Early detection lowers the death rate and allows for prompt treatment of the exhausted individual with neurodegenerative diseases. Most existing classification studies can either not generate probabilistic predictions or consider uncertainty, or do not reflect medical practice, where patients may have unusual variations, comorbidities, or early stages of the disease. This research proposes a novel method for classifying patients and healthy individuals from other distinctive neurodegenerative diseases that consider ambiguity and spatial information. Based on improved deep learning models, we presented a multi-class neurodegenerative disease classification in this research that accurately conducts multi-class or three-class classifications. First, we use various pre-processing methods to make the data suitable for analysis, such as noise reduction, contrast improvement, and data augmentation. The CapsNet model is then used to extract the images’ valuable features. Then, the multi-class classifications of neurodegenerative diseases are classified using the Modified DenseNet-169 model. After classification, the accurate delineation of disease regions is effectively segmented using the Enhanced DeepLabV3+ model. Aided by the PPMI and ADNI datasets, this Multi-class Neurodegenerative Disease Dataset (MNDD) was generated. The outcomes of our experiments illustrate that the proposed model attains an exceptional accuracy of 99.27% on Dataset 1 and 99.14% on Dataset 2, surpassing the performance of several well-known existing deep learning models. Through advanced deep-learning techniques and image segmentation, this research improves early diagnosis and treatment outcomes in neurodegenerative disease classifications.

Kidney tumor segmentation from MR images became a pivotal research area in kidney cancer diagnosis and treatment planning. Accurate and efficient segmentation enables precise tumor localization, treatment planning, and monitoring of disease progression. Former studies have demonstrated the remarkable capability of the U-Net architecture in semantic segmentation of kidney tumors. A recent variant of the U-Net architecture, known as 3D-CU-Net, has been specifically designed with fully-connected dense skip connections to tackle the kidney tumor segmentation challenges related to network depth invariance, segmentation errors, and enforced feature fusion. While the 3D-CU-Net model demonstrated improved effectiveness in kidney tumor segmentation, it still exhibits significant limitations, including challenges in precise localization, fixed feature selection, image diversity, limited contextual information, and computational complexity. To address the limitations of the 3D-CU-Net model, this paper introduces the Attention 3D-CU-Net as a novel variant. The attention-based mechanism is seamlessly integrated with the 3D-CU-Net, prioritizing informative features to enhance segmentation accuracy by concentrating on selective regions. This innovative approach serves to significantly improve the model’s performance, particularly in challenging cases. The proposed model is evaluated on the TCGA-KIRC dataset, a widely used benchmark for kidney tumor segmentation. In comparative experiments, we evaluated the results using metrics like IoU, DSC and accuracy. Our Attention 3D-CU-Net model outperforms the baseline 3D-CU-Net and U-Net with notably higher scores: IoU (0.92), DSC (0.94), and accuracy (0.96).

In the digital age, social media platforms are becoming vital tools for generating and detecting deepfake news due to the rapid dissemination of information. Unfortunately, today, fake news is being developed at an accelerating rate that can cause substantial problems, such as early detection of fake news, a lack of labelled data available for training, and identifying fake news instances that still need to be discovered. Identifying false news requires an in-depth understanding of authors, entities, and the connections between words in a long text. Unfortunately, many deep learning (DL) techniques have proven ineffective with lengthy texts to address these issues. This paper proposes a TL-MVF model based on transfer learning for detecting and generating deepfake news in social media. To generate the sentences, the T5, or Text-to-Text Transfer Transformer model, was employed for data cleaning and feature extraction. In the next step, we designed an optimal hyperparameter RoBERTa model for effectively detecting fake and real news. Finally, we propose a multiplicative vector fusion model for classifying fake news from real news efficiently. A real-time and benchmarked dataset was used to test and validate the proposed TL-MVF model. For the TL-MVF model, F-score, accuracy, precision, recall, and AUC were performance evaluation measures. As a result, the proposed TL-MVF performed better than existing benchmarks.

Software systems have grown significantly and in complexity. As a result of these qualities, preventing software faults is extremely difficult. Software defect prediction (SDP) can assist developers in finding potential bugs and reducing maintenance costs. When it comes to lowering software costs and assuring software quality, SDP plays a critical role in software development. As a result, automatically forecasting the number of errors in software modules is important, and it may assist developers in allocating limited resources more efficiently. Several methods for detecting and addressing such flaws at a low cost have been offered. These approaches, on the other hand, need to be significantly improved in terms of performance. Therefore in this paper, two deep learning (DL) models Multilayer preceptor (MLP) and deep neural network (DNN) are proposed. The proposed approaches combine the newly established Whale optimization algorithm (WOA) with the complementary Firefly algorithm (FA) to establish the emphasized metaheuristic search EMWS algorithm, which selects fewer but closely related representative features. To find the best-implemented classifier in terms of prediction achievement measurement factor, classifiers were applied to five PROMISE repository datasets. When compared to existing methods, the proposed technique for SDP outperforms, with 0.91% for the JM1 dataset, 0.98% accuracy for the KC2 dataset, 0.91% accuracy for the PC1 dataset, 0.93% accuracy for the MC2 dataset, and 0.92% accuracy for KC3.