75 research outputs found
Towards Accurate Duplicate Bug Retrieval Using Deep Learning Techniques
No full textDuplicate Bug Detection is the problem of identifying whether a newly reported bug is a duplicate of an existing bug in the system and retrieving the original or similar bugs from the past. This is required to avoid costly rediscovery and redundant work. In typical software projects, the number of duplicate bugs reported may run into the order of thousands, making it expensive in terms of cost and time for manual intervention. This makes the problem of duplicate or similar bug detection an important one in Software Engineering domain. However, an automated solution for the same is not quite accurate yet in practice, in spite of many reported approaches using various machine learning techniques. In this work, we propose a retrieval and classification model using Siamese Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) for accurate detection and retrieval of duplicate and similar bugs. We report an accuracy close to 90% and recall rate close to 80%, which makes possible the practical use of such a system. We describe our model in detail along with related discussions from the Deep Learning domain. By presenting the detailed experimental results, we illustrate the effectiveness of the model in practical systems, including for repositories for which supervised training data is not available.</p
Association of Defect Log Suitability for Machine Learning with Performance: An Experience Report
No full textMining Text in Incident Repositories: Experiences and Perspectives on Adopting Machine Learning Solutions in Practice
No full text
Deep Learning for UAV Detection and Classification Via Radio Frequency Signal Analysis
No full textUnmanned Aerial Vehicles (UAVs) are advertised as great tool that benefits society and humanity. However, UAVs also pose significant security threats ranging from privacy invasions, to interfering with commercial aircraft landing and takeoff, to accidently crashing into vehicles or people, to military or terrorist attacks. Consequently, there is a pressing need to detect and identify UAVs to mitigate such potential risks. While image-based methods are crucial for UAV detection, radio frequency (RF) emissions offer additional valuable insights. Analyzing RF signals, such as those used in UAV-ground station communications, can provide information about UAV types based on distinct frequency usage or communication patterns. This work introduces a deep-learning-based approach for recognizing and identifying UAVs using their RF emissions. Captured RF signals are transformed into spectrograms, which are subsequently analyzed using deep neural networks. Existing methods achieve low identification accuracy, for instance the ResNet-50V2 model achieves an accuracy of 85.39% even in controlled, laboratory, noise-free conditions. Moreover, in outdoor environments at distances of 50m and 100m, the accuracy drops to 68.90% and 56.88%, respectively. To improve classification accuracy in outdoors, a CNN model was developed, yielding an accuracy of 78.12%. Leveraging the ResNet 50 V2 architecture, remarkable accuracy of 95.08% was attained in binary classification tasks involving a dataset comprising 195 mixed UAV images and 290 non-mix UAV images
Klebsiella Species associated with bovine mastitis in Newfoundland
No full textKlebsiella spp. is a common cause of bovine mastitis, but information regarding its molecular epidemiology is lacking from many parts of the world. On using mass spectrometry and partial sequencing of the rpoB gene, it was found that over a one year study, K. variicola and Enterobacter cloacae were misidentified as K. pneumoniae in a small number of clinical mastitis (CM) cases from Newfoundland. Results suggest that the currently used standard biochemical/phenotypic tests lack the sensitivity required to accurately discriminate among the three mentioned Gram negative bacteria. In addition, a single strain of K. variicola was associated with CM from one farm in the study as demonstrated by Random Amplified Polymorphic DNA (RAPD) PCR. To the best of our knowledge, K. variicola, which is normally found in the environment, has not been isolated previously from milk obtained from cows with CM. Therefore, it is possible that K. variicola was not detected in milk samples in the past due to the inability of standard tests to discriminate it from other Klebsiella species
Comparative Performance Study and Analysis on Different Edge based Image Segmentation Techniques of Thermal Images
No full textIn this work, authors have been tried to analyse the edge-based approach for thermal image segmentation. Here, author?s have used different thermal images for the edge based analysis of image segmentation. Author?s have given studies regarding different edge operators like Prewitt, Sobel, LoG, and Canny edge detection operators for segmentation purposes and analyze their performance. This paper compares each of these operators by the manner of checking Peak signal to Noise Ratio (PSNR) and Mean Squared Error (MSE) of resultant image. It evaluates the performance of each algorithm using image quality analysis. This paper presents a comparative analysis of different edge based thermal image segmentation techniques
ADAM SMITH'S OPTIMISTIC TELEOLOGICAL VIEW OF HISTORY
No full textAdam Smith's four-stage theory provides the framework for his writings on history. The fourth stage is the commercial epoch; the culmination of history in this stage is a key component in the conventional interpretation of Adam Smith as a prophet of commercialism. In two historical case studies Smith shows the capacity of commercial society to regenerate itself. This potent capacity suggests that commercial society is inevitable. At a certain point in time it also overcomes the major obstacles to its permanence. Smith's philosophy of history anticipates the end of history views of Kant and Hegel.Political Economy,
- …
