Adaptive Equalization Research Articles

ConjunctiveNet: an improved deep learning-based conjunctive-eyes segmentation and severity detection model

PurposeThe study aims to enhance the detection and classification of conjunctival eye diseases' severity through the development of ConjunctiveNet, an innovative deep learning framework. This model incorporates advanced preprocessing techniques and utilizes a modified Otsu’s method for improved image segmentation, aiming to improve diagnostic accuracy and efficiency in healthcare settings.Design/methodology/approachConjunctiveNet employs a convolutional neural network (CNN) enhanced through transfer learning. The methodology integrates rescaling, normalization, Gaussian blur filtering and contrast-limited adaptive histogram equalization (CLAHE) for preprocessing. The segmentation employs a novel modified Otsu’s method. The framework’s effectiveness is compared against five pretrained CNN architectures including AlexNet, ResNet-50, ResNet-152, VGG-19 and DenseNet-201.FindingsThe study finds that ConjunctiveNet significantly outperforms existing models in accuracy for detecting various severity stages of conjunctival eye conditions. The model demonstrated superior performance in classifying four distinct severity stages – initial, moderate, high, severe and a healthy stage – offering a reliable tool for enhancing screening and diagnosis processes in ophthalmology.Originality/valueConjunctiveNet represents a significant advancement in the automated diagnosis of eye diseases, particularly conjunctivitis. Its originality lies in the integration of modified Otsu’s method for segmentation and its comprehensive preprocessing approach, which collectively enhance its diagnostic capabilities. This framework offers substantial value to the field by improving the accuracy and efficiency of conjunctival disease severity classification, thus aiding in better healthcare delivery.

DNIM: Deep-sea netting intelligent enhancement and exposure monitoring using bio-vision

Intelligent monitoring of deep-sea nets is affected by light attenuation, light scattering, and limited dynamic range factors of the camera, which can cause color shift, low visibility, and over/underexposure in monitoring, resulting in reduced farming efficiency, and misdetection of biological behavior. Therefore, we propose a method for underwater net tank scene enhancement and exposure using multicolor space and bio-vision, called DNIM. Specifically, we first propose an intelligent enhancement and exposure monitoring method for deep-sea nets using bio-vision, which eliminates the effect of exposure on underwater imaging by introducing a bio-vision system that uses a brightness transformation function to generate a series of exposure images. Inspired by the image fusion method, we designed a color correction and visibility recovery method using bio-vision. In the Lab color model, color shifts in bio-vision are corrected by guiding feature transformations with contrast-constrained adaptive histogram equalization; in the RGB color model, depth information is recovered by creating a linear model for the depth of field of underwater blurred images based on the characteristics of the bio-vision system. To obtain more qualified results, we also propose an efficient perceptual fusion module to mix the output of visibility recovery and color correction. Finally, we propose two deep-sea net tank culture datasets: salmon bait-eating behavior dataset (SBBD) and salmon non-bait-eating behavior dataset (SNBD). By comparing the experimental analysis in four real scenario datasets, our DNIM achieved superior results compared to 16 advanced underwater enhancement methods. The code is publicly available at: https://github.com/An-Shunmin/DNIM.

Allergy Wheal and Erythema Segmentation Using Attention U-Net.

The skin prick test (SPT) is a key tool for identifying sensitized allergens associated with immunoglobulin E-mediated allergic diseases such as asthma, allergic rhinitis, atopic dermatitis, urticaria, angioedema, and anaphylaxis. However, the SPT is labor-intensive and time-consuming due to the necessity of measuring the sizes of the erythema and wheals induced by allergens on the skin. In this study, we used an image preprocessing method and a deep learning model to segment wheals and erythema in SPT images captured by a smartphone camera. Subsequently, we assessed the deep learning model's performance by comparing the results with ground-truth data. Using contrast-limited adaptive histogram equalization (CLAHE), an image preprocessing technique designed to enhance image contrast, we augmented the chromatic contrast in 46 SPT images from 33 participants. We established a deep learning model for wheal and erythema segmentation using 144 and 150 training datasets, respectively. The wheal segmentation model achieved an accuracy of 0.9985, a sensitivity of 0.5621, a specificity of 0.9995, and a Dice similarity coefficient of 0.7079, whereas the erythema segmentation model achieved an accuracy of 0.9660, a sensitivity of 0.5787, a specificity of 0.97977, and a Dice similarity coefficient of 0.6636. The use of image preprocessing and deep learning technology in SPT is expected to have a significant positive impact on medical practice by ensuring the accurate segmentation of wheals and erythema, producing consistent evaluation results, and simplifying diagnostic processes.

Strong Single Frequency Jamming Detection Method based on Adaptive Equalization Coefficients

Abstract Serious jamming effect on the communication signal maybe comes from the result of single-frequency jamming which could concentrate energy applying into the transmitted spectra. Usually, the communication signal is covered by the jamming effect. In order to effectively detect the existence of single frequency interference signal or not, the paper presents a frequency domain abnormal phenomena detection method based on adaptive equalization coefficients. The proposed method directly transforms the calculated equalization coefficients into the frequency domain. Then, the existence of strong single-frequency interference signals can be directly detected online by observing the characteristics of the frequency domain. The simulation results show that this method has a good detection effect on strong single frequency jamming. The research shows that the mentioned detection method and the related anomaly recognition technology based on equalization coefficients can be used for jamming detection, and can provide a new technical approach for jamming detection.

Iridology based human health conditions predictions with computer vision and deep learning

In today’s world, ocular diseases have become widespread. The “ocular illness” refers to any abnormality, impairment, or dysfunction of vision that impacts the eye. The most common forms of ocular disease include dry eyes, conjunctivitis, blepharitis, and glaucoma. Each of these conditions can cause redness, pain, and blurry vision. To resolve the challenges in human ocular diseases, the need for detection becomes an important part of every person’s life. There are numerous approaches by various researchers to detect and predict the disease early, but the previous approaches required certain improvements to predict the ocular disease more accurately and easily. In the proposed method, deep learning-based ocular disease prediction with high accuracy and low cost is implemented. The framework deals with the collection of data from the diabetes-iridology dataset and pre-processing using the Contrast limited adaptive histogram equalization (CLAHE). The Attenuation-based U-net is the most advanced proposed method used for the segmentation of ocular disease with higher accuracy. The Adaptive Residual Squeeze and Excitation network (ARSEnet) is the proposed method used for a better classification process. Based on the evaluation results, the proposed technique better classified eye illness. The Python tool is used to carry out the recommended method. The proposed strategy outperformed others in terms of accuracy, precision, specificity, recall, and f1 score. The accuracy rate of the proposed method is 97.02%. The resultant analysis clearly proves that the proposed system provides the best accuracy for predicting ocular disease.

Detection of breast cancer by deep belief network with improved activation function

SummaryBreast cancer is the most prevalent kind of tumor to occur in females and the primary cause of death for women. Early detection is perhaps the most successful strategy to minimize breast cancer mortality. Early diagnosis necessitates a consistent and efficient diagnostics method that allows doctors to differentiate benign from malignant breast cancers without a surgical sample. The goal of this endeavor is to develop a sophisticated breast cancer diagnosis method. The primary goal of the paper is to reduce the death rate among women by promoting early detection of breast cancer. First, pre‐processing techniques such as median filtering and contrast limiting adaptive histogram equalization are used to the obtained raw images. By doing this, the machine‐learning model's computational complexity is decreased and the image quality is enhanced. K‐means clustering is used to segregate the pre‐processed image. Additionally, features including the enhanced local vector pattern, grey‐level co‐occurrence matrix and local vector patterns are produced in the course of the feature extraction stage. Finally, an optimized deep belief network (DBN) is carrying out the classification process. To boosts the classification accuracy, activation function of DBN (tanh, softmax, ReLu) as well as its weight function is optimized by the proposed grey wolf updated whale optimization algorithm The accuracy of the greywolf updated whale optimization algorithm+DBN is above 93% for datasets 1 and 2 when compared to extant models. Finally, calculation of the performance validates the proposed model's performance.

An Improved Underwater Visual SLAM through Image Enhancement and Sonar Fusion

To enhance the performance of visual SLAM in underwater environments, this paper presents an enhanced front-end method based on visual feature enhancement. The method comprises three modules aimed at optimizing and improving the matching capability of visual features from different perspectives. Firstly, to address issues related to insufficient underwater illumination and uneven distribution of artificial light sources, a brightness-consistency recovery method is proposed. This method employs an adaptive histogram equalization algorithm to balance the brightness of images. Secondly, a method for denoising underwater suspended particulates is introduced to filter out noise from images. After image-level processing, a combined underwater acousto–optic feature-association method is proposed, which associates acoustic features from sonar with visual features, thereby providing distance information for visual features. Finally, utilizing the AFRL dataset, the improved system incorporating the proposed enhancement methods is evaluated for its performance against the OKVIS framework. The system achieves a better trajectory estimation accuracy compared to OKVIS and demonstrates robustness in underwater environments.

Potential Screening, Grading and Follow-Up of Diabetic Retinopathy in Primary Care Using Artificial Intelligence – How Hard Would It Be to Implement? An Ophthalmologist’s Perspective

Diabetic retinopathy (DR) is a microvascular disorder caused by the long-term effects of diabetes mellitus and among the primary causes of blindness worldwide. Early detection of DR is the key to its effective treatment and subsequent reduction of associated economic burden, but manual screening is time-consuming and of limited availability. A highly sensitive and specific automatic diagnostic tool would significantly improve screening programs and allow referring for further evaluation and treatment in an ophthalmology clinic only patients with significant lesions or with changes between two successive evaluations. Several deep learning-based automated diagnosis tools have been proposed to aid screening but their implementation with minimal costs is not accessible to physicians with no coding knowledge. We aimed to develop a fundus images classification model with no coding knowledge by using generative artificial intelligence (AI) implemented in Windows 11 operating system under subscription (Copilot Pro), a free image analysis tool (Fiji ImageJ2), and Vertex AI, a machine learning (ML) platform launched by Google in 2021. For this purpose, we selected a total of 2961 labelled cases from the APTOS 2019 database of DR fundus images. Images were batch segmented using a Java ImageJ script generated by Copilot Pro and based on the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. Segmented images were used to train an automated ML classification model to detect DR severity (5 classes – no DR, mild non-proliferative DR, moderate DR, severe DR, proliferative DR). The model achieved an area under the precision-recall curve of 0.889, with a precision rate of 83.8% and a recall rate of 77%. In conclusion, generative AI implemented into Windows operating system together with a free imaging processing tool and Vertex AI allow ophthalmologists with no coding knowledge to benefit from publicly available image databases (thousands of cases) to develop accurate automated diagnostic tools. Such tools have the potential to facilitate screening especially in areas with few specialists.

Brain tumor classification in VIT-B/16 based on relative position encoding and residual MLP.

Brain tumors pose a significant threat to health, and their early detection and classification are crucial. Currently, the diagnosis heavily relies on pathologists conducting time-consuming morphological examinations of brain images, leading to subjective outcomes and potential misdiagnoses. In response to these challenges, this study proposes an improved Vision Transformer-based algorithm for human brain tumor classification. To overcome the limitations of small existing datasets, Homomorphic Filtering, Channels Contrast Limited Adaptive Histogram Equalization, and Unsharp Masking techniques are applied to enrich dataset images, enhancing information and improving model generalization. Addressing the limitation of the Vision Transformer's self-attention structure in capturing input token sequences, a novel relative position encoding method is employed to enhance the overall predictive capabilities of the model. Furthermore, the introduction of residual structures in the Multi-Layer Perceptron tackles convergence degradation during training, leading to faster convergence and enhanced algorithm accuracy. Finally, this study comprehensively analyzes the network model's performance on validation sets in terms of accuracy, precision, and recall. Experimental results demonstrate that the proposed model achieves a classification accuracy of 91.36% on an augmented open-source brain tumor dataset, surpassing the original VIT-B/16 accuracy by 5.54%. This validates the effectiveness of the proposed approach in brain tumor classification, offering potential reference for clinical diagnoses by medical practitioners.

Stitching method for panoramic nail fold images based on capillary contour enhancement.

Nail fold capillaroscopy is an important means of monitoring human health. Panoramic nail fold images improve the efficiency and accuracy of examinations. However, the acquisition of panoramic nail fold images is seldom studied and the problem manifests of few matching feature points when image stitching is used for such images. Therefore, this paper presents a method for panoramic nail fold image stitching based on vascular contour enhancement, which first solves the problem of few matching feature points by pre-processing the image with contrast-constrained adaptive histogram equalization (CLAHE), bilateral filtering (BF), and sharpening algorithms. The panoramic images of the nail fold blood vessels are then successfully stitched using the fast robust feature (SURF), fast library of approximate nearest neighbors (FLANN) and random sample agreement (RANSAC) algorithms. The experimental results show that the panoramic image stitched by this paper's algorithm has a field of view width of 7.43 mm, which improves the efficiency and accuracy of diagnosis.

Hybrid Ensemble Deep Learning Model for Advancing Ischemic Brain Stroke Detection and Classification in Clinical Application.

Ischemic brain strokes are severe medical conditions that occur due to blockages in the brain's blood flow, often caused by blood clots or artery blockages. Early detection is crucial for effective treatment. This study aims to improve the detection and classification of ischemic brain strokes in clinical settings by introducing a new approach that integrates the stroke precision enhancement, ensemble deep learning, and intelligent lesion detection and segmentation models. The proposed hybrid model was trained and tested using a dataset of 10,000 computed tomography scans. A 25-fold cross-validation technique was employed, while the model's performance was evaluated using accuracy, precision, recall, and F1 score. The findings indicate significant improvements in accuracy for different stages of stroke images when enhanced using the SPEM model with contrast-limited adaptive histogram equalization set to 4. Specifically, accuracy showed significant improvement (from 0.876 to 0.933) for hyper-acute stroke images; from 0.881 to 0.948 for acute stroke images, from 0.927 to 0.974 for sub-acute stroke images, and from 0.928 to 0.982 for chronic stroke images. Thus, the study shows significant promise for the detection and classification of ischemic brain strokes. Further research is needed to validate its performance on larger datasets and enhance its integration into clinical settings.

SegNet‐VOLO model for classifying microplastic contaminants in water bodies

AbstractIn recent times, microplastics (MPs) have emerged as notable contaminants within several environments, especially in water bodies. The characterization and description of MPs necessitate extensive and laborious analytical methods, making this part of MPs research an essential issue. In this research, SegNet‐Vision Outlooker (VOLO), a computer vision and deep learning (DL)‐based model, is proposed for detecting and classifying MPs present in a water environment. This research model includes step‐by‐step processes such as data collection, preprocessing, filtering and enhancement, augmentation, segmentation, feature extraction, and classification for detecting MPs. The key objective of this research model is to improve the classification accuracy in detecting MPs and to validate the model's effectiveness in handling holographic images. The Holographic Image MPs dataset is collected and used to evaluate the model. In preprocessing, image rescaling is performed to match the proposed model's input resolution as 224 × 224. After rescaling, the images are applied to remove noise using a bilateral filtering technique. The contrast‐limited adaptive histogram equalization (CLAHE) method is applied to enhance the image with better contrast and brightness, which helps the model to segment and classify the images accurately. The enhanced images are applied to the SegNet model for segmentation, which segmented the images according to the MP classes. Based on the segmented images, the VOLO‐D1 model extracted the features and classified the images to detect the MPs present in the images. The SegNet‐VOLO model attained 97.70% detection rate, 98.26% accuracy, 98.13% F1‐score, and 98.62% precision. These performances are compared with the various existing models discussed in the review, where the research model outperformed all the models with better performances.

Enhanced diabetic retinopathy detection and classification using fundus images with ResNet50 and CLAHE-GAN

Diabetic retinopathy (DR), a progressive eye disorder, can lead to irreversible vision impairment ranging from no DR to severe DR, necessitating precise identification for early treatment. This study introduces an innovative deep learning (DL) approach, surpassing traditional methods in detecting DR stages. It evaluated two scenarios for training DL models on balanced datasets. The first employed image enhancement via contrast limited adaptive histogram equalization (CLAHE) and a generative adversarial network (GAN), while the second did not involve any image enhancement. Tested on the Asia pacific tele-ophthalmology society 2019 blindness detection (APTOS-2019 BD) dataset, the enhanced model (scenario 1) reached 98% accuracy and a 99% Cohen kappa score (CKS), with the non-enhanced model (scenario 2) achieving 95.4% accuracy and a 90.5% CKS. The combination of CLAHE and GAN, termed CLANG, significantly boosted the model's performance and generalizability. This advancement is pivotal for early DR detection and intervention, offering a new pathway to prevent irreversible vision loss in diabetic patients.

Research on signal equalization technology based on visible light communication

Abstract Visible Light Communication (VLC) transmits signals through visible light and realizes the two functions of lighting and communication at the same time without the need for other hardware equipment. There are still some shortcomings in the visible light communication system. The optical signal propagated indoors is affected by inter-symbol interference (ISI) and external light noise at the receiving end. The signal will be severely distorted. These factors will significantly reduce the accuracy of the received signal decision, thereby seriously affecting the performance of the visible light communication system. Given the problems of intersymbol interference and optical noise in indoor visible light systems, this article studies adaptive equalization technology and modulation and demodulation technology suitable for visible light communication systems and improves the signal-receiving end equalization. Based on the existing equalizer structure, we combined the advantages of two different equalizers and optimized their combined structure parameters. On this basis, we added the MAP algorithm and proposed a hyperbolic tangent function to improve the traditional error function. The defects speed up the convergence speed without changing the mean square error. Experimental results show that the algorithm has improved in convergence performance. The algorithm’s convergence speed is 53.6% higher than the traditional algorithm, the steady-state error is reduced by about 6 dB, and the steady-state error of the algorithm is reduced by about 5 dB respectively.

Enhancing semantic segmentation in chest X-ray images through image preprocessing: ps-KDE for pixel-wise substitution by kernel density estimation.

In medical imaging, the integration of deep-learning-based semantic segmentation algorithms with preprocessing techniques can reduce the need for human annotation and advance disease classification. Among established preprocessing techniques, Contrast Limited Adaptive Histogram Equalization (CLAHE) has demonstrated efficacy in improving segmentation algorithms across various modalities, such as X-rays and CT. However, there remains a demand for improved contrast enhancement methods considering the heterogeneity of datasets and the various contrasts across different anatomic structures. This study proposes a novel preprocessing technique, ps-KDE, to investigate its impact on deep learning algorithms to segment major organs in posterior-anterior chest X-rays. Ps-KDE augments image contrast by substituting pixel values based on their normalized frequency across all images. We evaluate our approach on a U-Net architecture with ResNet34 backbone pre-trained on ImageNet. Five separate models are trained to segment the heart, left lung, right lung, left clavicle, and right clavicle. The model trained to segment the left lung using ps-KDE achieved a Dice score of 0.780 (SD = 0.13), while that of trained on CLAHE achieved a Dice score of 0.717 (SD = 0.19), p<0.01. ps-KDE also appears to be more robust as CLAHE-based models misclassified right lungs in select test images for the left lung model. The algorithm for performing ps-KDE is available at https://github.com/wyc79/ps-KDE. Our results suggest that ps-KDE offers advantages over current preprocessing techniques when segmenting certain lung regions. This could be beneficial in subsequent analyses such as disease classification and risk stratification.

Hand Gestures Recognition Model Using Adaptive Feature Extraction with Attention-Based Hybrid Deep Learning via Optimization Strategy

Research on continuous hand gesture recognition is motivated by applications of deaf people to provide effective communication between one another. Numerous techniques are adapted for effectively identifying the hand gesture. Moreover, the collection of data becomes a challenging task in the existing models. In some instances, hand gesture in low-resolution images becomes a complicated task. In this research work, a deep learning-based hand gesture detection model is designed using hand data points to uncover patterns that are used to convey information. Initially, hand gesture images are obtained from public sources. The collected inputs are preprocessed through Contrast-Limited Adaptive Histogram Equalization and filtering to eliminate the unnecessary blurs in the images. The preprocessed images undergo hand segmentation using four methods color space transformation, skin color detection, active contour, and morphological operation. The segmented image is subjected to data point feature extraction, where the Adaptive Weighted Scale-Invariant Feature Transform is utilized for further enhancement. The hand data point-extracted features are given to the recognition of hand gestures with the support of an attention-based hybrid network, where the Attention-based Hybrid 1D Convolutional Neural Network with Recurrent Neural Network recognizes the hand gestures from the hand data points. In the hybridization network, the values are optimized with the help of the investigated Adaptive Dandelion White Shark Optimizer to enhance recognition effectiveness. The test results are validated with the existing hand gesture recognition models using diverse evaluation metrics. The findings of the recommended method show 97% and 99% in terms of accuracy and NPV. Thus, the developed model is validated to outperform significant performance rather than the existing models.

A novel variable tap-length adaptive decision feedback equalization in underwater wireless communication

Fix-parameter decision feedback equalization (DFE) is prone to the challenge posed by the time-varying underwater acoustic (UWA) channels. This paper proposes a new adaptively adjusting the DFE’s tap length (TL) algorithm to solve this problem. The number of feedforward filter (FFF) taps of DFE is changed by comparing the fourth-order cumulants and second-order moments related to receiving signals with a threshold value. The feasibility of this approach is verified via theoretical analysis and numerical simulations. Further, the new system has processed the massive experimental data from two lakes. In light of the outcomes, for achieving the same bit error ratio (BER), the signal noise ratio (SNR) that the new algorithm requires is approximately 4 dB less than the variable tap-length method based on the mean square error (MSE). Additionally, this method can improve the system’s flexibility in addressing time-varying channels in underwater wireless communication.

Low complexity sub-baud rate sampling reception in a bandwidth-limited IM/DD system.

This Letter presents what is to our knowledge a novel approach to reduce the digital signal processing (DSP) complexity in intensity modulation and direct detection (IM/DD) systems, which is critical for short-reach optical communication systems with severe bandwidth limitations. We propose a sub-baud rate sampling reception method utilizing a polyphase feedforward equalizer-based maximum likelihood sequence estimation (PFFE-MLSE), which could operate effectively under a sampling rate of 0.6 samples per symbol. This new architecture eliminates the need for resampling, allowing the adaptive equalizer to operate with significantly reduced complexity-over 60% compared to traditional FFE-MLSE. An offline experiment, transmitting a 100-Gbaud on-off keying (OOK) signal over a 5-km single-mode fiber (SMF) link, demonstrates the feasibility of our approach with bit error ratio (BER) meeting the KP4-forward error correction (KP4-FEC) threshold in the optical back-to-back (OBTB) scenario and 7% hard-decision FEC (HD-FEC) threshold in the 5-km SMF transmission.

Effects of Contrast Limited Adaptive Histogram Equalization (CLAHE) on Manual and Automated Tracing of Lateral Cephalometric Radiographs

Objective: The aim of this study is to compare the difference between original lateral cephalometric radiographs (LCRs) and Contrast Limited Adaptive Histogram Equalization (CLAHE) LCRs in two examiners and WebCeph. Methods: A total of 200 LCRs were selected, and CLAHE (tile size: 20*20) was applied to the original LCRs. 27 LCR landmarks were manually determined by two examiners and, the selected LCR’s determined automatically using the WebCeph program. Absolute differences between the original LCRs and CLAHE-LCRs were calculated in the x-y axes and Euclidean distance. The Kruskal Wallis test was used for comparisons between the examiners and WebCeph. The Wilcoxon Signed Rank Test was used to evaluate the x and y axes within each group. Results: The best accuracy values were seen in examiner 1 along the x-y axes and Euclidean distance, while the worst accuracy values were seen in WebCeph. The mean differences according to the methods were higher along the y-axis than along the x-axis for both examiners (except PNS, Me’) and WebCeph (except Po, Co). The mean Euclidean distances were above 2 mm only in Co, PNS at Examiner 1, PNS, Po, Ba, Co, Go, Pog, U1RT, Me’, Pog at Examiner 2, and WebCeph in all measurements. However, the differences in Euclidean distances were less than 4 mm for both examiners and WebCeph. Conclusion: CLAHE-LCRs require more adjustments for landmark determination in WebCeph than the in the manual system.

Pipeline Leak Detection: A Comprehensive Deep Learning Model Using CWT Image Analysis and an Optimized DBN-GA-LSSVM Framework.

Detecting pipeline leaks is an essential factor in maintaining the integrity of fluid transport systems. This paper introduces an advanced deep learning framework that uses continuous wavelet transform (CWT) images for precise detection of such leaks. Transforming acoustic signals from pipelines under various conditions into CWT scalograms, followed by signal processing by non-local means and adaptive histogram equalization, results in new enhanced leak-induced scalograms (ELIS) that capture detailed energy fluctuations across time-frequency scales. The fundamental approach takes advantage of a deep belief network (DBN) fine-tuned with a genetic algorithm (GA) and unified with a least squares support vector machine (LSSVM) to improve feature extraction and classification accuracy. The DBN-GA framework precisely extracts informative features, while the LSSVM classifier precisely distinguishes between leaky and non-leak conditions. By concentrating solely on the advanced capabilities of ELIS processed through an optimized DBN-GA-LSSVM model, this research achieves high detection accuracy and reliability, making a significant contribution to pipeline monitoring and maintenance. This innovative approach to capturing complex signal patterns can be applied to real-time leak detection and critical infrastructure safety in several industrial applications.