/pdf/review-machine-learning-techniques-in-wireless-sensor-4y74cudhwt.pdf

Review—Machine Learning Techniques in Wireless Sensor Network Based Precision Agriculture

The addition of massive machine type communication (mMTC) as a category of Fifth Generation (5G) of mobile communication, have increased the popularity of Internet of Things (IoT). The sensors are one of the critical component of any IoT device. Although the sensors posses a well-known historical existence, but their integration in wireless technologies and increased demand in IoT applications have increased their importance and the challenges in terms of design, integration, etc. This survey presents a holistic (historical as well as architectural) overview of wireless sensor (WS) nodes, providing a classical definition, in-depth analysis of different modules involved in the design of a WS node, and the ways in which they can be used to measure a system performance. Using the definition and analysis of a WS node, a more comprehensive classification of WS nodes is provided. Moreover, the need to form a wireless sensor network (WSN), their deployment, and communication protocols is explained. The applications of WS nodes in various use cases have been discussed. Additionally, an overlook of challenges and constraints that these WS nodes face in various environments and during the manufacturing process, are discussed. Their main existing developments which are expected to augment the WS nodes, to meet the requirements of the emerging systems, are also presented.

/pdf/challenges-applications-and-future-of-wireless-sensors-in-2xrcahys.pdf

Challenges, Applications, and Future of Wireless Sensors in Internet of Things: A Review

We introduce TestU01, a software library implemented in the ANSI C language, and offering a collection of utilities for the empirical statistical testing of uniform random number generators (RNGs). It provides general implementations of the classical statistical tests for RNGs, as well as several others tests proposed in the literature, and some original ones. Predefined tests suites for sequences of uniform random numbers over the interval (0, 1) and for bit sequences are available. Tools are also offered to perform systematic studies of the interaction between a specific test and the structure of the point sets produced by a given family of RNGs. That is, for a given kind of test and a given class of RNGs, to determine how large should be the sample size of the test, as a function of the generator's period length, before the generator starts to fail the test systematically. Finally, the library provides various types of generators implemented in generic form, as well as many specific generators proposed in the literature or found in widely used software. The tests can be applied to instances of the generators predefined in the library, or to user-defined generators, or to streams of random numbers produced by any kind of device or stored in files. Besides introducing TestU01, the article provides a survey and a classification of statistical tests for RNGs. It also applies batteries of tests to a long list of widely used RNGs.

TestU01: A C Library for Empirical Testing of Random Number Generators

Weeds are one of the most important factors affecting agricultural production. The waste and pollution of farmland ecological environment caused by full-coverage chemical herbicide spraying are becoming increasingly evident. With the continuous improvement in the agricultural production level, accurately distinguishing crops from weeds and achieving precise spraying only for weeds are important. However, precise spraying depends on accurately identifying and locating weeds and crops. In recent years, some scholars have used various computer vision methods to achieve this purpose. This review elaborates the two aspects of using traditional image-processing methods and deep learning-based methods to solve weed detection problems. It provides an overview of various methods for weed detection in recent years, analyzes the advantages and disadvantages of existing methods, and introduces several related plant leaves, weed datasets, and weeding machinery. Lastly, the problems and difficulties of the existing weed detection methods are analyzed, and the development trend of future research is prospected.

Review of Weed Detection Methods Based on Computer Vision

Weeds are amongst the most impacting abiotic factors in agriculture, causing important yield loss worldwide. Integrated Weed Management coupled with the use of Unmanned Aerial Vehicles (drones), allows for Site-Specific Weed Management, which is a highly efficient methodology as well as beneficial to the environment. The identification of weed patches in a cultivated field can be achieved by combining image acquisition by drones and further processing by machine learning techniques. Specific algorithms can be trained to manage weeds removal by Autonomous Weeding Robot systems via herbicide spray or mechanical procedures. However, scientific and technical understanding of the specific goals and available technology is necessary to rapidly advance in this field. In this review, we provide an overview of precision weed control with a focus on the potential and practical use of the most advanced sensors available in the market. Much effort is needed to fully understand weed population dynamics and their competition with crops so as to implement this approach in real agricultural contexts.

/pdf/drone-and-sensor-technology-for-sustainable-weed-management-lylmd783x3.pdf

Drone and sensor technology for sustainable weed management: a review

Wireless sensor network (WSN) is used to sense the environment, collect the data, and further transmit it to the base station (BS) for analysis. A synchronized tree-based approach is an efficient approach to aggregate data from various sensor nodes in a WSN environment. However, achieving energy efficiency in such a tree formation is challenging. In this research work, an algorithm named fuzzy attribute-based joint integrated scheduling and tree formation (FAJIT) technique for tree formation and parent node selection using fuzzy logic in a heterogeneous network is proposed. FAJIT mainly focuses on addressing the parent node selection problem in the heterogeneous network for aggregating different types of data packets to improve energy efficiency. The selection of parent nodes is performed based on the candidate nodes with the minimum number of dynamic neighbors. Fuzzy logic is applied in the case of an equal number of dynamic neighbors. In the proposed technique, fuzzy logic is first applied to WSN, and then min–max normalization is used to retrieve normalized weights (membership values) for the given edges of the graph. This membership value is used to denote the degree to which an element belongs to a set. Therefore, the node with the minimum sum of all weights is considered as the parent node. The result of FAJIT is compared with the distributed algorithm for Integrated tree Construction and data Aggregation (DICA) on various parameters: average schedule length, energy consumption data interval, the total number of transmission slots, control overhead, and energy consumption in the control phase. The results demonstrate that the proposed algorithm is better in terms of energy efficiency.

/pdf/fajit-a-fuzzy-based-data-aggregation-technique-for-energy-4y4tp3kb59.pdf

FAJIT: a fuzzy-based data aggregation technique for energy efficiency in wireless sensor network

Weeds present in the crops are one of the factors that lead to decrease in crop production. The weeds take up nutrients, water which leads to weight reduction in plant and decreases the grains per ear and grain yield.so a method needs to be developed which would detect these weeds in the field and then herbicide is sprayed on them to completely destroy through the use of new drone technology and deep learning in field of convolutional neural networks. Using the dataset from the fields of Indian Agriculture Research Institute (IARI), THE AUTHORS have applied transfer learning technique to identify three weeds Phalaris minor, Dactyloctenium aegyptium, Digera arvensis, Echinochloa colona which achieved achieve accuracy of 95%,65%,61%,54% respectively for the datasets which were not involved in training of model.

An experimental set up for utilizing convolutional neural network in automated weed detection

Sequential pattern mining (SPM) is one of the main application areas in the field of online business, e-commerce, bioinformatics, etc. The traditional approaches in SPM are unable to accurately mine the huge volume of data. Therefore, the proposed work employs a sequential mining model based on deep learning to minimize complexity in handling huge data. Application areas such as online retailing, finance, and e-commerce face a dynamic change in data, which results in non-stationary data. Therefore, our proposed work uses discrete wavelet analysis to convert non-stationary data into time series. In the proposed SPM, a reformed hybrid combination of convolutional neural network (CNN) with long short-term memory (LSTM) is designed to find out customer behavior and purchasing patterns in terms of time. CNN is used to find the concerned itemsets (frequent) at the end of the pattern and LSTM for finding the time interval among each pair of successive itemsets. The proposed work mines the sequential pattern from a progressive database that removes the obsolete data. Finally, the accuracy of the proposed work is compared with some traditional algorithms to demonstrate its robustness.

Deep learning-based sequential pattern mining for progressive database

Nowadays, internet technology plays a vital role in all the fields of our daily lives ranging from the world economy, professional careers, higher education, and almost all the spheres that are deeply impacted. In the current situation, due to COVID19, the dependence on the Internet for almost everything, including learning, getting daily needs, etc., is heavily dependent on the Internet. Online learning is made possible by the Internet, and today most students, educators, researchers are leveraging online learning platforms to enhance their knowledge at their own pace. Generally, the quality of the E-learning courses is evaluated with the help of the courses' review and rating mechanisms. In the present context, review systems are centralized, storing highly valuable information at one location and are liable to manipulation, hacking, and tampering. In this paper, the Blockchain-based Online Education Content Ranking system is proposed for an online review and ranking system that offers a decentralized trustworthy system, ensuring the integrity of the rating and the independence and integrity of content reviews by Subject Matter Experts (SME).

Blockchain-based online education content ranking.

The cloud computing model has revolutionized the computing world for more than a decade. The cloud computing has enormous advantages over the traditional computing. The cloud computing encompasses several benefits like, cost effectiveness, faster speed, takes lesser set up time, works on pay per use, has resilient service, round the clock availability, service availability on the go and may more. Along with all these advantages there are some issues and challenges with cloud computing. The one of the major issue in cloud computing is security of data or information shared in virtual environment of cloud. As the cloud model is based on the virtual machines which provide a virtual environment. Hence the data shared on the cloud becomes vulnerable for security breach. There is requirement to protect the data from every stake holders including cloud service providers. Various data security mechanism is used in the cloud computing to secure the data. One of the important ways is encryption methods. The encryption methods varies in terms of its efficiency, speed, effectiveness and costing. The security level of data does not always remain same. Rather it varies as per the type of data or some time as per demand of owner of data. Thus a base for classification of data, which is to be shared on cloud, needs to be identified. So that a suitable encryption method can be applied dynamically, to make the data encryption optimum and cost effective. In this article the efforts are being put to analyze the foundation of data classification in cloud computing and to propose a data classification based on some important parameters which are responsible for security level of data shared in cloud environment.

Pramod Kumar

Papers

FAJIT: a fuzzy-based data aggregation technique for energy efficiency in wireless sensor network

An experimental set up for utilizing convolutional neural network in automated weed detection

Deep learning-based sequential pattern mining for progressive database

Blockchain-based online education content ranking.

Classification of Data to Enhance Data Security in Cloud Computing