In this paper, a novel infrared maritime small target detection method, called local dissimilarity measure with anti interference based on global graph clustering (LDMGGC), is proposed. The Wasserstein distance introduced to calculate the of gray level distribution between central region and its neighborhoods. These dissimilarities construct feature region. With feature, for recalling all suspected targets achieved. As interferences among are able be clustered, relaxing mutual k nearest...

Synthetic aperture radar (SAR) plays a crucial role in maritime surveillance due to its capability for all-weather, all-day operation. However, SAR ship recognition faces challenges, primarily the imbalance and inadequacy of samples publicly available datasets, along with presence numerous outliers. To address these issues, this paper proposes classification method based on text-generated images tackle dataset imbalance. Firstly, an image generation module is introduced augment data. This...

The filterbank multicarrier (FBMC) waveform has better properties in spectral as compared to the Orthogonal Frequency Division Multiplexing (OFDM) and it exhibits good anti-interference performance. We mainly consider an important variety of FBMC systems, namely based on offset orthogonal amplitude modulation (FBMC/OQAM). This letter presents analysis residual Doppler effect multipath underwater acoustic (UWA) channel for FBMC/OQAM system. Assuming received signal gone through coarse...

Abstract Evolution of cellular networks into dynamic, dense, and heterogeneous have introduced new challenges for cell resource optimization, especially in the imbalanced traffic load regions. Numerous balancing schemes been proposed to tackle this issue; however, they operate a reactive manner that confines their ability meet top‐notch quality experience demands. To address challenge, we propose novel proactive scheme. Our framework learns users' mobility demands statistics jointly...

Visual surveys and DNA analysis hold primary importance in marine mammal observation. Especially, recognition of whales their population density estimation rely heavily on these costly tedious methods. Acoustic survey vocalizing cetaceans, contrast, is emerging as a promising technique for efficient, automatic, non-invasive convenient observation such vocally active organisms. However, it is, yet, too premature to replace the conventional methods altogether. In this paper, we have presented...

This paper presents an unsupervised approach for crack detection in underwater concrete structures. It is based on local feature clustering using K-Medians Haralick texture features. An additional step outliers removal introduced, a bimodal Gaussian distribution candidate blocks. has been successfully tested dataset of 490 images, with quantitative results produced subset 40 random images the dataset.

Traditional road maintenance methods are costly; requiring expensive equipment and manpower. Road quality categorization based on machine learning techniques, using real-time opportunistic data gathered from inexpensive open-source inertial systems, is a promising alternative. Existing datasets for this problem small less representative of actual situation where imbalanced skewed towards regular surface instances. With the help an device collection platform developed by our lab, we have...

Whistle classification plays an essential role in studying the habitat and social behaviours of cetaceans. We obtained six categories sweep whistles two Tursiops aduncus individual signals using passive acoustic mornitoring technique over a period eight months Xiamen area. First, we propose depthwise separable convolutional neural network for whistle classification. The proposed model adopts convolution combined with followed point-by-point instead conventional convolution. As result, it...

This paper attempts to improve real-time detection of Roadway Surface Disruptions (RSDs) while pointing out the limitations imposed on this application owing hardware and data acquisition constraints. We have developed publicly shared a large amount heterogeneous set collected over continuous drive for four different kinds road anomalies -- Cat eyes, Potholes, Manholes Speed Bumps, along with regular road, using custom-made, dedicated device logging, recording vehicle acceleration GPS...

Underwater acoustic communication plays an essential role in underwater wireless information exchange, and nodes with such ability constitute sensor network (UASN). However, UASNs face many challenges, as high bit error rate propagation delay, significantly reducing performance. Because of the challenging nature environments, power consumption battery energy efficiency need to be considered. Directional technology can conserve by restraining beam directivity diminishing interference between...

Cetacean surveys are important for species' population assessments in ecological projects. Acoustics, this context, provides an efficient, automatic, non-invasive and convenient way to study observe vocally active cetaceans. Development of a reliable unbiased acoustic survey method can be good replacement conventional tools like line- transect method. However, realization goal is yet far from reality. Motivated by recent advancements acoustics computational methods, we propose automatic...

Darcy flow is a steady-state model for laminar of fluid through porous medium. The present work proposes an extended by introducing dynamic pressure and velocity to the classical formulation. solution proposed time-space attained discretizing problem with stabilized mixed Galerkin method in space forward Euler time. resulting matrix equation well-posed solved using conjugate gradient (CG) method. error analysis numerical solutions confirms convergence actual model.

This paper presents design and development of a low-cost Autonomous Underwater Vehicle (AUV). The main application domain is the exploration irrigation canals in Pakistan. underwater vehicle designed to work instead human beings because there are some areas that difficult reach for humans it can be very costly time-consuming activity. Human performances tasks also limited. Thus, dedicated tool or device such as AUV presented this required helping perform these tasks.

Electrical impedance tomography (EIT) is a noninvasive medical imaging technique in which small current applied to the electrodes attached surface of subject body and cross-sectional image resistivity (or conductivity) distribution inside reconstructed using an inverse algorithm. Due ill-posed nature EIT problem, bears poor spatial resolution behaves non-linearly nature. Point spread function (PSF), calculated over whole domain as responses circular anomaly moving around entire domain,...

Baleen whales produce a wide variety of frequency-modulated calls. Extraction the time–frequency (TF) structures these calls forms basis for many applications, including abundance estimation and species recognition. Typical methods to extract contours whale from spectrogram are based on short-time Fourier transform are, thus, restricted by fixed TF resolution. Considering low-frequency nature baleen calls, this work represents using pseudo-Wigner–Ville distribution higher resolution at cost...

The natural flows through porous media often exhibit transient behavior. Some of the examples include water movement in aquifers, oil flow reservoirs and blood passing arteries walls. For accurate modeling such flows, Darcy model is used with an additional time-dependent pressure term. In this paper, validation three-dimensional numerical solution using stabilized mixed finite element method presented. proposed employs implicit backward difference for discretization time, whereas, space...