Handling class imbalance problem in software maintainability prediction: an empirical investigation

As the complexity of software systems is increasing; software maintenance is becoming a challenge for software practitioners. The prediction of classes that require high maintainability effort is of utmost necessity to develop cost-effective and high-quality software. In research of software engineering predictive modeling, various software maintainability prediction (SMP) models are evolved to forecast maintainability. To develop a maintainability prediction model, software practitioners may come across situations in which classes or modules requiring high maintainability effort are far less than those requiring low maintainability effort. This condition gives rise to a class imbalance problem (CIP). In this situation, the minority classes’ prediction, i.e., the classes demanding high maintainability effort, is a challenge. Therefore, in this direction, this study investigates three techniques for handling the CIP on ten open-source software to predict software maintainability. This empirical investigation supports the use of resampling with replacement technique (RR) for treating CIP and develop useful models for SMP.     

VISCOELASTIC CHARACTERIZATION OF RICE GEL

Rice flour dispersions with 15–25% solids were subjected to microwave heating for 0–75 s and samples were subjected to oscillatory frequency sweep between 0.01–10 Hz. The initial rapid increase in storage modulus (G¹) with frequency decreased to a plateau at higher frequencies. An increase in G¹ and complex viscosity (η*) with an increase in the time of treatment or concentration of solid indicate the extent of sol-gel transformation. The sensory data on hardness, elasticity and stickiness also followed similar trend. Principal component analysis (PCA) of the sensory results indicate that a minimum treatment time of 45 s is needed to achieve a rice gel with acceptable sensory characteristics. The G' values were modeled (0.936 ≤ r ≤ 0.988, P ≤ .01) by the 4-element spring-dashpot model.     

LINEAR CODES HAVING A SUB-BLOCK STRUCTURE

Linear codes having a sub-block structure are discussed. A substitute method of constructing codes capable of detecting and correcting combinations of error patterns in various sub-blocks is given. Codes where error-correction capabilities are determined in terms of various sub-blocks of the word length are introduced.     

Shop floor control and tool loading policies in flexible manufacturing systems

We develop a classification scheme and taxonomy of operating decisions in flexible manufacturing systems (FMS). The taxonomy is used to identify a promising research area termed General FMSs (GFMS), where very little academic work has been reported to date in the prior literature. A decision framework for the development of tool loading and shop floor control policies in GFMS is also presented, and used to highlight specific future research directions. Strategic justification for developing operating policies for the GFMS classification is also provided.     

OXIDATIVE STRESS AND ANTIOXIDANT SYSTEMS IN TOMATO FRUITS DURING STORAGE

Tomato varieties ARTH‐3 (long shelf‐life; 14–15 days) and Sel‐7 (short shelf‐life; 5–7 days), harvested at color turning stage, were stored in open trays at 10, 25 and 35C and sampled at two day intervals until complete deterioration. Variety ARTH‐3 could be stored at all the temperatures for ten days, while Sel‐7 could tolerate 35C only for four days. However, at 10 and 25C, it could be stored for six days. In both varieties, lipoxygenase (LOX) activity, malondialdehyde (MDA) value and H₂O₂ content increased during storage. Increase in storage temperature further enhanced the activity of LOX, and also increased MDA value and H₂O₂ content. Sel‐7 had higher values for these parameters than ARTH‐3. Activities of enzymes responsible for scavenging reactive oxygen species (ROS) viz., superoxide dismutase, peroxidase, ascorbate peroxidase, glutathione reductase and catalase decreased continuously during storage. With increase in temperature, the activities of these enzymes further decreased significantly in both varieties. Sel‐7 had significantly lower activities of ROS scavenging enzymes than ARTH‐3 throughout the storage period. These results suggest that fruits stored at higher temperature are subjected to severe oxidative damage leading to extensive membrane damage and loss of tissue structure.