Heart sounds convey important information regarding potential heart diseases. Currently, heart sound classification attracts many researchers from the fields of telemedicine, digital signal processing, and machine learning—among others—mainly to identify cardiac pathology as quickly as possible. This article proposes chaogram as a new transform to convert heart sound signals to colour images. In the proposed approach, the output image is, therefore, the projection of the reconstructed phase space representation of the phonocardiogram (PCG) signal on three coordinate planes. This has two major benefits: (1) it makes possible to apply deep convolutional neural networks to heart sounds and (2) it is also possible to employ a transfer learning scheme by converting a heart sound signal to an image. The performance of the proposed approach was verified on the PhysioNet dataset. Due to the imbalanced data on this dataset, it is common to assess the results quality using the average of sensitivity and specificity, which is known as score, instead of accuracy. In this study, the best results were achieved using the $InceptionV3$ model, which achieved a score of 88.06%.

The analysis of ambient sounds can be very useful when developing sound base intelligent systems. Acoustic scene classification (ASC) is defined as identifying the area of a recorded sound or clip among some predefined scenes. ASC has huge potential to be used in urban sound event classification systems. This research presents a hybrid method that includes a novel mathematical fusion step which aims to tackle the challenges of ASC accuracy and adaptability of current state-of-the-art models. The proposed method uses a stereo signal, two ensemble classifiers (random subspace), and a novel mathematical fusion step. In the proposed method, a stable, invariant signal representation of the stereo signal is built using Wavelet Scattering Transform (WST). For each mono, i.e., left and right, channel, a different random subspace classifier is trained using WST. A novel mathematical formula for fusion step was developed, its parameters being found using a Genetic algorithm. The results on the DCASE 2017 dataset showed that the proposed method has higher classification accuracy (about 95%), pushing the boundaries of existing methods.

In this article, a hierarchical method for action recognition based on temporal and spatial features is proposed. In current HAR methods, camera movement, sensor movement, sudden scene changes, and scene movement can increase motion feature errors and decrease accuracy. Another important aspect to take into account in a HAR method is the required computational cost. The proposed method provides a preprocessing step to address these challenges. As a preprocessing step, the method uses optical flow to detect camera movements and shots in input video image sequences. In the temporal processing block, the optical flow technique is combined with the absolute value of frame differences to obtain a time saliency map. The detection of shots, cancellation of camera movement, and the building of a time saliency map minimise movement detection errors. The time saliency map is then passed to the spatial processing block to segment the moving persons and/or objects in the scene. Because the search region for spatial processing is limited based on the temporal processing results, the computations in the spatial domain are drastically reduced. In the spatial processing block, the scene foreground is extracted in three steps: silhouette extraction, active contour segmentation, and colour segmentation. Key points are selected at the borders of the segmented foreground. The last used features are the intensity and angle of the optical flow of detected key points. Using key point features for action detection reduces the computational cost of the classification step and the required training time. Finally, the features are submitted to a Recurrent Neural Network (RNN) to recognise the involved action. The proposed method was tested using four well-known action datasets: KTH, Weizmann, HMDB51, and UCF101 datasets and its efficiency was evaluated. Since the proposed approach segments salient objects based on motion, edges, and colour features, it can be added as a preprocessing step to most current HAR systems to improve performance.

Land cover classification (LCC) using satellite images is one of the rapidly expanding fields in mapping, highlighting the need for updating existing computational classification methods. Advances in technology and the increasing variety of applications have introduced challenges, such as more complex classes and a demand for greater detail. In recent years, deep learning and Convolutional Neural Networks (CNNs) have significantly enhanced the segmentation of satellite images. Since the training of CNNs requires sophisticated and expensive hardware and significant time, using pre-trained networks has become widespread in the segmentation of satellite image. This study proposes a hybrid synergistic semantic segmentation method based on the Deeplab v3+ network and a clustering-based post-processing scheme. The proposed method accurately classifies various land cover (LC) types in multispectral satellite images, including Pastures, Other Built-Up Areas, Water Bodies, Urban Areas, Grasslands, Forest, Farmland, and Others. The post-processing scheme includes a spectral bag-of-words model and K-medoids clustering to refine the Deeplab v3+ outputs and correct possible errors. The simulation results indicate that combining the post-processing scheme with deep learning improves the Matthews correlation coefficient (MCC) by approximately 5.7% compared to the baseline method. Additionally, the proposed approach is robust to data imbalance cases and can dynamically update its codewords over different seasons. Finally, the proposed synergistic semantic segmentation method was compared with several state-of-the-art segmentation methods in satellite images of Italy’s Lake Garda (Lago di Garda) region. The results showed that the proposed method outperformed the best existing techniques by at least 6% in terms of MCC.

All the works on writer's handwritten letters detection was based on the western languages and partly Chinese and Hindi, and there is a little study on Persian handwritten letters detection. Accordingly, in this paper a method is proposed to distinguish scanned Persian handwritten texts with image processing techniques. The proposed method assumes that the writer's handwritten are available in separate letters. The system trains with features extraction of these separate letters and then the trained system is used to detect individual handwritten among some indistinctive handwritten texts. The characteristics of our proposed method including highspeed of training in too much number of handwritten, is the content inattention and visual features considering. The results of procedures on 100 persons also admitted that the proposed method has a very good performance on Persian handwritten texts detection.

In recent years, with the growth of digital media and modern imaging equipment, the use of video processing algorithms and semantic film and image management has expanded. The usage of different video datasets in training artificial intelligence algorithms is also rapidly expanding in various fields. Due to the high volume of information in a video, its processing is still expensive for most hardware systems, mainly in terms of its required runtime and memory. Hence, the optimal selection of keyframes to minimize redundant information in video processing systems has become noteworthy in facilitating this problem. Eliminating some frames can simultaneously reduce the required computational load, hardware cost, memory and processing time of intelligent video-based systems. Based on the aforementioned reasons, this research proposes a method for selecting keyframes and adaptive cropping input video for human action recognition (HAR) systems. The proposed method combines edge detection, simple difference, adaptive thresholding and 1D and 2D average filter algorithms in a hierarchical method. Some HAR methods are trained with videos processed by the proposed method to assess its efficiency. The results demonstrate that the application of the proposed method increases the accuracy of the HAR system by up to 3% compared to random image selection and cropping methods. Additionally, for most cases, the proposed method reduces the training time of the used machine learning algorithm.