摘要:
Wireless sensor networks (WSNs) are widely used in various fields such as military, industrial, and transportation for real-time monitoring, sensing, and data collection of different environments or objects. However, the development of WSNs is hindered by several limitations, including energy, storage space, computing power, and data transmission rate. Among these, the availability of power energy plays a crucial role as it directly determines the lifespan of WSN. To extend the life cycle of WSN, two key approaches are power supply improvement and energy conservation. Therefore, we propose an energy harvesting system and a low-energy-consumption mechanism for WSNs. Firstly, we delved into the energy harvesting technology of WSNs, explored the utilization of solar energy and mechanical vibration energy to ensure a continuous and dependable power supply to the sensor nodes, and analyzed the voltage output characteristics of bistable piezoelectric cantilever. Secondly, we proposed a neighbor discovery mechanism that utilizes a separation beacon, is based on reply to ACK, and can facilitate the identification of neighboring nodes. This mechanism operates at a certain duty cycle ratio, significantly reduces idle listening time and results in substantial energy savings. In comparison to the Disco and U-connect protocols, our proposed mechanism achieved a remarkable reduction of 66.67% and 75% in the worst discovery delay, respectively. Furthermore, we introduced a data fusion mechanism based on integer wavelet transform. This mechanism effectively eliminates data redundancy caused by spatiotemporal correlation, resulting in a data compression rate of 5.42. Additionally, it significantly reduces energy consumption associated with data transmission by the nodes.
摘要:
Background and objective: Traditional disease diagnosis is usually performed by experienced physicians, but misdiagnosis or missed diagnosis still exists. Exploring the relationship between changes in the cor-pus callosum and multiple brain infarcts requires extracting corpus callosum features from brain image data, which requires addressing three key issues. (1) automation, (2) completeness, and (3) accuracy. Residual learning can facilitate network training, Bi-Directional Convolutional L STM (BDC-L STM) can ex-ploit interlayer spatial dependencies, and HDC can expand the receptive domain without losing resolu-tion.Methods: In this paper, we propose a segmentation method by combining BDC-LSTM and U-Net to seg-ment the corpus callosum from multiple angles of brain images based on computed tomography (CT) and magnetic resonance imaging (MRI) in which two types of sequence, namely T2-weighted imaging as well as the Fluid Attenuated Inversion Recovery (Flair), were utilized. The two-dimensional slice sequences are segmented in the cross-sectional plane, and the segmentation results are combined to obtain the final re-sults. Encoding, BDC-LSTM, and decoding include convolutional neural networks. The coding part uses asymmetric convolutional layers of different sizes and dilated convolutions to get multi-slice information and extend the convolutional layers' perceptual field.Results: This paper uses BDC-LSTM between the encoding and decoding parts of the algorithm. On the image segmentation of the brain in multiple cerebral infarcts dataset, accuracy rates of 0.876, 0.881, 0.887, and 0.912 were attained for the intersection of union (IOU), dice similarity coefficient (DS), sensitivity (SE), and predictive positivity value (PPV). The experimental findings demonstrate that the algorithm out-performs its rivals in accuracy.Conclusion: This paper obtained segmentation results for three images using three models, ConvLSTM, Pyramid-L STM, and BDC-L STM, and compared them to verify that BDC-LSTM is the best method to per-form the segmentation task for faster and more accurate detection of 3D medical images. We improve the convolutional neural network segmentation method to obtain medical images with high segmenta-tion accuracy by solving the over-segmentation problem.& COPY; 2023 Elsevier B.V. All rights reserved.
作者:
Wong, Kelvin K. L.;Ayoub, Muhammad;Cao, Zaijie;Chen, Cang;Chen, Weimin;...
期刊:
Computer Methods and Programs in Biomedicine,2023年240:107677 ISSN:0169-2607
通讯作者:
Wong, KK
作者机构:
[Chen, Weimin; Wong, Kelvin K. L.; Wong, KK] Hunan City Univ, Sch Informat & Elect, Yiyang 413000, Peoples R China.;[Wong, Kelvin K. L.] Deep Red Future Technol Co Ltd, Dept Res, Shenzhen, Peoples R China.;[Wong, Kelvin K. L.; Zhang, Chris W. J.] Univ Saskatchewan, Dept Mech Engn, Div Biomed Engn, Saskatoon, SK, Canada.;[Ayoub, Muhammad; Chen, Cang; Cao, Zaijie] Cent South Univ, Sch Comp Sci & Engn, Changsha, Hunan, Peoples R China.;[Ghista, Dhanjoo N.] Univ 2020 Fdn, San Jose, CA USA.
通讯机构:
[Wong, KK ] H;Hunan City Univ, Sch Informat & Elect, Yiyang 413000, Peoples R China.
关键词:
Cybernetical intelligence;Deep medicine;Diagnosis;Medical imaging;Precision medicine
摘要:
Conceptual Introduction: To introduce the concept of cybernetical intelligence, deep learning, development history, international research, algorithms, and the application of these models in smart medical image analysis and deep medicine are reviewed in this paper. This study also defines the terminologies for cybernetical intelligence, deep medicine, and precision medicine.Review of Methods: Through literature research and knowledge reorganization, this review explores the fundamental concepts and practical applications of various deep learning techniques and cybernetical intelligence by conducting extensive literature research and reorganizing existing knowledge in medical imaging and deep medicine. The discussion mainly centers on the applications of classical models in this field and addresses the limitations and challenges of these basic models.Evaluation and Discussions: In this paper, the more comprehensive overview of the classical structural modules in convolutional neural networks is described in detail from the perspective of cybernetical intelligence in deep medicine. The results and data of major research contents of deep learning are consolidated and summarized. Conclusion: There are some problems in machine learning internationally, such as insufficient research techniques, unsystematic research methods, incomplete research depth, and incomplete evaluation research. Some suggestions are given in our review to solve the problems existing in the deep learning models. Cybernetical intelligence has proven to be a valuable and promising avenue for advancing various fields, including deep medicine and personalized medicine.& COPY; 2023 Published by Elsevier B.V.
期刊:
Journal of Network and Computer Applications,2023年217:103698 ISSN:1084-8045
通讯作者:
Qin, H
作者机构:
[Chen, Weimin; Li, Ni; Qin, Hua; Yang, Gelan; Qin, H; Wang, Tao; Chen, Hao] Hunan City Univ, Coll Informat & Elect Engn, Yiyang, Hunan, Peoples R China.;[Peng, Yang] Univ Washington Bothell, Div Comp & Software Syst, Bothell, WA USA.
通讯机构:
[Qin, H ] H;Hunan City Univ, Coll Informat & Elect Engn, Yiyang, Hunan, Peoples R China.
关键词:
QoS;Partitioning;Scheduling;Multimedia;IoT
摘要:
In the Internet of Things (IoT), multimedia traffic for audio, image, and video accounts for the largest proportion (over 78.7%) of the total traffic, bringing forward the vision of multimedia IoT (M-IoT). As part of the realization of loT, M-IoT is a general network paradigm that constitutes many smart objects equipped with the capability to collect multimedia data from the physical environment and deliver the data to other things. To satisfy a certain level of user experience, Quality of Service (QoS) is required to be regulated to ensure acceptable delivery of the multimedia content. As the most widely-used wireless technology, WiFi has been recommended for IoT communications for its high data rate, native IP compatibility, and good reusability of the existing infrastructures. However, WiFi suffers from channel contention, especially during multi-hop communications, which degrades the QoS performance and hinders its use for many M-IoT services. Although numerous protocols have been proposed to mitigate WiFi contention, they often consume much WiFi bandwidth for network control, lowering the level of achievable QoS performance. To address this issue, we propose a distributed Cross-interface network Partitioning and Scheduling (CPS) protocol, which leverages the co-existing ZigBee communications to divide the network into partitions and allows only one node in each partition to use its WiFi interface to transmit data at any time, for bandwidth-efficient and delay-constrained data flow delivery in M-IoT. A prototype node is implemented by integrating COTS ZigBee and WiFi interfaces into a BeagleBone Green wireless platform for IoT. Extensive field experiments are conducted in a multi-hop network of 24 prototype nodes that deliver real multimedia data (images and videos). The experiment results show that CPS outperforms the standard WiFi and a state-of-the-art contention control scheme (by 62.6% and 26.4% under high data traffic, respectively) in terms of a QoS metric capturing two basic performance metrics (i.e., bandwidth efficiency and end-to-end delay) of multi-hop communications, while retaining fair QoS performance and high energy efficiency.
摘要:
BACKGROUND AND OBJECTIVE: Bone tumors present significant challenges in orthopedic medicine due to variations in clinical treatment approaches for different tumor types, which includes benign, malignant, and intermediate cases. Convolutional Neural Networks (CNNs) have emerged as prominent models for tumor classification. However, their limited perception ability hinders the acquisition of global structural information, potentially affecting classification accuracy. To address this limitation, we propose an optimized deep learning algorithm for precise classification of diverse bone tumors. MATERIALS AND METHODS: Our dataset comprises 786 computed tomography (CT) images of bone tumors, featuring sections from two distinct bone species, namely the tibia and femur. Sourced from The Second Affiliated Hospital of Fujian Medical University, the dataset was meticulously preprocessed with noise reduction techniques. We introduce a novel fusion model, VGG16-ViT, leveraging the advantages of the VGG-16 network and the Vision Transformer (ViT) model. Specifically, we select 27 features from the third layer of VGG-16 and input them into the Vision Transformer encoder for comprehensive training. Furthermore, we evaluate the impact of secondary migration using CT images from Xiangya Hospital for validation. RESULTS: Theproposed fusion model demonstrates notable improvements in classification performance. It effectively reduces the training time while achieving an impressive classification accuracy rate of 97.6%, marking a significant enhancement of 8% in sensitivity and specificity optimization. Furthermore, the investigation into secondary migration's effects on experimental outcomes across the three models reveals its potential to enhance system performance. CONCLUSION: Our novel VGG-16 and Vision Transformer joint network exhibits robust classification performance on bone tumor datasets. The integration of these models enables precise and efficient classification, accommodating the diverse characteristics of different bone tumor types. This advancement holds great significance for the early detection and prognosis of bone tumor patients in the future.
期刊:
Computer Methods and Programs in Biomedicine,2022年225:107073 ISSN:0169-2607
通讯作者:
Weimin Chen<&wdkj&>Kelvin K.L. Wong
作者机构:
[Chen, Weimin; Qin, Hua; Huang, Jing; Wang, Ke; Wong, Kelvin K. L.] Hunan City Univ, Sch Informat & Elect, Yiyang 413000, Peoples R China.;[Huang, Hongyuan] Jinjiang Municipal Hosp, Dept Urol, Quanzhou 362200, Fujian Province, Peoples R China.
通讯机构:
[Weimin Chen; Kelvin K.L. Wong] S;School of Information and Electronics, Hunan City University, Yiyang, 413000, China
关键词:
CT;Cardiac aorta segmentation;MRI;MSF model;U-Net;XR model
摘要:
Purpose: This paper proposes a CT images and MRI segmentation technology of cardiac aorta based on XR-MSF-U-Net model. The purpose of this method is to better analyze the patient's condition, reduce the misdiagnosis and mortality rate of cardiovascular disease in inhabitants, and effectively avoid the subjec-tivity and unrepeatability of manual segmentation of heart aorta, and reduce the workload of doctors.Method: We implement the X ResNet (XR) convolution module to replace the different convolution ker-nels of each branch of two-layer convolution XR of common model U-Net, which can make the model extract more useful features more efficiently. Meanwhile, a plug and play attention module integrating multi-scale features Multi-scale features fusion module (MSF) is proposed, which integrates global local and spatial features of different receptive fields to enhance network details to achieve the goal of efficient segmentation of cardiac aorta through CT images and MRI.Results: The model is trained on common cardiac CT images and MRI data sets and tested on our col-lected data sets to verify the generalization ability of the model. The results show that the proposed XR-MSF-U-Net model achieves a good segmentation effect on CT images and MRI. In the CT data set, the XR-MSF-U-Net model improves 7.99% in key index DSC and reduces 11.01 mm in HD compared with the benchmark model U-Net, respectively. In the MRI data set, XR-MSF-U-Net model improves 10.19% and re-duces 6.86 mm error in key index DSC and HD compared with benchmark model U-Net, respectively. And it is superior to similar models in segmentation effect, proving that this model has significant advantages.Conclusion: This study provides new possibilities for the segmentation of aortic CT images and MRI, improves the accuracy and efficiency of diagnosis, and hopes to provide substantial help for the segmen-tation of aortic CT images and MRI.(c) 2022 Elsevier B.V. All rights reserved.
关键词:
Wavelet transforms;Sensor phenomena and characterization;Licenses;Wireless sensor networks;Social networking (online);Routing;Magnetic sensors;Data collection;energy consumption;integer wavelet transform;multi-resolution communication;opportunistic social networks
摘要:
With the shaping of universal computing concept and the development of microelectronics technology, the mobile terminal devices have the strong functions of computing, storage and communication. The opportunistic social networks composed of a large number of terminal devices can be widely used in various scenarios by deploying them anytime and anywhere. One of its most important tasks is to collect data in order to communicate between people and things. The existing researches mainly focus on routing strategies that aim to improve the performance of data collection by optimizing the routing algorithm. However, the inherent characteristics of the opportunistic social networks such as the intermittent communication opportunities make it difficult to improve routing performance because nodes can not get global network topology information. In order to solve this problem, we should establish an efficient data collection mechanism based on wavelet multi-resolution to improve the efficiency of data collection from the source, which mainly studies the multi-resolution compression storage method of node data, the spatial multi-resolution data hierarchical storage framework, and the multi-resolution data management mechanism of mobile node. The experimental results show that the multi-resolution communication mode based on integer wavelet transform can greatly reduce the amount of data in the network and the energy consumption of nodes, and it is beneficial to the data collection of opportunistic social networks.
摘要:
The appearance of a large number of mobile intelligent devices boosts the fast rise of mobile health (mHealth) application. However, due to the sensitivity and complexity of medical data, an efficient and secure mobile communication mode is a very difficult and challenging task in mHealth. The Opportunistic Networks (OppNets) is self-organizing and can expand the communication capacity by the movement of nodes, so it has a good prospect in the application of mHealth. Unfortunately, due to the shortage of stable and reliable end-to-end links, the routing protocol in OppNets has usually lower performance and is unsafe. To address these issues, we propose an adaptive routing optimization algorithm in OppNets for mHealth. This routing scheme firstly analyzes the relationship between nodes and defines the average message forwarding delay as a new metric to selectively forward messages, and then designs a local community detection algorithm based on the metric to adapt to the characteristics of OppNets, and finally resorts to some super-nodes to ferry messages between different communication domains. The simulation results demonstrate the efficiency and effectiveness of the proposed scheme. It increases the delivery ratio by about 30%, decreases delay by about 35%, and decreases the number of forwarding by about 5%, by comparing it with several existing routing schemes. We believe that the relationship between nodes, community, and message ferrying will play an important role in routing of OppNets for mHealth.