Tree Complex Research Articles

SAR ship target detection method based on CNN structure with wavelet and attention mechanism.

Ship target detection in synthetic aperture radar (SAR) images is an important application field. Due to the existence of sea clutter, especially the SAR imaging in huge wave area, SAR images contain a lot of complex noise, which brings great challenges to the effective detection of ship targets in SAR images. Although the deep semantic segmentation network has been widely used in the detection of ship targets in recent years, the global information of the image cannot be fully utilized. To solve this problem, a new convolutional neural network (CNN) method based on wavelet and attention mechanism was proposed in this paper, called the WA-CNN algorithm. The new method uses the U-Net structure to construct the network, which not only effectively reduces the depth of the network structure, but also significantly improves the complexity of the network. The basic network of WA-CNN algorithm consists of encoder and decoder. Dual tree complex wavelet transform (DTCWT) is introduced into the pooling layer of the encoder to smooth the speckle noise in SAR images, which is beneficial to preserve the contour structure and detail information of the target in the feature image. The attention mechanism theory is added into the decoder to obtain the global information of the ship target. Two public SAR image datasets were used to verify the proposed method, and good experimental results were obtained. This shows that the method proposed in this article is effective and feasible.

Complex Wavelets and SPIHTL for Edge Feature Enhancement and Optimum Feature Selection with Deep Learning Algorithm for Video Salient Object Detection

Cognitive property of the human visual system to detect salient objects in image and video sequences to correlate with neighbouring objects for information retrieval and understanding is developed for computer vision application. Detecting salient objects with accurate boundaries and features is addressed in this work by using the directional selectivity property of complex wavelets. Computation complexity of processing complex wavelet sub band is addressed by companding the features into eight sub bands and optimum number of features are selected using SPIHTL (Set Partition In Hierarchical Trees List) algorithm. Five layered deep learning algorithm is designed with 2D FFNN ( Feed Forward Neural Network) structure and reordering units to detect salient object features. The 3D DTCWT (Dual Tree Complex Wavelet Transform) model combined with 2D SPIHTL encoder and deep learning algorithm is modelled in MATLAB and is trained to identify 120 objects with PSNR (Peak Signal To Noise Ration) of 40dB. The designed model is demonstrated to detect generic objects. Keywords: Video saliency, DTCWT, Directional Features, SPIHTL, Deep Learning, 2D Neural Network

Auto-encoder and bidirectional long short-term memory based automated arrhythmia classification for ECG signal

In this manuscript, the combination of Auto- Encoder and Bidirectional long short-term memory (AE-biLSTM) for automated arrhythmia classification is proposed to automatically classify the six kinds of Electrocardiogram (ECG) signals with low cost. Initially, the input Electrocardiogram signals are pre-processed by Dual tree complex wavelet transform (DTCWT) for removing the baseline. The pre-processed ECG signals are given to the combined network of AE-biLSTM. The proposed AE-biLSTM method contains an encoder that extracts higher level feature from the Electro cardiogram arrhythmias signals using bidirectional long short- term memory (biLSTM) network, then a decoder output reconstruct Electro cardiogram arrhythmias signals from higher level features using biLSTM network. Finally, the proposed method accurately classifies the 6 heartbeats types, such as normal (N) sinus beat, atrial fibrillation (AFIB), ventricular bigeminy (B), pacing beat (P), atrial flutter (AFL), sinus brady cardia (SBR). The simulating process is activated in MATLAB. Lastly, the AE-biLSTM method utilize 2 extra databases: (i) new N beat (ii) AFIB beat, which is self-determining of the network’s training database. The proposed model attains the better performance of 97.15 % accuracy, 98.33% positive predictive value, 99.43% sensitivity, 96.22% specificity compared to the existing methods, such as Automated arrhythmia classification based convolutional neural networks with long short-term memory networks (CNN-LSTM), and automated arrhythmia classification based deep code features with long short-term memory networks (DCF-LSTM) respectively.

An effective detection of COVID-19 using adaptive dual-stage horse herd bidirectional long short-term memory framework.

COVID‐19 is a quickly increasing severe viral disease that affects the human beings as well as animals. The increasing amount of infection and death due to COVID‐19 needs timely detection. This work presented an innovative deep learning methodology for the prediction of COVID‐19 patients with chest x‐ray images. Chest x‐ray is the most effective imaging technique for predicting the lung associated diseases. An effective approach with adaptive dual‐stage horse herd bidirectional LSTM model is presented for the classification of images into normal, lung opacity, viral pneumonia, and COVID‐19. Initially, the input images are preprocessed using modified histogram equalization approach. This is utilized to improve the contrast of the images by changing low‐resolution images into high‐resolution images. Subsequently, an extended dual tree complex wavelet with trigonometric transform is introduced to extract the high‐density features to decrease the complexity of features. Moreover, the dimensionality of the features reduced by adaptive beetle antennae search optimization is utilized. This approach enhances the performance of disease classification by reducing the computational complexity. Finally, an adaptive dual‐stage horse herd bidirectional LSTM model is utilized for the classification of images into normal, viral pneumonia, lung opacity, and COVID‐19. The implementation platform used in the work is PYTHON. The performance of the presented approach is proved by comparing with the existing approaches in accuracy (99.07%), sensitivity (97.6%), F‐measure (97.1%), specificity (99.36%), kappa coefficient (97.7%), precision (98.56%), and area under the receiver operating characteristic curve (99%) for COVID‐19 chest x‐ray database.

Robust audio watermarking scheme based on fractional Charlier moment transform and dual tree complex wavelet transform

The popular embedded watermarking method in transform domains such as DWT, LWT, DCT, and SVD achieves copyright protection of audio signals by embedding watermarks into the original audio signals. The main weaknesses of the existing methods include low payload and low robustness against common audio processing operations and attacks, especially, vulnerability to shifting attack. This paper proposes a new robust, secure, and blind audio watermarking scheme based on a novel hybrid transform which is a combination of the dual tree complex wavelet transform (DTCWT) and the fractional Charlier moment transform (FrCMT). After segmenting the original audio signal into several segments of the same length, the 3-level DTCWT is applied on each segment using filters designed specifically to have shift invariance, then FrCMT is applied on the approximation coefficients of DTCWT. Finally, a sequence of watermark bits is embedded in FrCMT coefficients by quantizing their relative energy. The fractional order in FrCMT is chosen in our scheme in a way to obtain high imperceptibility and robustness against most common audio processing operations and attacks. Moreover, it is used as a security key to ensure a high security level of the proposed scheme. The comparative analysis confirms the high robustness, security, and efficiency of the proposed watermarking method.

Postnatal development of projections of the postrhinal cortex to the entorhinal cortex in the rat.

The ability to encode and retrieve contextual information is an inherent feature of episodic memory that starts to develop during childhood. The postrhinal cortex (POR), an area of the parahippocampal region (PHR), has a crucial role in encoding object-space information and translating egocentric to allocentric representation of local space. The strong connectivity of POR with the adjacent entorhinal cortex (EC), and consequently the hippocampus, suggests that the development of these connections could support the postnatal development of contextual memory. Here, we report that POR projections of the rat develop progressively from the first to the third postnatal week starting in the medial EC (MEC) before spreading to the lateral EC (LEC). The increased spread and complexity of postrhinal axonal distributions is accompanied by an increased complexity of entorhinal dendritic trees and an increase of postrhinal-entorhinal synapses, which supports a gradual maturation in functional activity.

Using Machine Learning to Identify the Optimal Limb Symmetry Index Cut-Off Threshold in Paediatric Patients with ACL Injury

Background:The risk for a subsequent ACL injury following a primary paediatric ACL reconstruction is extremely high, with 17-30% of paediatric patients sustaining a second ACL injury within two years. It is possible that this risk is associated with a lack of evidence for identifying return-to-activity (RTA) measures to guide postoperative decision-making. Limb symmetry indices (LSI) derived from functional and strength tasks are commonly used, however LSIs used by paediatric orthopaedic surgeons can range from 75-95%, with no objective evidence to support these values.Purpose:To create knowledge that could be used to inform RTA and to determine if a machine learning approach could objectively identify LSI thresholds from functional tasks that classify paediatric individuals as injured or healthy.Methods:Forty-two patients (30 females) who had suffered an ACL injury (ACLi) and 69 matched uninjured controls (36 females; CON) performed isometric knee extension and flexion, and single-leg hopping tasks. LSIs were calculated as injured/uninjured limb for ACLi and non-dominant/dominant limb for CON. LSIs with significant between-group (ACLi vs CON) differences (independent t-tests), were used in a machine learning algorithm. A classification tree (CT) was used to classify ACLi and CON participants using LSI percentages. Ten-fold cross-validation was used to determine optimal tree complexity. LSIs were then converted from percentage to categorical ‘pass/fail’ grades according to cut-off thresholds ranging from 70-100%. CTs were then fit to the converted categorical data at each cut-off threshold and the model accuracies were compared.Results:Anterior, lateral, triple, and timed 6m hop tasks, and knee extension strength LSIs were used in the machine learning algorithm. The CT using the raw LSI percentages correctly classified 85.9% of participants. When data were converted from percentage to categorical ‘pass/fail’ grades, a plateau in classification accuracy occurred between LSIs cut-off thresholds of ˜83-90%. The most accurate LSI cut-off threshold was 89%, which correctly classified 84.4% of participants.Conclusion:Based on our preliminary analysis, the 90% LSI cut-off is an appropriate threshold for separating the hopping and strength performance of ACLi and CON paediatric participants. It is nevertheless important to recognize that this threshold can identify those with ACL injury, and not those who are ready for return to activity. A 90% LSI is therefore only a minimum criterion to reach as part of an RTA evaluation, and not a threshold that identifies when an individual is ready to return.

An Adaptive Gradient Boosting Model for the Prediction of Rainfall Using ID3 as a Base Estimator

While analyzing the data, it is crucial to choose the model that best matches the circumstance. Many experts in the field of classification and regression have proposed ensemble strategies for tabular data, as well as various approaches to classification and regression problems. In this paper, Gini Index is applied on raw geographical dataset to convert continuous data into discrete dataset. Decision tree algorithm is implemented on resultant discrete dataset, Information Gain is calculated for every attribute and the attribute with highest information gain is the splitting node, applied recursively. Decision tree algorithm implemented predicts the rainfall in Kashmir province with the accuracy of 81.5%. MDL pruning is applied on the resultant decision tree in order to reduce the size & complexity of the Decision tree. Pruning removes segments of the tree that contribute little towards classification; the accuracy is marginally reduced to 81.1%. Furthermore, after the implementation of Decision tree a boosting algorithm: gradient boosting has been implemented on the same set of data using decision tree as a base estimator. It was observed that the overall accuracy of the decision tree got increased to 87.5% after the implementation of gradient boosting model. Thus, the obtained results predict that gradient boosted-DT outperforms all other approaches with the highest accuracy measure and high susceptibility rate in rainfall prediction.

Classification of biological signals and time domain feature extraction using capsule optimized auto encoder‐electroencephalographic and electromyography

AbstractElectroencephalographic (EEG) and electromyography (EMG) signal classification seem to be a modulus topic in engineering and the medical field. The nature of the EEG and EMG signal is non‐stationary, noisy and high dimensional. The intrusion of noise in the signal may distress movement recognition. A novel methodology is being developed in this research to deal with these issues. Here, the EEG and EMG signals are recorded using the BCI2000 system. The proposed model comprises three phases: pre‐processing, feature extraction (FE), and motion classification. The pre‐processing method can be used to enhance visual appearances and the quality of the signal. The hybrid discrete wavelet based delayed error normalized least mean square error (DWT‐DENLMS) is introduced to eliminate the presence of motion artifacts in the recorded EEG and EMG signal. After pre‐processing, the recorded signals are combined and forwarded to the FE stage. The hybrid Dual tree complex wavelet transforms based on Walsh Hadamard transform (DTCWT‐WHT) is proposed to extract the indispensable time domain features from the combined biological signal. The hybrid capsule transient autoencoder (HCTAE) algorithm is proposed to classify the motion recognition (T0‐rest, T1‐left fist and both fists, and T2‐right fist, both feet). The error in the network model is diminished by transient search optimization (TSO) strategy. The Python platform is used to implement the developed approach, and the performance of the optimized classification approach yields accuracy, precision, recall, F1 score and specificity of 98.51%, 97.25%, 97.94%, 97.58% and 98.94%, respectively.

A novel Watermarking Technique Based on Hybrid Transforms

This paper proposed Anovel watermarking scheme using hybrid of Dual Tree Complex Wavelet Transform and singular value decomposition . Image watermarking is to embed copyright data in image bit streams. Our proposed technique demonestrates the effective and robust of image watermarking algorithms using a hybrid of two strong mathematical transforms; the 2-level Dual Tree Complex Wavelet Transform (DT-CWT) and Singular Value Decomposition (SVD). This technique shows high level of security and robustness against attacks. The algorithm was tested for imperceptibility and robustness and the results were compared with DWT-SVD-based technique, it is shown that the proposed watermarking schemes is considerably more robust and effective.

Measuring tree complexity with response times

Game-theoretic trees vary in complexity. This paper introduces the concept of graph-based complexity and relies on the subjects’ behavior to empirically derive a measure of tree complexity. Data comes from the mobile app Blues and Reds, designed specifically to conduct experiments. The sample consists of 6637 subjects from 143 countries who play 27 different dynamic games. Based on subjects’ response times, we find that two measures – the average response time spent at the first round and the average total time spent solving the tree – are the best candidates for the empirical measure of tree complexity. We focus on two-person, finite, zero-sum dynamic games with perfect and complete information.

Common Microscale and Macroscale Principles of Connectivity in the Human Brain.

The brain requires efficient information transfer between neurons and large-scale brain regions. Brain connectivity follows predictable organizational principles. At the cellular level, larger supragranular pyramidal neurons have larger, more branched dendritic trees, more synapses, and perform more complex computations; at the macroscale, region-to-region connections display a diverse architecture with highly connected hub areas facilitating complex information integration and computation. Here, we explore the hypothesis that the branching structure of large-scale region-to-region connectivity follows similar organizational principles as the neuronal scale. We examine microscale connectivity of basal dendritic trees of supragranular pyramidal neurons (300+) across 10 cortical areas in five human donor brains (1 male, 4 female). Dendritic complexity was quantified as the number of branch points, tree length, spine count, spine density, and overall branching complexity. High-resolution diffusion-weighted MRI was used to construct white matter trees of corticocortical wiring. Examining complexity of the resulting white matter trees using the same measures as for dendritic trees shows heteromodal association areas to have larger, more complex white matter trees than primary areas (p < 0.0001) and macroscale complexity to run in parallel with microscale measures, in terms of number of inputs (r = 0.677, p = 0.032), branch points (r = 0.797, p = 0.006), tree length (r = 0.664, p = 0.036), and branching complexity (r = 0.724, p = 0.018). Our findings support the integrative theory that brain connectivity follows similar principles of connectivity at neuronal and macroscale levels and provide a framework to study connectivity changes in brain conditions at multiple levels of organization.SIGNIFICANCE STATEMENT Within the human brain, cortical areas are involved in a wide range of processes, requiring different levels of information integration and local computation. At the cellular level, these regional differences reflect a predictable organizational principle with larger, more complexly branched supragranular pyramidal neurons in higher order regions. We hypothesized that the 3D branching structure of macroscale corticocortical connections follows the same organizational principles as the cellular scale. Comparing branching complexity of dendritic trees of supragranular pyramidal neurons and of MRI-based regional white matter trees of macroscale connectivity, we show that macroscale branching complexity is larger in higher order areas and that microscale and macroscale complexity go hand in hand. Our findings contribute to a multiscale integrative theory of brain connectivity.

Applying a Portable Backpack Lidar to Measure and Locate Trees in a Nature Forest Plot: Accuracy and Error Analyses

Accurate tree positioning and measurement of structural parameters are the basis of forest inventory and mapping, which are important for forest biomass calculation and community dynamics analyses. Portable backpack lidar that integrates the simultaneous localization and mapping (SLAM) technique with a global navigation satellite system receiver has greater flexibility for tree inventory than terrestrial laser scanning, but it has never been used to measure and map forest structure in a large area (&gt;101 hectares) with high tree density. In the present study, we used the LiBackpack DG50 backpack lidar system to obtain the point cloud data of a 10 ha plot of subtropical evergreen broadleaved forest, and applied these data to quantify errors and related factors in the diameter at breast height (DBH) measurements and positioning for more than 1900 individual trees. We found an average error of 4.19 cm in the DBH measurements obtained by lidar, compared with manual field measurements. The incompleteness of the tree stem point clouds was the main factor that caused the DBH measurement errors, and the field DBH measurements and density of the point clouds also had significant impacts. The average tree positioning error was 4.64 m, and it was significantly affected by the distance and route length from the measured trees to the data acquisition start position, whereas it was affected little by the habitat complexity and characteristics of tree stems. The tree positioning measurement error led to increases in the mean value and variability of paired-tree distance error as the sample plot scale increased. We corrected the errors based on the estimates of predictive models. After correction, the DBH measurement error decreased by 31.3%, the tree positioning error decreased by 44.3%, and the paired-tree distance error decreased by 56.3%. As the sample plot scale increased, the accumulated paired-tree distance error stabilized gradually.

Rigidity of the tree complex

In this note, we show that the complex of trees introduced by Belk-Lanier-Margalit-Winarski is isomorphically rigid.

Exploring the Potential of Mobile Laser Scanning to Quantify Forest Structural Complexity

Today, creating or maintaining forest structural complexity is a management paradigm in many countries due to the positive relationships between structural complexity and several forest functions and services. In this study, we tested whether the box-dimension (Db), a holistic and objective measure to describe the structural complexity of trees or forests, can be used to quantify the structural complexity of 14 European beech (Fagus sylvatica L.) dominated forest plots by means of mobile laser scanning (MLS). The goal of this study was to explore the potential of this approach for quantifying the effect of leaves (summer vs winter) and management (lately unmanaged vs managed) on forest structural complexity. The findings suggest that repeated measurements on the same site and at the same time yielded consistent results if the measuring scheme is standardized. The results also showed that standardized measurement protocols allowed quantifying differences in forest structural complexity due to season. The highest stand structural complexity was found in leaf-on condition during summer, with the complexity being significantly higher than in winter condition. Also, in case of our beech-dominated plots, managed forests were more complex in structure than formerly managed but now unmanaged forests. This study illustrates the potential of MLS for monitoring the changes in forest structural complexity and allows correcting stand structural information for seasonality.

IMAGE FUSION WITH CT AND MRI IMAGES FOR IMPROVING QUALITY OF DIAGNOSTICS

-Fusing several medical images will enhance sickness diagnosis and demonstrate the complicated relationship between them for medical research. Existing techniques are time consuming and require a higher amount of data to train the models.We will obtain complex information from medical pictures such as Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) in this model by fusing them using multi-stage fusion networks. We will utilise the Dual Tree Complex Wavelet Transform (DTCWT) to extract the challenging and related information from each image, and then divide the segmentation to get the segmented picture. The suggested technique uses the Dual Tree Complex Wavelet Transform to integrate several sample medical images, with the source medical image being converted to grayscale and degraded before the wavelet coefficients are produced using the DTCWT.The fused coefficients are then produced using wavelet approximation. The Inverse Dual Tree Complex Wavelet Transform is employed to develop the final fused picture. Segmentation is often used to create a segmented picture for better visual representation. The suggested technology has the potential to provide a higher quality final fused image.

Virtual reality technology in the processing of biological images of maxillary protrusion

It was to investigate the application of implant anchorage in the treatment of adolescent maxillary protrusion. Based on virtual reality (VR) technology, a three-dimensional digital model was constructed, and the dual tree complex wavelet transform (DT-CWT) compression sensing algorithm was added in the imaging. An isolated tooth with complete crown and root was taken, 360 full-range photos were taken, and the photos were imported into VR Worx system. Sixty adolescent patients with maxillary protrusion were randomly divided into groups A, B, and C, with 20 cases in each group. In group A, an external arch anchorage was used to slide the anterior teeth. Implant anchorage was used to slide the upper anterior teeth in groups B and C. Patients in group C were familiar with the surgical procedure using a three-dimensional digital model before surgery. After using digital camera and VR Worx software model reconstruction, three groups of patients had good occlusion after correction, but there were differences in anterior and posterior tooth movement control, maxillary occlusal plane, and mandibular plane angle. The treatment time of groups B and C was significantly shorter than that of group A, and the treatment time of group B was slightly shorter than that of group C, the difference was statistically significant (P < 0.05). In summary, the DT-CWT compression sensing algorithm can improve the quality of biological images, and utilize VR technology to build a three-dimensional digital model of teeth, which can improve the therapeutic effect.

Using Artificial Intelligence to Assist Tree Risk Assessment

Although the industry has raised the standards of tree risk assessment considerably in recent years, the quality of judgements is still very variable and influenced by a wide range of factors. Due to the complexity and diversity of trees and sites, collecting and verifying relevant personal experiences takes tree assessors many years. In many countries, new tree assessors learn from a small number of experienced peers. Artificial intelligence (AI) can be used to collect and condense scattered knowledge and deploy it in a support tool for basic tree assessment. In this project, the application of a commercial AI decision-making system software (Dylogos) to tree assessment is tested. The software is based on a new dynamic nonclassical logic, which combines diverse knowledge sources to an emergent system to support visual tree assessments. A set of rules describes existing knowledge about the mostly unsharp parameters affecting the likelihood of failure and damage. The software evaluates the data collected during a basic tree assessment and provides an estimate of the level of risk posed by the tree. The result and the reasons for it are presented in plain language. Users can then examine this estimate and feed their own assessment back into the system to train it further, so that this “white” AI system is self-learning based on experience acquired in practical use. The use of AI in tree risk assessment not only supports the user but can also be used to disseminate knowledge and promote the standardization of decision-making in tree assessment. Important directions for further research and knowledge gaps related to the training of AI systems in the absence of industry-wide, agreed-upon criteria for risk identified in this project are: how to collect sufficient quality-assured data sets to define the initial set of rules; and how to assess the level of expertise of users training the system further.

Optimized hybrid machine learning approach for smartphone based diabetic retinopathy detection.

Diabetic Retinopathy (DR) is defined as the Diabetes Mellitus difficulty that harms the blood vessels in the retina. It is also known as a silent disease and cause mild vision issues or no symptoms. In order to enhance the chances of effective treatment, yearly eye tests are vital for premature discovery. Hence, it uses fundus cameras for capturing retinal images, but due to its size and cost, it is a troublesome for extensive screening. Therefore, the smartphones are utilized for scheming low-power, small-sized, and reasonable retinal imaging schemes to activate automated DR detection and DR screening. In this article, the new DIY (do it yourself) smartphone enabled camera is used for smartphone based DR detection. Initially, the preprocessing like green channel transformation and CLAHE (Contrast Limited Adaptive Histogram Equalization) are performed. Further, the segmentation process starts with optic disc segmentation by WT (watershed transform) and abnormality segmentation (Exudates, microaneurysms, haemorrhages, and IRMA) by Triplet half band filter bank (THFB). Then the different features are extracted by Haralick and ADTCWT (Anisotropic Dual Tree Complex Wavelet Transform) methods. Using life choice-based optimizer (LCBO) algorithm, the optimal features are chosen from the mined features. Then the selected features are applied to the optimized hybrid ML (machine learning) classifier with the combination of NN and DCNN (Deep Convolutional Neural Network) in which the SSD (Social Ski-Driver) is utilized for the best weight values of hybrid classifier to categorize the severity level as mild DR, severe DR, normal, moderate DR, and Proliferative DR. The proposed work is simulated in python environment and to test the efficiency of the proposed scheme the datasets like APTOS-2019-Blindness-Detection, and EyePacs are used. The model has been evaluated using different performance metrics. The simulation results verified that the suggested scheme is provides well accuracy for each dataset than other current approaches.

Bidirectional RNN based early prediction of CVDs using ECG Signals for Type 2 diabetic patients

The ECG signal is important for early diagnosis of heart abnormalities. Type 2 Diabetic individuals’ ECG signals provide pertinent data about their hearts and are one of the most important diagnostic techniques used by doctors to identify cardiovascular diseases. The suggested study uses feature extraction and Bi-RNN based classification to analyse ECG signals of Type 2 patients. To reduce noise from the ECG signal, a hybrid preprocessing filter made up of a Median and Savitzky-Golay filter. Undecimated dual tree complex wavelet transform (UDTCWT) along with Detrended fluctuation (DA) analysis and empirical orthogonal function (EOF) analysis are then used to extract features. These features are classified with Bidirectional RNN. The proposed method was tested on the MIT-BIH, Physionet and DICARDIA databases, and the findings show that it achieves an average accuracy of 97.6% when compared to conventional techniques.