Search

Farming has a plethora of difficult responsibilities, and plant monitoring is one of them. There is also an urgent need to increase the number of alternative techniques for detecting plant diseases, which is now lacking. The agriculture and agricultural support sectors in India provide employment for the great majority of the country's people. In India, the agricultural production of the country is directly connected to the country's economic growth rate. In order to sustain healthy plant development, a variety of processes must be followed, including consideration of environmental factors and water supply management for the optimal production of crops. It is inefficient and uncertain in its outcomes to use the traditional method of watering a lawn. The devastation of more than 18% of the world's agricultural produce is caused by disease attacks on an annual basis. Because it is difficult to execute these activities manually, identifying plant diseases is essential to decreasing losses in the agricultural product business. In addition to diagnosing a wide range of plant ailments, our method also includes the identification of infections as a prophylactic step. Below is a detailed description of a farm-based module that includes numerous cloud data centers and data conversion devices for accurately monitoring and managing farm information and environmental elements. This procedure involves imaging the plant's visually obvious signs in order to identify disease. It is recommended that the therapy be used in conjunction with an application to minimize any harm. Increased productivity as a result of the suggested approach would help both the agricultural and irrigation sectors. The plant area module is fitted with a mobile camera that captures images of all of the plants in the area, and all of the plants' information is saved in a database, which is accessible from any computer with Internet access. It is planned to record information on the plant's name, the type of illness that has been afflicted, and an image of the plant. In a wide range of applications, bots are used to collect images of various plants as well as to prevent disease transmission. To ensure that all information given is retained on the Internet, data is collected and stored in cloud storage as it becomes essential to regulate the condition. According to our findings from our research on wide images of healthy and ill fruit and plant leaves, real-time diagnosis of plant leaf diseases may be done with 98.78% accuracy in a laboratory environment. We utilized 40,000 photographs and then analyzed 10,000 photos to construct a DCDM deep learning model, which was then used to train additional models on the data set. Using a cloud-based image diagnostic and classification service, consumers may receive information about their condition in less than a second on average, with the process requiring only 0.349 s on average.

Agriculture is a distinct sector of a country's economy. In recent years, new patterns have evolved in the agricultural industry. In conjunction with sensor scaling down and precision agriculture, the field of remote sensor networks, such as the wireless sensor network (WSN), was developed. Its major purpose is to make horticultural operations simpler to identify, assess, and manage. This paper uses the proposed DCNN to predict soil moisture and plan irrigation for precision agriculture farmers to reduce water consumption used for cultivation and increase production yield by comparing water content during various stages of plant growth and integrating IoT applications into agriculture. It also optimizes the water level for future irrigation decisions to maintain crop growth and water stability. The data must be served and stored in the form of a grid view, according to Apriori and GRU (gated recurrent unit). Using numerous sensor and parameter modelling methodologies, this system assists in the prediction of irrigation planning based on irrigation needs. The predicted parameters include soil moisture, temperature, and humidity. This observed experimental data supports smart irrigation in crop production with a high yield and little water use. DCNN has a 98.5% experimental result accuracy rate and the MSE value is predicted in DCNN 99.25% of the time.

In this digital period, internet has turned into an indispensable wellspring of correspondence in just about every calling. With the expanded use of system engineering, its security has developed to be exceptionally discriminating issue as the workstations in distinctive association hold very private data and touchy information. The system which helps in screening the system security is termed as Network detection. Intrusion detection is to get ambushes against a machine structure. One of the vital tests to Intrusion Detection is the issue of misjudgment, misdetection and unsuccessful deficiency of steady response to the strike. In the past years, as the second line of boundary after firewall, the Intrusion Detection (ID) strategy has got speedy progression. Two diverse Machine Learning techniques are prepared in this research work, which include both supervised and unsupervised, for Network Intrusion Detection. Naive Bayes (supervised learning) and Self Organizing Maps (unsupervised learning) are the presented techniques. Deep learning techniques such as CNN is used for feature extraction. These remain provisional chances adaptation technique and pointer variables transformation. The two machine learning procedures are prepared on both kind of transformed dataset and afterward their outcomes are looked at with respect to the correctness of intrusion detection. The best Detection Rate (DR) was for the 93.0% User to Root attack (U2R) attack type and the most horrible result was display for Denial of Service attack (DOS) attacks with 0.02%.

RBC called Erythrocytes is one of the important element in blood composition which is main responsible in all living cells for its gaseous exchanges with the environment externally. In general, at the physiological maintained conditions, RBC in view provides circular in the front and also looks bi-concave at side. One of serious disease with reference to blood cells is Cancer where the healthy RBC are affected. This reduces the body's immunity factors. To identify the cancer cell various methods are employed but it does not provide the proper detection of blood cells. In this method, proper identification of the cancer cells from the unaffected RBCs was identified in which are presented in blood samples using various imaging tools and also with the techniques. The proposed novel method called Online Region Based Segmentation (ORBS) method is done which is used to discover the areas of the boundary of the unaffected corpuscles. By using properties of region, a suitable metric is formulated to determine the shape which is abnormal in the blood cells. Overall accuracy of 96.9% is obtained using proposed ORBS methods and deep learning classification (DLC) method is accurate as 97.1% that helps to diagnose cancer cell using the feature extraction process which is done automatically. The computation time was found to be less when related to the other existing method which is 22 seconds. Closeness of Proposed method in relative to True Positive values at ROC curves indicates the performance which is higher than other methods. Experimental results prove proposed systems effectiveness when compared by means of other detection methods.

Big data research for health service applications, from the approval of the cloud computing and the Internet of Things (IoT) model of healthcare brought drastic changes in the medical field and imp...

A tragic crisis that is still daunting the healthcare workers is COVID-19. As its raging spread across the global creates a difficult situation for everyone to manage this crisis in a proper way. So, early detection and controlling of this process should be taken care as priority as number of cases increases and decrementing of detection kits, as there as high chance of the presences of disease which are difficult to identify. In this paper, it brings an effective and efficient Deep Learning solutions for the healthcare workers to make their way even easier and better. A VGG19 model is used in this paper for better detection and classification and it is performed over chest CT images obtained from SARS-CoV-2 CT-scan dataset as it provides clear and expeditious window for this process. As the aim of this paper to bring out a non-Covid-19/Covid-19classification, our model is compared with other cutting-edge models such as VGG16 DensNet-169, Resnet50, and Inception V3. These are evaluated under measures like accuracy, specificity, sensitivity, F1 score, recall, confusion matrix and precision in which VGG19 outperforms every other method.

The cognitive radio (CR) technology is a developing innovation and offers prominent solution to serious scarcity of spectrum and radio resources in today's situation. Multi-Input and Multi-Output cognitive radio networks (MIMO-CRN) comprise primary users (PUs) and secondary users (SUs) to cooperatively relay the primary traffic. It is extremely complicated to assign channel allocation and resources distribution in heterogeneous networks. The channel selection of SUs should fulfill rate and delay constraints of respective SUs. To overcome this issue we can formulate an efficient dynamic resource allocation technique which should uses very reliable nodes for efficient data transmission. The resources are allocated dynamically after ensuring that the nodes fulfill the specified constraints. This proposed framework should leads to effective data transmission and offer significant network throughput performance by comparing with the existing DRA-CRN algorithm and the simulation results shows that 27% more efficient than existing DSA-CRN algorithm. Furthermore limits the interference at PUs and it should avoid collision.

Cognitive Radio (CR) is novel technology which provides a great solution to genuine lack of range and radio assets in today's situation, intellectual radio offers extraordinary arrangements. Cognitive radio is a pioneering technology which has a capability to improve the effective utilization of valuable natural resources. Cognitive Radio Network (CRN) is a vital wireless communication system that has a great awareness of its atmospheres. The heterogeneous nodes have meets spectrum accessing challenges with varying computing power, sensing range and dynamic spectrum allocation. We have focused on optimum resource allocation and scheduling for primary users (PUs) and secondary users (SUs) to reduce interference to the PUs for improving the performance and throughput. In this article we studied the dissimilar resource allocation based on dynamic approach and proposed an idea of improving priority based scheduling algorithm by comparing with an existing CRN algorithm. The simulation result provides a significant improvement of throughput.

In this paper a method for vehicle license plate identification is implemented and analyzed, on the basis of a novel adaptive image segmentation technique conjunction with character recognition. A novel method for license plate localization based on texture and edge information is proposed. The whole process is divided into two parts: candidate extraction and candidate verification. In the first part, the license plate being extracted from complex environment, several candidate areas instead of one with the max texture information are extracted. In the second part, autocorrelation based binary image and projection algorithm are used to verify the plate candidates. Adaptive median filter is applied to remove the noise from the image. Image processing technique such as edge detection, thresholding, resampling and filtering have been used to locate and isolate the license plate and the characters. The system can recognize single line number plates under widely varying illumination conditions with a success rate of about 80%.