Skin cancer is the most common form of cancer affecting humans. Melanoma is the most dangerous type of skin cancer; and early diagnosis is extremely vital in curing the disease. So far, the human knowledge in this field is very limited, thus, developing a mechanism capable of identifying the disease early on can save lives, reduce intervention and cut unnecessary costs. In this paper, the researchers developed a new learning technique to classify skin lesions, with the purpose of observing and identifying the presence of melanoma. This new technique is based on a convolutional neural network solution with multiple configurations; where the researchers employed an International Skin Imaging Collaboration (ISIC) dataset. Optimal results are achieved through a convolutional neural network composed of 14 layers. This proposed system can successfully and reliably predict the correct classification of dermoscopic lesions with 97.78% accuracy.
In the last few years, a great attention was paid to the deep learning Techniques used for image analysis because of their ability to use machine learning techniques to transform input data into high level presentation. For the sake of accurate diagnosis, the medical field has a steadily growing interest in such technology especially in the diagnosis of melanoma. These deep learning networks work through making coarse segmentation, conventional filters and pooling layers. However, this segmentation of the skin lesions results in image of lower resolution than the original skin image. In this paper, we present deep learning based approaches to solve the problems in skin lesion analysis using a dermoscopic image containing skin tumor. The proposed models are trained and evaluated on standard benchmark datasets from the International Skin Imaging Collaboration (ISIC) 2018 Challenge. The proposed method achieves an accuracy of 96.67% for the validation set .The experimental tests carried out on a clinical dataset show that the classification performance using deep learning-based features performs better than the state-of-the-art techniques.
In industrial drive systems, one of the widest group of machines are induction motors. During normal operation, these machines are exposed to various types of damages, resulting in high economic losses. Electrical circuits damages are more than half of all damages appearing in induction motors. In connection with the above, the task of early detection of machine defects becomes a priority in modern drive systems. The article presents the possibility of using deep neural networks to detect stator and rotor damages. The opportunity of detecting shorted turns and the broken rotor bars with the use of an axial flux signal is presented.
In this paper deep neural networks are proposed to diagnose inter-turn short-circuits of induction motor stator windings operating under the Direct Field Oriented Control method. A convolutional neural network (CNN), trained with a Stochastic Gradient Descent with Momentum method is used. This kind of deep-trained neural network allows to significantly accelerate the diagnostic process compared to the traditional methods based on the Fast Fourier Transform as well as it does not require stationary operating conditions. To assess the effectiveness of the applied CNN-based detectors, the tests were carried out for variable load conditions and different values of the supply voltage frequency. Experimental results of the proposed induction motor fault detection system are presented and discussed.
In this work, we present a failure detection system in sensors of any robot. It is based on the k-fold cross-validation approach and built from N neural networks, where N is the number of signals read from sensors. Our tests were carried out using an unmanned aerial vehicle (UAV, quadrocopter), where signals were read from three sensors: accelerometer, magnetometer and gyroscope. Artificial neural network was used to determine Euler angles, based on signals from these sensors. The presented system is an extension of the system that we proposed in one of our previous papers. The improvement shown in this work took place on two levels. The first one was related to improvement of a neural network՚s reproduction quality – we have replaced a recurrent neural network with a convolutional one. The second level was associated with the improvement of the validation process, i.e. with adding some new criteria to check the values of Euler՚s angles determined by the convolutional neural network in subsequent time steps. To highlight the proposed system improvement we present a number of indicators such as RMSE, NRMSE and NDR (Normalized Detection Ratio).
Biometrics provide an alternative to passwords and pins for authentication. The emergence of machine learning algorithms provides an easy and economical solution to authentication problems. The phases of speaker verification protocol are training, enrollment of speakers and evaluation of unknown voice. In this paper, we addressed text independent speaker verification using Siamese convolutional network. Siamese networks are twin networks with shared weights. Feature space can be learnt easily by training these networks even if similar observations are placed in proximity. Extracted features from Siamese then can be classified using difference or correlation measures. We have implemented a customized scoring scheme that utilizes Siamese’ capability of applying distance measures with the convolutional learning. Experiments made on cross language audios of multi-lingual speakers confirm the capability of our architecture to handle gender, age and language independent speaker verification. Moreover, our designed Siamese network, SpeakerNet, provided better results than the existing speaker verification approaches by decreasing the equal error rate to 0.02.
The paper examines the usage of Convolutional Bidirectional Recurrent Neural Network (CBRNN) for a problem of quality measurement in a music content. The key contribution in this approach, compared to the existing research, is that the examined model is evaluated in terms of detecting acoustic anomalies without the requirement to provide a reference (clean) signal. Since real music content may include some modes of instrumental sounds, speech and singing voice or different audio effects, it is more complex to analyze than clean speech or artificial signals, especially without a comparison to the known reference content. The presented results might be treated as a proof of concept, since some specific types of artefacts are covered in this paper (examples of quantization defect, missing sound, distortion of gain characteristics, extra noise sound). However, the described model can be easily expanded to detect other impairments or used as a pre-trained model for other transfer learning processes. To examine the model efficiency several experiments have been performed and reported in the paper. The raw audio samples were transformed into Mel-scaled spectrograms and transferred as input to the model, first independently, then along with additional features (Zero Crossing Rate, Spectral Contrast). According to the obtained results, there is a significant increase in overall accuracy (by 10.1%), if Spectral Contrast information is provided together with Mel-scaled spectrograms. The paper examines also the influence of recursive layers on effectiveness of the artefact classification task.
To improve power system reliability, a protection mechanism is highly needed. Early detection can be used to prevent failures in the power transmission line (TL). A classification system method is widely used to protect against false detection as well as assist the decision analysis. Each TL signal has a continuous pattern in which it can be detected and classified by the conventional methods, i.e., wavelet feature extraction and artificial neural network (ANN). However, the accuracy resulting from these mentioned models is relatively low. To overcome this issue, we propose a machine learning-based on Convolutional Neural Network (CNN) for the transmission line faults (TLFs) application. CNN is more suitable for pattern recognition compared to conventional ANN and ANN with Discrete Wavelet Transform (DWT) feature extraction. In this work, we first simulate our proposed model by using Simulink® and Matlab®. This simulation generates a fault signal dataset, which is divided into 45.738 data training and 4.752 data tests. Later, we design the number of machine learning classifiers. Each model classifier is trained by exposing it to the same dataset. The CNN design, with raw input, is determined as an optimal output model from the training process with 100% accuracy.