Volume 10 | Issue 12 |

 Abstract

Two biocontrol agent viz., Trichoderma viride and Trichoderma harzianum were evaluated to test the antagonism against Fusarium oxysporum under in vitro conditions. All the two biocontrol agents have the potential of parasitizing the growth of Fusarium oxysporum in vitro. For control of seed-borne infection of F.oxysporum the best results were obtained from biological agent Trichoderma viride. Maximum control of F.oxysporum incidence (71.15%) and infected seedling (85.0%) was obtained when T.viride was applied as 80ml concentration which was followed by 20ml concentration. Control of pathogen incidence (42.3%), infected seedlings (60%) and seed germination (76.25%) was low in 120ml concentration. In F.oxysporum infected seeds, the maximum control for pathogen incidence 56% to 80% and infected seedling 47.61% to 92.86% was observed in 20ml-240ml dilutions of T.harzianum.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Bio-efficacy, Fusarium oxysporum, lentil, Trichoderma, Wilt

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Keywords: plant diseases and pests; classification; detection; forecasting; precision farming; machine learning; smart farming.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The technology of Internet of Things (IoT) and cloud has exposed devices to vulnerabilities. As they are distributed, the different devices communicate real time information to open, private or hybrid clouds, with the possibility of collecting, storing, and analyzing in new forms. In the healthcare context, the increased deployment of IoT devices makes patient information a subject to malicious attacks depending on the security and privacy of the IoT devices. While several researchers have explored such security challenges and open problems in IoT, there is an unfortunate lack of a systematic study of the security challenges in the IoT for e-Health on clouds. In this paper, we aim at bridging this gap by conducting a thorough analysis of IoT security Vulnerability. We present then security challenges in the cloud for e-Health domain and recent proposed solutions. We also provide a proposition of an IoT system in the cloud.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

IoT; CLOUD; EHEALTH; SECURITY.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

As we go from the original text to the translated text, we can understand that the translation undergoes a subjective interpretation by the translator. This leads to a(n) (in)voluntary manipulation of certain aspects of a literary work. This article aims to study the manipulation of self-image in the translation of Amrita Pritam's Rasidi ticket.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Identity, translation, manipulation

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Face recognition, OpenCV, Deep Learning, VGG

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project presents the prediction of traffic-violations using machine learning, more specifically, when most likely a traffic- violation may happen. Also, what are the contributing factors that may cause more damages (e.g., personal injury, property damage, etc.) are discussed in this work. The national database for trafficviolation was considered for the mining and analyzed results indicated that a few specific times are probable for traffic-violations. Moreover, most accidents happened on specific days and times. The findings of this work could help prevent some trafficviolations or reduce the chance of occurrence. These results can be used to increase cautions and traffic-safety tips. This work presents an in-depth analysis of road and traffic violations pattern using Data Analytics methods, aimed at improving road and traffic management, government planning and decision making. The study identified the road and traffic current management practice as basis of the design development and implementation of the road and traffic management system. The application managed all the road and traffic violation that will produce recorded set for analysis, which carried out from over of five years. Through data cleansing a total of twenty thousand six hundred forty record set was derived. It is important to find use of this record set, build analysis models, and use interactive tools to produce predictive data, understand the relevance, trends, and driving behaviors from the road and traffic violations data in terms of the following predictors: gender of the violator, vehicle owner address, location of violation, month and time the violation was committed and traffic enforcer who issued the citation. The study was able to establish a data analysis model by using a powerful classification and random forest which was executed using an open source application named PyCharm. Finally, the developed application was evaluated by Python.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Machine Learning, Traffic Violation,Data Analysis

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Video in the national defense, education, monitoring, entertainment and other fields have been widely used, so data security on the internet cannot be ignored. Video encryption protects the original video information and improves the security of video information. Researchers have done a lot of research on video encryption and put forward a lot of video encryption methods. Video encryption methods are mainly divided into complete encryption and partial encryption algorithm. In order to improve the generalization performance of video encryption and reduce the amount of data in video encryption, this paper proposes a video encryption on regions of interest (ROI) method based on Faster R-CNN by combining machine learning with information security. The method trains a Faster R-CNN model using the ROI dataset firstly, and then uses the model to extract ROI in the video. Different encryption algorithms are used to encrypt ROI and non-ROI in the video respectively. To overcome the shortcomings of encryption algorithms that can only be used for a specific coded video, a special video encryption method is proposed to encrypt the video with different video coding structure and has better generalization performance. Compared with the encryption method in the video coding process, this method considers the content information of the video fully and has better performance. It can be concluded through experiments that the encryption method in this paper has the characteristics of higher security and less calculation.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Video Encryption, Image Processing, Deep Learning

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Identification of faults via computer-based techniques is a growing trend in all fields these days. Two main characteristics of Bone Fracture Detection are fast identification and high precision which is described by highly sensitive device by incorporating advanced techniques and effective resource usage. The effect of undue external stress above the limits of what the bone may tolerate is a crack in a bone or bone fracture. Canny Edge detection is an image processing technique that identifies bone fracture by utilizing automatic fracture detection efficiently and overcomes the question of noise reduction. There are many methodologies accessible in today's world for edge detection, such as Sobel, Canny, Log, Prewitt, and Robert. These processes, though, are hampered by crucial limitations such as a lack of capacity to conduct multi resolution research, culminating in the failure to identify small information during the analysis. The other major drawback of the techniques is that they operate well with high resolution and high-quality pictures, but because of their intrinsic lack of ability to differentiate between edges and noise elements, they do not work well with blurry images. The approach being suggested uses the CNN algorithm to solve these issues. The findings of the simulations carried out suggest that the approach proposed is a far more effective system for conducting edge detection on aggregate scales. The suggested system has also shown to be sufficiently resilient to retrieve the required details and do the necessary analysis on key portions of the images and manage noise in a much better way than the edge detectors currently usable.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Machine Learning, Image processing using X-ray images, Canny Edge Detection, SVM algorithm.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Machine learning is an important decision support tool for crop yield prediction, including supporting decisions on what crops to grow and what to do during the growing season of the crops. Several machine learning algorithms have been applied to support crop yield prediction research. In this work, we performed a Systematic Literature Review (SLR) to extract and synthesize the algorithms and features that have been used in crop yield prediction studies. Based on our search criteria, we retrieved relevant studies from six electronic databases, of which we have selected five studies for further analysis using inclusion and exclusion criteria. We investigated these selected studies carefully, analyzed the methods and features used, and provided suggestions for further research. According to our analysis, the most used features are temperature, rainfall, and soil type, and the most applied algorithm is machine learning in these models. After this observation based on the analysis of machine learning-based algorithm, to recognize machine learning, we conducted additional researches in databases on crop yields. To find studies that used machine learning, we also searched crop yield datasets. This further study reveals that the Decision Tree Method is the most frequently employed machine learning algorithm in these studies.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Machine learning, Crop Yield Prediction, Decision tree algorithm

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Handwriting is one of the distinguishing characteristics that distinguishes a person's identity, and it is a method of identifying the writer's physical characteristics. It displays a person's genuine personality, including their actions, emotional outbursts, sense of self, rage, creativity, honesty, phobias, and a range of other traits. In this paper a multi-layered approach is proposed for analyzing personality traits by identifying the type of handwriting and classify the personality of the individual human being using deep learning models such as Resnet 34 and YOLO v5 model.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Handwriting Analysis, Personality Classification, Feature, Deep Learning.

  License

Creative Commons Attribution 4.0 and The Open Definition