deep Learning
- 2019
-
Ingår i: Proceedings of the 2019 5th International Conference on Computing and Artificial Intelligence, April 19-22, 2019, Bali, Indonesia. - New York, NY, USA : ACM Publications. - 9781450361064 ; , s. 175-180
-
Konferensbidrag (refereegranskat)abstract
- This paper proposes to use acoustic features employing deep neural network (DNN) and convolutional neural network (CNN) models for classifying video lectures in a massive open online course (MOOC). The models exploit the voice pattern of the lecturer for identification and for classifying the video lecture according to the right speaker category. Filter bank and Mel frequency cepstral coefficient (MFCC) feature along with first and second order derivatives (Δ/ΔΔ) are used as input features to the proposed models. These features are extracted from the speech signal which is obtained from the video lectures by separating the audio from the video using FFmpeg.The deep learning models are evaluated using precision, recall, and F1 score and the obtained accuracy is compared for both acoustic features with traditional machine learning classifiers for speaker identification. A significant improvement of 3% to 7% classification accuracy is achieved over the DNN and twice to that of shallow machine learning classifiers for 2D-CNN with MFCC. The proposed 2D-CNN model with an F1 score of 85.71% for text-independent speaker identification makes it plausible to use speaker ID as a classification approach for organizing video lectures automatically in a MOOC setting.
|
|
5. |
- Kastrati, Zenun, 1984-, et al.
(författare)
-
Integrating word embeddings and document topics with deep learning in a video classification framework
- 2019
-
Ingår i: Pattern Recognition Letters. - : Elsevier. - 0167-8655 .- 1872-7344. ; 128, s. 85-92
-
Tidskriftsartikel (refereegranskat)abstract
- The advent of MOOC platforms brought an abundance of video educational content that made the selection of best fitting content for a specific topic a lengthy process. To tackle this challenge in this paper we report our research efforts of using deep learning techniques for managing and classifying educational content for various search and retrieval applications in order to provide a more personalized learning experience. In this regard, we propose a framework which takes advantages of feature representations and deep learning for classifying video lectures in a MOOC setting to aid effective search and retrieval. The framework consists of three main modules. The first module called pre-processing concerns with video-to-text conversion. The second module is transcript representation which represents text in lecture transcripts into vector space by exploiting different representation techniques including bag-of-words, embeddings, transfer learning, and topic modeling. The final module covers classifiers whose aim is to label video lectures into the appropriate categories. Two deep learning models, namely feed-forward deep neural network (DNN) and convolutional neural network (CNN) are examined as part of the classifier module. Multiple simulations are carried out on a large-scale real dataset using various feature representations and classification techniques to test and validate the proposed framework.
|
|
6. |
- Kastrati, Zenun, 1984-, et al.
(författare)
-
Performance analysis of machine learning classifiers on improved concept vector space models
- 2019
-
Ingår i: Future generations computer systems. - : Elsevier. - 0167-739X .- 1872-7115. ; 96, s. 552-562
-
Tidskriftsartikel (refereegranskat)abstract
- This paper provides a comprehensive performance analysis of parametric and non-parametric machine learning classifiers including a deep feed-forward multi-layer perceptron (MLP) network on two variants of improved Concept Vector Space (iCVS) model. In the first variant, a weighting scheme enhanced with the notion of concept importance is used to assess weight of ontology concepts. Concept importance shows how important a concept is in an ontology and it is automatically computed by converting the ontology into a graph and then applying one of the Markov based algorithms. In the second variant of iCVS, concepts provided by the ontology and their semantically related terms are used to construct concept vectors in order to represent the document into a semantic vector space. We conducted various experiments using a variety of machine learning classifiers for three different models of document representation. The first model is a baseline concept vector space (CVS) model that relies on an exact/partial match technique to represent a document into a vector space. The second and third model is an iCVS model that employs an enhanced concept weighting scheme for assessing weights of concepts (variant 1), and the acquisition of terms that are semantically related to concepts of the ontology for semantic document representation (variant 2), respectively. Additionally, a comparison between seven different classifiers is performed for all three models using precision, recall, and F1 score. Results for multiple configurations of deep learning architecture are obtained by varying the number of hidden layers and nodes in each layer, and are compared to those obtained with conventional classifiers. The obtained results show that the classification performance is highly dependent upon the choice of a classifier, and that the Random Forest, Gradient Boosting, and Multilayer Perceptron are among the classifiers that performed rather well for all three models.
|
|
7. |
- Kastrati, Zenun, 1984-, et al.
(författare)
-
The impact of deep learning on document classification using semantically rich representations
- 2019
-
Ingår i: Information Processing & Management. - : Elsevier. - 0306-4573 .- 1873-5371. ; 56:5, s. 1618-1632
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents a semantically rich document representation model for automatically classifying financial documents into predefined categories utilizing deep learning. The model architecture consists of two main modules including document representation and document classification. In the first module, a document is enriched with semantics using background knowledge provided by an ontology and through the acquisition of its relevant terminology. Acquisition of terminology integrated to the ontology extends the capabilities of semantically rich document representations with an in depth-coverage of concepts, thereby capturing the whole conceptualization involved in documents. Semantically rich representations obtained from the first module will serve as input to the document classification module which aims at finding the most appropriate category for that document through deep learning. Three different deep learning networks each belonging to a different category of machine learning techniques for ontological document classification using a real-life ontology are used. Multiple simulations are carried out with various deep neural networks configurations, and our findings reveal that a three hidden layer feedforward network with 1024 neurons obtain the highest document classification performance on the INFUSE dataset. The performance in terms of F1 score is further increased by almost five percentage points to 78.10% for the same network configuration when the relevant terminology integrated to the ontology is applied to enrich document representation. Furthermore, we conducted a comparative performance evaluation using various state-of-the-art document representation approaches and classification techniques including shallow and conventional machine learning classifiers.
|
|
8. |
- Kastrati, Zenun, 1984-, et al.
(författare)
-
Transfer Learning to Timed Text Based Video Classification Using CNN
- 2019
-
Ingår i: Proceedings of the 9th International Conference on Web Intelligence, Mining and Semantics. - New York, NY, USA : ACM Publications. - 9781450361903
-
Konferensbidrag (refereegranskat)abstract
- Open educational video resources are gaining popularity with a growing number of massive open online courses (MOOCs). This has created a niche for content providers to adopt effective solutions in automatically organizing and structuring of educational resources for maximum visibility. Recent advances in deep learning techniques are proving useful in managing and classifying resources into appropriate categories. This paper proposes one such convolutional neural network (CNN) model for classifying video lectures in a MOOC setting using a transfer learning approach. The model uses a time-aligned text transcripts corresponding to video lectures from six broader subject categories. Video lectures and their corresponding transcript dataset is gathered from the Coursera MOOC platform. Two different CNN models are proposed: i) CNN based classification using embeddings learned from our MOOC dataset, ii) CNN based classification using transfer learning. Word embeddings generated from two well known state-of-the-art pre-trained models Word2Vec and GloVe, are used in the transfer learning approach for the second case.The proposed CNN models are evaluated using precision, recall, and F1 score and the obtained performance is compared with both conventional and deep learning classifiers. The proposed CNN models have an F1 score improvement of 10-22 percentage points over DNN and conventional classifiers
|
|
9. |
- Pireva, Krenare, et al.
(författare)
-
Evaluating learners' emotional states by monitoring brain waves for comparing game-based learning approach to pen-and-paper
- 2019
-
Ingår i: 2019 IEEE FRONTIERS IN EDUCATION CONFERENCE (FIE 2019). - : IEEE. - 9781728117461 ; , s. 1-8
-
Konferensbidrag (refereegranskat)abstract
- A new interest in the use of game factors while acquiring new knowledge has emerged, and a number of researchers are investigating the effectiveness of the game-based approach in education systems. Recent research in game-based learning suggests that this approach imparts learning by involving learners in the learning process. The game factors generate affective-cognitive reactions that absorb users in playing the game and positively influence the learning. This paper offers a comparison of the learning processes between the game based learning and pen-and-paper approaches. In this paper the analysis of both learning approaches is realized through a brain controlled technology, using the Emotiv EEG Tech headset, by analyzing the stress, excitement, relaxation, focus, interest, and engagement that the learner is experiencing while going through both approaches.
|
|