Multi‐gradient‐direction based deep learning model for arecanut disease identification

Mallikarjuna, S. B.; Shivakumara, Palaiahnakote; Khare, Vijeta; Basavanna, M.; Pal, Umapada; Poornima, B.

doi:10.1049/cit2.12088

Cited by 31 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the sensitivity analysis in this paper only focuses a single factor, and multifactor changes can be investigated in the future. In this case, various new approaches, e.g., deep learning [36][37][38][39][40], artificial neural network [41], etc., enable us consider a wide range of factors in estimating the near-to-exact response of various structures, which warrants further investigations in the future.…”

Section: Discussionmentioning

confidence: 99%

Sensitivity Analysis of Structural Parameters of Unequal-Span Continuous Rigid Frame Bridge with Corrugated Steel Webs

Duan,

Wang,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

To investigate the effect of structural parameters of bridges with unequal spans on the bridge alignment, the finite element model simulating the full-scale bridge was developed, considering the construction process. For ease of finite element modeling and investigation, the section of composite beam with corrugated steel web was first converted into the section composed of the same material. For this purpose, an equivalent method of replacing corrugated steel webs with concrete webs was proposed based on theoretical derivation. After equivalent replacement, the influences of material bulk density, internal prestress, pipe friction coefficient, and pipe deviation coefficient on the main beam at the maximum cantilever stage were analyzed, and the influences of external prestress on the main beam after bridge construction were analyzed. The results show that the most sensitive parameter to structural response is bulk density, subsequently the external prestress, internal prestress, pipe friction coefficient, and pipe deviation coefficient. Among them, the bulk density, internal prestress, and external prestress are all sensitive parameters, while pipe friction coefficient and pipe deviation coefficient are non-sensitive parameters.

show abstract

Section: Discussionmentioning

confidence: 99%

Sensitivity Analysis of Structural Parameters of Unequal-Span Continuous Rigid Frame Bridge with Corrugated Steel Webs

Duan,

Wang,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…When the low system traffic, the hop count-based routing scheme shows advantages, however, when the system traffic increase, this routing scheme presents disadvantages and provides the system performance is lower compared to others. According to our vision with the booming development of edge computing, 50 depending on the network environment context such as mobility, density, deep learning, and capacities of IoT devices, 51,52 the performance factors should be flexibly identified relying on edge computing aiming to optimize achieved performance.…”

Section: F I G U R Ementioning

confidence: 99%

A cross‐layer routing approach for MANET‐assisted IoT applications

Quy,

Van Anh,

Ban

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

The Internet of things (IoT) is a concept that allows all things such as sensors, actuators, humans, platforms, and software to interact with others relying on Internet infrastructure. The launch of the 5th generation communication networks allows providing network services with extremely high performance aiming to realize IoT concepts and forming a series of other smart IoT ecosystems. Nowadays, IoT is emerging as a dominant technology in almost domain. One of the most crucial technologies forming IoT networks is device‐to‐device (D2D) communication. D2D technology allows mobile nodes self‐setup, and self‐config to identify optimal paths for data transmission without relying on pre‐installed infrastructure, which is the principle of forming mobile ad‐hoc networks (MANETs). The fusing of MANETs and IoT technologies forming MANET‐assisted IoT networks architecture to provide abilities and novel unpredict services. However, mobility and network structure often change are the main limitations of this architecture, hence, identifying the optimal route is a significant challenge. In this study, we propose a cross‐layer routing approach for MANET‐assisted IoT networks. Our routing mechanism is based on considering three factors, including number of hops, link quality, and queue length. The simulation results show that our proposed solution improves performance compared to the traditional solutions. We hope that our simple and efficient solution will be applied popular for future MANET‐assisted IoT networks.

show abstract

“…Recent advances in machine learning in Materials Science and Engineering have provided material scientists with new tools to expedite the collection of microstructure properties. These advancements include deep learning, programming question generation, and automated control and calibration [78][79][80][81][82][83][84][85][86][87]. HPC also continues to expand along with computing offload [88].…”

Section: Future Improvementsmentioning

confidence: 99%

Reduced-Dimension Surrogate Modeling to Characterize the Damage Tolerance of Composite/Metal Structures

Arndt,

Crusenberry,

Heng

et al. 2023

Modelling

View full text Add to dashboard Cite

Complex engineering models are typically computationally demanding and defined by a high-dimensional parameter space challenging the comprehensive exploration of parameter effects and design optimization. To overcome this curse of dimensionality and to minimize computational resource requirements, this research demonstrates a user-friendly approach to formulating a reduced-dimension surrogate model that represents a high-dimensional, high-fidelity source model. This approach was developed specifically for a non-expert using commercially available tools. In this approach, the complex physical behavior of the high-fidelity source model is separated into individual, interacting physical behaviors. A separate reduced-dimension surrogate model is created for each behavior and then all are summed to formulate the reduced-dimension surrogate model representing the source model. In addition to a substantial reduction in computational resources and comparable accuracy, this method also provides a characterization of each individual behavior providing additional insight into the source model behavior. The approach encompasses experimental testing, finite element analysis, surrogate modeling, and sensitivity analysis and is demonstrated by formulating a reduced-dimension surrogate model for the damage tolerance of an aluminum plate reinforced with a co-cured bonded E-glass/epoxy composite laminate under four-point bending. It is concluded that this problem is difficult to characterize and breaking the problem into interacting mechanisms leads to improved information on influential parameters and efficient reduced-dimension surrogate modeling. The disbond damage at the interface between the resin and metal proved the most difficult mechanism for reduced-dimension surrogate modeling as it is only engaged in a small subspace of the full parameter space. A binary function was successful in engaging this damage mechanism when applicable based on the values of the most influential parameters.

show abstract

Multi‐gradient‐direction based deep learning model for arecanut disease identification

Cited by 31 publications

References 21 publications

Sensitivity Analysis of Structural Parameters of Unequal-Span Continuous Rigid Frame Bridge with Corrugated Steel Webs

Sensitivity Analysis of Structural Parameters of Unequal-Span Continuous Rigid Frame Bridge with Corrugated Steel Webs

A cross‐layer routing approach for MANET‐assisted IoT applications

Reduced-Dimension Surrogate Modeling to Characterize the Damage Tolerance of Composite/Metal Structures

Contact Info

Product

Resources

About