Brain tumor is a deadly disease and its classification is a challenging task for radiologists because of the heterogeneous nature of the tumor cells. Recently, computer-aided diagnosis-based systems have promised, as an assistive technology, to diagnose the brain tumor, through magnetic resonance imaging (MRI). In recent applications of pre-trained models, normally features are extracted from bottom layers which are different from natural images to medical images. To overcome this problem, this study proposes a method of multi-level features extraction and concatenation for early diagnosis of brain tumor. Two pretrained deep learning models i.e. Inception-v3 and DensNet201 make this model valid. With the help of these two models, two different scenarios of brain tumor detection and its classification were evaluated. First, the features from different Inception modules were extracted from pre-trained Inception-v3 model and concatenated these features for brain tumor classification. Then, these features were passed to softmax classifier to classify the brain tumor. Second, pre-trained DensNet201 was used to extract features from various DensNet blocks. Then, these features were concatenated and passed to softmax classifier to classify the brain tumor. Both scenarios were evaluated with the help of three-class brain tumor dataset that is available publicly. The proposed method produced 99.34 %, and 99.51% testing accuracies respectively with Inception-v3 and DensNet201 on testing samples and achieved highest performance in the detection of brain tumor. As results indicated, the proposed method based on features concatenation using pre-trained models outperformed as compared to existing state-of-the-art deep learning and machine learning based methods for brain tumor classification. INDEX TERMS Deep learning, magnetic resonance imaging, brain tumor classification, pre-trained model, dataset.

No abstract

No abstract

Artificial intelligence (AI) has provided significant help in many fields of life. This study proposed a framework that helped in understanding customers’ attitudes about the adoption of Robo-advisors. The role of the Technology Readiness Index moderated as one of the primary relationships. A total of 208 potential users of Robo-advisor services provided the data that confirmed the validity of the model. This model provided the input for structural equation modeling and analysis of the study hypotheses. The results indicated that consumers showed positive attitudes about Robo-advisor services, with the moderating effect of Technology Readiness Index dimensions, namely, contributors and inhibitors. Perceived ease of use, perceived usefulness, and perceived convenience influenced consumers in developing positive attitudes about this service. Financial businesses can design better AI Robo-advisor services to fulfill the requirements of a wide range of consumers. This proposed framework contributes to the consumers’ understanding of behavioral intentions for the use of Robo-advisors in FinTech.

Due to the rapid advancement of technology, the volume of online text data from numerous various disciplines is increasing significantly over time. Therefore, more work is needed to create systems that can effectively classify text data in accordance with its content, facilitating processing and the extraction of crucial information. Since these non-automated systems use manual feature extraction and classification, which is error-prone and time-consuming by choosing the best appropriate algorithms for feature extraction and classification, traditional procedures are typically resource intensive (computational, human, etc.), which is not a viable solution. To address the shortcomings of traditional approaches, we offer a unique text categorization strategy based on a well-known DL algorithm called BERT. The proposed framework is trained and tested using cutting-edge text datasets, such as the UCI email dataset, which includes spam and non-spam emails, and the BBC News dataset, which includes multiple categories such as tech, sports, politics, business, and entertainment. The system achieved the highest accuracy of 91.4% and can be used by different organizations to classify text-based data with a high performance. The effectiveness of the proposed framework is evaluated using multiple evaluation metrics such as Accuracy, Precision, and Recall.