Pulse Repetition Interval (PRI) modulation recognition is a key issue in radar identification process in modern electronic intelligent (ELINT) and electronic support measure (ESM) systems. In this study, a novel approach based on the intrinsic property of the temporal convolutional network (TCN) is presented for PRI modulation type recognition. Since a causal TCN is used for this purpose, the method is suitable for online ESM and ELINT analysis. The simulation results show that the method accurately classifies seven types of PRI modulation including simple, dwell and switch, stagger, jitter, agile, sliding and periodic modulations in realistic scenarios. In order to investigate the performance of the method when the problem of missing or spurious pulses occurs, the impacts of these problems are examined, separately and together, on the recognition process. It is shown that the method works effectively even with a relatively high percentage of missing and/or spurious pulses (up to 30%). The method also works effectively in the presence of unintentional jitter and large outliers, which can be due to radar antenna scan. The experimental results on real data confirm that the proposed method performs accurately and effectively in real world scenarios.

In image captioning models, the main challenge in describing an image is identifying all the objects by precisely considering the relationships between the objects and producing various captions. Over the past few years, many methods have been proposed, from an attribute-to-attribute comparison approach to handling issues related to semantics and their relationships. Despite the improvements, the existing techniques suffer from inadequate positional and geometrical attributes concepts. The reason is that most of the abovementioned approaches depend on Convolutional Neural Networks (CNNs) for object detection. CNN is notorious for failing to detect equivariance and rotational invariance in objects. Moreover, the pooling layers in CNNs cause valuable information to be lost. Inspired by the recent successful approaches, this paper introduces a novel framework for extracting meaningful descriptions based on a parallelized capsule network that describes the content of images through a high level of understanding of the semantic contents of an image. The main contribution of this paper is proposing a new method that not only overrides the limitations of CNNs but also generates descriptions with a wide variety of words by using Wikipedia. In our framework, capsules focus on the generation of meaningful descriptions with more detailed spatial and geometrical attributes for a given set of images by considering the position of the entities as well as their relationships. Qualitative experiments on the benchmark dataset MS-COCO show that our framework outperforms state-of-the-art image captioning models when describing the semantic content of the images.

In applications such as noise removal, speech separation, music reconstruction or integration, and many others, it is important to decompose a single-channel recorded sound into its sources. In this paper, we deal with the separation of single-channel audio sources and cocktail party problem in audio data using supervised learning. The basis of this method is using deep learning to separate audio signals. The data contains audio-visual videos and Persian musical instruments sounds which have been selected as audio sources. The proposed algorithm is the first method implemented based on deep learning to separate the sound sources of Persian musical instruments. In this method, first the audio part of the video signal is extracted, then the audio signal, which is a mixture of sound sources, is separated and decomposed by a deep neural network model. According to the evaluations, the proposed method has good quantitative and qualitative results for separation two audio sources. In addition, this method is a comprehensive solution that can be used for a wide range of audio sources and a combination of more than two audio sources.

Injection molding is a process which raw plastic materials are converted to plastic parts that are widely used in various industries like machinery, automobile, pharmaceutical, etc. This process is implemented by injection molding machines with mold component. Experience has shown that service life of mold directly influences the cost and quality of injection molding products. Therefore, injection molding requires an appropriate inspection system to make sure it could work normally and efficiently. Using an automated system instead of human monitoring, the inspection task will be more efficient and reliable. In this paper we employ an intelligent inspection system based on machine vision to protect mold from potential damages. Images provided by data acquisition section of the system will be processed by a computer vision based method. This method consists of a SVM model that classifies images based on features extracted by a LBP algorithm. In feature extraction phase, histograms of images are processed in a new way; which focuses on the most different parts between classes. Our experimental results show that the proposed method leads to a F-score of 96.7. Finally, the system will decide whether the machine stop or continue injection molding process depending on classification results.

Any clutter edge in the reference window of a radar CFAR detection, produces an error in the clutter power estimation which reduces the detectability of the cell under test (CUT). In processors such as OS-CFAR, the designers have attempted to improve the detection performance, nevertheless, none of these processors applies an intelligent method of clutter edge recognition and destroyer data elimination. Therefore any of these processors are effective in some especial cases of non-homogeneous environment, but are deficient in other cases. In this paper an intelligent method is proposed for clutter edge recognition. This method determines the borders in which the clutter statistics are changing and then sets the decision threshold according to the appropriate clutter statistics. It is shown that the new processor improves the radar detection intensively in nonhomogeneous environment.