Ge-Core/a-Si-Shell Nanowire-Based Field-Effect Transistor for Sensitive Terahertz Detection

Deng, Xiaolei; Simanullang, Marolop; Kawano, Yukio

doi:10.3390/photonics5020013

Cited by 18 publications

(7 citation statements)

References 33 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Advances might include more sophisticated algorithms for dynamic pruning and quantization that adapt to real-time data inputs [31][32][33][34][35][36][37][38] , potentially increasing both accuracy and efficiency. In addition, the hardware should be also improved to be more compatible with these algorithms [39][40][41][42][43][44][45] . Furthermore, as edge computing grows, the demand for lightweight models that can operate independently of large data centers will likely increase, amplifying the importance of effective compression techniques.…”

Section: Discussionmentioning

confidence: 99%

Double-Compressed Artificial Neural Network for Efficient Model Storage in Customer Churn Prediction

Lisang Zhou,

Zhang,

Zhou

2024

artif. intell. adv.

View full text Add to dashboard Cite

In the rapidly evolving field of Artificial Intelligence (AI), efficiently storing and managing AI models is crucial, particularly as their complexity and size increase. This paper explores the strategic importance of AI model storage, focusing on performance, cost-efficiency, and scalability within the realm of customer churn prediction, utilizing model compression technologies. Deep learning networks, integral to AI models, have become increasingly large, necessitating millions of parameters. These parameters make the models computationally expensive and voluminous in storage requirements. Addressing these issues, the paper discusses the application of model compression techniques—specifically pruning and quantization—to mitigate the storage and computational challenges. The experimental results demonstrated the effectiveness of the proposed method. These techniques reduce the physical footprint of AI models and enhance their processing efficiency, making them suitable for deployment on resource-constrained devices. Using these models in customer churn prediction in telecommunications illustrates their potential to improve service delivery and decision-making processes. By compressing models, telecom companies can better manage and analyze large datasets, enabling more effective customer retention strategies and maintaining a competitive edge in a dynamic market.

show abstract

Section: Discussionmentioning

confidence: 99%

Double-Compressed Artificial Neural Network for Efficient Model Storage in Customer Churn Prediction

Lisang Zhou,

Zhang,

Zhou

2024

artif. intell. adv.

View full text Add to dashboard Cite

show abstract

“…Combining ANFIS with nature-inspired optimization algorithms involves integrating the strengths of both approaches to enhance the modeling and optimization capabilities [ [54] , [55] , [56] , [57] , [58] , [59] , [60] , [61] ]. This integration approach allows for the creation of a hybrid system that benefits from the modeling capabilities of ANFIS and the optimization power of nature-inspired algorithms, potentially leading to improved model accuracy and generalization.…”

Section: Methodsmentioning

confidence: 99%

Evaluation of student failure in higher education by an innovative strategy of fuzzy system combined optimization algorithms and AI

Nie,

Ahmadi Dehrashid

2024

Heliyon

View full text Add to dashboard Cite

“…FETs and HEMTs are now favorable in the development of low noise and unbiased THz detectors. The fabrication technology readiness in Silicon and semiconductor foundry process have possessed a broad range of CMOS-and III-V material-based THz detectors [47], [48]. The fundamental limit in the rectifying detector is the parasitic effects generated from the electronic read-out components (resistors, capacitances, and inductances) that increase linearly with the frequency.…”

Section: B Operation Principlesmentioning

confidence: 99%

Input Power and Effective Area in Terahertz Detector Measurement: A Review

2023

View full text Add to dashboard Cite

The field of terahertz (THz) science and technology research area have been exponentially growing recently, motivated by the increasing demand for safer security imaging, better quality control within manufacturing industries, space and astronomical investigation, biomedical diagnostics, and larger communication bandwidth. The THz waves detection mechanism is one of the critical components in developing a high efficiency and high sensitivity THz communication system. This paper reviews the principle and instrumentation of THz optical metrology for the precise and accurate characterization of THz detectors in the range of 0.1 THz to several THz. In this context, we individually discuss the determination of radiation input power and effective area followed by a survey of THz optical measurement methodology used in the state-of-the-art THz detectors. In addition, challenging issues remaining in the THz detector measurements are provided. This paper sets out a guideline to address the main concept behind the THz detector measurement as well as their challenges and opportunities. Additionally, useful insight is given through a summary of available power meter instrumentation for THz input power calibration.INDEX TERMS THz detectors, THz input power, effective area, THz metrology, antenna, THz measurements, THz instrumentation.

show abstract

Ge-Core/a-Si-Shell Nanowire-Based Field-Effect Transistor for Sensitive Terahertz Detection

Cited by 18 publications

References 33 publications

Double-Compressed Artificial Neural Network for Efficient Model Storage in Customer Churn Prediction

Double-Compressed Artificial Neural Network for Efficient Model Storage in Customer Churn Prediction

Evaluation of student failure in higher education by an innovative strategy of fuzzy system combined optimization algorithms and AI

Input Power and Effective Area in Terahertz Detector Measurement: A Review

Contact Info

Product

Resources

About