Identification and classification of exfoliated graphene flakes from microscopy images using a hierarchical deep convolutional neural network

Mahjoubi, Soroush; Ye, Fan; Bao, Yi; Meng, Weina; Zhang, Xian

doi:10.1016/j.engappai.2022.105743

Cited by 9 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the analysis of data obtained by conventional instruments (optical microscopes, Raman microscopes, and atomic force microscopes) relies so heavily on the “intuition” of experienced researchers, making such process both time‐consuming and unreliable. Therefore, several ML models, such as CNN, [ 99 , 100 , 101 , 102 , 103 , 104 ] K‐means clustering (KMC), [ 106 , 108 ] SVM, [ 11 , 110 ] and RF, [ 111 ] have been developed to address this issue. Of these models, CNN has unrivalled advantages in terms of image segmentation and object classification, and hence is favored by researchers for identifying the number of layers of atom‐scale sheets on microscopic images.…”

Section: Characterizing 2d Materialsmentioning

confidence: 99%

“…[ 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 90 , 91 , 92 ] In terms of preparing 2D materials, ML methods have been applied to deposition and exfoliation to enable easier and more controllable preparation of 2D materials such as WTe 2 , [ 93 ] MoS 2 , [ 94 , 95 , 96 ] and WS 2 . [ 97 , 98 ] When it comes to characterizing 2D materials, ML has been combined with characterization techniques, like Raman spectroscopy, transmission electron microscopy, optical microscopy, and imaging, to acquire accurate information such as the thickness [ 99 , 100 , 101 , 102 , 103 , 104 , 105 , 106 , 107 , 108 , 109 , 110 , 111 , 112 , 113 ] and defects [ 114 , 115 , 116 , 117 ] of materials. The utilization of ML in 2D materials research, along with the algorithmic processing of experimental data, has the potential to support data analysis, leading to more conclusive results on the reliability and reproducibility of given datasets.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

When Machine Learning Meets 2D Materials: A Review

Lu,

Xia,

Ren

et al. 2024

Advanced Science

View full text Add to dashboard Cite

The availability of an ever‐expanding portfolio of 2D materials with rich internal degrees of freedom (spin, excitonic, valley, sublattice, and layer pseudospin) together with the unique ability to tailor heterostructures made layer by layer in a precisely chosen stacking sequence and relative crystallographic alignments, offers an unprecedented platform for realizing materials by design. However, the breadth of multi‐dimensional parameter space and massive data sets involved is emblematic of complex, resource‐intensive experimentation, which not only challenges the current state of the art but also renders exhaustive sampling untenable. To this end, machine learning, a very powerful data‐driven approach and subset of artificial intelligence, is a potential game‐changer, enabling a cheaper – yet more efficient – alternative to traditional computational strategies. It is also a new paradigm for autonomous experimentation for accelerated discovery and machine‐assisted design of functional 2D materials and heterostructures. Here, the study reviews the recent progress and challenges of such endeavors, and highlight various emerging opportunities in this frontier research area.

show abstract

Section: Characterizing 2d Materialsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

When Machine Learning Meets 2D Materials: A Review

Lu,

Xia,

Ren

et al. 2024

Advanced Science

View full text Add to dashboard Cite

show abstract

“…Addressing these challenges requires collaboration between researchers, manufacturers, policymakers, and end-users to balance innovation, safety, and accessibility. Despite these challenges, the practical benefits of nanomaterials in adaptive devices have already demonstrated their transformative potential in enhancing the lives of individuals with disabilities, and continued research and innovation in this area hold the key to furthering inclusivity and empowerment for all (Zhang et al, 2022;Mahjoubi et al, 2023).…”

Section: Journal Of Disability Research 2024mentioning

confidence: 99%

Nanotechnology and Prosthetic Devices: Integrating Biomedicine and Materials Science for Enhanced Performance and Adaptability

Karim,

Siddiqui,

Assaifan

et al. 2024

Journal of Disability Research

View full text Add to dashboard Cite

Nanomaterials are revolutionizing prosthetic device development. Nanotechnology has made prosthetic devices that replicate natural limb behavior and respond to users’ intentions possible. Nanomaterials improve prosthetic functionality, comfort, and lifespan. Nanocomposites, smart sensors, and medication delivery systems have addressed mechanical strength, control, and biocompatibility, resulting in enhanced prosthetic devices that improve user freedom, mobility, and quality of life. Biomedicine and materials science have helped nanomaterials reach their full potential, enabling their seamless integration into prosthetic devices and fostering interdisciplinary collaborations that advance prosthetics. The literature study shows substantial advances in nanomaterials for prosthetic devices; however, various gaps in present research and possible future research areas are indicated. First, long-term biocompatibility studies are needed to understand nanomaterials’ long-term effects on humans. Nanomaterial-based prosthetic devices must be tested and researched to assure safety and efficacy in real-world situations. Second, nanocomposites and nanoscale components must be standardized and quality-controlled to enable consistency and scalability in prosthetic devices. Third, nanoscale sensor and neural interface ethics must address privacy, security, and user consent issues. The nanomaterial-based prosthetic devices must be made more inexpensive and accessible to more disabled people. The study design was carried out to incorporate significant literature on the application of nanotechnology related to prosthetic devices. The literature was filtered from the Scopus database. The selected literature belongs to the original articles in which experimental work was carried out. Future research could combine nanotechnology with other developing technologies like artificial intelligence and robotics to produce more advanced and adaptable prosthetic devices.

show abstract

“…Since graphene was first exfoliated in 2004, two-dimensional (2D) materials [ 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 ], with their atomically thin crystalline structure, have received extensive research attention due to their unique atomically thin structure and novel physical properties. They have unique electronic [ 1 , 2 , 3 , 7 , 9 ], optical [ 4 , 7 , 10 , 11 , 12 ], mechanical [ 13 ], and energy harvesting [ 14 , 15 , 16 ] properties for enabling novel 2D devices that make them ideal materials and platforms for future information technology devices [ 14 , 17 , 18 , 19 , 20 ].…”

Section: Introductionmentioning

confidence: 99%

Experimental and Theoretical Investigations of Direct and Indirect Band Gaps of WSe2

Wang,

Zhang

2024

Micromachines

Self Cite

View full text Add to dashboard Cite

Low-dimension materials such as transition metal dichalcogenides (TMDCs) have received extensive research interest and investigation for electronic and optoelectronic applications. Due to their unique widely tunable band structures, they are good candidates for next-generation optoelectronic devices. Particularly, their photoluminescence properties, which are fundamental for optoelectronic applications, are highly sensitive to the nature of the band gap. Monolayer TMDCs in the room temperature range have presented a direct band gap behavior and bright photoluminescence. In this work, we investigate a popular TMDC material WSe2’s photoluminescence performance using a Raman spectroscopy laser with temperature dependence. With temperature variation, the lattice constant and the band gap change dramatically, and thus the photoluminescence spectra are changed. By checking the photoluminescence spectra at different temperatures, we are able to reveal the nature of direct-to-indirect band gap in monolayer WSe2. We also implemented density function theory (DFT) simulations to computationally investigate the band gap of WSe2 to provide comprehensive evidence and confirm the experimental results. Our study suggests that monolayer WSe2 is at the transition boundary between the indirect and direct band gap at room temperature. This result provides insights into temperature-dependent optical transition in monolayer WSe2 for quantum control, and is important for cultivating the potential of monolayer WSe2 in thermally tunable optoelectronic devices operating at room temperature.

show abstract

Identification and classification of exfoliated graphene flakes from microscopy images using a hierarchical deep convolutional neural network

Cited by 9 publications

References 39 publications

When Machine Learning Meets 2D Materials: A Review

When Machine Learning Meets 2D Materials: A Review

Nanotechnology and Prosthetic Devices: Integrating Biomedicine and Materials Science for Enhanced Performance and Adaptability

Experimental and Theoretical Investigations of Direct and Indirect Band Gaps of WSe2

Contact Info

Product

Resources

About