Infrared ship target segmentation is the important basis of infrared guided weapon in the sea-air context. Typically, accurate infrared ship target segmentation relies on a large number of ...pixel-level labels. However, it is difficult to obtain them. To this end, we present a method of Semi-supervised Infrared Ship Target Segmentation with Dual Branch (SeISTS-DB), which utilizes a small amount of labeled data and a large amount of unlabeled data to train model and improve segmentation performance. There are three main contributions. First, we design a target segmentation branch to generate the pseudo labels for unlabeled data. It consists of a dual learning network and a segmentation network. The dual learning network generates pseudo labels with weights for unlabeled data. The segmentation network is trained using both labeled data and unlabeled data with pseudo labels to achieve target segmentation of infrared ship, obtaining the preliminary segmentation results. Secondly, we introduce an error segmentation pixel correction branch, which contains a student network and a teacher network, to modify the pixel category error of the preliminary segmentation map. Finally, the outputs of the two branches are combined to obtain the final segmentation result. The SeISTS-DB is compared with other fully-supervised and semi-supervised methods on the infrared ship images dataset. Experimental results demonstrate that when the labeled data accounts for 1/8 of the training data, the mean Intersection over Union (mIou) is respectively improved by 15.35% and 6.19% at most. Besides, it is also compared with other methods on the public IRSTD-1k dataset, when the proportion of labeled images is 1/8, the mIoU is respectively improved by 11.76% at most compared to the state-of-the-art semi-supervised methods, demonstrating its effectiveness.
A novel design of multibeam array antenna without feeding network is presented in this communication. This array antenna consists of 3×3 microstrip patches as radiators. In this design, a feeding ...network is avoided where each patch is fed by a probe. Furthermore, whatever patch is excited, the input power can be coupled to all patches through four microstrip lines located between the radiating elements. In addition, nine radiation beams can be implemented depending on different field distributions that are generated by exciting each patch individually. The proposed antenna has a simple single-layered structure and does not suffer from a complex feeding network compared with traditional multibeam antennas. The experimental results demonstrate that the scanning ranges of the nine beams are ±24° and ±45° in the vertical and horizontal directions, respectively. Moreover, measured gain for the nine beams of the implemented antenna varies from 9.06 to 10.45 dBi.
Recent studies have reported that Fenton sludge and biochemical sludge contain high concentrations of toxic substances and heavy metals (HMs), whereas improper treatment can pose serious threats to ...environmental safety. Pyrolysis is considered an efficient technology to replace conventional sludge treatment. This study investigated the pyrolysis and kinetic processes of Fenton sludge and biochemical sludge, revealed the physicochemical properties of sludge biochar, and highlighted the role of co-pyrolysis in sludge immobilization of HMs and environmental risks. Results showed that Fenton sludge and biochemical sludge underwent three stages of weight loss during individual pyrolysis and co-pyrolysis, especially co-pyrolysis, which increased the rate of sludge pyrolysis and reduced the decomposition temperature. The kinetic reaction indicated that the activation energies of Fenton sludge, biochemical sludge, and mixed sludge were 11.59 kJ/mol, 8.50 kJ/mol, and 7.11 kJ/mol, respectively. Notably, co-pyrolysis reduced the activation energy of reactions and changed the specific surface area and functional group properties of the biochar produced from sludge. Meanwhile, co-pyrolysis effectively immobilized Cu, Pb, and Zn, increased the proportion of metals in oxidizable and residual states, and mitigated the environmental risks of HMs in sludge. This study provided new insights into the co-pyrolysis properties of sludge biochar and the risk assessment of HMs.
Although using image strip sum, an orthogonal Haar transform (OHT) pattern matching algorithm may have good performance, it requires three subtractions to calculate each Haar projection value on the ...sliding windows. By establishing a solid mathematical foundation for OHT, this paper based on the concept of image square sum, proposes a novel fast orthogonal Haar transform (FOHT) pattern matching algorithm, from which a Haar projection value can be obtained by only one subtraction. Thus, higher speed-ups can be achieved, while producing the same results with the full search pattern matching. A large number of experiments show that the speed-ups of FOHT are very competitive with OHT in most cases of matching one single pattern, and generally higher than OHT in all cases of matching multiple patterns, exceeding other high-level full search equivalent algorithms.
This paper mainly deals with the problem of short text classification. There are two main contributions. Firstly, we introduce a framework of deep uniform kernel mapping support vector machine ...(DUKMSVM). The significant merit of this framework is that by expressing the kernel mapping function explicitly with a deep neural network, it is in essence an explicit kernel mapping instead of the traditional kernel function, and it allows better flexibility in dealing with various applications by applying different neural network structures. Secondly, to validate the effectiveness of this framework and to improve the performance of short text classification, we explicitly express the kernel mapping using bidirectional recurrent neural network (BRNN), and propose a deep bidirectional recurrent kernel mapping support vector machine (DRKMSVM) for short text classification. Experimental results on five public short text classification datasets indicate that in terms of classification accuracy, precision, recall rate and F1-score, the DRKMSVM achieves the best performance with the average values of accuracy, precision, recall rate, and F1-score of 87.23%, 86.99%, 86.13% and 86.51% respectively compared to traditional SVM, convolutional neural network (CNN), Naive Bayes (NB), and Deep Neural Mapping Support Vector Machine (DNMSVM) which applies multi-layer perceptron for kernel mapping.
The complete mitochondrial genome of Cyrtacanthacris tatarica was firstly sequenced and analyzed. The circular mitogenome was 15,679 bp long, showing a bias of AT rich on the majority strand (42.34% ...of A, 29.99% of T, 11.19% of G, and 16.18% of C). It consisted of the typical 37 genes (13 protein-coding genes, two ribosomal RNA genes, and 22 transfer tRNA genes) and one longest non-coding region (called as control region). All PCGs used standard ATN initiation codons, and most PCGs were terminated with complete codons (TAA/TAG), apart from cox1 and nad5. Phylogenetic analyses based on the concatenated nucleotide sequences of PCGs supported that Cyrtacanthacridinae was monophyletic, and the sister group relationship between C. tatarica and Schistocerca gregaria gregaria was determined. Our results may provide molecular information for the genetic evolution and taxonomy of the acridid species.
Deep learning has been used to improve intelligent transportation systems (ITS) by classifying ship targets in interior waterways. Researchers have created numerous classification methods, but they ...have low accuracy and misclassify other ship targets. As a result, more research into ship classification is required to avoid inland waterway collisions. We present a new convolutional neural network classification method for inland waterways that can classify the five major ship types: cargo, military, carrier, cruise, and tanker. This method can also be used for other ship classes. The proposed method consists of four phases for the boosting of classification accuracy for Intelligent Transport Systems (ITS) based on convolutional neural networks (CNNs); efficient augmentation method, the hyper-parameter optimization (HPO) technique for optimum CNN model parameter selection, transfer learning, and ensemble learning are suggested. All experiments used Kaggle’s public Game of Deep Learning Ship dataset. In addition, the proposed ship classification achieved 98.38% detection rates and 97.43% F1 scores. Our suggested classification technique was also evaluated on the MARVEL dataset. This dataset includes 10,000 image samples for each class and 26 types of ships for generalization. The suggested method also delivered an excellent performance compared to other algorithms, with performance metrics with an accuracy of 97.04%, a precision of 96.1%, a recall of 95.92%, a specificity of 96.55%, and a 96.31% F1 score.
In this paper, we introduce Wide-TSNet, a novel hybrid approach for predicting Bitcoin prices using time-series data transformed into images. The method involves converting time-series data into ...Markov transition fields (MTFs), enhancing them using histogram equalization, and classifying them using Wide ResNets, a type of convolutional neural network (CNN). We propose a tripartite classification system to accurately represent Bitcoin price trends. In addition, we demonstrate the effectiveness of Wide-TSNet through various experiments, in which it achieves an Accuracy of approximately 94% and an F1 score of 90%. It is also shown that lightweight CNN models, such as SqueezeNet and EfficientNet, can be as effective as complex models under certain conditions. Furthermore, we investigate the efficacy of other image transformation methods, such as Gramian angular fields, in capturing the trends and volatility of Bitcoin prices and revealing patterns that are not visible in the raw data. Moreover, we assess the effect of image resolution on model performance, emphasizing the importance of this factor in image-based time-series classification. Our findings explore the intersection between finance, image processing, and deep learning, providing a robust methodology for financial time-series classification.
A simple and efficient manufacture method of helical long period fiber grating (HLPFG) in a single-mode fiber (SMF) is designed and verified through experiment. Different from the previous ...fabricating methods, the SMF is heated by a double-side CO 2 laser beam after being twisted. There are multiple transmission depletions caused by model coupling which could be observed when the period length is 500 μm. The sensing characteristics of the HLPFG have been investigated. Experimental results demonstrate axial strain sensitivities of 3.3 and 6.4 pm/μϵ at the selected dips in the range of 0-450 μϵ or temperature sensitivities of 35.3 and 49.5 pm/°C at the selected dips in the range of 20-70 °C, respectively. Moreover, through theoretical analysis, it is found that the fabricated HLPFG can measure axial strain and temperature concurrently by monitoring the resonance wavelength shift. Therefore, the fabricated HLPFG has brilliant applications value in dual measurement.
The complete mitochondrial genome (mitogenome) of Sinopodisma hengshanica (Orthoptera: Acrididae) was firstly determined and analyzed in the present study. Assembled mitogenome sequence of S. ...hengshanica is 15,623 bp in size, containing 13 protein-coding genes (PCGs), two ribosomal RNA genes (rRNAs), 22 transfer RNA genes (tRNAs), as well as one A + T-rich region. Its gene component and arrangement are identical with other Acrididae species. The overall nucleotide composition is as follows: A (42.89%), G (10.34%), T (33.07%), and C (13.70%). All PCGs are initiated by typical ATN codons, and terminated with harboring complete stop codons TAA and TAG. Furthermore, phylogenetic trees were reconstructed based on 13 PCGs to validate the taxonomic status of S. hengshanica, exhibiting a close relationship with Sinopodisma rostellocerca.