Machine Learning and the Future of Cardiovascular Care: JACC State-of-the-Art Review

Malaria is an infectious disease caused by single-celled parasite of plasmodium group. The disease is more often spread by an Infected Female Anopheles mosquito. In 2017 alone 219 million cases and nearly 435,000 deaths were reported, with more than 40% of global population at risk. In spite of many advanced evaluation techniques for identifying the infection, microscopists at resource constrained regions face challenge in improving the diagnostic accuracy. Deep learning based classification of cell images prevent the wrong diagnostic decisions. This paper focuses on the implementation of Transfer learning based classification of malarial infected cells to improve the diagnostic accuracy. The experimental results show that transfer learning performs well on microscopic cell-images

Transfer Learning with ResNet-50 for Malaria Cell-Image Classification

A complete blood cell count is an important test in medical diagnosis to evaluate overall health condition. Traditionally blood cells are counted manually using haemocytometer along with other laboratory equipment's and chemical compounds, which is a time-consuming and tedious task. In this work, the authors present a machine learning approach for automatic identification and counting of three types of blood cells using ‘you only look once’ (YOLO) object detection and classification algorithm. YOLO framework has been trained with a modified configuration BCCD Dataset of blood smear images to automatically identify and count red blood cells, white blood cells, and platelets. Moreover, this study with other convolutional neural network architectures considering architecture complexity, reported accuracy, and running time with this framework and compare the accuracy of the models for blood cells detection. They also tested the trained model on smear images from a different dataset and found that the learned models are generalised. Overall the computer-aided system of detection and counting enables us to count blood cells from smear images in less than a second, which is useful for practical applications.

Machine learning approach of automatic identification and counting of blood cells

With the emergence of Internet-of-Things (IoT) technologies, the application of Wireless Sensor Network (WSN) has become pervasive in our physical environment. These technologies rely on the WSN to capture environmental data and transmit it through the network to the specified location or storage. Given the massive data that captured by the WSN and the data transmission that happen in the process, there is a challenge for any developers and researchers in WSN in terms of a continuous operation of the WSN device. This is because WSNs are battery-powered and often deployed in a remote location that is hard to access for a battery replacement. The purpose of this paper is to survey the energy harvesting for improving the lifetime of the wireless sensor networks powered by the environmental energy. Energy harvesting takes advantages of the stray energy from the environment as the sustainable source of power.

Energy harvesting in wireless sensor networks: A survey

In power-limited wireless devices such as wireless sensor networks, wearable components, and Internet of Things devices energy efficiency is a critical concern. These devices are usually battery operated and have a radio transceiver that is typically their most power-hungry block. Wake-up radio schemes can be used to achieve a reasonable balance among energy consumption, range, data receiving capabilities and response time. In this paper, a high-sensitivity low power wake-up radio receiver (WUR) for wireless sensor networks is presented. The wake-up radio is comprised of a fully passive differential RF-to-DC converter that rectifies the incident RF signal, a low-power comparator and an ultra low power microcontroller to detects the envelope of the on-off keying (OOK) wake-up data used as address. We designed and implemented a novel low power tunable wake up radio with addressing capability, a minimal power consumption of only 196nW and a maximum sensitivity of -55dBm and minimal wake up time of 130μs without addressing and around 1,6ms with 2byte addressing at 10Kbit/s data rate. The flexibility of the solution makes the wake up radio suitable for both power constrained low range application (such as Body Area Network) or applications with long range needs. The wake up radio can work also at different frequencies and the addressing capability directly on board helps reduce false positives. Experimental on field results demonstrate the low power of the solution, the high sensitivity and the functionality.

An ultra low power high sensitivity wake-up radio receiver with addressing capability

This works gives an account of evaluation of white blood cell differential counts via computer aided diagnosis (CAD) system and hematology rules. Leukocytes, also called white blood cells (WBCs) play main role of the immune system. Leukocyte is responsible for phagocytosis and immunity and therefore in defense against infection involving the fatal diseases incidence and mortality related issues. Admittedly, microscopic examination of blood samples is a time consuming, expensive and error-prone task. A manual diagnosis would search for specific Leukocytes and number abnormalities in the blood slides while complete blood count (CBC) examination is performed. Complications may arise from the large number of varying samples including different types of Leukocytes, related sub-types and concentration in blood, which makes the analysis prone to human error. This process can be automated by computerized techniques which are more reliable and economical. In essence, we seek to determine a fast, accurate mechanism for classification and gather information about distribution of white blood evidences which may help to diagnose the degree of any abnormalities during CBC test. In this work, we consider the problem of pre-processing and supervised classification of white blood cells into their four primary types including Neutrophils, Eosinophils, Lymphocytes, and Monocytes using a consecutive proposed deep learning framework. For first step, this research proposes three consecutive pre-processing calculations namely are color distortion; bounding box distortion (crop) and image flipping mirroring. In second phase, white blood cell recognition performed with hierarchy topological feature extraction using Inception and ResNet architectures. Finally, the results obtained from the preliminary analysis of cell classification with (11200) training samples and 1244 white blood cells evaluation data set are presented in confusion matrices and interpreted using accuracy rate, and false positive with the classification framework being validated with experiments conducted on poor quality blood images sized 320 × 240 pixels. The deferential outcomes in the challenging cell detection task, as shown in result section, indicate that there is a significant achievement in using Inception and ResNet architecture with proposed settings. Our framework detects on average 100% of the four main white blood cell types using ResNet V1 50 while also alternative promising result with 99.84% and 99.46% accuracy rate obtained with ResNet V1 152 and ResNet 101, respectively with 3000 epochs and fine-tuning all layers. Further statistical confusion matrix tests revealed that this work achieved 1, 0.9979, 0.9989 sensitivity values when area under the curve (AUC) scores above 1, 0.9992, 0.9833 on three proposed techniques. In addition, current work shows negligible and small false negative 0, 2, 1 and substantial false positive with 0, 0, 5 values in Leukocytes detection.

Automatic white blood cell classification using pre-trained deep learning models: ResNet and Inception

A wireless sensor network (WSN) consists of a large number of sensor nodes which are deployed over an area to perform local computations based on information gathered from the surroundings. Each node in the network is equipped with a battery, but it is almost very difficult to change or recharge batteries; therefore, the crucial question is: “how to prolong the network lifetime to such a long time?” Hence, maximizing the lifetime of the network through minimizing the energy is an important challenge in WSN; sensors cannot be easily replaced or recharged due to their ad-hoc deployment in hazardous environment. Considering that energy saving acts as one of the hottest topics in wireless sensor networks, we will survey the main techniques used for energy conservation in sensor networks. The main focus of this article is primarily on duty cycling schemes which represent the most compatible technique for energy saving and we also focus on the data-driven approaches that can be used to improve the energy efficiency. Finally, we will make a review on some communication protocols proposed for sensor networks.

http://www.airccse.org/journal/ijcses/papers/0212ijcses03.pdf

Energy Saving in Wireless Sensor Networks

Adverse Drug Reaction Detection in Social Media by Deepm Learning Methods.

The bounded diameter minimum spanning tree (BDMST) problem aims at finding the minimum weight spanning tree subject to a predefined diameter constraint. Due to the NP-hardness of the BDMST problem, several heuristic and meta-heuristic approaches have been proposed to find a near optimal solution in a reasonable time. In this article, a distributed algorithm is proposed for solving the BDMST problem based on learning automata. Generally, the proposed algorithm consists of two main phases. In the former phase, the proposed algorithm forms the action-set of learning automata and paths from the root to every other node. The latter phase constructs different spanning trees until it finds the optimum one. To show the performance of the proposed algorithm, it is compared with one of the well-known methods. Experimental results confirm the superiority of the proposed algorithm both in terms of the computational complexity and the weight of the spanning tree.

A learning automata based approach to the bounded-diameter minimum spanning tree problem

Wireless sensor networks which are used to monitor and control a specific area, are made of many small sensor nodes; they are compressed and spread in an environment. One of the most challenges in these types of networks is Energy limitation which has direct influence on sensor network lifetime. Unicast routing in wireless sensor networks is a way for data delivery to a receiver. In this paper we are intended to present a unicast routing algorithm in wireless sensor networks, and we make a virtual backbone out of Minimum Connected Dominating Set (MCDS). This virtual backbone is initiated according to Energy level, Neighboring, and distance from Sink node. So, to this end we use an algorithm based on learning automata named UMCDS- LA deal with the unicast routing problem. Finally, we simulate proposed method by ns2 simulator. Thus the results show high performance of the proposed algorithm. Streszczenie. W artykule zaprezentowano algorytm routowania typu unicast w sieci bezprzewodowej (ang. Wireless Sensor Network). Szkielet sieci oparty zostal na strukturze typu MCDS (ang. Minimum Connected Dominating Set). Do realizacji wykorzystano algorytm oparty na automacie uczącym sie UMCDS-LA. Metode przebadano na symulatorze ns2. (Energowydajny algorytm routowania w sieciach bezprzewodowych oparty na strukturze MCDS - automaty uczące sie)

Zahra Rezaei

Papers

Automatic white blood cell classification using pre-trained deep learning models: ResNet and Inception

Energy Saving in Wireless Sensor Networks

Adverse Drug Reaction Detection in Social Media by Deepm Learning Methods.

A learning automata based approach to the bounded-diameter minimum spanning tree problem

An Energy-Efficient MCDS-based Routing Algorithm for Wireless Sensor Networks: Learning Automata Approach