Classification of mammogram for early detection of breast cancer using SVM classifier and Hough transform

This review paper summarizes various approaches developed in the literature for antenna sensors with an emphasis on flexible solutions. The survey helps to recognize the limitations and advantages of this technology. Furthermore, it offers an overview of the main points for the development and design of flexible antenna sensors from the selection of the materials to the framing of the antenna including the different scenario applications. With regard to wearable antenna sensors deployment, a review of the textile materials that have been employed is also presented. Several examples related to human body applications of flexible antenna sensors such as the detection of NaCl and sugar solutions, blood and bodily variables such as temperature, strain, and finger postures are also presented. Future investigation directions and research challenges are proposed.

https://www.mdpi.com/1996-1944/13/17/3781/pdf

A Review of Flexible Wearable Antenna Sensors: Design, Fabrication Methods, and Applications

System on chip (SoC) is a microchip which integrates many semiconductor devices into a single chip. The complete system that is integrated with many components and circuits has to be tested for its performance. At the same time, testing of SoC should not affect the final cost of the chip. The production cost of each and every chip can be reduced by minimizing the test time of each SoC. The testing time of each SoC can be minimized by using test scheduling techniques more efficiently and effectively. In this paper, artificial intelligence-based natural-inspired techniques such as ACO, MACO, ABC, bat and firefly algorithms are proposed to perform effective test scheduling, thereby reducing the total cost of the chip. The proposed algorithms are implemented on d695 and p22810 benchmark circuits for various values of TAM widths. The performance of the various algorithms was evaluated, and it is inferred that among the several algorithms used bat algorithm performs much better in reducing the overall testing time of SoC, and hence, the SoC cost is also reduced.

Minimization of test time in system on chip using artificial intelligence-based test scheduling techniques

The damage identification process provides relevant information about the current state of a structure under inspection, and it can be approached from two different points of view. The first approach uses data-driven algorithms, which are usually associated with the collection of data using sensors. Data are subsequently processed and analyzed. The second approach uses models to analyze information about the structure. In the latter case, the overall performance of the approach is associated with the accuracy of the model and the information that is used to define it. Although both approaches are widely used, data-driven algorithms are preferred in most cases because they afford the ability to analyze data acquired from sensors and to provide a real-time solution for decision making; however, these approaches involve high-performance processors due to the high computational cost. As a contribution to the researchers working with data-driven algorithms and applications, this work presents a brief review of data-driven algorithms for damage identification in structural health-monitoring applications. This review covers damage detection, localization, classification, extension, and prognosis, as well as the development of smart structures. The literature is systematically reviewed according to the natural steps of a structural health-monitoring system. This review also includes information on the types of sensors used as well as on the development of data-driven algorithms for damage identification.

/pdf/damage-identification-in-structural-health-monitoring-a-1h8tihxyn5.pdf

Damage Identification in Structural Health Monitoring: A Brief Review from its Implementation to the Use of Data-Driven Applications.

The Internet ofMedical Things (IoMT) is global infrastructure consisting of the collection of medical devices and applications that are interconnected through information and communication technologies [1–3]. IoMT is also known as healthcare IoT. The IoMT uses accelerometer sensor, visual sensor, temperature sensor, carbon dioxide sensor, ECG/EEG/EMG sensor, pressure sensor, gyroscope sensor, blood oxygen saturation sensor, humidity sensor, respiration sensor, and bloodpressure sensor to observe and monitor the patient’s health in a continuous manner. The IoMT sense the patients’ health status and then transfer the clinical data to doctors and care holders with the help of remote cloud data centers [4, 5]. This data is most often used for disease diagnosis and clinical care. The useful information mined from the clinical database is used for preventing and protecting the patient health during situations of emergency. However, the main challenge in IoMT is how to manage with critical applications, where a number of connected devices generate a large amount of medical data [6, 7]. This large volume of data often called big data that cannot be processed by traditional data processing algorithms and applications. By intelligently investigating and collecting large amounts of medical data (big data), IoMT can enhance the decision making and early disease diagnosis. Hence, there is a need for scalable machine learning and intelligent algorithms that lead to more interoperable solutions and that can make effective decisions in emerging IoMT. Padmavathy et al. investigated the feasibility of using circular and rectangular slotted microstrip patch antenna as a strain sensor for structural health monitoring without these aforementioned problems. The qualitative results obtained show that developed design of microstrip patch antenna can successfully detect and characterize the structural and rail line cracks [8]. Weiping Zhang et al. have monitored the medical data in the Internet of things and studied focusing on data fusion and related routing technology. According to the particularity of the data in the medical Internet of things, a data fusion cluster—tree construction algorithm based on event-driven (DFCTA) is proposed. The fusion delay problem in the network is analyzed, and the minimum fusion delay method is proposed by calculation of the fusion waiting time of the nodes [9]. Guizhen He et al. have solved skeleton extraction problems in the tree point cloud model; branch geometric features and local properties of point cloud are utilized to optimize tree skeleton extraction. The experiment results show that, this method displays strong anti-interference and high precision characteristics at branch bifurcation and crossed ending parts of fine tree branches [10]. Murali Dhar M S et al. have proposed a new policy oriented secured service model for providing the security to the services in cloud. The proposed model is the combination of a trust aware policy scheduling algorithm and an effective and intelligent re-encryption scheme. This model assured the scalability, reliability, and the security for the stored e-commerce data and access services [11]. Ching-Hsue Cheng et al. have modeled a hybrid knowledge-based classification system to organize expert experiences, integrated linear and nonlinear attribute-selection methods, data discretization of smart expert method, rough * Gunasekaran Manogaran gmanogaran@ucdavis.edu

/pdf/emerging-trends-issues-and-challenges-in-internet-of-medical-3uftkb9ety.pdf

Emerging trends, issues, and challenges in Internet of Medical Things and wireless networks

Breast cancer is the second highest death causing disease in female.
 From the data it’s clear that one of the eight women is affected by breast cancer.
 The most effective way to detect the cancer is by using mammography technique and
 also it detects masses and abnormal conditions. The cluster shaped white spots on
 mammograms are used the cancer in the early stages. The importance of breast cancer
 detection to reduce different noises which are commonly found in mammogram images
 and provides better image quality. Here the multi-scale and the multi-directional
 analysis would produce optimal approximation and detail coefficients of
 Non-subsampled shearlet transform (NSST). Hence in this paper, the noisy image is
 amended into piecewise smooth function in different subbands of frequency. NSST
 coefficients are amended into information and noise related coefficients are noise
 is removed by using the adaptive threshold. To evaluate the performance of this
 proposed algorithm, Mean Square Error (MSE) and Peak Signal-to-Noise Ratio (PSNR)
 are used. Testing these experimental results show that the proposed algorithm can
 preserve the edges and textures very well while weakening the noise can obtain
 better suppressed noise and enhances the objective of evaluations than other noise
 removal methods.

Performance analysis of pre-cancerous mammographic image enhancement feature using non-subsampled shearlet transform

Structural health monitoring (SHM) is the technique to identify the damage in the building or physical structures. Several structural health monitoring has been proposed in recent years. Increase in number of sensors and its wiring mechanism causes issue in signal processing demand, efficiency, and unreliability. In current state, already present sensors cannot be used for Structural Health Monitoring because of its high cost and low battery capacity, although none of these techniques are capable of monitoring the condition of complex physical structures. The measurement of strain can be done by using patch antenna as strain sensors. In currently available sensors only the wireless range. The main objective of this paper is to investigate the feasibility of using circular and rectangular slotted microstrip patch antenna as a strain sensor for structural health monitoring without these afore mentioned problems. These antenna sensors' (slotted rectangular and circular microstrip patch antennas) simulation results are confirmed. From the simulation results, the sensor provides information about crack orientation.

Design and development of microstrip patch antenna with circular and rectangular slot for structural health monitoring

Breast cancer is the most invasive cancer in women and second leading cause of mortality in women. Advances in detection and treatment have improved survival rates dramatically in patients. Now-a-days mammographic image based analysis is widely used to predict the breast cancer. The diagnosis is simple and survivals of the patient are high if the breast cancer is predicted at the early stage accurately. This paper heavily focuses on methodologies which provides accurate detection of cancerous tissues and thereby reduces the death rates. The algorithms are non-subsampled Shearlet transform (NSST) for image preprocessing, Adaptive clustering for image segmentation and finally adaptive neuro-fuzzy inference system (ANFIS) for image classification. NSST is an extension of wavelet transform in multidimensional and multidirectional case wherein the components are processed with the help of thresholding scheme. Adaptive clustering algorithm separates the pixels in the image into clusters based on both their intensity and sensitivity and thereby makes the segmentation much simpler and easier. ANFIS algorithm is the classifier which is a combination of both neural network adaptive capabilities and the fuzzy logic qualitative approach which is used to classify the normal and abnormal image accurately. The robustness of the proposed methodology is examined using classification accuracy, sensitivity and specificity.

Adaptive clustering based breast cancer detection with ANFIS classifier using mammographic images

Wireless sensor networks (WSNs) are mostly deployed in a remote working environment, since sensor nodes are small in size, cost-efficient, low-power devices, and have limited battery power supply. Because of limited power source, energy consumption has been considered as the most critical factor when designing sensor network protocols. The network lifetime mainly depends on the battery lifetime of the node. The main concern is to increase the lifetime with respect to energy constraints. One way of doing this is by turning off redun-dant nodes to sleep mode to conserve energy while active nodes can provide essential k-coverage, which improves fault-tolerance. Hence, we use scheduling algorithms that turn off redundant nodes after providing the required coverage level k. The scheduling algorithms can be implemented in centralized or localized schemes, which have their own advantages and disadvantages. To exploit the advantages of both schemes, we employ both schemes on the network according to a threshold value. This threshold value is estimated on the performance of WSN based on network lifetime comparison using centralized and localized algorithms. To extend the network lifetime and to extract the useful energy from the network further, we go for compromise in the area covered by nodes.

https://file.scirp.org/pdf/IJCNS20100100015_30962043.pdf

Extending the Network Lifetime of Wireless Sensor Networks Using Residual Energy Extraction—Hybrid Scheduling Algorithm

https://robots.iopscience.iop.org/article/10.1088/1757-899X/994/1/012033/pdf

T. V. Padmavathy

Papers

Performance analysis of pre-cancerous mammographic image enhancement feature using non-subsampled shearlet transform

Design and development of microstrip patch antenna with circular and rectangular slot for structural health monitoring

Adaptive clustering based breast cancer detection with ANFIS classifier using mammographic images

Extending the Network Lifetime of Wireless Sensor Networks Using Residual Energy Extraction—Hybrid Scheduling Algorithm

Design and Simulation of MIMO Antennas for Mobile Communication