One of the most frequent cancers in women is breast cancer, and in the year 2022, approximately 287,850 new cases have been diagnosed. From them, 43,250 women died from this cancer. An early diagnosis of this cancer can help to overcome the mortality rate. However, the manual diagnosis of this cancer using mammogram images is not an easy process and always requires an expert person. Several AI-based techniques have been suggested in the literature. However, still, they are facing several challenges, such as similarities between cancer and non-cancer regions, irrelevant feature extraction, and weak training models. In this work, we proposed a new automated computerized framework for breast cancer classification. The proposed framework improves the contrast using a novel enhancement technique called haze-reduced local-global. The enhanced images are later employed for the dataset augmentation. This step aimed at increasing the diversity of the dataset and improving the training capability of the selected deep learning model. After that, a pre-trained model named EfficientNet-b0 was employed and fine-tuned to add a few new layers. The fine-tuned model was trained separately on original and enhanced images using deep transfer learning concepts with static hyperparameters’ initialization. Deep features were extracted from the average pooling layer in the next step and fused using a new serial-based approach. The fused features were later optimized using a feature selection algorithm known as Equilibrium-Jaya controlled Regula Falsi. The Regula Falsi was employed as a termination function in this algorithm. The selected features were finally classified using several machine learning classifiers. The experimental process was conducted on two publicly available datasets—CBIS-DDSM and INbreast. For these datasets, the achieved average accuracy is 95.4% and 99.7%. A comparison with state-of-the-art (SOTA) technology shows that the obtained proposed framework improved the accuracy. Moreover, the confidence interval-based analysis shows consistent results of the proposed framework.

Lane departure warning systems have gained considerable research interest in the past decade for its promising usage in automotive, where lane detection and tracking is applied. However, it is a challenging task to improve the robustness of lane detection due to environmental factors, such as perspective effect, possible low visibility of lanes, and partial occlusions. To deal with these issues, we propose a reliable vision-based real-time lane markings detection and tracking system that can adapt to various environmental conditions. The lane detection is composed of three stages: pre-processing, Adaptive Region of Interest (AROI) setting, and lane marking detection and tracking. In the pre-processing stage, smoothing and edge detection operators are applied on input frames to automatically obtain binary images, then, lane markings segmentation are carried out. After that, An Adaptive Region of Interest is extracted to reduce the computational complexity. In the subsequent detection stages, Kalman filter is employed to track road boundaries detected in the AROI using Progressive Probabilistic Hough Transform (PPHT) in the next frame. Based on road boundaries and the vehicle’s position, the proposed algorithm decides if the vehicle has drifted off the lane. For the performance evaluation of lane detection and tracking, real-life datasets for both urban roads and highways in various lighting conditions are used. Applying our method to Catltech dataset, the average correct detection rate is 93.82%. In addition, the proposed method outperforms that of the state-of-the-art methods in processing time (21.54ms/frame).

Healthcare Internet of Things (HIoT) requires large-scale privacy features to ensure maximum security in sharing sensitive physiological data in consumer electronics. Recent approaches utilize the fusion concept to provide maximum privacy in health data sharing. Embedded signing data fusion with the health observed data ensures privacy preserved sharing across heterogeneous medical consumer devices for diagnosis. This article proposes a Dependency-correlated Data Fusion Scheme (DcDFS) to maximize the privacy of the health data-sharing process. The proposed scheme prepares separate key signing procedures using triple-DES (data encryption standard) to embed with the accumulated health data. The fusion process is carried out by defining key headers and integrity footers for authentication and verification. Therefore, the fusion generates a combined sequence of linear authentication and validation procedures enclosing the health data. In this scheme, the role of federated learning is to prevent permuted sequences for the same health data. This research integrates Small Language Model (SLM) and Large Language Model (LLM) into the federated learning module to support secure, scalable, and intelligent healthcare data sharing. Their collaboration enhances context-aware training while preserving privacy across decentralized, encrypted environments. A similar sequence mapped between the header and footer is responsible for discarding unauthorized data handling. The learning process verifies the permutation for many-to-one header to footer and vice versa. Therefore, the proposed fusion scheme generates a linear dependency between the actual and security-related data for maximum privacy. The proposed scheme achieves the following: the computation time is confined by 12.424%, the privacy leakage by 12.923%, and the computation efficiency is improved by 11.46%, as observed under the maximum sequences.

The competence of machine learning approaches to carry out clinical expertise tasks has recently gained a lot of attention, particularly in the field of medical-imaging examination. Among the most frequently used clinical-imaging modalities in the healthcare profession is chest radiography, which calls for prompt reporting of the existence of potential anomalies and illness diagnostics in images. Automated frameworks for the recognition of chest abnormalities employing X-rays are being introduced in health departments. However, the reliable detection and classification of particular illnesses in chest X-ray samples is still a complicated issue because of the complex structure of radiographs, e.g., the large exposure dynamic range. Moreover, the incidence of various image artifacts and extensive inter- and intra-category resemblances further increases the difficulty of chest disease recognition procedures. The aim of this study was to resolve these existing problems. We propose a deep learning (DL) approach to the detection of chest abnormalities with the X-ray modality using the EfficientDet (CXray-EffDet) model. More clearly, we employed the EfficientNet-B0-based EfficientDet-D0 model to compute a reliable set of sample features and accomplish the detection and classification task by categorizing eight categories of chest abnormalities using X-ray images. The effective feature computation power of the CXray-EffDet model enhances the power of chest abnormality recognition due to its high recall rate, and it presents a lightweight and computationally robust approach. A large test of the model employing a standard database from the National Institutes of Health (NIH) was conducted to demonstrate the chest disease localization and categorization performance of the CXray-EffDet model. We attained an AUC score of 0.9080, along with an IOU of 0.834, which clearly determines the competency of the introduced model.

The current paper explores the three-dimensional flow of an Oldroyd-B liquid with the impact of a magnetic dipole that occurred by stretching a flat surface placed in the plane with a linear velocity variation in two directions containing motile gyrotactic microorganisms. Using proper similarity transformations, the governing equations are reduced into nonlinear coupled ordinary differential equations (ODEs). The ODEs are then solved using Runge–Kutta-Fehlberg (RKF) method. The training, testing, and validation processes are carried out in parallel to adapt neural networks and calculate an approximate solution for the considered model. This helps to reduce the mean square error (MSE) function by Levenberg–Marquardt backpropagation. The efficiency of the suggested backpropagated neural networks methodology has been demonstrated by utilizing outcomes such as MSE, error histograms, correlation and regression. Results reveal that the heat transport augments for increased Biot number values. The mass transport declines for improved chemical reaction rate parameter values. A higher Peclet number will result in a lower motile diffusivity and result in a decline in the micro-organism’s density profile. For the least value of Mu and gradient, better convergence of the findings can be achieved with better network testing and training.