In the Vehicular Ad hoc Networks (VANET) environment, recognizing traffic accident events in the driving videos captured by vehicle-mounted cameras is an essential task. Generally, traffic accidents ...have a short duration in driving videos, and the backgrounds of driving videos are dynamic and complex. These make traffic accident detection quite challenging. To effectively and efficiently detect accidents from the driving videos, we propose an accident detection approach based on spatio-temporal feature encoding with a multilayer neural network. Specifically, the multilayer neural network is used to encode the temporal features of video for clustering the video frames. From the obtained frame clusters, we detect the border frames as the potential accident frames. Then, we capture and encode the spatial relationships of the objects detected from these potential accident frames to confirm whether these frames are accident frames. The extensive experiments demonstrate that the proposed approach achieves promising detection accuracy and efficiency for traffic accident detection, and meets the real-time detection requirement in the VANET environment.
It is clear that the learning effectiveness and learning speed of neural networks are in general far slower than required, which has been a major bottleneck for many applications. Recently, a simple ...and efficient learning method, referred to as extreme learning machine (ELM), was proposed by Huang , which has shown that, compared to some conventional methods, the training time of neural networks can be reduced by a thousand times. However, one of the open problems in ELM research is whether the number of hidden nodes can be further reduced without affecting learning effectiveness. This brief proposes a new learning algorithm, called bidirectional extreme learning machine (B-ELM), in which some hidden nodes are not randomly selected. In theory, this algorithm tends to reduce network output error to 0 at an extremely early learning stage. Furthermore, we find a relationship between the network output error and the network output weights in the proposed B-ELM. Simulation results demonstrate that the proposed method can be tens to hundreds of times faster than other incremental ELM algorithms.
Underwater images suffer from low contrast and color distortion. In order to improve the quality of underwater images and reduce storage and computational resources, this paper proposes a lightweight ...model Rep-UWnet to enhance underwater images. The model consists of a fully connected convolutional network and three densely connected RepConv blocks in series, with the input images connected to the output of each block with a Skip connection. First, the original underwater image is subjected to feature extraction by the SimSPPF module and is processed through feature summation with the original one to be produced as the input image. Then, the first convolutional layer with a kernel size of 3 × 3, generates 64 feature maps, and the multi-scale hybrid convolutional attention module enhances the useful features by reweighting the features of different channels. Second, three RepConv blocks are connected to reduce the number of parameters in extracting features and increase the test speed. Finally, a convolutional layer with 3 kernels generates enhanced underwater images. Our method reduces the number of parameters from 2.7 M to 0.45 M (around 83% reduction) but outperforms state-of-the-art algorithms by extensive experiments. Furthermore, we demonstrate our Rep-UWnet effectively improves high-level vision tasks like edge detection and single image depth estimation. This method not only surpasses the contrast method in objective quality, but also significantly improves the contrast, colorimetry, and clarity of underwater images in subjective quality.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
This paper proposes a novel and unified synthesis approach and design procedure for microwave filters with extracted pole and nonresonating node (NRN) technique. By introducing a general circuit ...topology, the traditional extracted pole and NRN filters can be unified to a general prototype. With the new design process, the exact mapping relationship between the electromagnetic (EM) model of the pole producing element and the circuit model can be achieved. All the physical dimensions of the filter structure can be obtained by a fully analytical approach. No full EM optimization or adjustment is needed in the filter design. A three pole TE 101 mode waveguide filter with one finite transmission zero is designed to illustrate the new procedure. In addition, a seven-pole TE 011 mode filter with four finite transmission zeros covering all three possible types of arrangements is designed and fabricated to demonstrate the versatility of the proposed method. The simulated and measured results verified the efficiency and the accuracy of the proposed design method.
The generalized Chebyshev (pseudoelliptical) filter functions may not be optimal for certain applications due to physical constrains. With redundancy in filter polynomials, this article breaks down ...the "mental barrier" in conventional synthesis and directly synthesizes the "Chebyshev-like" functions to achieve desired filter performance under physical limitations. By exploiting the redundant restrictions on exact equal-ripple response, the reflection zeros can be moved to the complex plane, thus forming the "Chebyshev-like functions." A class of inline filters with a block of second-order dangling resonators is synthesized, which can generate a pair of symmetric transmission zeros (Tzs) but is considered unrealizable using standard Chebyshev functions. With the proposed theories, an accurate and much improved filter prototype is directly derived from the "Chebyshev-like" polynomials, avoiding additional optimization in the design process. For verification, a group of examples with synthesis results are elucidated. Eight ten-pole filters with four Tzs are synthesized and fabricated. The simulated and measured results demonstrate the effectiveness and application of the proposed theories.
Fetal movement (FM) is an important indicator of fetal health. However, the current methods of FM detection are unsuitable for ambulatory or long-term observation. This paper proposes a non-contact ...method for monitoring FM. We recorded abdominal videos from pregnant women and then detected the maternal abdominal region within each frame. FM signals were acquired by optical flow color-coding, ensemble empirical mode decomposition, energy ratio, and correlation analysis. FM spikes, indicating the occurrence of FMs, were recognized using the differential threshold method. FM parameters including number, interval, duration, and percentage were calculated, and good agreement was found with the manual labeling performed by the professionals, achieving true detection rate, positive predictive value, sensitivity, accuracy, and F1_score of 95.75%, 95.26%, 95.75%, 91.40%, and 95.50%, respectively. The changes in FM parameters with gestational week were consistent with pregnancy progress. In general, this study provides a novel contactless FM monitoring technology for use at home.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
The extreme learning machine (ELM), which was originally proposed for "generalized" single-hidden layer feedforward neural networks, provides efficient unified learning solutions for the applications ...of clustering, regression, and classification. It presents competitive accuracy with superb efficiency in many applications. However, ELM with subnetwork nodes architecture has not attracted much research attentions. Recently, many methods have been proposed for supervised/unsupervised dimension reduction or representation learning, but these methods normally only work for one type of problem. This paper studies the general architecture of multilayer ELM (ML-ELM) with subnetwork nodes, showing that: 1) the proposed method provides a representation learning platform with unsupervised/supervised and compressed/sparse representation learning and 2) experimental results on ten image datasets and 16 classification datasets show that, compared to other conventional feature learning methods, the proposed ML-ELM with subnetwork nodes performs competitively or much better than other feature learning methods.
Data, in deep learning (DL), are crucial to detect ships in synthetic aperture radar (SAR) images. However, SAR image annotation limitations hinder DL-based SAR ship detection. A novel data-selection ...method and teacher–student model are proposed in this paper to effectively leverage sparse labeled data and improve SAR ship detection performance, based on the semi-supervised oriented object-detection (SOOD) framework. More specifically, we firstly propose a SAR data-scoring method based on fuzzy comprehensive evaluation (FCE), and discuss the relationship between the score distribution of labeled data and detection performance. A refined data selector (RDS) is then designed to adaptively obtain reasonable data for model training without any labeling information. Lastly, a Gaussian Wasserstein distance (GWD) and an orientation-angle deviation weighting (ODW) loss are introduced to mitigate the impact of strong scattering points on bounding box regression and dynamically adjusting the consistency of pseudo-label prediction pairs during the model training process, respectively. The experiments results on four open datasets have demonstrated that our proposed method can achieve better SAR ship detection performances on low-proportion labeled datasets, compared to some existing methods. Therefore, our proposed method can effectively and efficiently reduce the burden of SAR ship data labeling and improve detection capacities as much as possible.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
: There is accumulating evidence suggesting a connection between the gut and Parkinson's disease (PD). Gut microbiota may play an important role in the intestinal lesions in PD patients.
: This study ...aims to determine whether gut microbiota differs between PD patients and healthy controls in Northeast of China, and to identify the factors that influence the changes in the gut microbiota.
: We enrolled 51 PD patients and 48 healthy controls in this study. Microbial species in stool samples were determined through 16S-rRNA gene sequencing. Dietary intakes were collected from a subset of 42 patients and 23 controls using a food frequency questionnaire (FFQ). Gut microbiota species richness, diversity, differential abundance of individual taxa between PD patients and controls, and the relationship between the gut microbiota abundance and the dietary and clinical factors were analyzed.
: PD patients showed decreased species richness, phylogenetic diversity, β- diversity, and altered relative abundance in several taxa compared to the controls. PD- associated clinical scores appeared to be the most influential factors that correlated with the abundance of a variety of taxa. The most consistent findings suggested by multiple analyses used in this study were the increase of
and the decrease of
in PD patients in Northeast China.
: Gut microbiota significantly differed between a group of PD patients and healthy controls in Northeast China, with decreased species richness, phylogenetic diversity, β-diversity, and altered relative abundance in several taxa compared to the controls.
Machine learning algorithms such as those for object classification in images, video content analysis, and human action recognition are used to extract meaningful information from data recorded by ...image sensors and cameras. Among the existing machine learning algorithms for such purposes, extreme learning machines (ELMs) and online sequential ELMs (OS-ELMs) are well known for their computational efficiency and performance when processing large datasets. The latter approach was derived from the ELM approach and optimized for real-time application. However, OS-ELM classifiers are computationally demanding, and the existing state-of-the-art computing platforms are not efficient enough for embedded systems, especially for applications with strict requirements in terms of low power consumption, high throughput, and low latency. This paper presents the implementation of an ELM/OS-ELM in a customized system-on-a-chip field-programmable gate array-based architecture to ensure efficient hardware acceleration. The acceleration process comprises parallel extraction, deep pipelining, and efficient shared memory communication.
PDF
