Varıous Frameworks for IoT-Enabled Intellıgent Waste Management System Usıng ML for Smart Cıtıes

Belsare, Karan S.; Singh, Manwinder

doi:10.1007/978-981-19-2069-1_55

Cited by 9 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The FD technique, however, would impose a large computational and hardware load in a huge MIMO system because number of radio frequency chains equals number of antennas. Idea of UDN has been more and more popular in recent years as a potential way to increase energy efficiency (EE) and spectral efficiency (SE) over tiny geographic areas [13][14][15]. However, since channel state information (CSI) is necessary, deployment of large number of APs may not only expressively rise signaling burden but also take advantage of pilot pollution effect.…”

Section: Introductionmentioning

confidence: 99%

“…The simulation outcomes proves that the proposed technique attains provides 21. 25%, 23.19% and 22.14% lower NMSE, 23.12%, 24.43% and 21.32% lower latency, 23.25%, 22.19% and 25.32% higher Spectral Efficiency while analyzed with existing techniques likes machine learning adaptive beamforming framework for 5G millimeter wave massive MIMO multi cellular networks (MLAB-MMWM-MIMO), deep learning-enabled relay node placement with selection framework in multicellular networks (DL-ERN-MCN) and deep learning framework for beam selection with power control in massive MIMO-millimeter-wave communications (DLF-BSPC-MIMO) respectively.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Alternating Graph-Regularized Neural Network for Adaptive Beamforming in 5G milli meter wave Massive MIMO Multicellular Networks

BOLLA,

SINGH

2023

Preprint

Self Cite

View full text Add to dashboard Cite

The idea of ultra-dense networking (UDN) has been more and more popular in recent years as a potential way to increase energy efficiency (EE), spectral efficiency (SE) over tiny geographic areas. However, since channel state information (CSI) is necessary, deployment of large number of Access Points may not only significantly increase signaling burden but also take advantage of the pilot contamination effect. To overcome this issue, present an Alternating Graph-Regularized Neural Network for Adaptive Beamforming in 5G Milli Metre Wave Massive MIMO Multicellular Networks (AGNN-ABM-MIMO-MCN) is proposed. When each active base stations of evaluated orientations use huge multiple-input, multiple-output setups, here, beamforming is carried out with aid of preset set of configurations by appropriately producing higher directional beams on demand, can handle variety of traffic circumstances. Then, Beam forming approach depend on AGNN, which is trained to generate appropriate beam forming configuration. In general, AGNN classifier does not describe modifying optimization techniques to identify optimal parameters to beamforming configuration. Therefore, it is proposed to use Tyrannosaurus Optimization Algorithm (TOA) to optimize Alternating Graph-regularized Neural Network, which accurately generates the beamforming configuration. The proposed method is analyzed with different metrics likes Energy Efficiency, Spectral efficiency, Normalized Mean-Squared Error, Latency, Bit Error Rate, blocking probability and computational complexity. The simulation outcomes proves that the proposed technique attains provides 21.25%, 23.19% and 22.14% lower NMSE, 23.12%, 24.43% and 21.32% lower latency, 23.25%, 22.19% and 25.32% higher Spectral Efficiency while analyzed with existing techniques likes machine learning adaptive beamforming framework for 5G millimeter wave massive MIMO multi cellular networks (MLAB-MMWM-MIMO), deep learning-enabled relay node placement with selection framework in multicellular networks (DL-ERN-MCN) and deep learning framework for beam selection with power control in massive MIMO-millimeter-wave communications (DLF-BSPC-MIMO) respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Alternating Graph-Regularized Neural Network for Adaptive Beamforming in 5G milli meter wave Massive MIMO Multicellular Networks

BOLLA,

SINGH

2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Despite its significance, the predominant method of waste identification has been reliant on human efforts. Manual sorting, though widely practiced, is not only marked by inefficiencies but also poses potential health threats to the workforce [8,9]. Given these challenges, a shift towards leveraging artificial intelligence for waste categorization has been advocated.…”

Section: Introductionmentioning

confidence: 99%

Efficient Differentiation of Biodegradable and Non-Biodegradable Municipal Waste Using a Novel MobileYOLO Algorithm

Suman,

Arulanantham

2023

View full text Add to dashboard Cite

In the realm of waste management, the accurate identification of biodegradable and nonbiodegradable items remains a critical challenge. An advanced real-time object detection method, termed "MobileYOLO", was proposed, leveraging the strengths of the YOLO v4 framework. The MobileNetv2 network was integrated, and a section of the conventional computation was substituted with depth-wise separable convolutions utilizing the PAnet and head network. To enhance feature expressiveness capabilities during feature fusion, a refined lightweight channel attention mechanism, known as Efficient Channel Attention (ECA), was introduced. The Improved Single Stage Headless (ISSH) context module was incorporated into the micro-object identification branch to broaden the receptive field. Evaluations conducted on the KITTI dataset indicated an impressive accuracy of 95.7%. Remarkably, when compared to the standard YOLOv4, the MobileYOLO model exhibited a reduction in model parameters by 53.12M, a decrease in connectivity size by one-fifth, and an augmentation in detection speed by 85%.

show abstract

Analytics and Decision-making Model Using Machine Learning for Internet of Things-based Greenhouse Precision Management in Agriculture

Rokade,

Singh,

Goraya

et al. 2024

Microorganisms for Sustainability

View full text Add to dashboard Cite

Varıous Frameworks for IoT-Enabled Intellıgent Waste Management System Usıng ML for Smart Cıtıes

Cited by 9 publications

References 37 publications

Alternating Graph-Regularized Neural Network for Adaptive Beamforming in 5G milli meter wave Massive MIMO Multicellular Networks

Alternating Graph-Regularized Neural Network for Adaptive Beamforming in 5G milli meter wave Massive MIMO Multicellular Networks

Efficient Differentiation of Biodegradable and Non-Biodegradable Municipal Waste Using a Novel MobileYOLO Algorithm

Analytics and Decision-making Model Using Machine Learning for Internet of Things-based Greenhouse Precision Management in Agriculture

Contact Info

Product

Resources

About