International Journal of Neural Systems

The majority of current smart health applications are deployed on a smartphone paired with a smartwatch. The phone is used as the computation platform or the gateway for connecting to the cloud while the watch is used mainly as the data sensing device. In the case of fall detection applications for older adults, this kind of setup is not very practical since it requires users to always keep their phones in proximity while doing the daily chores. When a person falls, in a moment of panic, it might be difficult to locate the phone in order to interact with the Fall Detection App for the purpose of indicating whether they are fine or need help. This paper demonstrates the feasibility of running a real-time personalized deep-learning-based fall detection system on a smartwatch device using a collaborative edge-cloud framework. In particular, we present the software architecture we used for the collaborative framework, demonstrate how we automate the fall detection pipeline, design an appropriate UI on the small screen of the watch, and implement strategies for the continuous data collection and automation of the personalization process with the limited computational and storage resources of a smartwatch. We also present the usability of such a system with nine real-world older adult participants.

Researchers have shown the limitations of using the single-modal data stream for emotion classification. Multi-modal data streams are therefore deemed necessary to improve the accuracy and performance of online emotion classifiers. An online decision ensemble is a widely used approach to classify emotions in real-time using multi-modal data streams. There is a plethora of online ensemble approaches; these approaches use a fixed parameter ($\beta$) to adjust the weights of each classifier (called penalty) in case of wrong classification and no reward for a good performing classifier. Also, the performance of the ensemble depends on the $\beta$, which is set using trial and error. This paper presents a new Reward-Penalty-based Weighted Ensemble (RPWE) for real-time multi-modal emotion classification using multi-modal physiological data streams. The proposed RPWE is thoroughly tested using two prevalent benchmark data sets, DEAP and AMIGOS. The first experiment confirms the impact of the base stream classifier with RPWE for emotion classification in real-time. The RPWE is compared with different popular and widely used online ensemble approaches using multi-modal data streams in the second experiment. The average balanced accuracy, F1-score results showed the usefulness and robustness of RPWE in emotion classification in real-time from the multi-modal data stream.

It has been proven that, compared to using 32-bit floating-point numbers in the training phase, Deep Convolutional Neural Networks (DCNNs) can operate with low-precision during inference, thereby saving memory footprint and power consumption. However, neural network quantization is always accompanied by accuracy degradation. Here, we propose a quantization method called double-stage Squeeze-and-Threshold (double-stage ST) to close the accuracy gap with full-precision models. While accurate colors in pictures can be pleasing to the viewer, they are not necessary for distinguishing objects. The era of black and white television proves this idea. As long as the limited colors are filled reasonably for different objects, the objects can be well identified and distinguished. Our method utilizes the attention mechanism to adjust the activations and learn the thresholds to distinguish objects (features). We then divide the numerically rich activations into intervals (a limited variety of numerical values) by the learned thresholds. The proposed method supports both binarization and multi-bit quantization. Our method achieves state-of-the-art results. In binarization, ReActNet [Z. Liu, Z. Shen, S. Li, K. Helwegen, D. Huang and K. Cheng, arXiv:abs/2106.11309] trained with our method outperforms the previous state-of-the-art result by 0.2 percentage points. Whereas in multi-bit quantization, the top-1 accuracy of the 3-bit ResNet-18 [K. He, X. Zhang, S. Ren and J. Sun, Deep residual learning for image recognition, 2016 IEEE Conf. Computer Vision and Pattern Recognition, CVPR 2016, 27–30 June 2016, Las Vegas, NV, USA (IEEE Computer Society, 2016), pp. 770–778] model exceeds the top-1 accuracy of its full-precision baseline model by 0.4 percentage points. The double-stage ST activation quantization method is easy to apply by inserting it before the convolution. Besides, the double-stage ST is detachable after training and introducing no computational cost in inference.

This paper proposes a generative model and transfer learning powered system for classification of Scanning Electron Microscope (SEM) images of defective nanofibers (D-NF) and nondefective nanofibers (ND-NF) produced by electrospinning (ES) process. Specifically, a conditional-Generative Adversarial Network (c-GAN) is developed to generate synthetic D-NF/ND-NF SEM images. A transfer learning-oriented strategy is also proposed. First, a Convolutional Neural Network (CNN) is pre-trained on real images. The transfer-learned CNN is trained on synthetic SEM images and validated on real ones, reporting accuracy rate up to 95.31%. The achieved encouraging results endorse the use of the proposed generative model in industrial applications as it could reduce the number of needed laboratory ES experiments that are costly and time consuming.

Computer-aided diagnosis of health problems and pathological conditions has become a substantial part of medical, biomedical, and computer science research. This paper focuses on the diagnosis of early and progressive dementia, building on the potential of deep learning (DL) models. The proposed computational framework exploits a magnetic resonance imaging (MRI) brain asymmetry biomarker, which has been associated with early dementia, and employs DL architectures for MRI image classification. Identification of early dementia is accomplished by an eight-layered convolutional neural network (CNN) as well as transfer learning of pretrained CNNs from ImageNet. Different instantiations of the proposed CNN architecture are tested. These are equipped with Softmax, support vector machine (SVM), linear discriminant (LD), or $k$ -nearest neighbor (KNN) classification layers, assembled as a separate classification module, which are attached to the core CNN architecture. The initial imaging data were obtained from the MRI directory of the Alzheimer’s disease neuroimaging initiative 3 (ADNI3) database. The independent testing dataset was created using image preprocessing and segmentation algorithms applied to unseen patients’ imaging data. The proposed approach demonstrates a 90.12% accuracy in distinguishing patients who are cognitively normal subjects from those who have Alzheimer’s disease (AD), and an 86.40% accuracy in detecting early mild cognitive impairment (EMCI).

“Fake news” refers to the deliberate dissemination of news with the purpose to deceive and mislead the public. This paper assesses the accuracy of several Machine Learning (ML) algorithms, using a style-based technique that relies on textual information extracted from news, such as part of speech counts. To expand the already proposed styled-based techniques, a new method of enhancing a linguistic feature set is proposed. It combines Named Entity Recognition (NER) with the Frequent Pattern (FP) Growth association rule mining algorithm, aiming to provide better insight into the papers’ sentence level structure. Recursive feature elimination was used to identify a subset of the highest performing linguistic characteristics, which turned out to align with the literature. Using pre-trained word embeddings, document embeddings and weighted document embeddings were constructed using each word’s TF-IDF value as the weight factor. The document embeddings were mixed with the linguistic features providing a variety of training/test feature sets. For each model, the best performing feature set was identified and fine-tuned regarding its hyper parameters to improve accuracy. ML algorithms’ results were compared with two Neural Networks: Convolutional Neural Network (CNN) and Long-Short-Term Memory (LSTM). The results indicate that CNN outperformed all other methods in terms of accuracy, when companied with pre-trained word embeddings, yet SVM performs almost the same with a wider variety of input feature sets. Although style-based technique scores lower accuracy, it provides explainable results about the author’s writing style decisions. Our work points out how new technologies and combinations of existing techniques can enhance the style-based approach capturing more information.