Software effort estimation accuracy prediction of machine learning techniques: A systematic performance evaluation

Software effort estimation accuracy is a key factor in effective planning, controlling, and delivering a successful software project within budget and schedule. The overestimation and underestimation both are the key challenges for future software development, henceforth there is a continuous need for accuracy in software effort estimation. The researchers and practitioners are striving to identify which machine learning estimation technique gives more accurate results based on evaluation measures, datasets and other relevant attributes. The authors of related research are generally not aware of previously published results of machine learning effort estimation techniques. The main aim of this study is to assist the researchers to know which machine learning technique yields the promising effort estimation accuracy prediction in software development. In this article, the performance of the machine learning ensemble and solo techniques are investigated on publicly and non-publicly domain datasets based on the two most commonly used accuracy evaluation metrics. We used the systematic literature review methodology proposed by Kitchenham and Charters. This includes searching for the most relevant papers, applying quality assessment (QA) criteria, extracting data, and drawing results. We have evaluated a state-of-the-art accuracy performance of 35 selected studies (17 ensemble, 18 solo) using mean magnitude of relative error and PRED (25) as a set of reliable accuracy metrics for performance evaluation of accuracy among two techniques to report the research questions stated in this study. We found that machine learning techniques are the most frequently implemented in the construction of ensemble effort estimation (EEE) techniques. The results of this study revealed that the EEE techniques usually yield a promising estimation accuracy than the solo techniques.     

A cooperative mobile throwbox-based routing protocol for social-aware delay tolerant networks

Wireless Networks - In delay tolerant networks (DTNs), nodes have intermittent connectivity patterns due to various factors such as mobility, sparse network topology, and unpredictable movement...     

Dystrophin isoforms DP71 and DP427 have distinct roles in myogenic cells

The efficacy of MHC class I-derived peptides to induce tolerance was tested in a cardiac transplantation model. Two 25-mer peptides from the polymorphic region of the DA class I molecule (RT1.Aa) were synthesized by F-moc chemistry and injected intrathymically or intraperitoneally into LEW (RT1.1) responder animals. Intrathymic treatment of the recipient animals with peptide 1 (residues 56-80) accompanied by intraperitoneal treatment with peptide 4 (residues 96-120) led to indefinite survival of allogeneic DA cardiac allografts (n = 7; > 100 days). The tolerogenicity of both peptides differed according to the site of inoculation, as donor-specific tolerance was only observed after administration of peptide 1 into the thymus and injection of peptide 2 into the abdominal cavity of LEW recipients, but not vice versa. Donor-specific tolerance was confirmed in vivo by grafting of full-thickness skin and in vitro by appropriate proliferation and cytotoxicity assays using donor and third-party rats. Donor-specific tolerance was associated with up-regulation of interleukin-4, transforming growth factor beta, and interleukin-10 gene expression within cardiac allografts, thus suggesting intrathymic clonal deletion and external suppression with expansion of T-helper 2-type lymphocytes as the underlying mechanisms of tolerance induction.     

Thermal properties and formation mechanism of h‐BN nanoneedles synthesized via carbothermic reduction reaction

Hexagonal boron nitride (BN) was synthesized through the carbothermic reduction reaction (CRR) of boric acid using lactose as a carbon source under the nitrogen atmosphere at 1500^°C for 3 hours. The boron/carbon (B/C) molar ratio was controlled during the CRR, and the produced samples were investigated by XRD diffraction pattern, FTIR analysis, and Raman spectra. Boron carbide (B₄C) was formed in samples that have a higher carbon content, in addition to boron nitride. While boron nitride pure sample was produced from lower carbon content samples. Formation of B₄C was found to depend on the B/C molar ratio. The morphology of the produced powder was also investigated by SEM and TEM, which revealed that the samples consist of nanoneedles of BN and hexagonal particles of B₄C. The vapor‐solid (VS) reaction mechanism was processed greatly with increasing boron amount, producing boron nitride nanoneedles, which compete with the liquid‐solid (LS) reaction mechanism. The physicochemical properties of the produced samples were studied by DTA, UV, PL, and AC impedance measurements, and revealed that the samples are promising to many proper applications.     

Physical Properties of Starches Isolated from Yellow Corn,Sorghum, Sordan and Pearl Millet

Water-binding capacity, swelling power and solubility, amylograph viscosity, relative, specific, reduced and intrinsic viscosities of starches isolated from yellow corn, sorghum (Giza 3 and 114), Sordan 79 and pearl millet were investigated. Yellow corn and pearl millet starches were characterized by their higher water binding capacities. Pearl millet starch showed higher initial transition temperatures (about 91°C) to be gelatinized than the other starch which gelatinized at initial transition temperature ranging from 66 to 70°C. Differences in maximum viscosities expressed as Brabender units were also ranging from 780 to 185 BU. On the other hand, slight differences in intrinsic viscosity were observed.     

Reactions with 5-Substituted 2-Thiazolidinone-4-thiones. Part IV

5-Arylidene-2-thiazolidinone-4-thiones 1 undergo Michael type reactions with Ω-nitrostyrene, α,β-unsaturated ketones and N-arylmaleimides to give the corresponding 7-aryl-tetrahydro-7H-thiopyrano[2,3-d]thiazole-2-one derivatives 3 and 4 . Arylmagnesium bromides add to the lateral double bond of 5-arylidene-3-phenyl-2-thiazolidinone-4-thiones 5 to yield products 6 . With phenyl-hydrazine at room temperature, 1 or 5 yield the corresponding aldehyde phenylhydrazones and 4-phenyl-hydrazono-2-thiazolidinone or its 3-phenyl derivative. The thione group in 5-diaryl-methyl-2-thiazolidinone-4-thiones condenses with phenylhydrazine to yield 5-diarylmethyl-4-phenyl-hydrazono-2-thiazolidinones 9 .     

Unsaturated-sulfur-rich MoS<Subscript>2</Subscript> nanosheets decorated on free-standing SWNT film: Synthesis,characterization and electrocatalytic application

Herein, we report a bottom-up solvothermal route to synthesize a flexible, highly efficient MoS₂@SWNT electrocatalyst for hydrogen evolution reactions (HER). Characterization revealed that branch-like MoS₂ nanosheets containing sulfurrich sites were in situ uniformly dispersed on free-standing single-walled carbon nanotube (SWNT) film, which could expose more unsaturated sulfur atoms, allowing excellent electrical contact with active sites. The flexible catalyst exhibited excellent HER performance with a low overpotential (~150 mV at 10 mA/cm²) and small Tafel slope (41 mV/dec). To further explain the improved performance, the local electronic structure was investigated by X-ray absorption near-edge structure (XANES) analysis, proving the presence of unsaturated sulfur atoms and strong electronic coupling between MoS₂ and SWNT. This study provides an in-situ synthetic route to create new multifunctional flexible hybridized catalysts and useful insights into the relationships among the catalyst microstructure, electronic structure, and properties.

Open image in new window

     

Multiproduct multiple-buyer single-vendor supply chain problem with stochastic demand, variable lead-time, and multi-chance constraint

In this paper, a multi-product multi-chance constraint joint single-vendor multi-buyers inventory problem is considered in which the demand follows a uniform distribution, the lead-time is assumed to vary linearly with respect to the lot size, and the shortage in combination of backorder and lost-sale is assumed. Furthermore, the orders are placed in multiple of packets, there is a limited space available for the vendor, there are chance constraints on the vendor service rate to supply the products, and there is a limited budget for each buyer to purchase the products. While the elements of the buyers’ cost function are holding, shortage, order and transportation costs, the set up and holding costs are assumed for the vendor. The goal is to determine the re-order point and the order quantity of each product for each buyer such that the chain total cost is minimized. We show the model of this problem to be a mixed integer nonlinear programming type and in order to solve it a particle swarm optimization (PSO) approach is used. To justify the results of the proposed PSO algorithm, a genetic algorithm (GA) is applied as well to solve the problem. Then, the quality of the results and the CPU times of reaching the solution are compared through three numerical examples that are given to demonstrate the applicability of the proposed methodology in real world inventory control problems. The comparison results show the PSO approach has better performances than the GA method.