Twitter sentimental analysis from time series facts: the implementation of enhanced support vector machine

Sentiment analysis through textual data mining is an indispensable system used to extract the contextual social information from the texts submitted by the intended users. Now days, world wide web is playing a vital source of textual content being shared in different communities by the people sharing their own sentiments through the websites or web blogs. Sentiment analysis has become a vital field of study since based on the extracted expressions, individuals or the businesses can access or update their reviews and take significant decisions. Sentimental mining is typically used to classify these reviews depending on its assessment as whether these reviews come out to be neutral, positive or negative. In our study, we have boosted feature selection technique with strong feature normalization for classifying the sentiments into negative, positive or neutral. Afterwards, support vector machine (SVM) classifier powered with radial basis kernel with adjusted hyper plane parameters, was employed to categorize reviews. Grid search with cross validation as well as logarithmic scale were employed for optimal values of hyper parameters. The classification results of this proposed system provides optimal results when compared to other state of art classification methods.

GicoFace: A Deep Face Recognition Model Based on Global-Information Loss Function

As CNNs have a strong capacity to learn discriminative facial features, CNNs have greatly promoted the development of face recognition, where the loss function plays a key role in this process. Nonetheless, most of the existing loss functions do not simultaneously apply weight normalization, apply feature normalization and follow the two goals of enhancing the discriminative capacity (optimizing intra-class/inter-class variance). In addition, they are updated by only considering the feedback information of each mini-batch, but ignore the information from the entire training set. This paper presents a new loss function called Gico loss. The deep model trained with Gico loss in this paper is then called GicoFace. Gico loss satisfies the four aforementioned key points, and is calculated with the global information extracted from the entire training set. The experiments are carried out on five benchmark datasets including LFW, SLLFW, YTF, MegaFace and FaceScrub. Experimental results confirm the efficacy of the proposed method and show the state-of-the-art performance of the method.

Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning

Biological spiking neurons with intrinsic dynamics underlie the powerful representation and learning capabilities of the brain for processing multimodal information in complex environments. Despite recent tremendous progress in spiking neural networks (SNNs) for handling Euclidean-space tasks, it still remains challenging to exploit SNNs in processing non-Euclidean-space data represented by graph data, mainly due to the lack of effective modeling framework and useful training techniques. Here we present a general spike-based modeling framework that enables the direct training of SNNs for graph learning. Through spatial-temporal unfolding for spiking data flows of node features, we incorporate graph convolution filters into spiking dynamics and formalize a synergistic learning paradigm. Considering the unique features of spike representation and spiking dynamics, we propose a spatial-temporal feature normalization (STFN) technique suitable for SNN to accelerate convergence. We instantiate our methods into two spiking graph models, including graph convolution SNNs and graph attention SNNs, and validate their performance on three node-classification benchmarks, including Cora, Citeseer, and Pubmed. Our model can achieve comparable performance with the state-of-the-art graph neural network (GNN) models with much lower computation costs, demonstrating great benefits for the execution on neuromorphic hardware and prompting neuromorphic applications in graphical scenarios.

Automatic Sleep Stage Classification Based on Two-channel EOG and One-channel EMG

The sleep monitoring with PSG severely degrades the sleep quality. In order to simplify the hygienic processing and reduce the load of sleep monitoring, an approach to automatic sleep stage classification without electroencephalogram (EEG) was explored. Totally 108 features from two-channel electrooculogram (EOG) and 6 features from one-channel electromyogram (EMG) were extracted. After feature normalization, the random forest (RF) was used to classify five stages, including wakefulness, REM sleep, N1 sleep, N2 sleep and N3 sleep. Using 114 normalized features from the combination of EOG (108 features) and EMG (6 features), the Cohen’s kappa coefficient was 0.749 and the accuracy was 80.8% by leave-one -out cross-validation (LOOCV) for 124 records from ISRUC-Sleep. As a reference for AASM standard, the Cohen’s kappa coefficient was 0.801 and the accuracy was 84.7% for the same dataset based on 438 normalized features from the combination of EEG (324 features), EOG (108 features) and EMG (6 features). In conclusion, the approach by EOG+EMG with the normalization can reduce the load of sleep monitoring, and achieves comparable performances with the "gold standard" EEG+EOG+EMG on sleep classification.