Reputation systems aim to reduce the risk of loss due to untrustworthy participants by providing a mechanism for establishing trustworthiness between mutually unknown online entities in an information asymmetric e-market. These systems encourage honest behavior and discourage malicious behavior of buyer and seller agents by laying a foundation for security and stability in the e-market. However, the success of a reputation system depends on its built-in resilience capabilities to foil various attacks. This paper focuses on how to safeguard buyers from dishonest sellers and advisors by incorporating an attack resilient reputation computation methodology. The objectives of the proposed dynamic reputation system in the distributed environment are to reduce the incentive for behaving dishonestly, and to minimize harm in case of attacks by dishonest participants with the inherent purpose of improving the quality of services in the e-market.

Depth of Anesthesia is the degree of reversible unconsciousness achieved through anesthetic agents. An appropriate anesthetic depth must be maintained during surgical procedures to prevent perioperative complications. Electroencephalogram (EEG) signals allow us to capture the extent of brain activity in various stages of anesthesia. EEG signals thereby help anesthesiologists make informed decisions regarding the administration of anesthesia based on the extent of brain activity displayed by a patient. Bi-spectral Index (BIS) monitors use features extracted from EEG signal to display the depth of anesthesia as a value between 0 and 100. However, the algorithm behind BIS monitors’ functioning is unknown and these are costly machines. Under these circumstances, patient care or monitoring becomes entirely dependent on anesthesiologists’ experience. In this paper, we propose a model using deep Convolutional Neural Network (CNN) to predict the depth of anesthesia into three classes (Anesthesia Light, Anesthesia OK, Anesthesia Deep). The input of this network is a spectrogram obtained using Short-Time Fourier Transform (STFT) applied to EEG signals. This choice of using an STFT-derived spectrogram was made based on CNN’s superior performance over raw EEG waveforms-based CNN. The trained model achieved an accuracy of 90.8%. Experimental results reveal that the proposed scheme utilizing spectrograms achieves either superior or similar performance as compared to other works for accuracy and sensitivity even though it uses relatively fewer parameters. Further, beyond traditional evaluation metrics, this study employs F1-score and precision as additional criteria for assessing the proposed scheme, offering a comprehensive view of its efficacy.

This paper introduces a new Neutrosophic Adaptive Neuro-Fuzzy Inference System paired with Explainable Artificial Intelligence to classify oral cancer from clinical photos. The ANFIS model’s interpretability and accuracy have been enhanced in resolving challenging medical images by deploying Neutrosophic logic on a 1000-image dataset to solve the word indeterminacy. A combination of Neutrosophic sets addresses ambiguity, enabling an adaptive neuro-fuzzy network to learn from data to accurately classify oral cancer. This exhibits the benefits of fuzzy logic and neural networks in action. The parameters of this model have been changed meticulously to increase sensitivity, specificity, and accuracy toward diagnostic readiness. These results reflect a substantive enhancement in the model’s ability to distinguish between benign and malignant lesions by delivering accurate and understandable diagnostic decisions existence for clinical adoption. AI medical diagnostic confidence increases the understanding of how the model makes decisions. The ideal objective is to develop a strong, dependable, and easy-to-understand tool to diagnose cancer early. The experimentation on this model can be improved as it may lead to real-time testing, more data for the testing dataset, and using how many types of cancer the model can be applied.