Cucumber Leaf Diseases Recognition Using Multi Level Deep Entropy-ELM Feature Selection

Agriculture has becomes an immense area of research and is ascertained as a key element in the area of computer vision. In the agriculture field, image processing acts as a primary part. Cucumber is an important vegetable and its production in Pakistan is higher as compared to the other vegetables because of its use in salads. However, the diseases of cucumber such as Angular leaf spot, Anthracnose, blight, Downy mildew, and powdery mildew widely decrease the quality and quantity. Lately, numerous methods have been proposed for the identification and classification of diseases. Early detection and then treatment of the diseases in plants is important to prevent the crop from a disastrous decrease in yields. Many classification techniques have been proposed but still, they are facing some challenges such as noise, redundant features, and extraction of relevant features. In this work, an automated framework is proposed using deep learning and best feature selection for cucumber leaf diseases classification. In the proposed framework, initially, an augmentation technique is applied to the original images by creating more training data from existing samples and handling the problem of the imbalanced dataset. Then two different phases are utilized. In the first phase, fine-tuned four pre-trained models and select the best of them based on the accuracy. Features are extracted from the selected fine-tuned model and refined through the Entropy-ELM technique. In the second phase, fused the features of all four fine-tuned models and apply the Entropy-ELM technique, and finally fused with phase 1 selected feature. Finally, the fused features are recognized using machine learning classifiers for the final classification. The experimental process is conducted on five different datasets. On these datasets, the best-achieved accuracy is 98.4%. The proposed framework is evaluated on each step and also compared with some recent techniques. The comparison with some recent techniques showed that the proposed method obtained an improved performance.

Response Times Reconstructor Based on Mathematical Expectation Quotient for a High Priority Task over RT-Linux

Every computer task generates response times depending on the computer hardware and software. The response times of tasks executed in real-time operating systems such as RT-Linux can vary as their instances evolve even though they always execute the same algorithm. This variation decreases as the priority of the tasks increases; however, the minimum and maximum response times are still present in the same task, and this complicates its monitoring, decreasing its level of predictability in case of contingency or overload, as well as making resource sizing difficult. Therefore, the need arises to propose a model capable of reconstructing the dynamics of response times for the instances of a task with high priority in order to analyze their offline behavior under specific working conditions. For this purpose, we develop the necessary theory to build the response time reconstruction model. Then, to test the proposed model, we set up a workbench consisting of a single board computer, PREEMPT_RT, and a high priority task generated by the execution of a matrix inversion algorithm. This work demonstrates the application of the theory in an experimental process, presenting a way to model and reconstruct the dynamics of response times by a high-priority task on RT-Linux.

Series Arc Fault Breaker in Low Voltage Using Microcontroller Based on Fast Fourier Transform

Series Arc Fault is one of the disturbances of arcing jump is caused by gas ionization between two ends of damaged conductors or broken wire forming a gap in the insulator. Series arc fault is the primary driver of electrical fire. However, lack of knowledge of the disturbance of series arc fault causes the problem of electrical fire not be mitigated. Magnitude current is not capable to detect of series arc fault. Therefore, this paper proposes fast fourier transform (FFT) to detect series AC arc fault in low voltage using microcontroller ARM STM32F7NGH in real time. A cheap and high speed of microcontroller ARM STM32F7NGH can be used for FFT computation to transform signal in time domain to frequency domain. Moreover, in this paper, protection of series AC arc fault is proposed in the real time mode. In this experimental process, some various experiments are tested to evaluate the reliability of FFT and protection with various load starts from 1 A, 2 A, 3 A, 4 A in resistive load. The result of this experiment shows that series AC arc fault protection with STM32F7 microcontroller and FFT algorithm can be utilized to ensure series AC arc fault properly.

Scaled Experiment of the Detonation Control System for the High-Speed Penetration on Concrete

The design scheme and fabrication technology of the detonation control system for the high-speed deep penetration need to be tested for reliability and effectiveness through shooting range tests. However, the shooting range tests of the high-speed deep penetration are so demanding and expensive that it is difficult for the detonation control system to be tested many times. This paper focuses on penetration characteristics of the detonation control system to put forward a laboratory-scaled experiment method with the low impact velocity. Independent parameters of projectile and target affecting the penetration characteristics are effectively analyzed and extracted. A multi-parameter programming method of the scaled experiment for high-speed deep penetration is established. By adjusting the key parameters, the loading conditions of the scaled experiment can be obtained, which can get the comparable deceleration curve with those of the high-speed deep penetration. Finally, the extreme working environment for the detonation control system in the high-speed deep penetration is simulated through the scaled experiment in the laboratory. The scaled experiment method can get the comparable deceleration peak and time history. It is highly economical, and the experimental process is also repeatable, which can provide a reliable reference for the protection design into the projectile.

Confirming a Drosophila Melanogaster Model of Huntingtin Aggregation

For decades, doctors, psychologists, and psychiatrists alike have struggled to treat the symptomatic effects of Huntington’s disease. Huntington’s disease is an autosomal dominant brain disease that results in the deterioration of a person’s physical and mental state. Once a person inherits the disease, they end up dying from it more often than not. At present, there are 41,000 Americans with symptomatic Huntington’s disease, and 200,000 more are currently at-risk of inheriting the disease. Given its 50/50 chance of inheritance, there seems to be no end in sight to this degenerative ailment. My research study, however, will show that with a more robust approach, finding a cure for this disease is possible. Ultimately, the aim of this project was to test an already established model in Drosophila melanogaster regarding the “huntingtin” protein responsible for Huntington’s disease. This was achieved by first demonstrating that the flies which were modified to produce huntingtin could, in fact, produce the protein. Secondly, an experimental process was created to configure a system through which the amount of protein produced by each fly could be quantified. This quantification was vital in creating a baseline that would allow for the identification of potential therapeutic treatments in the future. In short, by establishing a quantifiable model for huntingtin, this study will pave the way to new insights on huntingtin aggregation and the identification of possible treatments for Huntington’s disease in the future.

A simple method for the application of exogenous phytohormones to the grass leaf base protodermal zone to improve grass leaf epidermis development research

Background The leaf epidermis functions to prevent the loss of water and reduce gas exchange. As an interface between the plant and its external environment, it helps prevent damage, making it an attractive system for studying cell fate and development. In monocotyledons, the leaf epidermis grows from the basal meristem that contains protodermal cells. Leaf protoderm zone is covered by the leaf sheath or coleoptile in maize and wheat, preventing traditional exogenous phytohormone application methods, such as directly spraying on the leaf surface or indirectly via culture media, from reaching the protoderm areas directly. The lack of a suitable application method limits research on the effect of phytohormone on the development of grass epidermis. Results Here, we describe a direct and straightforward method to apply exogenous phytohormones to the leaf protoderms of maize and wheat. We used the auxin analogs 2,4-D and cytokinin analogs 6-BA to test the system. After 2,4-D treatment, the asymmetrical division events and initial stomata development were decreased, and the subsidiary cells were induced in maize, the number of GMC (guard mother cell), SMC (subsidiary mother cell) and young stomata were increased in wheat, and the size of the epidermal cells increased after 6-BA treatment in maize. Thus, the method is suitable for the application of phytohormone to the grass leaf protodermal areas. Conclusions The method to apply hormones to the mesocotyls of maize and wheat seedlings is simple and direct. Only a small amount of externally applied substances are needed to complete the procedure in this method. The entire experimental process lasts for ten days generally, and it is easy to evaluate the phytohormones’ effect on the epidermis development.

A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series Forecasting

In practice, time series forecasting involves the creation of models that generalize data from past values and produce future predictions. Moreover, regarding financial time series forecasting, it can be assumed that the procedure involves phenomena partly shaped by the social environment. Thus, the present work is concerned with the study of the use of sentiment analysis methods in data extracted from social networks and their utilization in multivariate prediction architectures that involve financial data. Through an extensive experimental process, 22 different input setups using such extracted information were tested, over a total of 16 different datasets, under the schemes of 27 different algorithms. The comparisons were structured under two case studies. The first concerns possible improvements in the performance of the forecasts in light of the use of sentiment analysis systems in time series forecasting. The second, having as a framework all the possible versions of the above configuration, concerns the selection of the methods that perform best. The results, as presented by various illustrations, indicate, on the one hand, the conditional improvement of predictability after the use of specific sentiment setups in long-term forecasts and, on the other, a universal predominance of long short-term memory architectures.

Highlighting considerations in experimental design: the case of multimeters

The instructional lab setting has been found to be dominated by prescribed tasks and pre-prepared lab kits. This was explained by teachers’ need to guide students to simultaneously progress through a lab curriculum, which prompts them to standardize the lab experience. Nevertheless, prominent professional associations have persistently called to better represent experimental research practices in the lab, and to grant students more agency in the experimental process by orienting them towards more open-ended lab experiences. This paper reports a lab activity designed to advance students’ agency in the practice of experimental design, in a setting governed by a high-stakes national matriculation exam. Three hundred teachers of advanced level high-school physics experienced the lab activity in a national network of professional learning communities (PLCs). The activity was anchored in an experiment to determine the relationship between the current through a battery and its terminal voltage. It was designed to problematize students’ considerations underlying the choices of the location of the voltmeter and the measuring scale of the ammeter, and the possible implications for the validity of the experimental results; e.g. control of the variables, as well as the range and the accuracy of measurements. Teachers first performed the lab activity as learners, discussed it in the PLC meeting, and finally reflected on their experience. Individual responses to the lab worksheets and the reflections were analyzed. Initially, teachers’ considerations did not portray key aspects related to the validity of the experimental results, such as how design choices related to the location of the voltmeter and the ammeter measuring scale impacted the accuracy and range of the measurements and the control of variables. The teachers were highly engaged in the peer discussion in the PLC and found the lab activity valuable in raising students’ awareness of important considerations in experimental design.