Software Performance Research Articles

Structuring Semantic‐Aware Relations Between Bugs and Patches for Accurate Patch Evaluation

ABSTRACTPatches can help fix security vulnerabilities and optimize software performance, thereby enhancing the quality and security of the software. Unfortunately, patches generated by automated program repair tools are not always correct, as they may introduce new bugs or fail to fully rectify the original issue. Various methods for evaluating patch correctness have been proposed. However, most methods face the challenge of capturing long‐distance dependencies in patch correctness evaluation, which leads to a decline in the predictive performance of the models. To address the challenge, this paper presents a method named Qamhaen to evaluate the correctness of patches generated by APR. Specifically, text embedding of bugs and patches component address the challenge of long‐distance dependencies across functions in patch correctness evaluation by using bug reports and patch descriptions as inputs instead of code snippets. BERT is employed for pretraining to capture these dependencies, followed by an additional multihead self‐attention mechanism for further feature extraction. Similarity evaluator component devises a similarity calculation to assess the effectiveness of patch descriptions in resolving issues outlined in bug reports. Comprehensive experiments are conducted on a dataset containing 9135 patches and a patch correctness assessment metric, and extensive experiments demonstrate that Qamhaen outperforms baseline methods in terms of overall performance across AUC, F1, +Recall, ‐Recall, and Precision. For example, compared to the baseline, Qamhaen achieves an F1 of 0.691, representing improvements of 24.2%, 22.1%, and 6.3% over the baseline methods, respectively.

Evaluation of hypotension prediction index software in patients undergoing orthotopic liver transplantation: retrospective observational study.

Extreme hemodynamic changes, especially intraoperative hypotension (IOH), are common and often prolonged during Liver Transplant (LT) surgery and during initial hours of recovery. Hypotension Prediction Index (HPI) software is one of the tools which can help in proactive hemodynamic management. The accuracy of the advanced hemodynamic parameters such as Cardiac Output (CO) and Systemic Vascular Resistance (SVR) obtained from HPI software and prediction performance of the HPI in LT surgery remains unknown. This was a retrospective observational study conducted in a tertiary academic center with a large liver transplant program. We enrolled 23 adult LT patients who received both Pulmonary Artery Catheter (PAC) and HPI software monitoring. Primarily, we evaluated agreement between PAC and HPI software measured CO and SVR. A priori, we defined a relative difference of less than 20% between measurements as an adequate agreement for a pair of measurements and estimated the Lin's Concordance Correlation Coefficient and Bland-Altman Limits of Agreement (LOA). Clinically acceptable LOA was defined as ±1 L.min-1 for CO and ±200 dynes s.cm-5 for SVR. Secondary outcome was the ability of the HPI to predict future hypotension, defined as Mean Arterial Pressure (MAP) less than 65 mmHg lasting at least one minute. We estimated sensitivity, positive predictive value, and time from alert to hypotensive events for HPI software. Overall, 125 pairs of CO and 122 pairs of SVR records were obtained from 23 patients. Based on our predefined criteria, only 42% (95% CI 30%, 55%) of CO records and 53% (95% CI 28%, 72%) of SVR records from HPI software were considered to agree with those from PAC. Across all patients, there were a total of 1860 HPI alerts (HPI ≥85) and 642 hypotensive events (MAP< 65 mmHg). Out of the 642 hypotensive events, 618 events were predicted by HPI alert with sensitivity of 0.96 (95% CI: 0.95). Many times, the HPI value remained above alert level and was followed by multiple hypotensive events. Thus, to evaluate PPV and time to hypotension metric, we considered only the first HPI alert followed by a hypotensive event ("true alerts"). The "true alert" was the first alert when there were several alerts before a hypotension. There were 614 "true alerts" and the PPV for HPI was 0.33 (95% CI 0.31, 0.35). The median time from HPI alert to hypotension was 3.3 [Q1, Q3: 1, 9.3] mins. There was poor agreement between the pulmonary artery catheter and HPI software calculated advanced hemodynamic parameters (CO and SVR), in the patients undergoing LT surgery. HPI software had high sensitivity but poor specificity for hypotension prediction, resulting in a high burden of false alarms.

MAIL: Micro-Accelerator-in-the-Loop Framework for MCU Integrated Accelerator Peripheral Fast Prototyping

The resource-constrained MCU-based platform is unable to use high-performance accelerators such as GPUs or servers due to insufficient resources for ML applications. We define a Micro-Accelerator (MA) that can accelerate ML operations by being connected to the on-chip bus peripheral of the MCU core. ML applications using general-purpose accelerators have a well-equipped SDK environment, making design and verification flow straightforward. In contrast, MA must be connected to the MCU core and on-chip bus interface within the chip. However, evaluating the interaction between the MCU core and an MA is challenging, as it requires the MA to connect with the core and the on-chip bus interface during target software execution. The cost of fabricating physical MA hardware is enormous, compounded by licensing issues with commercial cores. We propose a MA-in-the-loop (MAIL) framework that integrates a custom-designed MA into an emulation platform. This platform enables virtual execution by loading software onto the MCU, allowing observation of hardware-software interactions during ML execution. The proposed framework in this paper is a mixture of software that can emulate the environment in which general ML applications run on the MCU and RTL simulations to profile the acceleration on the MA. To evaluate the flow of ML software execution and performance changes according to the various architectures of MA in the framework, the MA can be reconfigured at runtime to explore the design space. To benchmark our proposed framework, we compared TinyML application profiles to the pure software execution. Experimental results show that the MA-accelerated framework performs comparably to actual MCUs, validating the efficacy of the proposed approach.

Evaluation of AI-based auto-contouring tools in radiotherapy: A single-institution study.

Accurate delineation of organs at risk (OARs) is crucial yet time-consuming in the radiotherapy treatment planning workflow. Modern artificial intelligence (AI) technologies had made automation of OAR contouring feasible. This report details a single institution's experience in evaluating two commercial auto-contouring software tools and making well-informed decisions about their clinical adoption. A cohort of 36 patients previously treated at our institution were selected for the software performance assessment. Fifty-eight OAR structures from seven disease sites were automatically segmented with each tool. Five radiation oncologists with different specialties qualitatively scored the automatic OAR contours' clinical usability by a 4-level scale (0-3), termed as quality score (QS), representing from "0: not usable" to "3: directly usable for a clinic." Additionally, quantitative comparison with clinically approved contours using Dice similarity coefficient (DSC) and the 95% Hausdorff distance (HD95) was performed in complement to QS from physicians. Software A achieved an average QS of 2.17±0.69, comparable to Software B's average QS of 2.17±0.72. Software B performed better with more OARs (42vs. 37) that required minor or no modification than Software A. Major modifications were needed for 13 out of 58 automated contours from both tools. Both DSC and HD95 scores for the two tools were comparable to each other, with DSC: 0.67±0.23versus 0.66±0.21 and HD95: 13.07±15.84versus 15.55±18.45 for Software A and Software B, respectively. Correlation coefficients between the physician score and the quantitative metrics suggested that the contouring results from Software A aligned more closely with the physician's evaluations. Based on our study, either software tool could produce clinically acceptable contours for about 65% of the OAR structures. However, further refinement is necessary for several challenging OARs to improve model performance.

What Quantum Can Learn from Classical Computer Engineering

Quantum computing represents a paradigm shift requiring reconceptualization of algorithms, architectures, and software. Although much is new, there is much that quantum computing can learn from traditional classical computer engineering. In this Special Issue, we focus on examples of quantum research inspired by classical computer engineering, ranging from quantum machine learning and image processing to the extension of the “multi-core” concept to quantum computing. Hardware/software co-design is difficult when communities have their unique jargon and disjoint problem domains. For parallel programming on classical computers, an approach for communicating application developer needs emerged around identifying key bottlenecks that limited software. It was difficult to guess features of future applications, but experienced developers knew features of a computer system that would limit software performance. For each feature, a small kernel was developed with the idea that if the kernel ran well, a system would be an effective system for application developers. This set of kernels was called the Parallel Research Kernels . They have been useful to guide design of parallel computers. We hypothesize that an analogous tool for quantum computing, called Quantum Research Kernels , may aid hardware/software co-design of quantum computing systems. In this article, we motivate the Quantum Research Kernels and provide working examples.

Optimizing Software Performance in Distributed Cloud Systems: Challenges and Solutions

The rapid proliferation of distributed cloud systems has revolutionized software deployment and scalability, enabling organizations to meet dynamic demands efficiently. However, optimizing software performance in such environments presents unique challenges, including resource heterogeneity, network latency, and dynamic workload variations. This paper explores the critical factors influencing software performance in distributed cloud systems, highlighting common bottlenecks and their root causes. It also presents a comprehensive analysis of state-of-the-art solutions, such as advanced resource allocation algorithms, load balancing techniques, and containerized microservices. Additionally, the study introduces a framework for evaluating performance metrics and proposes strategies to mitigate inefficiencies while ensuring scalability and cost-effectiveness. By addressing these challenges, this research aims to provide actionable insights and foster innovation in the design and optimization of software systems for distributed clouds.

Verification of Vulnerable Road User Pre-Crash Scenarios in Vision-Based Safety Applications

&lt;div&gt;Verifying training datasets in vision-based vehicle safety applications is crucial to understanding the potential limitations of detection capabilities that may result in a higher safety risk. Vision-based pedestrian safety applications with crash avoidance technologies rely on prompt detection to avoid a crash. This research aims to develop a verification process for vulnerable road user safety applications with vision-based detection functionalities. It consists of reviewing the application’s safety requirements, identifying the target objects of detection in the operational design domain and pre-crash scenarios, and evaluating the safety risks qualitatively by examining the training dataset based on the results of pre-crash scenarios classification. As a demonstration, the process is implemented using open-source pedestrian tracking software, and the pre-crash scenarios are classified based on the trajectories of pedestrians in an example training dataset used in a pedestrian automatic emergency braking system. The dataset provides abundant vulnerable road users under various operating conditions. Results show that the dataset does not cover snowy weather, fog, smoke, smog, and dust/dirt of particulate matter conditions. Crossing, cut-in, and front pre-crash scenarios are less well-represented in the dataset than pedestrians on the sidewalk. Very few pedestrians were found in the front-near zone, which suggests the dataset lacks sufficient imminent pre-crash scenarios that pose the greatest safety risk. The performance of the pedestrian tracking software is evaluated and future research for improving the proposed mechanism is discussed.&lt;/div&gt;

Design and Research on Evaluation System of Computer Pro-gramming Code Quality

With the ongoing development of software engineering and programming education, the demand for evaluating programming code quality is increasing. High-quality code not only en-hances software maintainability and performance but also helps developers and learners optimize their coding skills. This paper focuses on the design and implementation of an evaluation system for computer programming code quality, proposing a multi-dimensional evaluation method that includes readability, complexity, efficiency, and security. The system combines static analysis with machine learning to automate code analysis and optimization recommendations, providing users with objective feedback on code quality. Additionally, this paper explores application cases of the system in programming education and software development, demonstrating its effectiveness in improving code quality and enhancing users' programming skills. Finally, the research contribu-tions are summarized, and directions for future improvements are proposed to further enhance the system’s intelligence and applicability.

Rapid Identification of Clinically Relevant Candida spp. by I-dOne Software Using Attenuated Total Reflectance Fourier Transform Infrared (ATR-FTIR) Spectroscopy.

Attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy is a spectrum-based technique that quantifies the absorption of infrared light by molecules present in the microbial cell. The aim of the present study was to evaluate the performance of the ATR-FTIR spectroscopic technique via I-dOne software (Version 2.0) compared with the MALDI-TOF MS in identifying Candida spp. Each infrared spectrum was compared with spectra stored in the software database. The updated version of the I-dOne software was used to analyze ATR-FTIR spectra. All Candida isolates 284/284 (100%) were classified correctly according to the genus. Overall species identification yielded 272/284 (95.8%) concordant identification results with MALDI-TOF MS. Additionally, all 79 isolates belonging to the Candida parapsilosis species complex were identified correctly to the species level with the updated version of the I-dOne software. Only 12 (4.2%) isolates were misidentified at the species level. The present study highlights the potential diagnostic performance of the I-dOne software with ATR-FTIR spectroscopic technique referral spectral database as a real alternative for routine identification of the most frequently isolated Candida spp.

A comparison of CXR-CAD software to radiologists in identifying COVID-19 in individuals evaluated for Sars CoV-2 infection in Malawi and Zambia.

AI based software, including computer aided detection software for chest radiographs (CXR-CAD), was developed during the pandemic to improve COVID-19 case finding and triage. In high burden TB countries, the use of highly portable CXR and computer aided detection software has been adopted more broadly to improve the screening and triage of individuals for TB, but there is little evidence in these settings regarding COVID-19 CAD performance. We performed a multicenter, retrospective cross-over study evaluating CXRs from individuals at risk for COVID-19. We evaluated performance of CAD software and radiologists in comparison to COVID-19 laboratory results in 671 individuals evaluated for COVID-19 at sites in Zambia and Malawi between January 2021 and June 2022. All CXRs were interpreted by an expert radiologist and two commercially available COVID-19 CXR-CAD software. Radiologists interpreted CXRs for COVID-19 with a sensitivity of 73% (95% CI: 69%- 76%) and specificity of 49% (95% CI: 40%-58%). One CAD software (CAD2) showed performance in diagnosing COVID-19 that was comparable to that of radiologists, (AUC-ROC of 0.70 (95% CI: 0.65-0.75)), while a second (CAD1) showed inferior performance (AUC-ROC of 0.57 (95% CI: 0.52-0.63)). Agreement between CAD software and radiologists was moderate for diagnosing COVID-19, and agreement was very good in differentiating normal and abnormal CXRs in this high prevalent population. The study highlights the potential of CXR-CAD as a tool to support effective triage of individuals in Malawi and Zambia during the pandemic, particularly for distinguishing normal from abnormal CXRs. These findings suggest that while current AI-based diagnostics like CXR-CAD show promise, their effectiveness varies significantly. In order to better prepare for future pandemics, there is a need for representative training data to optimize performance in key populations, and ongoing data collection to maintain diagnostic accuracy, especially as new disease strains emerge.

Data-Driven User Personas in Requirement Engineering with NLP and Behavior Analysis

As technology rapidly evolves, software development faces growing complexity, requiring adaptation to dynamic user expectations. This study addresses a critical gap in the existing literature by integrating behavioral data and sentiment analysis into the user persona development process within the requirement engineering framework. The primary objective is to create more accurate and representative user personas that better guide software design and development. To achieve this, the research employs advanced Natural Language Processing (NLP) techniques to systematically analyze extensive behavioral and sentiment data collected from social media platforms. The integration process involves segmenting user data into behavioral patterns and emotional states, which are then synthesized to develop nuanced user personas. These personas are expected to significantly improve the accuracy of user requirements, leading to enhanced software performance, increased user satisfaction, and greater development efficiency. The target application area for this research is mobile telecommunications, where precise user understanding is critical. The results indicate that this approach not only refines the traditional persona method but also addresses the evolving needs of users more holistically. By advancing the methodology for user-centered design, this study contributes to the broader field of requirement engineering. Future research will validate and refine this approach across diverse domains, ensuring its adaptability and effectiveness in different contexts. This paper thus has the potential to make a significant impact on how user personas are developed and utilized in software engineering.

Monitoring Performance of Golang Applications Using Code Profiling

Abstract—Debugging and monitoring are essential for building scalable and reliable applications. Often, real-world applications have performance regressions. These can be hard to root cause using conventional debugging and monitoring tools. Code profiling tools can be quite handy for such scenarios. Profiling tools can be used to detect hotspots, i.e., parts of code that have poor performance and high resource utilization. Profiling tools provide deep insights into the runtime behavior of an application which can be useful in general. The pprof package can be used for profiling of Golang applications. This tool is easy to use and can provide information about a lot of runtime aspects of a program. In this paper, we take a look at pprof, how to use it in Golang and review the benefits and caveats associated with its use. Keywords—software monitoring, software performance, code profiling

Diagnostic performance of ClinCheck, Dolphin Imaging, and 3D Slicer software for Bolton discrepancy analysis.

To evaluate the diagnostic performance of ClinCheck, Dolphin Imaging orthodontic software, and 3D Slicer for the analysis of Bolton discrepancy (BD). Fifty-five pairs of early-stage digital models of patients treated with Invisalign were printed to measure the BD by manual method with a digital caliper (gold standard). The discrepancy values calculated by ClinCheck were obtained. In addition, the sample STL files were measured using Dolphin Imaging and 3D Slicer software to obtain BD values. To assess reliability, precision, and accuracy of the methods, intraclass correlation coefficients (ICCs), Dahlberg's formula, paired t-tests, and the Bland-Altman method were used, respectively. Repeated-measures analysis of variance with Bonferroni post hoc test was used to assess the difference between groups. The three methods showed reliable measurements (ICC ≥ 0.7), with the values of anterior Bolton slightly higher than overall Bolton. Measurements for the anterior Bolton showed higher precision (Dahlberg's formula 0.65, 0.70, and 0.55) than those for the overall Bolton. For anterior Bolton, only the measurements obtained by ClinCheck and Dolphin Imaging were accurate (P > .05, no proportion bias), while for overall Bolton, all groups had a significant difference. The Bland-Altman plots demonstrated no consistency for anterior Bolton measurements when 3D Slicer was used and for the overall Bolton. ClinCheck and Dolphin Imaging showed accuracy to quantify anterior BD. For the overall Bolton measurements, ClinCheck showed a statistical difference from the manual assessment but without relevant clinical significance.

Artificial Intelligence for Tooth Detection in Cleft Lip and Palate Patients.

Introduction: Cleft lip and palate patients often present with unique anatomical challenges, making dental anomaly detection and numbering particularly complex. The accurate identification of teeth in these patients is crucial for effective treatment planning and long-term management. Artificial intelligence (AI) has emerged as a promising tool for enhancing diagnostic precision, yet its application in this specific patient population remains underexplored. Objectives: This study aimed to evaluate the performance of an AI-based software in detecting and numbering teeth in cleft lip and palate patients. The research focused on assessing the system's sensitivity, precision, and specificity, while identifying potential limitations in specific anatomical regions and demographic groups. Methods: A total of 100 panoramic radiographs (52 males, 48 females) from patients aged 6 to 15 years were analyzed using AI software. Sensitivity, precision, and specificity were calculated, with ground truth annotations provided by four experienced orthodontists. The AI system's performance was compared across age and gender groups, with particular attention to areas prone to misidentification. Results: The AI system demonstrated high overall sensitivity (0.98 ± 0.03) and precision (0.96 ± 0.04). No statistically significant differences were found between age groups (p > 0.05), but challenges were observed in the maxillary left region, which exhibited higher false positive and false negative rates. These findings were consistent with the prevalence of unilateral left clefts in the study population. Conclusions: The AI system was effective in detecting and numbering teeth in cleft lip and palate patients, but further refinement is required for improved accuracy in the cleft region, particularly on the left side. Addressing these limitations could enhance the clinical utility of AI in managing complex craniofacial cases.

Single-Molecule Tracking dataset for histone H3 (hht1) from live and fixed cells of Schizosaccharomyces pombe

Single-molecule tracking provides direct real-time measurements of protein dynamics in live cells with high spatiotemporal resolution. In the last decade, this method has been adopted by several labs to understand the dynamics of DNA replication, transcription, telomerase, chromatin remodeling, etc. in a variety of model systems (bacteria, yeast S. cerevisiae, cell lines, embryo). However, it has not been employed for the yeast Schizosaccharomyces pombe, despite being a valuable model system. Here, we present single-molecule tracking datasets for chromatin-bound histone H3 (Hht1) in live and fixed cells and freely diffusing GFP in S. pombe nuclei to benchmark the diffusion parameters (diffusion coefficient, mean squared displacement, fraction of bound molecules, residence time). These parameters will be used to differentiate chromatin-bound molecules from unbound (free) molecules of any protein. It will be a valuable resource for any lab that starts employing this method for studying protein dynamics. This dataset can also be used to validate the performance of various tracking software and as a training dataset for machine learning-based automated tracking.

Computational Algorithms for Representing Aircraft Instruments with Barometric Physics (Numerical Methods Applied to Flight Simulation)

The present work describes the development of a graphical environment to represent typical flight instruments on a computer screen. The instruments’ behavior is displayed according to information regarding the aircraft’s flight conditions. Some of the instruments represented in this work, such as the altimeter, the vertical speed indicator, the aircraft speed indicator, and the Mach indicator, use air pressure principles. The algorithms and routines developed for the screen display are created using the C++ programming language and compiled independently to be included as libraries to improve the software performance. The algorithms developed for this purpose also include the corresponding relationship between the physical variables, such as the speed and displacement, and the standard atmosphere to provide an equivalent value. These algorithms are successfully tested using data information to simulate three hypothetical flights, which are divided into maneuvers with the aircraft in a stopped position, running on the ground, taking off and flying away, including some changes in directions. Moreover, the routines for displaying the aircraft path with the instruments’ animation are also successfully tested by comparison. Finally, an approach analysis as a function of the step time (Δt) used for calculation of the aircraft displacement to evaluate the efficiency of the numerical method integrated in the simulator is also described. It is proved that the aircraft instrument representation is appropriate according to the input data of the analyzed flights, and an improvement in the calculation can be easily obtained, making it possible to represent any flight condition on the aircraft instruments.

Artificial intelligence applications in smile design dentistry: A scoping review.

Artificial intelligence (AI) applications are growing in smile design and aesthetic procedures. The current expansion and performance of AI models in digital smile design applications have not yet been systematically documented and analyzed. The purpose of this review was to assess the performance of AI models in smile design, assess the criteria of points of reference using AI analysis, and assess different AI software performance. An electronic review was completed in five databases: MEDLINE/PubMed, EMBASE, World of Science, Cochrane, and Scopus. Studies that developed AI models for smile design were included. The search strategy included articles published until November 1, 2024. Two investigators independently evaluated the quality of the studies by applying the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Quasi-Experimental Studies and Textual Evidence: Expert Opinion Results. The search resulted in 2653 articles. A total of 2649 were excluded according to the exclusion criteria after reading the title, abstract, and/or full-text review. Four articles published between 2023 and 2024 were included in the present investigation. Two articles compared 2D and 3D points while one article compared the outcome of satisfaction between dentists and patients, and the last article emphasized the ethical components of using AI. The results of the studies reviewed in this paper suggest that AI-generated smile designs are not significantly different from manually created designs in terms of esthetic perception. 3D designs are more accurate than 2D designs and offer more advantages. More articles are needed in the field of AI and smile design.

Combining crystallographic and binding affinity data towards a novel dataset of small molecule overlays

Although small molecule superposition is a standard technique in drug discovery, a rigorous performance assessment of the corresponding methods is currently challenging. Datasets in this field are sparse, small, tailored to specific applications, unavailable, or outdated. The newly developed LOBSTER set described herein offers a publicly available and method-independent dataset for benchmarking and method optimization. LOBSTER stands for “Ligand Overlays from Binding SiTe Ensemble Representatives”. All ligands were derived from the PDB in a fully automated workflow, including a ligand efficiency filter. So-called ligand ensembles were assembled by aligning identical binding sites. Thus, the ligands within the ensembles are superimposed according to their experimentally determined binding orientation and conformation. Overall, 671 representative ligand ensembles comprise 3583 ligands from 3521 proteins. Altogether, 72,734 ligand pairs based on the ensembles were grouped into ten distinct subsets based on their volume overlap, for the benefit of introducing different degrees of difficulty for evaluating superposition methods. Statistics on the physicochemical properties of the compounds indicate that the dataset represents drug-like compounds. Consensus Diversity Plots show predominantly high Bemis–Murcko scaffold diversity and low median MACCS fingerprint similarity for each ensemble. An analysis of the underlying protein classes further demonstrates the heterogeneity within our dataset. The LOBSTER set offers a variety of applications like benchmarking multiple as well as pairwise alignments, generating training and test sets, for example based on time splits, or empirical software performance evaluation studies. The LOBSTER set is publicly available at https://doi.org/10.5281/zenodo.12658320, representing a stable and versioned data resource. The Python scripts are available at https://github.com/rareylab/LOBSTER, open-source, and allow for updating or recreating superposition sets with different data sources. Graphical abstractSimplified illustration of the LOBSTER dataset generation.

RPerf: Mining user reviews using topic modeling to assist performance testing: An industrial experience report

Software performance affects the user-perceived quality of software. Therefore, it is important to analyze the performance issues that users are concerned with. In this paper, we document our experience working with our industry partner on analyzing user reviews to identify and analyze performance issues users are concerned with. In particular, we designed an approach, RPerf, which automatically analyzes unstructured user reviews and generates a performance analysis report that can assist performance engineers with performance testing. In particular, RPerf uses BERTopic to uncover performance-related topics in user reviews. RPerf then maps the derived topics to performance KPIs (key performance indicators) such as response time. Such performance KPIs better help performance test design and allocate performance testing resources. Finally, RPerf extracts user usage scenarios from user reviews to help identify the causes. Through a manual evaluation, we find RPerf achieves a high accuracy (over 93%) in identifying the performance-related topics and performance KPIs from user reviews. RPerf can also accurately extract usage scenarios in over 80% of user reviews. We discuss the performance analysis report that is generated based on RPerf. We believe that our findings can assist practitioners with analyzing performance-related user reviews and inspire future research on user review analysis.

Software Performance Optimization for Classification and Linking of Administrative Documents

Software Performance Optimization for Classification and Linking of Administrative Documents