Skin cancer is the most commonly diagnosed and reported malignancy worldwide. To reduce the death rate from cancer, it is essential to diagnose skin cancer at a benign stage as soon as possible. To save lives, an automated system that can detect skin cancer in its earliest stages is necessary. For the diagnosis of skin cancer, various researchers have performed tasks using deep learning and transfer learning models. However, the existing literature is limited in terms of its accuracy and its troublesome and time-consuming process. As a result, it is critical to design an automatic system that can deliver a fast judgment and considerably reduce mistakes in diagnosis. In this work, a deep learning-based model has been designed for the identification of skin cancer at benign and malignant stages using the concept of transfer learning approach. For this, a pre-trained VGG16 model is improved by adding one flatten layer, two dense layers with activation function (LeakyReLU) and another dense layer with activation function (sigmoid) to enhance the accuracy of this model. This proposed model is evaluated on a dataset obtained from Kaggle. The techniques of data augmentation are applied in order to enhance the random-ness among the input dataset for model stability. The proposed model has been validated by considering several useful hyper parameters such as different batch sizes of 8, 16, 32, 64, and 128; different epochs and optimizers. The proposed model is working best with an overall accuracy of 89.09% on 128 batch size with the Adam optimizer and 10 epochs and outperforms state-of-the-art techniques. This model will help dermatologists in the early diagnosis of skin cancers.

Breast cancer has evolved as the most lethal illness impacting women all over the globe. Breast cancer may be detected early, which reduces mortality and increases the chances of a full recovery. Researchers all around the world are working on breast cancer screening tools based on medical imaging. Deep learning approaches have piqued the attention of many in the medical imaging field due to their rapid growth. In this research, mammography pictures were utilized to detect breast cancer. We have used four mammography imaging datasets with a similar number of 1145 normal, benign, and malignant pictures using various deep CNN (Inception V4, ResNet-164, VGG-11, and DenseNet121) models as base classifiers. The proposed technique employs an ensemble approach in which the Gompertz function is used to build fuzzy rankings of the base classification techniques, and the decision scores of the base models are adaptively combined to construct final predictions. The proposed fuzzy ensemble techniques outperform each individual transfer learning methodology as well as multiple advanced ensemble strategies (Weighted Average, Sugeno Integral) with reference to prediction and accuracy. The suggested Inception V4 ensemble model with fuzzy rank based Gompertz function has a 99.32% accuracy rate. We believe that the suggested approach will be of tremendous value to healthcare practitioners in identifying breast cancer patients early on, perhaps leading to an immediate diagnosis.

Alzheimer’s disease (AD) is a degenerative condition of the brain that affects the memory and reasoning abilities of patients. Memory is steadily wiped out by this condition, which gradually affects the brain’s ability to think, recall, and form intentions. In order to properly identify this disease, a variety of manual imaging modalities including CT, MRI, PET, etc. are being used. These methods, however, are time-consuming and troublesome in the context of early diagnostics. This is why deep learning models have been devised that are less time-intensive, require less high-tech hardware or human interaction, continue to improve in performance, and are useful for the prediction of AD, which can also be verified by experimental results obtained by doctors in medical institutions or health care facilities. In this paper, we propose a hybrid-based AI-based model that includes the combination of both transfer learning (TL) and permutation-based machine learning (ML) voting classifier in terms of two basic phases. In the first phase of implementation, it comprises two TL-based models: namely, DenseNet-121 and Densenet-201 for features extraction, whereas in the second phase of implementation, it carries out three different ML classifiers like SVM, Naïve base and XGBoost for classification purposes. The final classifier outcomes are evaluated by means of permutations of the voting mechanism. The proposed model achieved accuracy of 91.75%, specificity of 96.5%, and an F1-score of 90.25. The dataset used for training was obtained from Kaggle and contains 6200 photos, including 896 images classified as mildly demented, 64 images classified as moderately demented, 3200 images classified as non-demented, and 1966 images classified as extremely mildly demented. The results show that the suggested model outperforms current state-of-the-art models. These models could be used to generate therapeutically viable methods for detecting AD in MRI images based on these results for clinical prospective.

Recent technological advancement in wireless communication has led to the invention of wireless body area networks (WBANs), a cutting-edge technology in healthcare applications. WBANs interconnect with intelligent and miniaturized biomedical sensor nodes placed on human body to an unattended monitoring of physiological parameters of the patient. These sensors are equipped with limited resources in terms of computation, storage, and battery power. The data communication in WBANs is a resource hungry process, especially in terms of energy. One of the most significant challenges in this network is to design energy efficient next-hop node selection framework. Therefore, this paper presents a green communication framework focusing on an energy aware link efficient routing approach for WBANs (ELR-W). Firstly, a link efficiency-oriented network model is presented considering beaconing information and network initialization process. Secondly, a path cost calculation model is derived focusing on energy aware link efficiency. A complete operational framework ELR-W is developed considering energy aware next-hop link selection by utilizing the network and path cost model. The comparative performance evaluation attests the energy-oriented benefit of the proposed framework as compared to the state-of-the-art techniques. It reveals a significant enhancement in body area networking in terms of various energy-oriented metrics under medical environments.

The phenomenal increase in the usage of Internet promotes the quality of trust in the scope of the Internet of Things (IoT). Trust is beneficial in the provision of an effective, reliable, scalable, and trustworthy environment to users of the IoT network, where they can share their private information with each other on a secure communication platform. For successful communications among the Internet users, trust is an important factor to provide them with private infrastructures and secure environments, where exchanging data among devices becomes more easy and trustworthy. Therefore, trust management is a backbone for the successful and secure transmission of data among various nodes in a large-scale IoT network. To overcome the security issues, latency, and risk of malicious activities, a lightweight approach is proposed for those nodes in Industrial IoT that cannot maintain security. LightTrust utilizes a centralized trust agent to generate and manage trust certificates that allow nodes to communicate for a specific time without performing trust computations. Trust agents also maintain a trust database to store the current trust degree for the aggregation/propagation purposes. Trust between two nodes is developed by direct observations in terms of compatibility, cooperativeness, and delivery ratio, whereas recommendations are used to develop trust in the context of indirect observations, i.e., experience or previous knowledge. The comparative simulations of the proposed and existing approaches are also performed whereby the results illustrate that the proposed approach efficiently maintains resilience and robust environments.

Drunkenness or tiredness is a leading cause of car accidents, and it has serious consequences for road safety. More fatal accidents can be avoided by alerting tired drivers ahead of time. While driving, several drowsiness detection technologies watch for signs of inattention and alert the driver. It is critical to be aware of such events to avoid potential danger by alerting the driver of their condition and automatically initiating emergency measures in real-time to ensure the safety of all passengers in the vehicle. To overcome this, we need a system that can continuously monitor the driver’s facial expressions and detect facial landmarks to extract their state of expression to determine whether they are sleepy or have extreme changes in their emotions, such as anger. As soon as the system detects such changes, it takes control of the vehicle, immediately slows it down, and alerts the driver by sounding an alarm to make them aware of the situation. The proposed system will be integrated with the vehicle’s electronics, tracking the vehicle’s statistics and providing more accurate results. In this paper, we have implemented real-time image segmentation and drowsiness using machine learning methodologies. In the proposed work, an emotion detection method based on Support Vector Machines (SVM) has been implemented using facial expressions. The algorithm was tested under variable luminance conditions and outperformed current research in terms of accuracy. We have achieved 83.25 % to detect the facial expression change.