EDGF: Empirical dataset generation framework for wireless sensor networks

The accuracy of the location estimation of sensors in wireless sensor networks (WSNs) is important to many applications such as environment surveillance applications. In large-scale and distributed WSNs, locations of the sensors may not be recorded during the deployment process, resulting in the need of localization techniques to help collect the sensor location information. WSNs are highly vulnerable to localization attacks since the localization techniques totally rely on the neighboring relations to determine the location of sensors. In other words, some of malicious sensor nodes can take the advantage of the neighboring relations to manipulate the localization process. In this paper, we propose two localization algorithms to overcome both common types of localization attacks, independent attacks and collusion attacks. In the first algorithm, we propose the Improved Randomized Consistency Position Algorithm to determine the location of unknown nodes using the location estimation information provided by the three random anchor nodes and using the PSO algorithm paradigm to identify the coordinates of the unknown nodes’ location. In addition, the second algorithm, which is a combination of voting method, location optimization, and the PSO algorithm paradigm to identify the location of unknown nodes, is referred to as the Enhanced Attack-Resistant Secure Localization Algorithm. Through rigorous theoretical analysis and experimentation, we demonstrate that our proposed localization algorithms yield better performance comparing to the existing methods.

Secure Localization Algorithms Against Localization Attacks in Wireless Sensor Networks

Data collection is one of the most important issues in Wireless Sensor Networks (WSNs). Many data collection algorithms have been proposed for collecting data using a mobile sink. However, the appropriateness and the number of the selected anchors, which significantly impact the network lifetime of the given WSNs, still can be improved. This paper proposes a Joint Density-Aware and Energy-Limited Path Construction algorithm for Data Collection, called DEDC, aiming to select as more as possible appropriate anchors under the path length constraint for prolonging the network lifetime. Initially, the proposed DEDC determines the grid size according to the path length constraint, partitions the monitoring region into several grids and identifies the grids to be balance or unbalance grids. Based on the partitioned grids, the proposed DEDC constructs a regular path and then further adjusts the path segments for these unbalanced grids. The regular path construction and path adjustment aim to construct a path passing through as more as possible anchors for balancing the forwarding loads and prolonging the network lifetime. Performance evaluations reveal that the proposed DEDC outperforms existing data collection mechanisms in terms of energy consumption, network lifetime, and SD energy consumptions.

/pdf/dedc-joint-density-aware-and-energy-limited-path-15drcss9zk.pdf

DEDC: Joint Density-Aware and Energy-Limited Path Construction for Data Collection Using Mobile Sink in WSNs

In India, half the population depends on agriculture for a livelihood. Microbial diseases are a significant threat to food security, but their rapid identification remains difficult due to limited infrastructure. With AI, automatic detection of plant diseases from raw images is possible using deep learning and transfer learning. This paper aims to detect and classify Grapes and Mango leaf diseases, employing a dataset of 8,438 images of diseased and healthy leaves collected from the Plant Village dataset and acquired locally. The deep convolutional neural network (CNN) is trained to identify diseases or their absence. A pre-trained CNN architecture called AlexNet is modeled for automatic feature extraction and classification. The system is developed with MATLAB achieves an accuracy rate of the detection of 99% and 89% for Grape leaves and Mango leaves respectively. An app named "JIT CROPFIX" is developed to implement the same on an Android Smartphone.

Deep Learning Precision Farming: Grapes and Mango Leaf Disease Detection by Transfer Learning

In wireless sensor networks (WSNs), the problem of reporting data to the sink with minimum latency has been widely discussed in many research works. Many studies address on using data aggregation to report the same type of data to the sink without data collision in a short period of time. However, due to the rapid development of sensor technology in recent years, a sensor is allowed to have multiple sensing capabilities, that is, it can generate and collect different types of data. Because different types of data have different meanings and required aggregation functions, only the data that belong to the same type are allowed to be aggregated. In addition, due to the interference of the environment or the noise, the links in the WSNs are often not bidirectional. This motivates us to study the problem of using minimum latency scheduling to aggregate and report data to the sink without data collision in multiple-data-type WSNs having unidirectional links, which is shown to be NP-hard in the paper. In addition, the Relative-Collision-Graph-Based Scheduling Algorithm (RCGBSA) is therefore proposed accordingly. Simulations are conducted to demonstrate the performance of the RCGBSA.

Minimizing Latency for Multiple-Type Data Aggregation in Wireless Sensor Networks

Because of the limited energies of sensors, efficient data gathering in wireless sensor network has been received a great deal of attention recently. To prolong the network lifetime, in this paper, we study the problem of scheduling a mobile sink to some specific nodes, termed anchor nodes in this paper, for data collection and reducing the energy consumption of data transmission. While considering data aggregation and imbalance initial energies of sensors, a method, termed the Heuristic Algorithm, is proposed to prolong the lifetime of wireless sensor networks. In addition, a simulation is conducted to evaluate the performance of the proposed method. Simulation results show that our proposed method performs better than other existing method.

An efficient mobile sink scheduling method for data collection in wireless sensor networks

Nowadays, the problem of using minimum number of time slots for data aggregation such that sensors can work without data collision for data transmissions has received a great deal of attention in Wireless Sensor Network (WRSN). It is worth mentioning that there exists many approaches that are tried to reduce the number of time slots for data aggregation in WSNs. However, most of previous works are fallen into reducing time slots in certain circle. In this paper, we investigate the problem of Reducing Data Aggregation Time without Data Collision (RDATDC) problem and first propose a new overlap circle technique, which is termed the Overlap-Circle-based algorithm (OCBA), to solve the RDATDC problem. Simulation results show that the OCBA has better performance than other method.

Tong Lin

Papers

Minimizing Latency for Multiple-Type Data Aggregation in Wireless Sensor Networks

An efficient mobile sink scheduling method for data collection in wireless sensor networks

A new overlap circle technique for Reducing Data Aggregation Time in Wireless Sensor Networks