Aggregation-Based Dynamic Channel Bonding to Maximise the Performance of Wireless Local Area Networks (WLAN)

Parashar, Vivek; Kashyap, Ramgopal; Rizwan, Ali; Karras, D.A.; Altamirano, Gilder Cieza; Dixit, Ekta; Ahmadi, Fardin

doi:10.1155/2022/4464447

Cited by 117 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To achieve this goal, we employ the Random Forest, Long Short-Term Memory, and k-Nearest Neighbors (k-NN) algorithms. Clinical notes, neuroimaging results, genetic data, and sensor readings from wearable devices are just some of the types of patient data we collect and organize first [17][18][19]. The data must go through normalization and feature extraction before it can be transformed into a structured dataset.…”

Section: Proposed Methodologymentioning

confidence: 99%

Machine Learning-Enhanced Decision Support for Neurological Disorders Management in Healthcare

Dr. Divya Jain, Dr. Vibha Tiwari, Akshra Tiwari

2023

tjjpt

View full text Add to dashboard Cite

In a nutshell: Neurological illnesses, which include a wide range of ailments from Parkinson's disease to epilepsy, present considerable problems to the administration of healthcare. The purpose of this abstract is to present an overview of a unique technique called Machine Learning-Enhanced Decision Support (ML-EDS) for Neurological Disorders Management, which aims to improve patient treatment as well as patient outcomes. Within the scope of this investigation, we have suggested a complete ML-EDS framework that integrates cutting-edge machine learning strategies with more conventional approaches to medical treatment. The framework provides a comprehensive solution that makes use of several types of patient data, such as clinical records, neuroimaging data, genetic information, and data from wearable sensors. The Random Forest, Long Short-Term Memory (LSTM), and k-Nearest Neighbours (k-NN) algorithms are integrated into our methodology in order to improve illness progression prediction, seizure event detection, and individualized medication suggestion. In comparison to more conventional approaches, the suggested framework reveals noteworthy advantages. When compared to conventional algorithms, it demonstrates superior accuracy, sensitivity, and specificity in the prediction of illness development. Additionally, its F1 score is significantly higher. In addition, the application of LSTM for the identification of seizure episodes demonstrates the effectiveness of the method in determining crucial occurrences, which in turn enables prompt intervention. The possibility of tailored medical treatment based on k-means clustering is also highlighted in this research. Patients with comparable clinical characteristics can be grouped together to facilitate the development of personalized treatment methods, which can then provide individualized care pathways. The performance evaluation demonstrates that k-NN is capable of making therapy recommendations with high precision, hence contributing to an overall improvement in the health of the patient. Additionally, the proposed framework performs very well in terms of computational efficiency, reducing the amount of time required for both training and prediction, which positions it as a viable option for healthcare applications that are used in the real world. In summation, the use of machine learning in decision support for the management of neurological disorders in healthcare is a ground-breaking strategy that is reshaping the therapeutic landscape. It does this by using the power of machine learning, which enables it to provide more accurate illness progression predictions, rapid seizure event detection, and highly tailored medical care. The findings and efficiency metrics conclusively indicate that this strategy is superior to existing procedures, suggesting a paradigm change in the therapy of neurological disorders.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Machine Learning-Enhanced Decision Support for Neurological Disorders Management in Healthcare

Dr. Divya Jain, Dr. Vibha Tiwari, Akshra Tiwari

2023

tjjpt

View full text Add to dashboard Cite

show abstract

“…They found that channel width selection should consider not only a link's signal quality, but also the strength of neighboring links, their physical rates, and interferer load. Other DCB methods have been proposed in [15]- [20]. These methods are based on collision-detection, carrier sensing adaptation, or load.…”

Section: Related Workmentioning

confidence: 99%

An Intelligence-Based Framework for Managing WLANs: The Potential of Non-Contiguous Channel Bonding

Abusubaih

2024

IEEE Access

View full text Add to dashboard Cite

Managing WLANs efficiently while optimizing performance remains a challenge. This article proposes an innovative approach that utilizes the strengths of Software-Defined Networking (SDN) to create an advanced framework for WLAN management. Since the implementation of fully centralized solutions is not always feasible, the proposed framework adopts both decentralized and centralized policies. By leveraging the programmability of SDN, the framework aims to enhance WLAN performance and improve overall network efficiency. We present the design, implementation, and evaluation of the SDN-based framework, showcasing the potential of non-contiguous channel bonding and channel allocation. Algorithms for coexistence of heterogeneous WLANs, channel bonding and management are developed. We investigate the performance of heterogeneous WLANs and show how the framework can facilitate management of heterogeneous WLANs. We conducted extensive simulation experiments that confirmed the need of such framework. The results have shown that channel assignment can significantly improve network throughput as well the fairness among WLAN users. However; under high interference; non-contiguous channel bonding did not outperform contiguous channel bonding.INDEX TERMS 802.11ac, channel bonding, SDN, WLANs, WLAN management..

show abstract

“…As sepsis worsens, it leads to organ failure and a significant rise in mortality. Therefore, it's critical to identify sepsis as soon as possible and stop it from worsening (Parashar et al 2022).…”

Section: Introductionmentioning

confidence: 99%

Enhancing sepsis detection with nature-inspired optimization integrated neural network

Haria,

Mewara,

Tarekar

2023

Multidiscip. Sci. J.

View full text Add to dashboard Cite

Sepsis, a disorder that can be fatal that is brought on by a dysregulated immunological reaction to an infection, keeps presenting complex problems for early detection and treatment. In this article, they suggest a novel (MBSO-LSTM) method for improving sepsis diagnosis that combines long short-term memory (LSTM) networks and modified bird swarm optimization (MBSO). The biases and weights of the network known as LSTM are optimized using the MBSO algorithm, which was developed in response to research on the social behavior of bird flocks. MBSO enables faster and more successful learning of the LSTM model, resulting in increased sepsis detection performance by emulating the self-organizing behavior of bird swarms. Our work uses a sizable collection of medical records from individuals who have probable sepsis, including demographic information, laboratory findings, and vital signs. The LSTM network in the suggested framework recognizes the time-dependent relationships and patterns present in the data by using these characteristics as inputs. They contrast our method's effectiveness with other cutting-edge sepsis detection strategies, such as conventional approaches. The outcomes show that concerning sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC-ROC), our proposed system performs better than alternative methods.

show abstract

Aggregation-Based Dynamic Channel Bonding to Maximise the Performance of Wireless Local Area Networks (WLAN)

Cited by 117 publications

References 40 publications

Machine Learning-Enhanced Decision Support for Neurological Disorders Management in Healthcare

Machine Learning-Enhanced Decision Support for Neurological Disorders Management in Healthcare

An Intelligence-Based Framework for Managing WLANs: The Potential of Non-Contiguous Channel Bonding

Enhancing sepsis detection with nature-inspired optimization integrated neural network

Contact Info

Product

Resources

About