Improving the Accuracy of Multi-Valued Datasets in Agriculture Using Logistic Regression and LSTM-RNN Method

Changes in environmental factors such as water quality, soil quality, and pollution factors lead to diseases in food producing plants. Identifying plant disease is a very difficult task in agriculture. Plant diseases are also mainly caused by many influences in agriculture which includes hybrid genetics, and the plant lifetime during the infection, environmental changes like climatic changes, soil, temperature, rain, wind, weather etc. The infections may be single or mixed, according to the infections the plants diseases spread. Early detection of plant diseases using recent technologies helps the plants growth. Therefore, Machine Learning techniques are used for early prediction of the diseases. This paper is used to improve the accuracy of detecting plant diseases using the prediction of the soil content in the field land. The techniques Nave Bayes (NB) and Neural Network (NN) were used in the existing system. The proposed system uses Logistic Regression method with Long Short- Term Memory (LSTM) in Neural Networks (NN) for predicting the soil content and also detects the plant diseases, improves the accuracy level in the plant growth.

Effect of social media use on learning, social interactions, and sleep duration among university students

Background

Social networking sites are widely used by university students. This study investigated the purposes for which social networking sites are used and their effects on learning, social interaction, and sleep duration.

Material and methods

A cross-sectional study was conducted among 300, 17–29-year-old female students at Prince Sattam bin Abdul Aziz University. A questionnaire was used to collect data. Chi-squared (Fisher’s exact test) test was used to analyze the data.

Results

The results showed that 97% of the students used social media applications. Only 1% of them used social media for academic purposes. Whereas 35% of them used these platforms to chat with others, 43% of them browsed these sites to pass time. Moreover, 57% of them were addicted to social media. Additionally, 52% of them reported that social media use had affected their learning activities, 66% of them felt more drawn toward social media than toward academic activities, and 74% of them spent their free time on social media platforms. The most popular applications (i.e., based on usage) were Snapchat (45%), Instagram (22%), Twitter (18%), and WhatsApp (7%). Further, 46% and 39% of them reported going to bed between 11 pm and 12 am and between 1 am and 2 am, respectively. Finally, 68% of them attributed their delayed bedtime to social media use, and 59% of them reported that social media had affected their social interactions.

Conclusions

A majority of the participants reported prolonged use of social networking sites for nonacademic purposes. These habitual behaviors can distract students from their academic work, adversely affect their academic performance, social interactions, and sleep duration, and lead to a sedentary lifestyle and physical inactivity, which in turn can render them vulnerable to non-communicable diseases and mental health problems.

University learning with anti-plagiarism systems

We have designed an anti-plagiarism software to detect plagiarism in students' assignments, especially written assignments, homework, and research reports, which will hereinafter be collectively referred to as student work. We used our university network to gather student work to detect plagiarism. . To collect data, we used a domain name system to store the student work data based on the respective location, time, and the subject on which each student was assigned work. Once the student work data were collected, they were sent to an extraction module to remove unwanted data. The remaining data were then fed to a similarity index module, which produced similarity values based on comparisons between the collected data and the student work. This module uses mathematical equations that are built using semantic and syntactic similarity reports. Furthermore, in this study, we recommended procedures that can be applied to avoid plagiarism using the programming approach. This approach can raise awareness of plagiarism among students and encourage them to generate innovative ideas instead of plagiarizing. To attract faculty members to use the software, promotional materials can be customized based on the actual control factors that directly affect their adoption of the software. For example, the campaign should provide information highlighting the ease of implementation of the software for senior faculty members.

Optimization Driven Deep Learning Approach for Health Monitoring and Risk Assessment in Wireless Body Sensor Networks

Wireless body sensor networks (WBSNs) plays a vital role in monitoring health conditions of patients and is a low-cost solution for dealing with several healthcare applications. Processing large amounts of data and making feasible decisions in emergency cases are the major challenges for WBSNs. Thus, this article addresses these challenges by designing a deep learning approach for health risk assessment by proposing a Fractional Cat-based Salp Swarm Algorithm (FCSSA). At first, the WBSN nodes are utilized for sensing data from patient health records to acquire certain parameters for making the assessment. Based on the obtained parameters, WBSN nodes transmit the data to the target node. Here, the hybrid Harmony Search Algorithm and Particle Swarm Optimization (hybrid HSA-PSO) is used for determining the optimal cluster head. Then, the results produced by the hybrid HSA-PSO are given to the target node, in which the Deep Belief Network (DBN) is used for classifying the health records for the health risk assessment. Here, the DBN is trained using the proposed FCSSA, which is developed by integrating a Fractional Cat Swarm Optimization (FCSO) and Salp Swarm Algorithm (SSA) for initiating the classification. The proposed FCSSA shows better performance using metrics, namely accuracy, energy and throughput with values 94.604, 0.145, and 0.058, respectively.

A Three Layered Decentralized IoT Biometric Architecture for City Lockdown During COVID-19 Outbreak

In this article, we have built a prototype of a decentralized IoT based biometric face detection framework for cities that are under lockdown during COVID-19 outbreaks. To impose restrictions on public movements, we have utilized face detection using three-layered edge computing architecture. We have built a deep learning framework of multi-task cascading to recognize the face. For the face detection proposal we have compared with the state of the art methods on various benchmarking dataset such as FDDB and WIDER FACE. Furthermore, we have also conducted various experiments on latency and face detection load on three-layer and cloud computing architectures. It shows that our proposal has an edge over cloud computing architecture.

Clustering and Classification based real time analysis of health monitoring and risk assessment in Wireless Body Sensor Networks

Wireless body sensor networks (WBSNs) play a vital role in monitoring the health conditions of patients and are a low-cost solution for dealing with several healthcare applications. However, processing a large amount of data and making feasible decisions in emergency cases are the major challenges attributed to WBSNs. Thus, this paper addresses these challenges by designing a deep learning approach for health risk assessment by proposing fractional cat based salp swarm algorithm (FCSSA). At first, the WBSN nodes are utilized for sensing data from patient health records to acquire certain parameters for making the assessment. Based on the obtained parameters, WBSN nodes transmit the data to the target node. Here, the hybrid harmony search algorithm and particle swarm optimization (hybrid HSA-PSO) is used for determining the optimal cluster head. Then, the results produced by the hybrid HSA-PSO are given to the target node, in which the deep belief network (DBN) is used for classifying the health records for the health risk assessment. Here, the DBN is trained using the proposed FCSSA, which is developed by integrating fractional cat swarm optimization (FCSO) and salp swarm algorithm (SSA) for initiating the classification. The proposed FCSSA-based DBN shows better performance using metrics, namely accuracy, energy, and throughput with values 94.604, 0.145, and 0.058, respectively.

A Proposal to Detect the Double Submission of a Manuscript Sent for Review

Along with the rapid growth of editorial systems and publishers, the number of research articles is increasing, which creates a need for an effective dissemination strategy. Researchers commonly use editorial systems in a candid manner. However, when researchers concurrently submit the same contribution in more than one editorial system, it is considered unethical. In this paper, we propose a novel approach called DeMSum for detecting such duplicate submissions. DeMSum verifies a manuscript (MS) by processing the MS attributes that are accessed through the editorial system. To the best of our knowledge, DeMSum is the first system to address the double submission issue, thus enabling the use of diverse editorial systems for MS review. We implemented a prototype, and our evaluation of the prototype produced excellent results.

An Online Lab Examination Management System (OLEMS) to Avoid Malpractice

Examination and evaluation are two important phases of education at any level of a student's curriculum. However, these assessment processes are problematic in the sense that they encourage learners to devise ways to be dishonest. The traditional way of conducting exams is particularly conducive to dishonesty. In view of this, this letter proposes an online lab examination management system to prevent misconduct and to secure the process of lab examination.