| 1. |
|
|
| 2. |
- Kabir, Md Alamgir, et al.
(författare)
-
Cross-Version Software Defect Prediction Considering Concept Drift and Chronological Splitting
- 2023
-
Ingår i: Symmetry. - : Multidisciplinary Digital Publishing Institute (MDPI). - 2073-8994. ; 15:10
-
Tidskriftsartikel (refereegranskat)abstract
- Concept drift (CD) refers to a phenomenon where the data distribution within datasets changes over time, and this can have adverse effects on the performance of prediction models in software engineering (SE), including those used for tasks like cost estimation and defect prediction. Detecting CD in SE datasets is difficult, but important, because it identifies the need for retraining prediction models and in turn improves their performance. If the concept drift is caused by symmetric changes in the data distribution, the model adaptation process might need to account for this symmetry to maintain accurate predictions. This paper explores the impact of CD within the context of cross-version defect prediction (CVDP), aiming to enhance the reliability of prediction performance and to make the data more symmetric. A concept drift detection (CDD) approach is further proposed to identify data distributions that change over software versions. The proposed CDD framework consists of three stages: (i) data pre-processing for CD detection; (ii) notification of CD by triggering one of the three flags (i.e., CD, warning, and control); and (iii) providing guidance on when to update an existing model. Several experiments on 30 versions of seven software projects reveal the value of the proposed CDD. Some of the key findings of the proposed work include: (i) An exponential increase in the error-rate across different software versions is associated with CD. (ii) A moving-window approach to train defect prediction models on chronologically ordered defect data results in better CD detection than using all historical data with a large effect size (Formula presented.).
|
|
| 3. |
- Ahsan, Amimul, et al.
(författare)
-
Modeling of a new triangular shape solar distillation system integrated with solar PV panel and DC water heater
- 2023
-
Ingår i: Case Studies in Thermal Engineering. - : Elsevier. - 2214-157X. ; 44
-
Tidskriftsartikel (refereegranskat)abstract
- A new triangular shape solar distillation system is fabricated using locally available materials by integrating with solar PV panel connected to DC water heater. It is designed for the first time to distill saline water or seawater using solar heat energy directly (to heat sample water) and indirectly (through water heater to heat sample water). The trough is made of Plexiglass and painted in black color which is placed inside the triangular frame made of UPVC pipe. The performance of the still is experimented in field. The diurnal variations of solar heat energy, distillate output, various temperatures and relative humidity are observed. A few linear proportional relationships are obtained between the sunlight heat energy and the productivity, between the ambient temperature and the productivity, and between the productivity and water-cover temperature difference. The production rate of the still is higher than the conventional one. An improved simulation model is proposed to estimate the productivity of the still as some previous simulation models cannot estimate the productivity of the solar still precisely. A few new factors are incorporated in the new model as these factors affect the distillate output of the solar still.
|
|
| 4. |
|
|
| 5. |
- Haq, M. U., et al.
(författare)
-
Capsule Network with Its Limitation, Modification, and Applications—A Survey
- 2023
-
Ingår i: Machine Learning and Knowledge Extraction. - : Multidisciplinary Digital Publishing Institute (MDPI). - 2504-4990. ; 5:3, s. 891-921
-
Tidskriftsartikel (refereegranskat)abstract
- Numerous advancements in various fields, including pattern recognition and image classification, have been made thanks to modern computer vision and machine learning methods. The capsule network is one of the advanced machine learning algorithms that encodes features based on their hierarchical relationships. Basically, a capsule network is a type of neural network that performs inverse graphics to represent the object in different parts and view the existing relationship between these parts, unlike CNNs, which lose most of the evidence related to spatial location and requires lots of training data. So, we present a comparative review of various capsule network architectures used in various applications. The paper’s main contribution is that it summarizes and explains the significant current published capsule network architectures with their advantages, limitations, modifications, and applications.
|
|
| 6. |
- Jaffari, G. Hassnain, et al.
(författare)
-
Extrinsic contributions to the dielectric response in sintered BaTiO3 nanostructures in paraelectric and ferroelectric regimes
- 2017
-
Ingår i: Physica. B, Condensed matter. - : ELSEVIER SCIENCE BV. - 0921-4526 .- 1873-2135. ; 525, s. 70-77
-
Tidskriftsartikel (refereegranskat)abstract
- Post sintering studies of BaTiO3 (BTO) nanoparticles are presented in detail. Bulk nanostructures were prepared via three different compaction processes, namely, uniaxial cold pressing (UCP), Cold Isostatic Pressing (CIP) and Spark Plasma Sintering (SPS). Effect of compaction technique on microstructures have been investigated and correlated with electrical response for each sample. In addition to the transport properties, temperature and frequency dependent dielectric response of variously sintered samples and bulk counterpart was recorded. Several aspects have been identified that are essential to be taken into account in order to completely understand physical processes. Drastically distinct features were observed in paraelectric (PE) regime well above ferroelectric (FE)-PE transition temperature. These features include intra grain conduction with a reduction in the magnitude of PE to FE peak dielectric constant magnitude. Role of strain, grain boundary conduction associated with observation of Maxwell Wagner relaxation and hopping conduction in dielectric and ferroelectric response have been observed and discussed. Densification with presence of oxygen vacancies, significantly enhances conductivity associated with the hopping of the carriers, in turn deteriorated ferroelectric response.
|
|
| 7. |
- Atiq, Ferdows, et al.
(författare)
-
Endothelial Dysfunction, Atherosclerosis, and Increase of von Willebrand Factor and Factor VIII : A Randomized Controlled Trial in Swine
- 2021
-
Ingår i: Thrombosis and Haemostasis. - Stuttgart : Georg Thieme Verlag. - 0340-6245 .- 2567-689X. ; 121:5, s. 676-686
-
Tidskriftsartikel (refereegranskat)abstract
- All rights reserved.It is well known that high von Willebrand factor (VWF) and factor VIII (FVIII) levels are associated with an increased risk of cardiovascular disease. It is still debated whether VWF and FVIII are biomarkers of endothelial dysfunction and atherosclerosis or whether they have a direct causative role. Therefore, we aimed to unravel the pathophysiological pathways of increased VWF and FVIII levels associated with cardiovascular risk factors. First, we performed a randomized controlled trial in 34 Göttingen miniswine. Diabetes mellitus (DM) was induced with streptozotocin and hypercholesterolemia (HC) via a high-fat diet in 18 swine (DM + HC), while 16 healthy swine served as controls. After 5 months of follow-up, FVIII activity (FVIII:C) was significantly higher in DM + HC swine (5.85 IU/mL [5.00-6.81]) compared with controls (4.57 [3.76-5.40], p = 0.010), whereas VWF antigen (VWF:Ag) was similar (respectively 0.34 IU/mL [0.28-0.39] vs. 0.34 [0.31-0.38], p = 0.644). DM + HC swine had no endothelial dysfunction or atherosclerosis during this short-term follow-up. Subsequently, we performed a long-term (15 months) longitudinal cohort study in 10 Landrace-Yorkshire swine, in five of which HC and in five combined DM + HC were induced. VWF:Ag was higher at 15 months compared with 9 months in HC (0.37 [0.32-0.42] vs. 0.27 [0.23-0.40], p = 0.042) and DM + HC (0.33 [0.32-0.37] vs. 0.25 [0.24-0.33], p = 0.042). Both long-term groups had endothelial dysfunction compared with controls and atherosclerosis after 15 months. In conclusion, short-term hyperglycemia and dyslipidemia increase FVIII, independent of VWF. Long-term DM and HC increase VWF via endothelial dysfunction and atherosclerosis. Therefore, VWF seems to be a biomarker for advanced cardiovascular disease. © 2021 Georg Thieme Verlag.
|
|
| 8. |
- Das, Sushil K., et al.
(författare)
-
Calibration, validation and uncertainty analysis of a SWAT water quality model
- 2024
-
Ingår i: Applied water science. - : Springer Nature. - 2190-5487 .- 2190-5495. ; 14:4
-
Tidskriftsartikel (refereegranskat)abstract
- Sediment and nutrient pollution in water bodies is threatening human health and the ecosystem, due to rapid land use changes and improper agricultural practices. The impact of the nonpoint source pollution needs to be evaluated for the sustainable use of water resources. An ideal tool like the soil and water assessment tool (SWAT) can assess the impact of pollutant loads on the drainage area, which could be beneficial for developing a water quality management model. This study aims to evaluate the SWAT model’s multi-objective and multivariable calibration, validation, and uncertainty analysis at three different sites of the Yarra River drainage area in Victoria, Australia. The drainage area is split into 51 subdrainage areas in the SWAT model. The model is calibrated and validated for streamflow from 1990 to 2008 and sediment and nutrients from 1998 to 2008. The results show that most of the monthly and annual calibration and validation for streamflow, nutrients, and sediment at the three selected sites are found with Nash–Sutcliffe efficiency values greater than 0.50. Furthermore, the uncertainty analysis of the model shows satisfactory results where the p-factor value is reliable by considering 95% prediction uncertainty and the d-factor value is close to zero. The model's results indicate that the model performs well in the river's watershed, which helps construct a water quality management model. Finally, the model application in the cost-effective management of water quality might reduce pollution in water bodies due to land use and agricultural activities, which would be beneficial to water management managers.
|
|
| 9. |
- Rehman, Atiq Ur, et al.
(författare)
-
Salp Swarm Algorithm for Drift Compensation in E-nose
- 2023
-
Ingår i: 2023 15th International Conference on Advanced Computational Intelligence, ICACI 2023. - : Institute of Electrical and Electronics Engineers Inc.. - 9798350321456
-
Konferensbidrag (refereegranskat)abstract
- E-nose technology relies on the proper functioning of sensors to identify and discriminate between different chemicals and odors. The long-term reliability of e-nose technology is hindered by the phenomenon of sensor drift. The effect of sensor drift is seen as a random and unpredictable shift in the data domain. This random shift in data deteriorates the performance of machine learning algorithms used in e-nose technology. Swarm intelligence based optimization has been successfully applied in different domains to deal with NP-hard optimization problems. In this paper, a swarm intelligence-based metaheuristic is proposed to deal with the sensors drift issue in e-nose technology. The proposed framework is validated using a benchmark dataset of sensor drift, and a significant improvement is observed in terms of the classification accuracy of different industrial gases. The proposed framework has the following benefits over conventional approaches: (i) there is no need for sensor re-calibration; (ii) there is no need for sensor replacement; (iii) there is no need for target domain data; and (iv) there is no need for domain transformation. Instead, the proposed work relies only on the source domain data and optimizes the feature space to deal with sensor drift. This makes the proposed framework more suitable for real applications of E-nose technology.
|
|
