International Journal of Modeling, Simulation, and Scientific Computing

As opposed to using many unrelated photographs to depict the same scene, image fusions combine multiple, similar images to generate a single, unified image with greater detail. Imaging sensors and the need for a wideband signal to transmit most source images limit their resolution. This study suggests new methods of fusing medical pictures from different modalities in order to increase image quality and, by extension, the accuracy with which brain tumors can be detected and identified. Improved convolutional neural network (ICNN) and region growth-based $K$-means clustering (RKMC) are used in the suggested strategy to boost the quality of brain image fusions obtained from Computed tomography scanned image (CTSI) and magnetic resonance imaging (MRI) in this study. The first stages of this task consist of eliminating noise, segmenting images, extracting and selecting features, and fusing images. AMF (Adaptive Median Filtering) are first used to eliminate noise from MRI images and CTSI of the brain, improving the image quality. With the help of the RKMC algorithm, MRI image and CTSI scans can be segmented into their constituent pieces, which can then be seen either as grayscale images or as pictures of objects. The RKMC algorithm is able to adequately account for the possibility of tumors in white images. More useful image features can be extracted with the use of MPCA (Modified Principal Component Analysis). Afterward, features with the highest fitness values are chosen by using AFO (Adaptive Firefly Optimization). Image fusions of multimodal images are carried out using ICNN, which generates the image’s lower-, middle-, and higher-level contents. Incorporating important and relevant image characteristics from all viewpoints and perspectives improves feature training and testing. The results show that the proposed RKMC+ICNNs outperform the state-of-the-art approaches in terms of accuracy, PSNR, RMSE, and runtime.

Current healthcare applications commonly incorporate the Internet of Things (IoT) and cloud computing ideas. IoT devices provide massive amounts of patient data in the healthcare industry. These data stored in the cloud are analyzed using mobile devices’ built-in storage and processing power. The Internet of Medical Healthcare Things (IoMHT) integrates health monitoring components including sensors and medical equipment to remotely monitor patient records in order to provide more intelligent and sophisticated healthcare services. In this research, we analyze one of the deadliest illnesses with a high fatality rate worldwide, the chronic kidney disease (CKD), to provide the finest healthcare services possible to users of e-health and m-health applications by presenting the IoTC services based on healthcare delivery system for the prediction and observation of CKD with its severity level. The suggested architecture gathers patient data from linked IoT devices and saves it in the cloud alongside real-time data, pertinent medical records that are collected from the UCI Machine Learning Repository, and relevant medical documents. We further use a Deep Neural Network (DNN) classifier to predict CKD and its severity. To boost the effectiveness of the DNN classifier, a Particle Swarm Optimization (PSO)-based feature selection technique is also applied. We compare the performance of the proposed model using different classification measures utilizing different classifiers. A Quick Flower Pollination Algorithm (QFPA)- (DNN)-based IoT and cloud-based CKD diagnosis model, is presented in this paper. The CKD diagnosis steps in the QFPA- DNN model involve data gathering, preparation, feature selection and classification stages.

Cancer of the breast is a deadly disease that can take a person’s life in many different ways. Predicting breast cancer at an early stage is crucial in the fight to end the disease. The usage of deep learning and blockchain technology has been implemented with the intention of integrating optimal prediction with clinical diagnostics and protecting private health information. Patients’ medical records are encrypted and stored in the blockchain for maximum safety. As a result, a large portion of time and energy is spent on feature engineering, a tedious process that requires prior expert domain knowledge of the data to develop effective features, and is crucial to the success of most conventional classification systems. Deep learning, on the other hand, can arrange the discriminative information in the data without the need for a domain expert to develop feature extractors. The research community and industry have paid attention to deep, feedforward networks like convolutional neural networks (CNNs) because of their empirical results in areas including speech recognition, signal processing, object recognition, natural language processing, and transfer learning. For the best breast cancer prediction, a new method called a “Hybrid CNN” combining the Sine Cosine Algorithm (SCA) with a transfer learning algorithm has been presented. Mini-batch size and drop-out rate are just two of the factors that the SCA algorithm may fine-tune. To stop the model from overfitting, we employ a transfer learning strategy. The hyperparameters found using sine cosine algorithm is used in Visual geometry Group (VGG 16) architecture. ImageNet is used to pretrain the network and last three convolutional layers are trained using transfer learning. The integration of sine cosine algorithm and transfer learning together increases the accuracy thereby preventing the model from overfitting. The experimentation is performed in Google Colab and the proposed Hybrid CNN is compared with existing methodologies such as K-NN, SVM. Also, the proposed Hybrid CNN is compared with CNN without transfer learning and CNN without SCA. The metrics taken into account for comparison are accuracy, sensitivity, specificity, F-score. The proposed Hybrid CNN achieves 96.9% accuracy that shows the effectiveness of the integration of SCA and transfer learning.

With the broader development of networking, data acquired from IoT and big data have grown significantly in various real-time applications. It provides a transparent role of human life as it shows an extensive bond with data provisioning. On the other hand, it has some challenging issues like verification of authenticity of the enormous data over an un-trusted environment like cloud. It causes privacy leakage, delay, and unidentified data size by third-party. Thus, there is a need for a novel authentication to handle all these problems using a tree data structure for establishing authentication for privacy preservation. Here, a novel graph-based traversing algorithm (GTA) is proposed for realizing the data stream verification and validates the arrival of data streams. This model reduces the failure rate and improves the authentication mechanism and robustness. An integrity verification scheme is used to handle privacy leakage issues during third-party analysis. The simulation is performed in MATLAB 2016b environment to project the significance of the model, and the outcomes are more desirable for authentication and privacy preservation during practical examination. Here, metrics like path length, total verification time, and total insertion time are evaluated. The proposed model gives a better trade-off compared to existing approaches. The path length variation of GTA is 1.3, 1.4, and 1.5 for depth rates 6, 8, and 10, respectively. The total verification time with data size is 1, 2, 3, and 4GB, respectively. The total insertion time of GTA is 5, 10, 15, and 18s for 1, 2, 3, and 4GB, respectively. It is remarkably lesser than P-ATHAT and Merkle tree, respectively. The time needed for two successive data verification is 16, 23, 43, and 57s for data sizes of 1, 2, 3, and 4GB, respectively. The proposed model consumes 15, 28, 44, and 54s, respectively, for the data size from 1GB to 4GB.

This work presents a novel multi-class detection approach for predicting car damage due to accidents or other reasons. The proposed prediction model intends to extract the class information to analyze the objects over the frames. Here, a novel masking-based deep convolutional neural network (MD-CNN) is proposed to capture the car parts’ regions and the classification process. The proposed model works well compared to the various existing approaches. The computation is initiated with the acquisition of damaged images, and pre-processing is performed for data labeling, which is further divided into training and testing samples. The features are internally analyzed by the proposed MD-CNN model, where the internal feature extraction process is a significant advantage with the classification process. The simulation is done in MATLAB 2020a environment where various performance metrics like accuracy, precision, $F$-measure, recall and detection rate are evaluated and compared with conventional learning approaches. The model gives an average precision of 94.5% and $F$1-score of 91% which is higher than other approaches. The proposed model establishes a better trade-off among the prevailing approaches with superior prediction accuracy.

Detection of any disease in the early stage can save a life. There are many medical imaging modalities like MRI, FMRI, ultrasound, CT, and X-ray used in the detection of disease. In the last decades, neural network-based methods are effective in detecting and classifying the disease based on abnormalities present in the medical images. Acute laryngotracheobronchitis (croup) is one of the common diseases seen in children among the 0.5–3 years age group which infects the respiratory system that can cause the larynx, trachea, and bronchi. Prior detection can lower the risk of spreading and can be treated accurately by a pediatrician. Commonly this infection can be diagnosed though physical examination. But due to the similarity of Covid-19 symptoms urges the physicians to get accurate detection of this disease using X-ray and CT images of the infant’s chest and throat. The proposed work aims to develop a croup diagnose system (CDS) which identify the Croup infection through post anterior (PA) view of pediatric X-ray using deep learning algorithm. We used the well-known transfer learning algorithm VGG19 and ResNet50. Data augmentation being adapted for reducing the overfitting and to improve the quantity of image samples. We show that the proposed transfer learning based CDS method can be used to classify the X-ray images into two classes namely, croup and normal. The experiment results confirm that VGG19 performs better than ResNet50 with promising classification accuracy (90.91%.). The results show that the proposed CDS models can be used for more pediatric medical image classification problem.

Medical image analysis gains huge advancements with deep learning approaches which boosts the computational capability and accurate prediction. An expert in the field analyzes the feature representation, and an intelligent model helps to categorize and forecast diseases. The MRI images from cancer imaging archives are used to give a novel learning approach for soft tissue diagnosis. This work suggests a Type-2 fuzzy model that chooses local and maximum absolute value to handle the data. According to the experimental investigation, the predicted model works better than several current strategies. Deep convolutional neural networks built on the VGG-16 architecture and the Adam optimizers are used to pre-train the proposed model. The classification accuracy is anticipated based on the experimentation, demonstrating the need for complementary information for learning systems. The goal is to forecast the depth of knowledge extraction by boosting pre-trained CNN’s ability to be fine-tuned by improving the accuracy of soft tissue classification. The proposed model improves performance and validates the significance of the network model by categorizing the tissues as benign or cancerous. The proposed model attains 96.8% accuracy and 9% for depths of 5 and 8 mm and 93% for 10 mm. Similarly, the model attains 96.8% without inclusion, 100% with inclusion and an average outcome of 99%.

Brain disease is considered a major cause of increased mortality worldwide. Clinical decision support system (CDSS) is utilized for predicting individuals with brain disease in its earlier state. This work proposes a novel disease prediction approach for earlier prediction by handling the dataset issues, where an improved SMOTE sampling approach is used for balancing the target data distribution. Then, Extreme Convolutional Network Model ($\mathrm{\text{XCNM}})$ is used for predicting the disease with better accuracy. For the validation purpose, two publicly available ADNI-1 and ADNI-2 online datasets are used for the model construction, and the outcomes are compared with other techniques like Support Vector Machine (SVM), Artificial Neural Network (ANN), Voxel-based SVM (VW-SVM), standard Convolutional Neural Network (CNN), Deep Neural Network (DNN) and Weighted-Score Multimodal DNN (WS-MTDNN). The outcomes show that the proposed $\mathrm{\text{XCNM}}$ model outperforms various existing approaches with 94% and 95% accuracies on the input ADNI-1 and ADNI-2 datasets. Also, the CDSS-based framework is designed to assist the doctors in critical cases and help reduce the mortality rate.

Evolution of Wireless sensor networks (WSN) has found its identity in Wireless Body Area Networks (WBAN) to monitor the health status of adults undergone a surgery, etc. In addition, the mobility of the sensor nodes deployed on/in the human body plays a vital role in maintaining the accuracy of the physiological signal. In this paper, a Distributed Posture-based Traffic-Medium Access Control (DPT-MAC) protocol is proposed where the sensor nodes follow the Disc Communication model for the detection of neighbor nodes based on the proximity of the sensing range. Further, the modified IEEE 802.15.4 superframe structure determines the potential sleep posture of a subject to ensure a collision-free data transmission and prioritize the data traffic based on the criticality of the data like critical, periodic and nonregular data. The critical data detection occupies the channel on high priority and will have the probability to access the other channel space during the contention period of the noncritical data. The regular guaranteed time slot (GTS) is reduced from the tradition number of slots to five, which allows the nodes to handle the throughput. This uninterrupted data transmission minimizes the delay rate and collision ratio with any number of sensor nodes as the channel synchronization is strictly followed using the Carrier Sense Multiple Access/Collision Avoidance mechanism. Here, the optimization of the network quality parameters like energy consumption, throughput, delay and collision ratio assures a guaranteed increase in the Network Lifetime. The results show that the distributed topology outperforms the conventional star topology in sustaining the Network Lifetime.