The human body contains identity information that can be used for the person recognition (verification/recognition) problem. In this paper, we propose a person recognition method using the information extracted from body images. Our research is novel in the following three ways compared to previous studies. First, we use the images of human body for recognizing individuals. To overcome the limitations of previous studies on body-based person recognition that use only visible light images for recognition, we use human body images captured by two different kinds of camera, including a visible light camera and a thermal camera. The use of two different kinds of body image helps us to reduce the effects of noise, background, and variation in the appearance of a human body. Second, we apply a state-of-the art method, called convolutional neural network (CNN) among various available methods, for image features extraction in order to overcome the limitations of traditional hand-designed image feature extraction methods. Finally, with the extracted image features from body images, the recognition task is performed by measuring the distance between the input and enrolled samples. The experimental results show that the proposed method is efficient for enhancing recognition accuracy compared to systems that use only visible light or thermal images of the human body.

Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras.

Crop diseases are a noteworthy risk to sustenance security, however their quick distinguishing proof stays troublesome in numerous parts of the world because of the non attendance of the important foundation. Emergence of accurate techniques in the field of leaf-based image classification has shown impressive results. This paper makes use of Random Forest in identifying between healthy and diseased leaf from the data sets created. Our proposed paper includes various phases of implementation namely dataset creation, feature extraction, training the classifier and classification. The created datasets of diseased and healthy leaves are collectively trained under Random Forest to classify the diseased and healthy images. For extracting features of an image we use Histogram of an Oriented Gradient (HOG). Overall, using machine learning to train the large data sets available publicly gives us a clear way to detect the disease present in plants in a colossal scale.

Plant Disease Detection Using Machine Learning

The coverage problem in wireless sensor networks (WSNs) can be generally defined as a measure of how effectively a network field is monitored by its sensor nodes. This problem has attracted a lot of interest over the years and as a result, many coverage protocols were proposed. In this survey, we first propose a taxonomy for classifying coverage protocols in WSNs. Then, we classify the coverage protocols into three categories (i.e., coverage-aware deployment protocols, sleep scheduling protocols for flat networks, and cluster-based sleep scheduling protocols) based on the network stage where the coverage is optimized. For each category, relevant protocols are thoroughly reviewed and classified based on the adopted coverage techniques. Finally, we discuss open issues (and recommend future directions to resolve them) associated with the design of realistic coverage protocols. Issues such as realistic sensing models, realistic energy consumption models, realistic connectivity models and sensor localization are covered.

/pdf/coverage-protocols-for-wireless-sensor-networks-review-and-4ds5g0oeu1.pdf

Coverage protocols for wireless sensor networks: Review and future directions

In this manuscript, we present a survey of designs and implementations of research sensor nodes that rely on FPGAs, either based upon standalone platforms or as a combination of microcontroller and FPGA. Several current challenges in sensor networks are distinguished and linked to the features of modern FPGAs. As it turns out, low-power optimized FPGAs are able to enhance the computation of several types of algorithms in terms of speed and power consumption in comparison to microcontrollers of commercial sensor nodes. We show that architectures based on the combination of microcontrollers and FPGA can play a key role in the future of sensor networks, in fields where processing capabilities such as strong cryptography, self-testing and data compression, among others, are paramount.

/pdf/sensor-systems-based-on-fpgas-and-their-applications-a-875jev4ng8.pdf

Sensor Systems Based on FPGAs and Their Applications: A Survey

A novel trust mechanism based on Fog Computing in Sensor–Cloud System

Wireless Sensor Network (WSN) is an emerging technology that is gaining much importance owing to its immense contribution in various day-to-day applications. A sensor is battery-operated, unattended low-cost device with limited computing, communication and storage capabilities. Thus the network lifetime has become the key characteristic for evaluating sensor networks in an application-specific way. There are certain approaches in literature which consider the lifetime maximization problem. However, they suffer from impulsive energy hole, coverage hole and communication hole. In this paper we propose a novel Energy Efficient Connected Coverage (EECC) scheduling to maximize the lifetime of the WSN. The EECC adheres to Quality of Service (QoS) metrics such as remaining energy, coverage and connectivity. In EECC the sensor which doesn't contribute to coverage will act as a relay node to reduce the burden of the sensing node. The sensing node senses the target whereas the relaying node communicates the sensory information to the sink. The EECC forms non-disjoint cover sets using remaining energy, coverage and connectivity of every sensor. The proposed EECC outperforms similar scheduling algorithms found in the literature in an energy efficient way with the short execution time. Through simulations the constancy of EECC in extending the lifetime of WSN is confirmed.

Maximizing the wireless sensor networks lifetime through energy efficient connected coverage

Agriculture is the mother of all cultures. It played a vital role in the development of human civilization. But plant leaf diseases can damage the crops there may be economic losses in crops. Without knowing about the diseases affected in the plant, the farmers are using excessive pesticides for the plant disease treatment. To overcome this, the detected spot diseases in leaves are classified based on the diseased leaf types using various neural network algorithms. By this approach one can detect the diseased leaf variety and thus can take necessary steps in time to minimize the loss of production. The proposed methodology uses to classify the diseased plant leaves using Feed Forward Neural Network (FFNN), Learning Vector Quantization (LVQ) and Radial Basis Function Networks (RBF) by processing the set of shape and texture features from the affected leaf image. The simulation results show the effectiveness of the proposed scheme. With the help of this work, a machine learning based system can be formed for the improvement of the crop quality in the Indian Economy.

Classification of diseased plant leaves using neural network algorithms

Wireless sensor networks (WSNs) are used in many applications nowadays, because of its extensive usage. Due to the distinct characteristics, they are vulnerable to many attacks. To secure WSN, trust management plays a pertinent role. In trust based security model, decision is taken based on some specific behavior, and so it has uncertainty. Fuzzy logic deals with uncertainty and has tolerance of imprecise data with high power of precision. In this study, fuzzy logic based multi-attribute trust model is suggested. The proposed trust model has message success rate, elapsed time at node, correctness and fairness as trust metrics. Once the four trust values are calculated, fuzzy computational theory is applied to compute the final trust value of every node that can be anyone of low (l), medium (m) and high (h). Simulation results show that the fuzzy based multi-attribute trust evaluation outperforms weighted summation based multi-attribute trust evaluation.

Fuzzy Trust Protocol for Malicious Node Detection in Wireless Sensor Networks

Wind energy is one of the fastest-growing sources of electricity in India and around the world In spite of being cheap, clean and abundant the continuous fluctuations in the renewable energy causes significant power quality issues This paper presents a technical review of power quality problems associated with grid connected wind power plant and describes the Dynamic Voltage Restorer that injects voltage into the system with a view to enhance the network power factor while stabilizing the voltage and reducing the network losses On the basis of measurements and norms followed according to the guidelines specified in IEC-61400 (International Electro-technical Commission) standard, the performance of the wind turbine and thereby power quality should be determined Wind turbines, especially of Induction type, can draw large amount of reactive power from the grid Insufficient supply of reactive power from the grid to the wind generators may cause voltage stability problems To minimize reactive power exchange between wind generators and grid, dynamic compensation of reactive power can be employed by using DVR This paper also describes the analysis of Dynamic Voltage Restorer (DVR) using MATLAB/SIMULINK for the grid connected Wind Power Plant

Analysis of power quality problems in grid connected wind power plant

Surveillance plays a crucial role in day-to-day life. A typical surveillance system continuously monitors its vicinity and stores the surveillance data locally. This may end up in lots of memory and energy wastage. Moreover, the surveillance records are under security threat, when the surveillance system is seized or damaged by the intruders. In this paper, a new design for surveillance using smartphone along with the passive infrared (PIR) sensor and the microcontroller unit (MCU) is proposed. The PIR sensor is attached to the smartphone through the MCU to detect motion. The video is captured only when the motion is detected and the short message services alert is sent to the user straight away. To overcome the memory restrictions of smartphone and to ensure the safe storage of surveillance records, it is uploaded in cloud, and the link is sent to the user through email. The proposed intelligent surveillance system offers cost effective, storage effective, energy efficient, and secured solution as it uses the computation and communication capabilities of the smartphone and the storage capabilities of cloud.

P. Latha

Papers

Maximizing the wireless sensor networks lifetime through energy efficient connected coverage

Classification of diseased plant leaves using neural network algorithms

Fuzzy Trust Protocol for Malicious Node Detection in Wireless Sensor Networks

Analysis of power quality problems in grid connected wind power plant

Smartphone Enabled Intelligent Surveillance System