Automated Tool for Extraction of Software Fault Data

Improving the software product quality before releasing by periodic tests is one of the most expensive activities in software projects. Due to limited resources to modules test in software projects, it is important to identify fault-prone modules and use the test sources for fault prediction in these modules. Software fault predictors based on machine learning algorithms, are effective tools for identifying fault-prone modules. Extensive studies are being done in this field to find the connection between features of software modules, and their fault-prone. Some of features in predictive algorithms are ineffective and reduce the accuracy of prediction process. So, feature selection methods to increase performance of prediction models in fault-prone modules are widely used. In this study, we proposed a feature selection method for effective selection of features, by using combination of filter feature selection methods. In the proposed filter method, the combination of several filter feature selection methods presented as fused weighed filter method. Then, the proposed method caused convergence rate of feature selection as well as the accuracy improvement. The obtained results on NASA and PROMISE with ten datasets, indicates the effectiveness of proposed method in improvement of accuracy and convergence of software fault prediction.

Download Full-text

The software fault prediction model based on the AltaRica language

2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) ◽

10.1109/itnec.2019.8729235 ◽

2019 ◽

Author(s):

Jingyu Song ◽

Bo Chen ◽

Xueliang Li ◽

Yi Yang ◽

Chang Liu ◽

...

Keyword(s):

Prediction Model ◽

Fault Prediction ◽

Software Fault Prediction ◽

Model Based ◽

Software Fault

Download Full-text

Deep Learning Based Automated tool for cancer diagnosis from bone histopathology images

2021 International Conference on Intelligent Technologies (CONIT) ◽

10.1109/conit51480.2021.9498367 ◽

2021 ◽

Author(s):

B.S Vandana ◽

Sathyavathi R. Alva

Keyword(s):

Deep Learning ◽

Cancer Diagnosis ◽

Histopathology Images ◽

Automated Tool

Download Full-text

Software Fault Prediction Using LSSVM with Different Kernel Functions

Arabian Journal for Science and Engineering ◽

10.1007/s13369-021-05643-2 ◽

2021 ◽

Author(s):

Vinod Kumar Kulamala ◽

Lov Kumar ◽

Durga Prasad Mohapatra

Keyword(s):

Kernel Functions ◽

Fault Prediction ◽

Software Fault Prediction ◽

Software Fault

Download Full-text

Design and Calibration of Robot Base Force/Torque Sensors and Their Application to Non-Collocated Admittance Control for Automated Tool Changing

Sensors ◽

10.3390/s21092895 ◽

2021 ◽

Vol 21 (9) ◽

pp. 2895

Author(s):

Hubert Gattringer ◽

Andreas Müller ◽

Philip Hoermandinger

Keyword(s):

Steel Plate ◽

Robotic Manipulators ◽

Indirect Measurement ◽

Local Deformation ◽

Contact Forces ◽

The Novel ◽

Admittance Control ◽

Load Cells ◽

Series Elastic Actuators ◽

Automated Tool

Robotic manipulators physically interacting with their environment must be able to measure contact forces/torques. The standard approach to this end is attaching force/torque sensors directly at the end-effector (EE). This provides accurate measurements, but at a significant cost. Indirect measurement of the EE-loads by means of torque sensors at the actuated joint of a robot is an alternative, in particular for series-elastic actuators, but requires dedicated robot designs and significantly increases costs. In this paper, two alternative sensor concept for indirect measurement of EE-loads are presented. Both sensors are located at the robot base. The first sensor design involves three load cells on which the robot is mounted. The second concept consists of a steel plate with four spokes, at which it is suspended. At each spoke, strain gauges are attached to measure the local deformation, which is related to the load at the sensor plate (resembling the main principle of a force/torque sensor). Inferring the EE-load from the so determined base wrench necessitates a dynamic model of the robot, which accounts for the static as well as dynamic loads. A prototype implementation of both concepts is reported. Special attention is given to the model-based calibration, which is crucial for these indirect measurement concepts. Experimental results are shown when the novel sensors are employed for a tool changing task, which to some extend resembles the well-known peg-in-the-hole problem.

Download Full-text