Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Vimal K. Shrivastava, Monoj K. Pradhan, Mahesh P. Thakur Pages: 1 - 12 Abstract: Agriculture products and its productivity considerably contribute to the nation’s economy. Rice among other crops is a staple food and grown globally. However, various diseases affect the rice plants and cause a huge loss in both productivity and quality. Hence, rice plant disease detection in their early stage and their classification is an essential step to control its spread over the field by applying suitable techniques for sustainable agriculture. Currently, farmers are dependent on experts for this task which is time taking and prone to human error. Identification of diseases from images of rice plant is one of the important research area and machine learning concept can be applied for accurate, effective and fast detection. Recently, deep learning models specifically convolution neural network (CNN) has shown tremendous success result in image classification task. Motivated by this, we have explored 16 off-the-shelf deep CNN models and demonstrated their performances on classification of image-based diseases from rice plant. Further, the performance of these 16 models were compared with three approaches: transfer learning, fine tuning and scratch learning. Here, we have considered 1216 images collected from the real agriculture field that belongs to seven classes: (a) Rice Blast, (b) Bacterial Leaf Blight, (c) Sheath Blight, (d) Brown Spot, (e) Sheath Rot, (f) False Smut and (d) Healthy Leave. DenseNet121 model obtained superior performance with an average classification accuracy of 98.36%. Hence, the analysis presented in this paper exemplifies that DenseNet121 model can be used as an advisory for early detection and classification of image based diseases from rice plant. PubDate: 2021-09-30 Issue No:Vol. 21, No. 2 (2021)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Roza Dastres, Mohsen Soori Pages: 13 - 25 Abstract: Artificial Neural Networks is a calculation method that builds several processing units based on interconnected connections. The network consists of an arbitrary number of cells or nodes or units or neurons that connect the input set to the output. It is a part of a computer system that mimics how the human brain analyzes and processes data. Self-driving vehicles, character recognition, image compression, stock market prediction, risk analysis systems, drone control, welding quality analysis, computer quality analysis, emergency room testing, oil and gas exploration and a variety of other applications all use artificial neural networks. Predicting consumer behavior, creating and understanding more sophisticated buyer segments, marketing automation, content creation and sales forecasting are some applications of the ANN systems in the marketing. In this paper, a review in recent development and applications of the Artificial Neural Networks is presented in order to move forward the research filed by reviewing and analyzing recent achievements in the published papers. Thus, the developed ANN systems can be presented and new methodologies and applications of the ANN systems can be introduced. PubDate: 2021-09-30 Issue No:Vol. 21, No. 2 (2021)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Leger Bopda Youmissi, Narcisse Talla Tankam, Pascal Vagssa, Hayatou Oumarou, Dina Taïwé Kolyang Pages: 26 - 38 Abstract: This paper proposes an algorithm for identifying regions of interest by inverse contrast enhancement that provides a representation of the different contours (mass, pectoral muscle, breast outer contour and Mcs). The second contribution is the detection of masses and micro-calcifications by manual thresholding and prewitt detector. This algorithm was tested using mammography images of different densities from multiple databases in a health clinic and images taken from the internet (40 images in total). The results are highly accurate, allowing better identification of the different contours, and better detection of breast pathologies (mass and micro-calcification). Finally, the identification of breast contours was performed using inverse contrast enhancement, which is the input of a manual thresholding algorithm specially designed for this purpose. After segmentation by manual thresholding, morphological opening, morphological dilatation and Prewitt contour detection we have a demarcation of the breast masses and micro-calcification. The results obtained show the robustness of the proposed enhancement and manual thresholding method. In order to evaluate the efficiency of our pathology detector, we performed a qualitative evaluation with a rate of 99% for the identification of the different contours and 98% for the detection of breast pathologies. A radiologist from the health clinic evaluated the results and considered them acceptable for the CAD. PubDate: 2021-09-30 Issue No:Vol. 21, No. 2 (2021)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Kamlesh Kumar Shukla, Rama Shanker Pages: 39 - 51 Abstract: In this paper, Inverse Pranav distribution has been suggested and studied. Its descriptive measures based on moments hazard function, distribution of order statistics; stochastic ordering and Renyi entropy have been discussed. Maximum likelihood estimation has been discussed to estimate its parameter. A simulation study is presented. Applications, goodness of fit and comparison with other lifetime distributions have also been discussed. PubDate: 2021-09-30 Issue No:Vol. 21, No. 2 (2021)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Moh’d Fatima Mukhopadhyay, Darma Sanusi Abu Pages: 52 - 63 Abstract: For more than a decade, the face recognition system has been getting significant consideration in the field of biometric technology due to its frequent application in law enforcement, security systems, and different human-computer interactions. It is the biometric system for verifying and identifying humans or objects in a controlled environment. The challenging issues with face recognition systems are getting the right approaches for modeling face images. Face recognition methods are categorized into geometric or photometric approaches. The geometrics are those approaches that look for the characteristics of the face image. For example, the shapes and positions of the face's facial features. Whereas photometric methods are mathematical approaches that modify computer reference face images into values, by matching their shapes and positions with those of training images to reduce alterations for the purpose of face identification. In this paper, we investigate and discuss the most recent used machine learning and deep learning approaches and how these different approaches deal with those issues affecting the system in different existing literature works. The paper also highlights the background and origin of the face recognition system. Furthermore, we outline some of the application areas of face recognition systems. PubDate: 2021-09-30 Issue No:Vol. 21, No. 2 (2021)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Neeta Singh Pages: 64 - 66 Abstract: We apply the Goebel and Kirk fixed point theorem for the existence of solutions of operator equations involving asymptotically nonexpansive mappings in uniformly convex Banach spaces. PubDate: 2021-09-30 Issue No:Vol. 21, No. 2 (2021)
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Authors:Mahek Jain, Kushagra Sirothia, Shanta Rangaswamy Pages: 67 - 78 Abstract: Sign language is one of the more experienced and regular types of correspondence language, however, since most are unfamiliar with sign communication and interpreters are undeniably challenging to stop by we have concocted a constant technique that uses neural organization for fingerspelling based American gesture-based communication. It is a profoundly visual-spatial, semantically complete language. It is typically the first language and the main means of communication for deaf individuals. Sign Language is communication that relies on hand signs, gestures, and expressions, generally used in the deaf community. But people outside of the deaf community find it hard or almost impossible to speak with deaf people. They need to rely on an interpreter which may both be expensive and hurt the privacy of the people trying to communicate. This paper proposes a method that makes use of a Convolutional Neural Network to identify and recognize hand signs which are captured in real-time through a webcam. Since there is no universal sign language. The model was specifically trained on American Sign Language alphabets. PubDate: 2021-09-30 Issue No:Vol. 21, No. 2 (2021)
Subscription journal
[11 journals]
