Deep learning is one of the most unexpected machine learning techniques which is being used in many applications like image classification, image analysis, clinical archives and object recognition.With an extensive utilization of digital images as information in the hospitals, the archives of medical images are growing exponentially. Digital images play a vigorous role in predicting the patient disease intensity and there are vast applications of medical images in diagnosis and investigation. Due to recent developments in imaging technology, classifying medical images in an automatic way is an open research problem for researchers of computer vision. For classifying the medical images according to their relevant classes a most suitable classifier is most important. Image classification is beneficial to predict the appropriate class or category of unknown images. The less discriminating ability and domain-specific categorization are the main drawbacks of low-level features. A semantic gap that exists between features of low-level as machine understanding and features of human understanding as high-level perception. In this research, a novel image representation method is proposed where the algorithm is trained for classifying medical images by deep learning technique. A pre-trained deep convolution neural network method with the fine-tuned approach is applied to the last three layers of deep neural network. The results of the experiment exhibit that our method is best suited to classify various medical images for various body organs. In this manner, data can sum up to other medical classification applications which supports radiologist’s efforts for improving diagnosis.

The flow of data traffic has been vastly increased because of the implementation of the Internet of Things (IoT)-and security is a top need for Internet communication. The encryption-decryption process ensures that data access is restricted to legitimate users. But there is a tradeoff between the level of security and the communication overhead.

Nowadays, electric load forecasting through a data analytic approach has become one of the most active and emerging research areas. It provides future consumption patterns of electric load. Since there are large fluctuations in both electricity production and use, it is a difficult task to achieve a balance between electric load and demand. By analyzing past electric consumption records to estimate the upcoming electricity load, the issue of fluctuating behavior can be resolved. In this study, a framework for feature selection, extraction, and regression is put forward to carry out the electric load prediction. The feature selection phase uses a combination of extreme gradient boosting (XGB) and random forest (RF) to determine the significance of each feature. Redundant features in the feature extraction approach are removed by applying recursive feature elimination (RFE). We propose an enhanced support vector machine (ESVM) and an enhanced convolutional neural network (ECNN) for the regression component. Hyperparameters of both the proposed approaches are set using the random search (RS) technique. To illustrate the effectiveness of our proposed strategies, a comparison is also performed between the state-of-the-art approaches and our proposed techniques. In addition, we perform statistical analyses to prove the significance of our proposed approaches. Simulation findings illustrate that our proposed approaches ECNN and ESVM achieve higher accuracies of 98.83% and 98.7%, respectively.

Effective content caching plays a crucial role in meeting the latency and reliability requirements of Industrial Internet of Things (IIoT) networks. However, existing caching mechanisms in NDN-based IIoT networks often exhibit problems in adaptability, semantic awareness, and structural efficiency, resulting in limited performance in dynamic and resource-constrained environments. This paper introduces the Intelligent Semantic-Aware Caching and Control framework (ISCC), which integrates Cuckoo Hashing with Reinforcement Learning (RL) to enhance content replacement decisions in IIoT networks based on Named Data Networking (NDN). The framework presents a semantic scoring model that integrates content domain, source reliability, and criticality to enhance caching prioritisation. A reinforcement learning (RL) agent utilising Q-learning dynamically chooses actions by using unified caching scores that take into account frequency, time, and semantic fidelity. The results of the simulation indicate that ISCC outperforms conventional strategies, such as FIFO, LRU, and LRFU, in terms of cache hit ratio, semantic fidelity, and latency, achieving up to 23% fewer replacements and a 16% improvement in preserving semantic content. The results show ISCC’s capability to facilitate intelligent and adaptive caching in memory-constrained IIoT environments.

Data and information security is considered to be an important and challenging task for any field of life. But it becomes more critical especially when it deals with the medical field due to life and health hazards. The ratio of internal security threats to external threats always remains high. A huge number of efforts and technical expertise are required in the case of attacking the system from the external environment. But it requires fewer efforts if a system is attacked internally by the stakeholders of the system. This article presents an access control model that secures the medical data of patients against internal cybersecurity threats. It allows only the legitimate users, that is, authorized patients and doctors to communicate despite the fact of physical boundaries. The proposed model implements authorization in combination with permissions and roles instead of roles only for medical staff. It removes the discrepancies in the existing access control models. The proposed model ensures communication among doctors and patients in a secure, private, and efficient manner. The model is demonstrated by using mathematical modeling along with implementation examples. The proposed model outperformed in comparison with state-of-the-art access control models.