A Health Decision Support System for Disease Diagnosis Based on Wearable Medical Sensors and Machine Learning Ensembles

Yin, Hongxu; Jha, Niraj K.

doi:10.1109/tmscs.2017.2710194

Cited by 98 publications

(49 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So the number of wearable sensors sold rate expected to be 123 million by 2018 [9]. These devices catch, store, and convey physiological statistics unpretentiously, successfully, and efficiently.…”

Section: Associated Effortmentioning

confidence: 99%

See 1 more Smart Citation

Sensor Enabled Wearable Technological Tool to Detect Breast Abnormality

Kavitha¹,

Raja²

2018

IJET

View full text Add to dashboard Cite

Our Historical records say that, Women are back bone to every family. Generally we observe that health risk rate in women increases depends on age. Statistical medical reports proven that, early identification of health risks will increase the survival rate of patient. From last sixty years, we heard that breast cancer is one of the big health dare for women after forty years of age. Early phase detection of breast tumor is a big research issue in both developed and developing countries. Due to the limits in existing breast abnormality detecting tools like mammography, thermography, ultrasound, MRI there is a need to introduce smart, cost effective, patient comfortable, nonionic radiated compact testing tool to detect breast abnormality at early stage. In this work I am going to propose an advanced sensor enabled wearable technological tool design to detect breast abnormality. This tool is portable, patient comfortable, light weight, cost effective and suitable for dense breast, pregnant women and surgically altered breasts, younger women also.

show abstract

Section: Associated Effortmentioning

confidence: 99%

“…Mammogram does not give good results for the women having dense breast. Paper [16] shows the lab view of mammography test procedure. To get clear internal structure, the breast is pressed in between flat surface plates.…”

Section: Associated Effortmentioning

confidence: 99%

Sensor Enabled Wearable Technological Tool to Detect Breast Abnormality

Kavitha¹,

Raja²

2018

IJET

View full text Add to dashboard Cite

show abstract

“…These WMSs enable a continuous sensing of physiological signals during daily activities, and thus provide a powerful, yet user-transparent, human-machine interface for tracking the user's health status. Combining WMSs and machine learning brings up the possibility of pervasive health condition tracking and disease diagnosis in a daily context [7]. This approach exploits the superior knowledge distillation capability of machine learning to extract medical insights from health-related physiological signals [8].…”

Section: Introductionmentioning

confidence: 99%

“…This helps enable a unified smart healthcare system that serves people in both the daily and clinical scenarios [6]. However, disease diagnosis based on WMS data and its effective deployment at the edge still remain challenging [7]. Conventional approaches typically involve feature extraction, model training, and model deployment.…”

Section: Introductionmentioning

confidence: 99%

DiabDeep: Pervasive Diabetes Diagnosis Based on Wearable Medical Sensors and Efficient Neural Networks

Yin

Mukadam

Dai

et al. 2021

IEEE Trans. Emerg. Topics Comput.

Self Cite

View full text Add to dashboard Cite

Diabetes impacts the quality of life of millions of people around the globe. However, diabetes diagnosis is still an arduous process, given that this disease develops and gets treated outside the clinic. The emergence of wearable medical sensors (WMSs) and machine learning points to a potential way forward to address this challenge. WMSs enable a continuous, yet user-transparent, mechanism to collect and analyze physiological signals. However, disease diagnosis based on WMS data and its effective deployment on resource-constrained edge devices remain challenging due to inefficient feature extraction and vast computation cost. To address these problems, we propose a framework called DiabDeep that combines efficient neural networks (called DiabNNs) with off-the-shelf WMSs for pervasive diabetes diagnosis. DiabDeep bypasses the feature extraction stage and acts directly on WMS data. It enables both an (i) accurate inference on the server, e.g., a desktop, and (ii) efficient inference on an edge device, e.g., a smartphone, to obtain a balance between accuracy and efficiency based on varying resource budgets and design goals. On the resource-rich server, we stack sparsely connected layers to deliver high accuracy. On the resource-scarce edge device, we use a hidden-layer long short-term memory based recurrent layer to substantially cut down on computation and storage costs while incurring only a minor accuracy loss. At the core of our system lies a grow-and-prune training flow: it leverages gradient-based growth and magnitude-based pruning algorithms to enable DiabNNs to learn both weights and connections, while improving accuracy and efficiency. We demonstrate the effectiveness of DiabDeep through a detailed analysis of data collected from 52 participants. For server (edge) side inference, we achieve a 96.3% (95.3%) accuracy in classifying diabetics against healthy individuals, and a 95.7% (94.6%) accuracy in distinguishing among type-1 diabetic, type-2 diabetic, and healthy individuals. Against conventional baselines, such as support vector machines with linear and radial basis function kernels, k-nearest neighbor, random forest, and linear ridge classifiers, DiabNNs achieve higher accuracy, while reducing the model size (floating-point operations) by up to 454.5× (8.9×). Therefore, the system can be viewed as pervasive and efficient, yet very accurate.

show abstract

“…Smart wearable devices provide opportunities for upgrading traditional industries, and traditional enterprises are entering smart operation. Modern medical, industrial, home, and technology industries will also focus on wearable device concepts. Through these devices, people can better perceive the information of the outside and their own, processing information more efficiently with the aid of computers, networks, and even other people and achieve more seamless communication.…”

Section: Introductionmentioning

confidence: 99%

SEWMS: An edge‐based smart wearable maintenance system in communication network

Rui

Qin

et al. 2019

Softw Pract Exp

View full text Add to dashboard Cite

Summary The development of the Internet of Things (IoT) and wearable technology provides an opportunity for the development of maintenance of communication. The use of wearable technology and instant messaging technology of IoT can improve the support capabilities and data interaction ability of on‐site maintenance of the communication network. Existing communication maintenance systems lack real‐time operation and maintenance of data interaction. In the field operation decision‐making and execution process, there are problems of lack of field links and inconvenient information interaction. On‐site maintenance mainly relies on maintenance personnel to actively search for information, and the retrieval results are lacking of personalization, which makes it difficult to meet the needs of on‐site maintenance of the communication network. Edge computing and information push technology can solve these problems to some extent. In this paper, we focus on the current low level in information, complicated scenes, and various information of on‐site maintenance and propose a dynamic context‐aware information push algorithm. The simulation results demonstrate that the algorithm delivers good performance in terms of precision, recall, and F1. Besides, we present a smart wearable maintenance system, an edge computing–assisted IoT platform for the real‐time guidance of technical experts and systems for on‐site maintenance personnel, aiming to improve the efficiency and quality of on‐site maintenance.

show abstract

A Health Decision Support System for Disease Diagnosis Based on Wearable Medical Sensors and Machine Learning Ensembles

Cited by 98 publications

References 40 publications

Sensor Enabled Wearable Technological Tool to Detect Breast Abnormality

Sensor Enabled Wearable Technological Tool to Detect Breast Abnormality

DiabDeep: Pervasive Diabetes Diagnosis Based on Wearable Medical Sensors and Efficient Neural Networks

SEWMS: An edge‐based smart wearable maintenance system in communication network

Contact Info

Product

Resources

About