Design and implementation of auto encoder based bio medical signal transmission to optimize power using convolution neural network

Kumar, K N Sunil; Gb, Arjun Kumar; Gatti, Ravi; Kumar, S. Santosh; Bhyratae, Darshan A.; Satyasrikanth, Palle

doi:10.1016/j.neuri.2023.100121

Cited by 5 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model has garnered considerable attention in the realm of deep learning due to its diverse range of applications, which encompass image and audio processing, anomaly detection, and data compression. Li et al [49,50] provide a thorough analysis of the development and practical use of autoencoders in deep learning. The paper explores the use of autoencoders in various tasks, including image and speech recognition, anomaly detection, data compression, and feature extraction.…”

Section: Auto-encodermentioning

confidence: 99%

CovidSafe: A Deep Learning Framework for Covid Detection Using Multi-Modal Approach

Panigrahi,

Behera,

Routhu

2024

Preprint

View full text Add to dashboard Cite

This work introduces CovidSafe, a framework designed to classify COVID patients as positive or negative based on CXR images. With the global impact of COVID-19, there is a need for effective tools to aid in patient diagnosis. CovidSafe utilizes a multi-model deep feature extractor, combining features from the ResNet family and an autoencoder. The ResNet 18, ResNet 34, and ResNet 50 architectures are employed, and model weights are fine-tuned for optimal performance. The framework leverages the ResNet family models and theautoencoder to extract relevant features. The features from intermediate layers in Resnet family are extracted to capture increasingly complex and high-level information. Similarly, the bottleneck features from Autoencoder are extracted to capture compressed, abstract representation and important features of the image for the classification. These features are then utilized for analysis and classification within the CovidSafe framework. To ensure accessibility for online users, the proposed model is integrated into a web application. Through experimental analysis, the performance of the proposed model is evaluated with various metrics. Results indicate that CovidSafe outperforms baseline models, achieving a precision of 98.67%, recall of 98.62%, and F1-score of 98.64%. These promising results highlight the efficacy of CovidSafe in accurately classifying COVID patients based on CXR images, offering a valuable tool in the fight against the ongoing pandemic.

show abstract

Section: Auto-encodermentioning

confidence: 99%

CovidSafe: A Deep Learning Framework for Covid Detection Using Multi-Modal Approach

Panigrahi,

Behera,

Routhu

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Moreover, if the nodes' signal strength is very low, they will not cover the network region. 11,12 As a result, coverage holes can be developed in the WMSN that may jam the transmission. The node deployment process may create an energy hole in the network.…”

Section: Introductionmentioning

confidence: 99%

“…Subsequently, the energy hole will turn out to be bigger and bigger, so it causes network paralysis. Moreover, if the nodes' signal strength is very low, they will not cover the network region 11,12 . As a result, coverage holes can be developed in the WMSN that may jam the transmission.…”

Section: Introductionmentioning

confidence: 99%

Energy aware optimal routing model for wireless multimedia sensor networks using modified Voronoi assisted prioritized double deep Q‐learning

Suseela,

Krithiga,

Revathi

et al. 2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe energy hole problem is critical in Wireless Multimedia Sensor Network (WMSN), wherein the nodes closer to the sink node will expire sooner than the outer sub‐regions. Because they transmit their packet and forward the outer sub‐regions packet to the sink. Hence, a hole arises near the sink node after a very short time. Thus, an energy‐aware optimal routing model is introduced in this research using Modified Voronoi‐assisted prioritized double deep Q‐learning (PDDQL). Initially, the sensor nodes are deployed using the Voronoi cell structure that splits the entire region of interest into different Voronoi polygons. However, the Voronoi diagram will not always predict an efficient route because of the nodes at a Voronoi edge or vertex outside the transmission range. To tackle this issue, a new Voronoi diagram is proposed that depends on the maximum horizontal transmission range to remove the portion of Voronoi edges uncovered by the sensor node. After the deployment, a PDDQL algorithm is used to select the Relay Nodes based on their remaining energy. The proposed PDDQL determines an alternate route to transmit the packet if an energy hole problem has occurred in WMSN. The analysis of a proposed routing protocol based on the assessment measures like packet delivery ratio, average residual energy, number of alive nodes, and average end‐to‐end delay accomplished the value of 198.33 (ms), 2.05 (J), 100, and 0.85, respectively.

show abstract

“…There has been little study done to reduce latency [8]- [11]. Semantic segmentation research has been carried out by several significant projects, including FCN, PSPNet, U-Net, SegNet, and DeepLab [12]- [15]. It is well-known that the aforementioned networks take a long time to process a single frame; nonetheless, they are extremely accurate in predicting the future.…”

Section: Introductionmentioning

confidence: 99%

“…However, due to the lack of available labels, training a vehicle detection model from scratch is a formidable task in this Challenge. Instead, we use the 3D Deformable model [15] to do inference on our dataset, a transfer learning technique, for vehicle detection. We also took into account an alternative to the 3D Deformable model by Zhang et al [2], whose model performed similarly well in the 2017 challenge.…”

Section: Introductionmentioning

confidence: 99%

Vehicle Detection and Speed Estimation Using Semantic Segmentation with Low Latency

C K,

G K

2023

Int. j. commun. netw. inf. secur.

View full text Add to dashboard Cite

Computer vision researchers are actively studying the use of video in traffic monitoring. TrafficMonitor uses a stationary calibrated camera to automatically track and classify vehicles on roadways. In practical uses like autonomous vehicles, segmenting semantic video continues to be difficult due to high-performance standards, the high cost of convolutional neural networks (CNNs), and the significant need for low latency. An effective machine learning environment will be developed to meet the performance and latency challenges outlined above. The use of deep learning architectures like SegNet and Flownet2.0 on the CamVid dataset enables this environment to conduct pixel-wise semantic segmentation of video properties while maintaining low latency. In this work, we discuss some state-of-the-art ways to estimating the speed of vehicles, locating vehicles, and tracking objects. As a result, it is ideally suited for real-world applications since it takes advantage of both SegNet and Flownet topologies. The decision network determines whether an image frame should be processed by a segmentation network or an optical flow network based on the expected confidence score. In conjunction with adaptive scheduling of the key frame approach, this technique for decision-making can help to speed up the procedure. Using the ResNet50 SegNet model, a mean IoU of "54.27 per cent" and an average fps of "19.57" were observed. Aside from decision network and adaptive key frame sequencing, it was discovered that FlowNet2.0 increased the frames processed per second to "30.19" on GPU with such a mean IoU of "47.65%". Because the GPU was utilised "47.65%" of the time, this resulted. There has been an increase in the speed of the Video semantic segmentation network without sacrificing quality, as demonstrated by this improvement in performance.

show abstract

Design and implementation of auto encoder based bio medical signal transmission to optimize power using convolution neural network

Cited by 5 publications

References 41 publications

CovidSafe: A Deep Learning Framework for Covid Detection Using Multi-Modal Approach

CovidSafe: A Deep Learning Framework for Covid Detection Using Multi-Modal Approach

Energy aware optimal routing model for wireless multimedia sensor networks using modified Voronoi assisted prioritized double deep Q‐learning

Vehicle Detection and Speed Estimation Using Semantic Segmentation with Low Latency

Contact Info

Product

Resources

About