Development of use-specific high-performance cyber-nanomaterial optical detectors by effective choice of machine learning algorithms

Abstract

P( |T) (nm) Unknown Narrow-Band Light arXiv:1912.11751v3 [physics.app-ph] 3 Jan 2020 term reliability can be equal or more important considerations. Although various machine learning (ML) tools are frequently used on sensor and detector networks to address these considerations and dramatically enhance their functionalities, nonetheless, their effectiveness on nanomaterials-based sensors has not been explored. Here, we show that the best choice of ML algorithm in a cyber-nanomaterial detector is largely determined by the specific useconsiderations, including accuracy, computational cost, speed, and resilience against drifts and long-term ageing effects. When sufficient data and computing resources are provided, the highest sensing accuracy can be achieved by the k-nearest neighbors (kNN) and Bayesian inference algorithms, however, these algorithms can be computationally expensive for real-time applications. In contrast, artificial neural networks (ANN) are computationally expensive to train (off-line), but they provide the fastest result under testing conditions (on-line) while remaining reasonably accurate. When access to data is limited, support vector machines (SVMs) can perform well even with small training sample sizes, while other algorithms show considerable reduction in accuracy if data is scarce, hence, setting a lower limit on the size of required training data. We also show by tracking and modeling the long-term drifts of the detector performance over large (i.e. one year) time-frame, it is possible to dramatically improve the predictive accuracy without the need for any recalibration. Our research shows for the first time that if the ML algorithm is chosen specific to the use-case, lowcost solution-processed cyber-nanomaterial detectors can be practically implemented under diverse operational requirements, despite their inherent variabilities.

RETRACTED ARTICLE: Study of integration of block chain and Internet of Things (IoT): an opportunity, challenges, and applications as medical sector and healthcare

“…As soon as they are connected with the internet and with other devices, they turn out to be an interrelated and intricate system. Hence, the system becomes open to web attacks (Hejazi et al 2020). Conversely, a generic "one-size-fits-all" security model is tough to contrivance.…”

“…There is a necessity for innovative security models predicting the specific policies' development. The best practices should be accomplished both security-by-design methods with specific technical hostage measures designed at various technological stacks (Rao et al 2018;Hejazi et al 2020).…”

Internet of Things (IoT) Cybersecurity: Literature Review and IoT Cyber Risk Management

“…While many IoT devices are designed to be low energy and lightweight, they often collect enormous amounts of data from the environment in real time and therefore apply various energy-saving methods. Technologies such as machine learning are often used to make reliable inferences from the data generated [12]. However, due to the resource-constrained capacity of devices, embedding computation-intensive security and privacy measures into lightweight IoT devices has been challenging [13][14][15][16].…”

MoS2 Nanosheets with Narrowest Excitonic Line Widths Grown by Flow-Less Direct Heating of Bulk Powders: Implications for Sensing and Detection

“…[1][2][3][4][5] With an atomically-thin layers confined in a 2D plane, 2D-TMDs manifest remarkable properties including indirect-to-direct bandgap switching, [6][7][8] emergent photoluminescence, 9 strong photovoltaic response, 6,9 anomalous lattice vibrations, 10 strong light-matter interactions at heterojunctions, [11][12][13][14] valley-selective circular dichroism, [15][16][17] excitonic dark states, [18][19][20] control of valley polarization using optical helicity, 21,22 and field-induced transport with a current ON-OFF ratio exceeding 10 8 , 23,24 that gives 2D-TMDs immense potential for transistors, photodetectors, sensors, many other applications. [25][26][27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42] Among the variety of materials being investigated, the thinnest semiconductor, 25 molybdenum disulfide (2D-MoS 2 ), exhibits p...…”

“…Two-dimensional transition metal dichalcogenides (2D-TMDs) are beyond-graphene layered materials that have become the new platform for studying the physics of 2D semiconductors. With atomically thin layers confined in a 2D plane, 2D-TMDs manifest remarkable properties including indirect-to-direct band gap switching, emergent photoluminescence, strong photovoltaic response, anomalous lattice vibrations, strong light–matter interactions at heterojunctions, valley-selective circular dichroism, excitonic dark states, control of valley polarization using optical helicity, and field-induced transport with a current ON–OFF ratio exceeding 10 8 , that give 2D-TMDs immense potential for transistors, photodetectors, sensors, and many other applications. − Among the variety of materials being investigated, the thinnest semiconductor, molybdenum disulfide (2D-MoS 2 ), exhibits promising prospects for low-cost, highly sensitive, and flexible next-generation optoelectronic, nanoelectronic, photovoltaic, and valleytronic applications. Unlike graphene that does not manifest a band gap, 2D-MoS 2 has a layer thickness-dependent band gap, which is indirect in the bilayer and above but becomes direct in the monolayer limit .…”