Mahin Khan Mahadi

This article presents a novel transition metal nitride (TMN)–based plasmonic pressure sensor (PPS) that utilizes a TMN-Insulator-TMN structure. Our proposed sensor is built with Zirconium Nitride (ZrN), an alternative plasmonic material that provides several benefits over conventional plasmonic metals like silver and gold. Notably, ZrN is compatible with standard Complementary Metal Oxide Semiconductor (CMOS) technology and it offers tunability of optical properties. The sensor demonstrates a maximum pressure sensitivity of 177.56 nm/MPa with a resolution of 5.63 × 10 ^-6 MPa. Furthermore, the incorporation of TMN endows the PPS with several beneficial characteristics, such as exceptional hardness, high-temperature thermal stability, optical tunability, and lower electrical resistivity which are typically absent in conventional plasmonic noble metals, limiting their practical application in plasmonic devices. Consequently, our proposed configuration outperforms the conventional noble material-based Metal-Insulator-Metal (MIM) configuration, which removes the barriers to wide-scale adaptations of plasmonic devices by paving the way for the research and development of efficient, robust, and long-lasting sensors at subwavelength scales, thereby forging a link between nanoelectronics and plasmonics.

The endeavor to detect human activities and behaviors is targeted as a real-time detection mechanism that tends to predict the form of human motions and actions. Though sensors like accelerometer and gyroscopes are noticeable in human motion detection, categorizing unique and individual human gestures require software-based assistance. With the widespread implementation of machine learning algorithms, human actions can be distinguished into multiple classes. Several state-of-the-art machine learning algorithms can be applied to this specified field which will give suitable outcomes, yet due to the bulk of the dataset, complexity can be made apparent, which will reduce the efficiency of the model. In our proposed research, ensemble learning methods have been established by assembling several trained and tuned machine learning models. The adopted dataset for the model has been preprocessed through PCA (principal component analysis), SMOTE oversampling (synthetic minority oversampling technique), and K-means clustering, which reduced the dataset to essentials, keeping the weight of the features intact and reducing complexity. Maximum accuracy of 99.36% was achieved from both stacking and voting ensemble methods.