Full depth CNN classifier for handwritten and license plate characters recognition.

Character recognition is an important research field of interest for many applications. In recent years, deep learning has made breakthroughs in image classification, especially for character recognition. However, convolutional neural networks (CNN) still deliver state-of-the-art results in this area. Motivated by the success of CNNs, this paper proposes a simple novel full depth stacked CNN architecture for Latin and Arabic handwritten alphanumeric characters that is also utilized for license plate (LP) characters recognition. The proposed architecture is constructed by four convolutional layers, two max-pooling layers, and one fully connected layer. This architecture is low-complex, fast, reliable and achieves very promising classification accuracy that may move the field forward in terms of low complexity, high accuracy and full feature extraction. The proposed approach is tested on four benchmarks for handwritten character datasets, Fashion-MNIST dataset, public LP character datasets and a newly introduced real LP isolated character dataset. The proposed approach tests report an error of only 0.28% for MNIST, 0.34% for MAHDB, 1.45% for AHCD, 3.81% for AIA9K, 5.00% for Fashion-MNIST, 0.26% for Saudi license plate character and 0.97% for Latin license plate characters datasets. The license plate characters include license plates from Turkey (TR), Europe (EU), USA, United Arab Emirates (UAE) and Kingdom of Saudi Arabia (KSA).

Seizure Prediction in Scalp EEG Using 3D Convolutional Neural Networks With an Image-Based Approach.

Epileptic seizures occur as a result of a process that develops over time and space in epileptic networks. In this study, we aim at developing a generalizable method for patient-specific seizure prediction by evaluating the spatio-temporal correlation in the features obtained from multichannel EEG signals. Spectral band power, statistical moment and Hjorth parameters are used to reveal the frequency and time domain features of the EEG signals. The features are given as input to a convolutional neural network (CNN) by transforming into a sequence of multi-color images according to the topology of the EEG channels. The multi-frame 3D CNN model is proposed to evaluate the temporal and spatial correlation in training data collectively. The proposed 3D CNN model achieves a sensitivity of 85.7%, a false prediction rate of 0.096/h, and a proportion of time-in-warning of 10.5%, in the tests performed with 16 patients from the CHB-MIT scalp EEG dataset. The results show that the superiority of the proposed method to a Poisson based random predictor was statistically significant for 93.7% of the patients, at significance level of 0.05. Our experiments with various timing constraints show that epileptic stage lengths are an important factor affecting seizure performance. We present a subject-specific seizure prediction method that is robust for unbalanced data and can be generalized to any scalp EEG dataset without the need for subject-specific engineering.

Clustering Through Hybrid Network Architecture With Support Vectors.

In this paper, we propose a clustering algorithm based on a two-phased neural network architecture. We combine the strength of an autoencoderlike network for unsupervised representation learning with the discriminative power of a support vector machine (SVM) network for fine-tuning the initial clusters. The first network is referred as prototype encoding network, where the data reconstruction error is minimized in an unsupervised manner. The second phase, i.e., SVM network, endeavors to maximize the margin between cluster boundaries in a supervised way making use of the first output. Both the networks update the cluster centroids successively by establishing a topology preserving scheme like self-organizing map on the latent space of each network. Cluster fine-tuning is accomplished in a network structure by the alternate usage of the encoding part of both the networks. In the experiments, challenging data sets from two popular repositories with different patterns, dimensionality, and the number of clusters are used. The proposed hybrid architecture achieves comparatively better results both visually and analytically than the previous neural network-based approaches available in the literature.

The effect of memantine in harmaline-induced tremor and neurodegeneration.

Essential tremor (ET) is one of the most common and most disabling movement disorders among adults. The drug treatment of ET remains unsatisfactory. Additional therapies are required for patients with inadequate response or intolerable side effects. The current study aims to investigate the anti-tremogenic and neuroprotective effects of memantine (NMDA receptor antagonist) on the harmaline model of transient action tremor. The effects of memantine were further compared with ethanol. Three separate groups of male Wistar rats were injected either with saline, ethanol (1.5 gr/kg), or memantine (5 mg/kg) 15 min prior to a single intraperitoneal injection of harmaline (20 mg/kg). Tremor and locomotion were evaluated by a custom-built tremor and locomotion analysis system. After 24 h of harmaline injection, cellular viability, and apoptosis were assessed using crystal violet staining, and caspase-3 immunostaining, respectively. Harmaline caused neuronal cell loss and caspase-3 mediated apoptosis in cerebellar granular and purkinje cells as well as the inferior olivary neurons. Despite a reduction in tremor intensity and duration with ethanol, this compound resulted in cell loss in cerebellum and olivary nucleus. Memantine exhibited neuroprotective efficacy on cerebellar and inferior olivary neurons albeit weaker anti-tremor effect compared to ethanol. In conclusion, anti-tremogenic and neuroprotective effects do not necessarily overlap. Memantine is a potential treatment for ET particularly given its neuroprotective efficacy.