Search

In response to the growing number of diabetes cases worldwide, Our study addresses the escalating issue of diabetic eye disease (DED), a significant contributor to vision loss globally, through a pioneering approach. We propose a novel integration of a Genetic Grey Wolf Optimization (G-GWO) algorithm with a Fully Convolutional Encoder-Decoder Network (FCEDN), further enhanced by a Kernel Extreme Learning Machine (KELM) for refined image segmentation and disease classification. This innovative combination leverages the genetic algorithm and grey wolf optimization to boost the FCEDN's efficiency, enabling precise detection of DED stages and differentiation among disease types. Tested across diverse datasets, including IDRiD, DR-HAGIS, and ODIR, our model showcased superior performance, achieving classification accuracies between 98.5% to 98.8%, surpassing existing methods. This advancement sets a new standard in DED detection and offers significant potential for automating fundus image analysis, reducing reliance on manual examination, and improving patient care efficiency. Our findings are crucial to enhancing diagnostic accuracy and patient outcomes in DED management.

Accidental falls pose a significant threat to the elderly population, and accurate fall detection from surveillance videos can significantly reduce the negative impact of falls. Although most fall detection algorithms based on video deep learning focus on training and detecting human posture or key points in pictures or videos, we have found that the human pose-based model and key points-based model can complement each other to improve fall detection accuracy. In this paper, we propose a preposed attention capture mechanism for images that will be fed into the training network, and a fall detection model based on this mechanism. We accomplish this by fusing the human dynamic key point information with the original human posture image. We first propose the concept of dynamic key points to account for incomplete pose key point information in the fall state. We then introduce an attention expectation that predicates the original attention mechanism of the depth model by automatically labeling dynamic key points. Finally, the depth model trained with human dynamic key points is used to correct the detection errors of the depth model with raw human pose images. Our experiments on the Fall Detection Dataset and the UP-Fall Detection Dataset demonstrate that our proposed fall detection algorithm can effectively improve the accuracy of fall detection and provide better support for elderly care.

Recent works have illustrated that many facial privacy protection methods are effective in specific face recognition algorithms. However, the COVID-19 pandemic has promoted the rapid innovation of face recognition algorithms for face occlusion, especially for the face wearing a mask. It is tricky to avoid being tracked by artificial intelligence only through ordinary props because many facial feature extractors can determine the ID only through a tiny local feature. Therefore, the ubiquitous high-precision camera makes privacy protection worrying. In this paper, we establish an attack method directed against liveness detection. A mask printed with a textured pattern is proposed, which can resist the face extractor optimized for face occlusion. We focus on studying the attack efficiency in adversarial patches mapping from two-dimensional to three-dimensional space. Specifically, we investigate a projection network for the mask structure. It can convert the patches to fit perfectly on the mask. Even if it is deformed, rotated and the lighting changes, it will reduce the recognition ability of the face extractor. The experimental results show that the proposed method can integrate multiple types of face recognition algorithms without significantly reducing the training performance. If we combine it with the static protection method, people can prevent face data from being collected.

Several biometric privacy-enhancing techniques have been appraised to protect face image privacy. However, a face privacy protection algorithm is usually designed for a specific face recognition algorithm. When the structure or threshold of the face recognition algorithm is fine-tuned, the protection algorithm may be invalid. It will cause the network bloated and make the image distortion target multiple FRAs through the existing technology simultaneously. To address this problem, a fusion technology is developed to cope with the changeable face recognition algorithms via an image perturbation method. The image perturbation is performed by using a GAN-improved algorithm including generator, nozzles and validator, referred to as the Adversarial Fusion algorithm. A nozzle structure is proposed to replace the discriminator. Paralleling multiple face recognition algorithms on the nozzle can improve the compatibility of the generated image. Next, a validator is added to the training network, which takes part in the inverse back coupling of the generator. This component can make the generated graphics have no impact on human vision. Furthermore, the group hunting theory is quoted to make the network stable and up to 4.8 times faster than other models in training. The experimental results show that the Adversarial Fusion algorithm can not only change the image feature distribution by over 42% but also deal with at least 5 commercial face recognition algorithms at the same time.

With the recent development of non-contact physiological signal detection methods based on videos, it is possible to obtain the physiological parameters through the ordinary video only, such as heart rate and its variability of an individual. Therefore, personal physiological information may be leaked unknowingly with the spread of videos, which may cause privacy or security problems. In this paper a new method is proposed, which can shield physiological information in the video without reducing the video quality significantly. Firstly, the principle of the most widely used physiological signal detection algorithm: remote photoplethysmography (rPPG) was analyzed. Then the region of interest (ROI) of face contain physiological information with high signal to noise ratio was selected. Two physiological information forgery operation: single-channel periodic noise addition with blur filtering and brightness fine-tuning are conducted on the ROIs. Finally, the processed ROI images are merged into video frames to obtain the processed video. Experiments were performed on the VIPL-HR video dataset. The interference efficiencies of the proposed method on two mainly used rPPG methods: Independent Component Analysis (ICA) and Chrominance-based Method (CHROM) are 82.9 % and 84.6 % respectively, which demonstrated the effectiveness of the proposed method.

Objective: Diabetic retinopathy is the leading cause of vision loss in working-age adults. Early screening and diagnosis can help to facilitate subsequent treatment and prevent vision loss. Deep learning has been applied in various fields of medical identification. However, current deep learning-based lesion segmentation techniques rely on a large amount of pixel-level labeled ground truth data, which limits their performance and application. In this work, we present a weakly supervised deep learning framework for eye fundus lesion segmentation in patients with diabetic retinopathy. Methods: First, an efficient segmentation algorithm based on grayscale and morphological features is proposed for rapid coarse segmentation of lesions. Then, a deep learning model named Residual-Attention Unet (RAUNet) is proposed for eye fundus lesion segmentation. Finally, a data sample of fundus images with labeled lesions and unlabeled images with coarse segmentation results is jointly used to train RAUNet to broaden the diversity of lesion samples and increase the robustness of the segmentation model. Results: A dataset containing 582 fundus images with labels verified by doctors, including hemorrhage (HE), microaneurysm (MA), hard exudate (EX) and soft exudate (SE), and 903 images without labels was used to evaluate the model. In ablation test, the proposed RAUNet achieved the highest intersection over union (IOU) on the labeled dataset, and the proposed attention and residual modules both improved the IOU of the UNet benchmark. Using both the images labeled by doctors and the proposed coarse segmentation method, the weakly supervised framework based on RAUNet architecture significantly improved the mean segmentation accuracy by over 7% on the lesions. Significance: This study demonstrates that combining unlabeled medical images with coarse segmentation results can effectively improve the robustness of the lesion segmentation model and proposes a practical framework for improving the performance of medical image segmentation given limited labeled data samples.

Cancer is a deadly disease that arises due to the growth of uncontrollable body cells. Every year, a large number of people succumb to cancer and it’s been labeled as the most serious public health snag. Cancer can develop in any part of the human anatomy, which may consist of trillions of cellules. One of the most frequent type of cancer is skin cancer which develops in the upper layer of the skin. Previously, machine learning techniques have been used for skin cancer detection using protein sequences and different kinds of imaging modalities. The drawback of the machine learning approaches is that they require human-engineered features, which is a very laborious and time-taking activity. Deep learning addressed this issue to some extent by providing the facility of automatic feature extraction. In this study, convolution-based deep neural networks have been used for skin cancer detection using ISIC public dataset. Cancer detection is a sensitive issue, which is prone to errors if not timely and accurately detected. The performance of the individual machine learning models to detect cancer is limited. The combined decision of individual learners is expected to be more accurate than the individual learners. The ensemble learning technique exploits the diversity of learners to yield a better decision. Thus, the prediction accuracy can be enhanced by combing the decision of individual learners for sensitive issues such as cancer detection. In this paper, an ensemble of deep learners has been developed using learners of VGG, CapsNet, and ResNet for skin cancer detection. The results show that the combined decision of deep learners is superior to the finding of individual learners in terms of sensitivity, accuracy, specificity, F-score, and precision. The experimental results of this study provide a compelling reason to be applied for other disease detection.

Fire disaster brings enormous danger to the safety of human life and property, and it is important to identify the fire situation in time through image processing technology. The current instance segmentation algorithms suffer from problems such as inadequate fire images and annotations, low recognition accuracy, and slow inference speed for fire recognition tasks. In this paper, we propose a semi-supervised learning-based fire instance segmentation method based on deep learning image processing technology. We used a lightweight version of the SOLOv2 network and optimized the network structure to improve accuracy. We propose a semi-supervised learning method based on fire features. To reduce the negative impact of error pseudo-labels on the model training, the pseudo-labels are matched by the color and morphological features of flames and smoke at the pseudo-label generation stage, and some images are screened for strong image enhancement before entering the next round of training for the student model. We further exploit the potential of the model with a limited dataset and improve the model accuracy without affecting the inference efficiency of the model. Experiments show that our proposed algorithm can successfully improve the accuracy of fire instance segmentation with good inference speed.

Diabetic retinopathy (DR) is a primary cause of blindness in which damage occurs to the retina due to an accretion of sugar levels in the blood. Therefore, prior detection, classification, and diagnosis of DR can prevent vision loss in diabetic patients. We proposed a novel and hybrid approach for prior DR detection and classification. We combined distinctive models to make the DR detection process robust or less error-prone while determining the classification based on the majority voting method. The proposed work follows preprocessing feature extraction and classification steps. The preprocessing step enhances abnormality presence as well as segmentation; the extraction step acquires merely relevant features; and the classification step uses classifiers such as support vector machine (SVM), K-nearest neighbor (KNN), and binary trees (BT). To accomplish this work, multiple severities of disease grading databases were used and achieved an accuracy of 98.06%, sensitivity of 83.67%, and 100% specificity.

To reduce the high pre-weaning mortality rate of new-born piglets crushed by sows, a kind of recognition and evaluation method for sows’ behavior based on the scheme of time-sharing and multiplexing by adopting triaxial acceleration and video sensors at day and night is proposed in this paper. For darker scene at night, random forest classifier with optimal 43-dimensional feature vector subset proposed in this paper is adopted to recognize four kinds of macro behaviors of sows roughly by adopting triaxial acceleration sensor MPU6050. The recognition rate can reach 89.4%. For brighter light scene during the day, an improved bilinear convolutional neural network method based on CBAM module is proposed in this paper to recognize seven kinds of micro behaviors of sows by video sensor. The recognition rate can reach 84.4%. The methods proposed in this paper can meet the requirement of real-time to recognize the behavior of sows during 24 hours on the premise of ensuring accuracy. Finally, an evaluation model of sows’ maternal behavior level is set up in this paper. The achivement of the study can not only help the farm to select sows with higher maternal ability for breeding piglets, but also avoid the large-scale economic losses caused by the high mortality rate of piglets before weaning of the farm.

The real visual attention areas of students during the learning process are vital data. They represent the students' visual concentration and provide strong support for the analysis of learning effects. It is necessary to use professional equipment to collect the visual attention areas of students on a screen but this equipment is expensive, so it cannot be solely depended upon. A binocular camera can directly obtain the depth information under static conditions; thus, detected pupil and iris sizes do not change as the user-to-screen distance changes. Robust pupil detection is an important prerequisite for gaze detection in a real-world setting. Hence, an accurate algorithm to calculate the position of pupils and the size of irises under natural light is proposed in this paper. It is based on the positive and negative oblique projection of relative linear density. The MPIIGaze dataset was used to test the algorithm, and the experimental results show that the algorithm is resistant to changes in illumination and the presence of glasses. Moreover, compared with a system based on a monocular camera, the error in the distance between label points and gaze location is decreased by 5 pixels and dispersion is decreased by 3 pixels. Finally, the line of sight is concentrated and the dispersion is low. With the `user-screen' distance between 60cm and 80cm, the accuracy can reach up to 1.5° to 2.2°.

Vegetation is a land-use type that attracting growing attention in urban studies. Extraction of urban vegetation information can be achieved by land-use/land-cover (LULC) classification. It has been proved that SAR remote sensing provides complementary information in LULC classification. However, how the complementary information from SAR features contribute to the classification in highly-dense urban area is still unclear. In this study, taking the highly urbanized area of Hong Kong as the study site, comprehensive studies were conducted to investigate the contribution of optical and polarimetric SAR features for LULC classification and urban vegetation extraction. Firstly, large amount of redundant information was found within optical and SAR features sets by Pearson correlation analysis. Then analysis based on J-S distance revealed that optical features have much stronger capabilities on LULC classification and some key features such as NDVI and Mean value of GLCM carry distinct information for discriminating certain land-use types. Supervised classification based on random forest further proved this result. The complementary mechanism of optical and polarimetric SAR features can be clearly observed in the radar chart. Therefore, when fusing optical and SAR features on the feature-level, the classification accuracy further improved. It was discovered that the volume scatter mechanism plays a vital role in the feature-level classification model. Finally, the overall classification accuracy of the classification model does not significantly grow after several key optical and SAR features are inputted, confirming again the high correlation between the features. In vegetation extraction, optical features provide most information and achieved the high accuracy of 99.02%. The results discovered in the above research could benefit the designing algorithms and selecting features for high accuracy urban LULC classification and vegetation extraction based on optical and SAR data.

Microwave radiometers can be used in human tissue temperature measurement scenarios due to the advantages of non-destructive and non-contact temperature measurement. However, their accuracy often cannot meet the needs of practical applications. In this paper, a Ku-Band high-precision blackbody calibration target is designed to provide calibration for microwave radiometers and meet the requirements of a high temperature-measurement accuracy and high temperature-measurement resolution. From a practical application point of view, the blackbody calibration target needs to have the characteristics of high emissivity and high temperature uniformity. However, previous studies on blackbody calibration targets often focused on the scattering characteristics or temperature uniformity of the calibration target separately, and thus lack a comprehensive consideration of the two characteristics. In this paper, the electromagnetic scattering model and the temperature-distribution model of the calibration target are established through the multi-physical simulation combined with the Finite Element Method. Then, according to the simulation results of the two characteristic models, the structural parameters and composition of the coated cone array are continuously optimized. In addition, to achieve high-precision temperature control of the blackbody calibration target, this paper studies three PID controller parameter self-tuning algorithms, namely, BP-PID, PSO-PID and Fuzzy-PID for the optimal parameter tuning problem of traditional PID algorithms and determines the optimal temperature-control algorithm by comparing the performance of heating and cooling processes. Then, the blackbody calibration target is processed and manufactured. The arch test system is used to validate the reflectance of the calibration target, the emissivity is calculated indirectly, and the temperature-distribution uniformity of the temperature-control panel of the calibration target is tested by a multi-point distribution method. Finally, the uncertainty of the brightness temperature of the blackbody calibration target is analyzed.

Background: Road network data are crucial in various applications, such as emergency response, urban planning, and transportation management. The recent application of deep neural networks has significantly boosted the efficiency and accuracy of road network extraction based on remote sensing data. However, most existing methods for road extraction were designed at local or regional scales. Automatic extraction of large-scale road datasets from satellite images remains challenging due to the complex background around the roads, especially the complicated land cover types. To tackle this issue, this paper proposes a land cover background-adaptive framework for large-scale road extraction. Method: A large number of sample image blocks (6820) are selected from six different countries of a wide region as the dataset. OpenStreetMap (OSM) is automatically converted to the ground truth of networks, and Esri 2020 Land Cover Dataset is taken as the background land cover information. A fuzzy C-means clustering algorithm is first applied to cluster the sample images according to the proportion of certain land use types that obviously negatively affect road extraction performance. Then, the specific model is trained on the images clustered as abundant with that certain land use type, while a general model is trained based on the rest of the images. Finally, the road extraction results obtained by those general and specific modes are combined. Results: The dataset selection and algorithm implementation were conducted on the cloud-based geoinformation platform Google Earth Engine (GEE) and Google Colaboratory. Experimental results showed that the proposed framework achieved stronger adaptivity on large-scale road extraction in both visual and statistical analysis. The C-means clustering algorithm applied in this study outperformed other hard clustering algorithms. Significance: The promising potential of the proposed background-adaptive network was demonstrated in the automatic extraction of large-scale road networks from satellite images as well as other object detection tasks. This search demonstrated a new paradigm for the study of large-scale remote sensing applications based on deep neural networks.

Nowadays, customer churn has been reflected as one of the main concerns in the processes of the telecom sector, as it affects the revenue directly. Telecom companies are looking to design novel methods to identify the potential customer to churn. Hence, it requires suitable systems to overcome the growing churn challenge. Recently, integrating different clustering and classification models to develop hybrid learners (ensembles) has gained wide acceptance. Ensembles are getting better approval in the domain of big data since they have supposedly achieved excellent predictions as compared to single classifiers. Therefore, in this study, we propose a customer churn prediction (CCP) based on ensemble system fully incorporating clustering and classification learning techniques. The proposed churn prediction model uses an ensemble of clustering and classification algorithms to improve CCP model performance. Initially, few clustering algorithms such as k-means, k-medoids, and Random are employed to test churn prediction datasets. Next, to enhance the results hybridization technique is applied using different ensemble algorithms to evaluate the performance of the proposed system. Above mentioned clustering algorithms integrated with different classifiers including Gradient Boosted Tree (GBT), Decision Tree (DT), Random Forest (RF), Deep Learning (DL), and Naive Bayes (NB) are evaluated on two standard telecom datasets which were acquired from Orange and Cell2Cell. The experimental result reveals that compared to the bagging ensemble technique, the stacking-based hybrid model (k-medoids-GBT-DT-DL) achieve the top accuracies of 96%, and 93.6% on the Orange and Cell2Cell dataset, respectively. The proposed method outperforms conventional state-of-the-art churn prediction algorithms.

Water is a vital component of life that exists in a variety of forms, including oceans, rivers, ponds, streams, and canals. The automated methods for detecting, segmenting, and mapping surface water have improved significantly with the advancements in satellite imagery and remote sensing. Many strategies and techniques to segment water resources have been presented in the past. However, due to the variant width and complex appearance, the segmentation of the water channel remains challenging. Moreover, traditional supervised deep learning frameworks have been restricted by the scarcity of water channel datasets that include precise water annotations. With this in mind, this research presents the following three main contributions. Firstly, we curated a new dataset for water channel mapping in the Pakistani region. Instead of employing pixel-level water channel annotations, we used a weakly trained method to extract water channels from VHR pictures, relying only on OpenStreetMap (OSM) waterways to create sparse scribbling annotations. Secondly, we benchmarked the dataset on state-of-the-art semantic segmentation frameworks. We also proposed AUnet, an atrous convolution inspired deep learning network for precise water channel segmentation. The experimental results demonstrate the superior performance of the proposed AUnet model for segmenting using weakly supervised labels, where it achieved a mean intersection over union score of 0.8791 and outperformed state-of-the-art approaches by 5.90% for the extraction of water channels.

In this paper, a multiband noncontact temperature-measuring microwave radiometer system is developed. The system can passively receive the microwave signal of the core temperature field of the human body without removing the clothes of the measured person. In order to accurately measure the actual temperature of multilayer tissue in human core temperature field, four frequency bands of 4–6 GHz, 8–12 GHz, 12–16 GHz, and 14–18 GHz were selected for multifrequency design according to the internal tissue depth model of human body and the relationship between skin depth and electromagnetic frequency. Used to measure the actual temperature of human epidermis, dermis, and subcutaneous tissue, a small and highly directional multiband angular horn antenna was designed for the radiometer front end. After the error analysis of the full-power microwave radiometer, a novel hardware architecture of the microwave interferometric temperature-measuring radiometer is proposed, and it is proven that the novel interferometric microwave radiometer has less error uncertainty through theoretical deduction. The experimental results show that the maximum detection sensitivity of the novel interferometric microwave temperature-measuring radiometer is 215 mV/dBm, and the temperature sensitivity is 0.047 K/mV. Compared with the scheme of the full-power radiometer, the detection sensitivity is increased 7.45-fold, and the temperature sensitivity is increased 13.89-fold.

In this paper, the key technology of interferometric microwave thermometer is studied, the research can be applied to the temperature measurement of human body and subcutaneous tissue. This paper proposes a hardware architecture of interferometric microwave thermometer with 2 GHz bandwidth, in which the phase shifter is used to correct phase error and the quadrature demodulator is used to realize autocorrelation detection function. The results show that when input power is 7 dBm, the detection sensitivity can reach 176.54 mV/dBm and the temperature resolution of the microwave radiometer can reach 0.4 K. Correction algorithm is designed to improve the accuracy of temperature measurement. After correction, the phase error is reduced from 40° to 1.4° and when temperature changes 0.1 °C, the voltage value changes obviously. Step-by-step calibration and overall calibration are used to calibrate the device. Inversion algorithm can determine the relationship between physical temperature and output voltage. The mean square error of water temperature inversion by multiple linear regression algorithm is 0.607 and that of BP neural network algorithm is 0.334. The inversion accuracy can be improved by reducing the temperature range. Our work provides a promising realization of accurate, rapid and non-contact detection device of human body temperature.

Vehicle detection based on very high-resolution (VHR) remote sensing images is beneficial in many fields such as military surveillance, traffic control, and social/economic studies. However, intricate details about the vehicle and the surrounding background provided by VHR images require sophisticated analysis based on massive data samples, though the number of reliable labeled training data is limited. In practice, data augmentation is often leveraged to solve this conflict. The traditional data augmentation strategy uses a combination of rotation, scaling, and flipping transformations, etc., and has limited capabilities in capturing the essence of feature distribution and proving data diversity. In this study, we propose a learning method named Vehicle Synthesis Generative Adversarial Networks (VS-GANs) to generate annotated vehicles from remote sensing images. The proposed framework has one generator and two discriminators, which try to synthesize realistic vehicles and learn the background context simultaneously. The method can quickly generate high-quality annotated vehicle data samples and greatly helps in the training of vehicle detectors. Experimental results show that the proposed framework can synthesize vehicles and their background images with variations and different levels of details. Compared with traditional data augmentation methods, the proposed method significantly improves the generalization capability of vehicle detectors. Finally, the contribution of VS-GANs to vehicle detection in VHR remote sensing images was proved in experiments conducted on UCAS-AOD and NWPU VHR-10 datasets using up-to-date target detection frameworks.

Polarimetric synthetic aperture radar (SAR) remote sensing provides an outstanding tool in oil spill detection and classification, for its advantages in distinguishing mineral oil and biogenic lookalikes. Various features can be extracted from polarimetric SAR data. The large number and correlated nature of polarimetric SAR features make the selection and optimization of these features impact on the performance of oil spill classification algorithms. In this paper, deep learning algorithms such as the stacked autoencoder (SAE) and deep belief network (DBN) are applied to optimize the polarimetric feature sets and reduce the feature dimension through layer-wise unsupervised pre-training. An experiment was conducted on RADARSAT-2 quad-polarimetric SAR image acquired during the Norwegian oil-on-water exercise of 2011, in which verified mineral, emulsions, and biogenic slicks were analyzed. The results show that oil spill classification achieved by deep networks outperformed both support vector machine (SVM) and traditional artificial neural networks (ANN) with similar parameter settings, especially when the number of training data samples is limited.

Sonar signals recognition is an important task in detecting the presence of some significant objects under the sea. In military, sonar signals are used in lieu of visuals to navigate underwater and/or locate enemy submarines in proximity. In particular, classification algorithm in data mining has been applied in sonar signal recognition for recognizing the type of surfaces from which the sonar waves are bounced. Classification algorithms in traditional data mining approach offer fair accuracy by training a classification model with the full dataset, in batches. It is well known that sonar signals are continuous and they are collected as data streams. Although the earlier classification algorithms are effective in traditional batch training, it may not be practical for incremental classifier learning. Since sonar signal data streams can amount to infinity, the data preprocessing time must be kept to a minimum to fulfill the need for high speed. This paper presents an alternative data mining strategy suitable for the progressive purging of noisy data via fast conflict analysis from the data stream without the need to learn from the whole dataset at one time. Simulation experiments are conducted and superior results are observed in supporting the efficacy of the methodology.

Standard classification algorithms are often inaccurate when used in a wireless sensor network (WSN), where the observed data occur in imbalanced classes. The imbalanced data classification problem occurs when the number of samples in one class, usually the class of interest, is much lower than the number in the other classes. Many classification models have been studied in the data-mining research community. However, they all assume that the input data are stationary and bounded in size, so that resampling techniques and postadjustment by measuring the classification cost can be applied. In this paper, we devise a new scheme that extends a popular stream classification algorithm to the analysis of WSNs for reducing the adverse effects of the imbalanced class in the data. This new scheme is resource light at the algorithm level and does not require any data preprocessing. It uses weighted naïve Bayes predictors at the decision tree leaves to effectively reduce the impact of imbalanced classes. Experiments show that our modified algorithm outperforms the original stream classification algorithm.

Wireless sensor networks (WSNs) are a rapidly emerging technology with a great potential in many ubiquitous applications. Although these sensors can be inexpensive, they are often relatively unreliable when deployed in harsh environments characterized by a vast amount of noisy and uncertain data, such as urban traffic control, earthquake zones, and battlefields. The data gathered by distributed sensors—which serve as the eyes and ears of the system—are delivered to a decision center or a gateway sensor node that interprets situational information from the data streams. Although many other machine learning techniques have been extensively studied, real-time data mining of high-speed and nonstationary data streams represents one of the most promising WSN solutions. This paper proposes a novel stream mining algorithm with a programmable mechanism for handling missing data. Experimental results from both synthetic and real-life data show that the new model is superior to standard algorithms.

Skin cancer diagnosis is difficult due to lesion presentation variability. Conventionalmethods struggle to manually extract features and capture lesions spatial and temporal variations. This study introduces a deep learning-based Convolutional and Recurrent Neural Network (CNN-RNN) model with a ResNet-50 architecture which used as the feature extractor to enhance skin cancer classification. Leveraging synergistic spatial feature extraction and temporal sequence learning, the model demonstrates robust performance on a dataset of 9000 skin lesion photos from nine cancer types. Using pre-trained ResNet-50 for spatial data extraction and Long Short-Term Memory (LSTM) for temporal dependencies, the model achieves a high average recognition accuracy, surpassing previous methods. The comprehensive evaluation, including accuracy, precision, recall, and F1-score, underscores the model's competence in categorizing skin cancer types. This research contributes a sophisticated model and valuable guidance for deep learning-based diagnostics, also this model excels in overcoming spatial and temporal complexities, offering a sophisticated solution for dermatological diagnostics research. [ABSTRACT FROM AUTHOR]