A novel type of activation function in artificial neural networks: Trained activation function.

Determining optimal activation function in artificial neural networks is an important issue because it is directly linked with obtained success rates. But, unfortunately, there is not any way to determine them analytically, optimal activation function is generally determined by trials or tuning. This paper addresses, a simpler and a more effective approach to determine optimal activation function. In this approach, which can be called as trained activation function, an activation function was trained for each particular neuron by linear regression. This training process was done based on the training dataset, which consists the sums of inputs of each neuron in the hidden layer and desired outputs. By this way, a different activation function was generated for each neuron in the hidden layer. This approach was employed in random weight artificial neural network (RWN) and validated by 50 benchmark datasets. Achieved success rates by RWN that used trained activation functions were higher than obtained success rates by RWN that used traditional activation functions. Obtained results showed that proposed approach is a successful, simple and an effective way to determine optimal activation function instead of trials or tuning in both randomized single and multilayer ANNs.

A stable feature extraction method in classification epileptic EEG signals.

Epilepsy is one of the most common neurological disorders. Electroencephalogram (EEG) signals are generally employed in diagnosing epilepsy. Therefore, extracting relevant features from EEG signals is one of the major tasks in an accurate diagnosis. In this study, the local ternary patterns, which is an image processing method, was improved in order to extract robust features from epileptic EEG signals. The EEG signals that were recorded by the Department of Etymology in the Bonn University were employed in the evaluation and validation of the proposed approach. Low and up features, which were extracted by the proposed one-dimensional ternary patterns, were classified by some machine learning methods such that support vector machine, functional trees, random forest (RF), Bayes networks (BayesNet), and artificial neural network, while the highest accuracies were obtained by RF. Achieved accuracies were found successful according to the current literature.

Treatment-failure tularemia in children.

PURPOSE: Tularemia is an infection caused by Francisella tularensis. Its diagnosis and treatment may be difficult in many cases. The aim of this study was to evaluate treatment modalities for pediatric tularemia patients who do not respond to medical treatment. METHODS: A single-center, retrospective study was performed. A total of 19 children with oropharyngeal tularemia were included. RESULTS: Before diagnosis, the duration of symptoms in patients was 32.15±17.8 days. The most common lymph node localization was the cervical chain. All patients received medical treatment (e.g., streptomycin, gentamicin, ciprofloxacin, and doxycycline). Patients who had been given streptomycin, gentamicin, or doxycycline as initial therapy for 10-14 days showed no response to treatment, and recovery was only achieved after administration of oral ciprofloxacin. Response to treatment was delayed in 5 patients who had been given ciprofloxacin as initial therapy. Surgical incision and drainage were performed in 9 patients (47.5%) who were unresponsive to medical treatment and were experiencing abcess formation and suppuration. Five patients (26.3%) underwent total mass excision, and 2 patients (10.5%) underwent fine-needle aspiration to reach a conclusive differential diagnosis and inform treatment. CONCLUSION: The causes of treatment failure in tularemia include delay in effective treatment and the development of suppurating lymph nodes.

A novel approach for SEMG signal classification with adaptive local binary patterns.

Feature extraction plays a major role in the pattern recognition process, and this paper presents a novel feature extraction approach, adaptive local binary pattern (aLBP). aLBP is built on the local binary pattern (LBP), which is an image processing method, and one-dimensional local binary pattern (1D-LBP). In LBP, each pixel is compared with its neighbors. Similarly, in 1D-LBP, each data in the raw is judged against its neighbors. 1D-LBP extracts feature based on local changes in the signal. Therefore, it has high a potential to be employed in medical purposes. Since, each action or abnormality, which is recorded in SEMG signals, has its own pattern, and via the 1D-LBP these (hidden) patterns may be detected. But, the positions of the neighbors in 1D-LBP are constant depending on the position of the data in the raw. Also, both LBP and 1D-LBP are very sensitive to noise. Therefore, its capacity in detecting hidden patterns is limited. To overcome these drawbacks, aLBP was proposed. In aLBP, the positions of the neighbors and their values can be assigned adaptively via the down-sampling and the smoothing coefficients. Therefore, the potential to detect (hidden) patterns, which may express an illness or an action, is really increased. To validate the proposed feature extraction approach, two different datasets were employed. Achieved accuracies by the proposed approach were higher than obtained results by employed popular feature extraction approaches and the reported results in the literature. Obtained accuracy results were brought out that the proposed method can be employed to investigate SEMG signals. In summary, this work attempts to develop an adaptive feature extraction scheme that can be utilized for extracting features from local changes in different categories of time-varying signals.

Does Bedside Sonography Effectively Identify Nasogastric Tube Placements in Pediatric Critical Care Patients?

BACKGROUND: A nasogastric tube (NGT) insertion is a common procedure in intensive care units, with some serious complications that result from the malposition of the NGT tip. This pilot study was designed to investigate the efficiency of ultrasound in verifying correct NGT placement and to compare these results with radiographic findings. MATERIALS AND METHODS: This was a single-center, double-blind prospective study of patients who had received an NGT in the pediatric critical care unit. Twenty-one patients aged 1 month to 18 years were included in this study. All NGTs were inserted by the same critical care physician. After insertion, the physician first confirmed NGT placement by the auscultation of the epigastrium following the insufflation of air. Confirmation was supplemented with an abdominal radiograph. A radiologist who was unaware of the radiographic findings performed bedside sonography on all patients and verified the location of the NGTs. The findings from these 2 physicians were then compared. RESULTS: NGTs were inserted without any complications, and none of the NGTs were positioned in the respiratory tract in any of the patients. All NGT tips were visualized by radiography and sonography with a sensitivity of 100%. CONCLUSION: Bedside sonography performed by a radiologist is an effective and sensitive diagnostic procedure for confirming the correct NGT position in patients in the pediatric critical care unit.