Search

To achieve a highly reliable and adaptive packet routing protocol in a complex urban Internet of vehicles, an end-edge-cloud edge intelligence architecture was proposed which consisted of an end user layer, an edge collaboration layer, and a cloud computing layer.Based on the proposed edge intelligence architecture, an packet routing protocol based on multi-intelligent reinforcement learning technologies was designed.The experimental results show that the proposed protocol could significantly improve the transmission delay and the packet reception rate in the interval of 29.65%～44.06% and 17.08%～25.38% compared to the state-of-the-art transmission mechanism for emergency data (TMED), intersection fog-based distributed routing protocol (IDR), and double deep Q-net based routing protocol (DRP).

With the advancement of remote sensing satellites and sensor technology, the quantity and diversity of remote sensing imagery have exhibited a sustained trend of growth. Remote sensing image retrieval has gained significant attention in the realm of remote sensing. Hashing methods have been widely applied in remote sensing image retrieval due to their high computational efficiency, low storage cost, and effective performance. However, existing remote sensing image retrieval methods often struggle to accurately capture the intricate information of remote sensing images. They often lack high attention to key features. The neglect of multiscale and saliency information in remote sensing images can result in feature loss and difficulties in maintaining the balance of hash codes. In response to the issues, we introduce a multiscale context deep hashing network (MSCDH). First, we can obtain finer-grained multi-scale features and achieve a larger receptive field by incorporating the proposed multiscale residual blocks. Then, the proposed multicontext attention modules can increase the perceptual field and suppress the interference from irrelevant information by aggregating contextual information along channels and spatial dimensions. The experimental results on the UCMerced dataset and WHU-RS dataset demonstrate that the proposed method achieves state-of-the-art retrieval performance.

For remote sensing (RS) image retrieval task, hashing technology have been extensively researched in recent works. Unsupervised hashing approaches have attracted much attention in the RS data processing field because label collection takes a lot of time. Most of which fail to consider the interactions among the multichannel information of multispectral RS images and the disparity between the hash-like codes space and the Hamming space, which lead to the poor performance of multispectral RS image retrieval. In this article, we tackle these dilemmas with a novel unsupervised hashing approach, namely Unsupervised Transformer Balanced Hashing (UTBH), to utilize a convolutional variational autoencoder architecture with a novel RS transformer to perform effective hash codes learning. We first integrate a convolutional variational autoencoder architecture with a novel RS transformer, which can guide the interactions among the multichannel information of multispectral RS images. Meanwhile, a new objective function is proposed to preserve discrimination of hash codes in the hashing learning process and reduce the disparity between the hash-like codes space and the Hamming space effectively. Finally, experimental results on two multispectral RS image datasets indicate that UTBH approach achieves superior performance over other unsupervised image retrieval approaches.

Recently, low-altitude remote sensing platforms are widely used for various practical applications. Object detection is a basic and significant technology, serving them. The scale imbalance problem is predominant in low-altitude remote sensing images, which brings a great challenge to detect objects from these imageries. Consequently, in this article, we boost performance from the perspective of mitigating scale imbalance issues. First, we choose a one-stage object detector with decoupled heads as the baseline because of its comparatively high efficiency and accuracy. Current-decoupled heads ignore the interlayer relationship and the information contained. On the other hand, all existing feature pyramid structures generate one feature map for two branches at every layer. Inspired by them, we propose a novel feature pyramid network paradigm—decoupled feature pyramid network with consideration of different preferences for classification and localization. Meanwhile, the introduction of feature pyramid architecture will cause performance deterioration of larger objects because upper layers receive insufficient supervision in the training phase. Therefore, we adopt a distinct supervision strategy—level supervision, which pays more attention to upper layers. We demonstrate extensive experiments on two popular benchmarks of object detection in low-altitude remote sensing images to validate the effectiveness of our proposed method. In addition, we introduce a scale imbalance metric to quantify the degree of size change of objects to better illustrate the ability to relieve the scale imbalance problem. Finally, our proposed approach achieves state-of-the-art performance on both datasets.

Unsupervised hashingalgorithms are widely used in large-scale remote sensing images (RSIs) retrieval task. However, existing RSI retrieval algorithms fail to capture the multichannel characteristic of multispectral RSIs and the balanced property of hash codes, which lead the poor performance of RSI retrieval. To tackle these issues, we develop an unsupervised hashing algorithm, namely, variational autoencoder balanced hashing (VABH), to leverage multichannel feature fusion and multiscale context information to perform RSI retrieval task. First, multichannel feature fusion module is designed to extract RSI feature information by leveraging the multichannel properties of multispectral RSI. Second, multiscale learning module is developed to learn the multiscale context information of RSIs. Finally, a novel objective function is designed to capture the discrimination and balanced property of hash codes in the hashing learning process. Comprehensive experiments on diverse benchmark have well demonstrated the reasonableness and effectiveness of the proposed VABH algorithm.

In this paper, a multiscale contour steered region integral (MCSRI) method is proposed to classify highly similar shapes with flexible interior connection architectures. A component distance map (CDM) is developed to robustly characterize the flexible interior connection structure, shape of the exterior contour, and their inter-relationship in a shape image. A novel multiscale region transform (MReT) is proposed to perform region integral over different contour-steered strips at all possible scales to effectively integrate patch features, and thus enables a better description of the shape image in a coarse-to-fine manner. It is applied to solve a challenging problem of classifying cultivars from leaf images, which is a new attempt in both biology and computer vision research communities. A soybean cultivar leaf vein database (SoyCultivarVein), which is the first cultivar leaf vein database, is created and presented for performance evaluation. The experimental results demonstrate the superiority of the proposed method over the state-of-the-art methods in similar shape classification and the possibility of cultivar recognition via leaf pattern analysis, which may lead to a new research interest towards fine-level shape analysis on cultivar classification.

In cognitive radio ad hoc networks (CRAHNs), the secondary users' links are interrupted by the arrival of primary users, which leads to a significant increase of the number of transmissions per packet. Since network coding and opportunistic routing can reduce the number of transmissions over unreliable wireless links, they are more suitable for CRAHNs. Network coding-based opportunistic routing has been well studied in previous works for traditional ad hoc networks. However, existing approaches have limitations to handle CRAHNs. First, the routing decisions of these methods aim to find one optimal forwarding set for the whole path from the source to the destination. If the channel conditions change dynamically, the pre-selected forwarding set may become unavailable or non-optimal. Second, their coding schemes are not efficient enough to cope with the dynamic spectrum variation in CRAHNs. In this paper, we attempt to overcome these limitations and propose a network-coding-based geographic segmented opportunistic routing scheme for CRAHNs, by fully embracing its characteristics. In our scheme, the whole path from the source to the destination is cut down into several smaller opportunistic route segments, where the packets are transmitted through multiple segments based on a step-by-step forwarding procedure until all the packets are delivered to the destination. Since our scheme utilizes only local spectrum opportunities, topology information, and geometric conditions to compute the forwarding set for each short-term opportunistic route segment, it can better adapt to dynamic spectrum environments and changing network topologies in CRAHNs. Furthermore, we construct a coding graph to show that our coding problem is a reduction from the maximum clique problem, and we propose an efficient network coding strategy to solve it. Simulation results show that our scheme can achieve a considerable performance, compared with the latest opportunistic routing protocols designed for CRAHNs.

Classification algorithms have shown exceptional prediction results in the supervised learning area. These classification algorithms are not always efficient when it comes to real-life datasets due to class distributions. As a result, datasets for real-life applications are generally imbalanced. Several methods have been proposed to solve the problem of class imbalance. In this paper, we propose a hybrid method combining the preprocessing techniques and those of ensemble learning. The original training set is undersampled by evaluating the samples by stochastic measurement (SM) and then training these samples selected by Multilayer Perceptron to return a balanced training set. The MLPUS (Multilayer perceptron undersampling) balanced training set is aggregated using the bagging ensemble method. We applied our method to the real-life Niger_Rice dataset and forty-four other imbalanced datasets from the KEEL repository in this study. We also compared our method with six other existing methods in the literature, such as the MLP classifier on the original imbalance dataset, MLPUS, UnderBagging (combining random under-sampling and bagging), RUSBoost, SMOTEBagging (Synthetic Minority Oversampling Technique and bagging), SMOTEBoost. The results show that our method is competitive compared to other methods. The Niger_Rice real-life dataset results are 75.6, 0.73, 0.76, and 0.86, respectively, for accuracy, F-measure, G-mean, and ROC with our proposed method. In contrast, the MLP classifier on the original imbalance Niger_Rice dataset gives results 72.44, 0.82, 0.59, and 0.76 respectively for accuracy, F-measure, G-mean, and ROC.

Abstract This paper presents a new approach for the automatic detection of galaxy morphology from datasets based on an image-retrieval approach. Currently, there are several classification methods proposed to detect galaxy types within an image. However, in some situations, the aim is not only to determine the type of galaxy within the queried image, but also to determine the most similar images for query image. Therefore, this paper proposes an image-retrieval method to detect the type of galaxies within an image and return with the most similar image. The proposed method consists of two stages, in the first stage, a set of features is extracted based on shape, color and texture descriptors, then a binary sine cosine algorithm selects the most relevant features. In the second stage, the similarity between the features of the queried galaxy image and the features of other galaxy images is computed. Our experiments were performed using the EFIGI catalogue, which contains about 5000 galaxies images with different types (edge-on spiral, spiral, elliptical and irregular). We demonstrate that our proposed approach has better performance compared with the particle swarm optimization (PSO) and genetic algorithm (GA) methods.

In this paper, we study the concomitants of dual generalized order statistics (and consequently generalized order statistics) when the parameters γ1,…,γn are assumed to be pairwise different from Huang–Kotz Farlie–Gumble–Morgenstern bivariate distribution. Some useful recurrence relations between single and product moments of concomitants are obtained. Moreover, Shannon’s entropy and the Fisher information number measures are derived. Finally, these measures are extensively studied for some well-known distributions such as exponential, Pareto and power distributions. The main motivation of the study of the concomitants of generalized order statistics (as an important practical kind to order the bivariate data) under this general framework is to enable researchers in different fields of statistics to use some of the important models contained in these generalized order statistics only under this general framework. These extended models are frequently used in the reliability theory, such as the progressive type-II censored order statistics.

Out-of-vocabulary (OOV) words are the most challenging problem in automatic speech recognition (ASR), especially for morphologically rich languages. Most end-to-end speech recognition systems are performed at word and character levels of a language. Amharic is a poorly resourced but morphologically rich language. This paper proposes hybrid connectionist temporal classification with attention end-to-end architecture and a syllabification algorithm for Amharic automatic speech recognition system (AASR) using its phoneme-based subword units. This algorithm helps to insert the epithetic vowel እ[ɨ], which is not included in our Grapheme-to-Phoneme (G2P) conversion algorithm developed using consonant–vowel (CV) representations of Amharic graphemes. The proposed end-to-end model was trained in various Amharic subwords, namely characters, phonemes, character-based subwords, and phoneme-based subwords generated by the byte-pair-encoding (BPE) segmentation algorithm. Experimental results showed that context-dependent phoneme-based subwords tend to result in more accurate speech recognition systems than the character-based, phoneme-based, and character-based subword counterparts. Further improvement was also obtained in proposed phoneme-based subwords with the syllabification algorithm and SpecAugment data augmentation technique. The word error rate (WER) reduction was 18.38% compared to character-based acoustic modeling with the word-based recurrent neural network language modeling (RNNLM) baseline. These phoneme-based subword models are also useful to improve machine and speech translation tasks.

This article studies convolutional neural networks for Tigrinya (also referred to as Tigrigna), which is a family of Semitic languages spoken in Eritrea and northern Ethiopia. Tigrinya is a “low-resource” language and is notable in terms of the absence of comprehensive and free data. Furthermore, it is characterized as one of the most semantically and syntactically complex languages in the world, similar to other Semitic languages. To the best of our knowledge, no previous research has been conducted on the state-of-the-art embedding technique that is shown here. We investigate which word representation methods perform better in terms of learning for single-label text classification problems, which are common when dealing with morphologically rich and complex languages. Manually annotated datasets are used here, where one contains 30,000 Tigrinya news texts from various sources with six categories of “sport”, “agriculture”, “politics”, “religion”, “education”, and “health” and one unannotated corpus that contains more than six million words. In this paper, we explore pretrained word embedding architectures using various convolutional neural networks (CNNs) to predict class labels. We construct a CNN with a continuous bag-of-words (CBOW) method, a CNN with a skip-gram method, and CNNs with and without word2vec and FastText to evaluate Tigrinya news articles. We also compare the CNN results with traditional machine learning models and evaluate the results in terms of the accuracy, precision, recall, and F1 scoring techniques. The CBOW CNN with word2vec achieves the best accuracy with 93.41%, significantly improving the accuracy for Tigrinya news classification.

Wheat is the main food crop today world-wide. In order to improve its yields, researchers are committed to understand the relationships between wheat genotypes and phenotypes. Compared to progressive technology of wheat gene section identification, wheat trait measurement is mostly done manually in a destructive, labor-intensive and time-consuming way. Therefore, this study will be greatly accelerated and promoted if we can automatically discover wheat phenotype in a nondestructive and fast manner. In this paper, we propose a novel pipeline based on 3D morphological processing to detect wheat spike grains and stem nodes from 3D X-ray micro computed tomography (CT) images. We also introduce a set of newly defined 3D phenotypes, including grain aspect ratio, porosity, Grain-to-Grain distance, and grain angle, which are very difficult to be manually measured. The analysis of the associations among these traits would be very helpful for wheat breeding. Experimental results show that our method is able to count grains more accurately than normal human performance. By analyzing the relationships between traits and environment conditions, we find that the Grain-to-Grain distance, aspect ratio and porosity are more likely affected by the genome than environment (only tested temperature and water conditions). We also find that close grains will inhibit grain volume growth and that the aspect ratio 3.5 may be the best for higher yield in wheat breeding.

Memory optimization, energy conservation, over-the-air reprogramming, and fault tolerance are the critical challenges for the proliferation of the wireless sensor network. To address these challenges, a new wireless sensor network platform termed LiveWSN is presented in this article. In LiveWSN, several new design concepts are implemented, such as the hierarchical shared-stack scheduling and the pre-linking native-code reprogramming. By doing so, the data memory cost of the LiveWSN scheduling system can be optimized by 25% if compared with that of the traditional multithreaded MANTIS OS. Moreover, the application reprogramming code size can be decreased by 72.6% if compared with that of the Contiki dynamic-linking reprogramming. In addition to the new design concepts, the new research approach which addresses the energy conservation and fault tolerance challenges by combining the software technique and the multi-core hardware technique is applied in LiveWSN. By means of the multi-core hardware infrastructure, the lifetime of the LiveWSN nodes can be prolonged by 34% if compared with the single-core Live node. Moreover, the fault-tolerant performance of the wireless sensor network node can be optimized significantly. With the above features, LiveWSN becomes memory efficient, energy efficient, reprogrammable, and fault tolerant, and it can run on the high resource-constrained nodes to execute the outdoor real-time wireless sensor network applications.

The differential evolution algorithm (DE) is one of the most powerful stochastic real-parameter optimization algorithms. The theoretical studies on DE have gradually attracted the attention of more and more researchers. However, few theoretical researches have been done to deal with the convergence conditions for DE. In this paper, a sufficient condition and a corollary for the convergence of DE to the global optima are derived by using the infinite product. A DE algorithm framework satisfying the convergence conditions is then established. It is also proved that the two common mutation operators satisfy the algorithm framework. Numerical experiments are conducted on two parts. One aims to visualize the process that five convergent DE based on the classical DE algorithms escape from a local optimal set on two low dimensional functions. The other tests the performance of a modified DE algorithm inspired of the convergent algorithm framework on the benchmarks of the CEC2005.

Video target tracking is a critical problem in the field of computer vision. Particle filters have been proven to be very useful in target tracking for nonlinear and non-Gaussian estimation problems. Although most existing algorithms are able to track targets well in controlled environments, it is often difficult to achieve automated and robust tracking of pedestrians in video sequences if there are various changes in target appearance or surrounding illumination. To surmount these difficulties, this paper presents multitarget tracking of pedestrians in video sequences based on particle filters. In order to improve the efficiency and accuracy of the detection, the algorithm firstly obtains target regions in training frames by combining the methods of background subtraction and Histogram of Oriented Gradient (HOG) and then establishes discriminative appearance model by generating patches and constructing codebooks using superpixel and Local Binary Pattern (LBP) features in those target regions. During the process of tracking, the algorithm uses the similarity between candidates and codebooks as observation likelihood function and processes severe occlusion condition to prevent drift and loss phenomenon caused by target occlusion. Experimental results demonstrate that our algorithm improves the tracking performance in complicated real scenarios.