Software Performance Research Articles

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.

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.

Software Performance Optimization for Classification and Linking of Administrative Documents

Software Performance Optimization for Classification and Linking of Administrative Documents

Scabbard: An Exploratory Study on Hardware Aware Design Choices of Learning with Rounding-based Key Encapsulation Mechanisms

Recently, the construction of cryptographic schemes based on hard lattice problems has gained immense popularity. Apart from being quantum resistant, lattice-based cryptography allows a wide range of variations in the underlying hard problem. As cryptographic schemes can work in different environments under different operational constraints such as memory footprint, silicon area, efficiency, power requirement, and so on, such variations in the underlying hard problem are very useful for designers to construct different cryptographic schemes. In this work, we explore various design choices of lattice-based cryptography and their impact on performance in the real world. In particular, we propose a suite of key-encapsulation mechanisms based on the learning with rounding problem with a focus on improving different performance aspects of lattice-based cryptography. Our suite consists of three schemes. Our first scheme is Florete, which is designed for efficiency. The second scheme is Espada, which is aimed at improving parallelization, flexibility, and memory footprint. The last scheme is Sable, which can be considered an improved version in terms of key sizes and parameters of the Saber key-encapsulation mechanism, one of the finalists in the National Institute of Standards and Technology’s post-quantum standardization procedure. In this work, we have described our design rationale behind each scheme. Furthermore, to demonstrate the justification of our design decisions, we have provided software and hardware implementations. Our results show Florete is faster than most state-of-the-art KEMs on software platforms. For example, the key-generation algorithm of high-security version Florete outperforms the National Institute of Standards and Technology’s standard Kyber by 47%, the Federal Office for Information Security’s standard Frodo by 99%, and Saber by 57% on the ARM Cortex-M4 platform. Similarly, in hardware, Florete outperforms Frodo and NTRU Prime for all KEM operations. The scheme Espada requires less memory and area than the implementation of most state-of-the-art schemes. For example, the encapsulation algorithm of high-security version Espada uses 30% less stack memory than Kyber, 57% less stack memory than Frodo, and 67% less stack memory than Saber on the ARM Cortex-M4 platform. The implementations of Sable maintain a tradeoff between Florete and Espada regarding software performance and memory requirements. Sable outperforms Saber at least by 6% and Frodo by 99%. Through an efficient polynomial multiplier design, which exploits the small secret size, Sable outperforms most state-of-the-art KEMs, including Saber, Frodo, and NTRU Prime. The implementations of Sable that use number theoretic transform-based polynomial multiplication (SableNTT) surpass all the state-of-the-art schemes in performance, which are optimized for speed on the Cortext M4 platform. The performance benefit of SableNTT against Kyber lies in between 7-29%, 2-13% for Saber, and around 99% for Frodo.

A Survey System for Artificial Intelligence-Based Painting Using Generative Adversarial Network Techniques

The purpose of this paper is to construct an evaluation system for AI painting software based on generative adversarial network (GAN) technology, which optimizes the performance of the related software in terms of functionality, ease of use, system performance, and safety. The results of the questionnaires are statistically analyzed. In addition, an exploratory factor analysis was conducted to extract the data of the study, which were ultimately used to calculate the weight and importance of each index using the fuzzy hierarchical analysis method. This study constructed an evaluation system for AI painting software based on GAN technology, including 16 indicators of functionality, 16 indicators of ease of use, 7 indicators of system performance, and 8 indicators of safety, respectively, whose alpha coefficients were 0.882, 0.962, 0.932, 0.932, and 0.932, respectively. In addition, the accumulated explanatory variances of their coefficients were 84.405%, 84.897%, 84.013%, 72.606%, 73.013%, and 72.606%, respectively. It is clear that the items included in each of the indicators are homogeneous, with a high degree of internal consistency. This paper suggests that the development of AI painting software focusing on functionality, ease of use, system performance, and safety can enhance the market competitiveness of the software.

The Development of Volumetric Quantitative Evaluation Software for Assessing Respiratory-Induced Target Motion.

Purpose We developed a volumetric quantitative evaluation software called vector volume histogram (VVH) to evaluate respiratory-induced organ motion using deformable image registration (DIR). Methods The B-spline-based DIR algorithm was used to compute the deformation vector field (DVF), which included the DVFLR (left-right), DVFAP (anterior-posterior), and DVFCC (craniocaudal). The VVH software was written as a plug-in using Python, thus allowing anyone to easily modify the code. A shifted target within the moving phantom was used to evaluate the performance of the VVH software. The 2 cm diameter target was systematically shifted by 5, 10, 15, and 20 mm in the CC direction. To evaluate respiration-induced target motion, the VVH method was applied during the inhalation and exhalation phases of 4D CT scans in a patient with lung cancer. Length at 5% volume (L5%) and length at 50% volume (L50%​​​​​) were calculated to evaluate the target motion. Results In the phantom study, the VVH software accurately measured target displacements with L5% and L50% values of 5.4 mm and 4.8 mm, 10.4 mm and 9.8 mm, 14.9 mm, and 14.6 mm, and 19.9 mm and 19.6 mm for 5, 10, 15 and 20 mm displacements, respectively. For the lung cancer patient study, the VVH method showed target motion with L5% and L50% values of 1.9 mm and 1.8 mm in LR, 1.9 mm and 0.9 mm in AP, 18.8 mm and 15.8 mm in CC, and 18.9 mm and 15.8 mm in 3D vector. The centroid method measured respiratory tumor motion between the inhalation and exhalation phases as 0.5 mm, 0.7 mm, 13.5 mm, and 13.5 mm in the LR, AP, and CC directions and in the 3D vector. Conclusions The VVH software provided a volumetric quantitative assessment of respiratory-induced target motion and may provide strategic decisions for clinical use at the time of treatment planning.

Flexible Generation of Fast and Accurate Software Performance Simulators From Compact Processor Descriptions

Flexible Generation of Fast and Accurate Software Performance Simulators From Compact Processor Descriptions

E-code: Mastering efficient code generation through pretrained models and expert encoder group

Context:With the waning of Moore’s Law, the software industry is placing increasing importance on finding alternative solutions for continuous performance enhancement. The significance and research results of software performance optimization have been on the rise in recent years, especially with the advancement propelled by Large Language Models (LLMs). However, traditional strategies for rectifying performance flaws have shown significant limitations at the competitive code efficiency optimization level, and research on this topic is surprisingly scarce. Objective:This study aims to address the research gap in this domain, offering practical solutions to the various challenges encountered. Specifically, we have overcome the constraints of traditional performance error rectification strategies and developed a Language Model (LM) tailored for the competitive code efficiency optimization realm. Methods:We introduced E-code, an advanced program synthesis LM. Inspired by the recent success of expert LMs, we designed an innovative structure called the Expert Encoder Group. This structure employs multiple expert encoders to extract features tailored for different input types. We assessed the performance of E-code against other leading models on a competitive dataset and conducted in-depth ablation experiments. Results:Upon systematic evaluation, E-code achieved a 54.98% improvement in code efficiency, significantly outperforming other advanced models. In the ablation experiments, we further validated the significance of the expert encoder group and other components within E-code. Conclusion:The research findings indicate that the expert encoder group can effectively handle various inputs in efficiency optimization tasks, significantly enhancing the model’s performance. In summary, this study paves new avenues for developing systems and methods to assist programmers in writing efficient code.

Automated analysis of flow cytometry data with minimal training files: Research evaluation of an elastic image registration algorithm for TBNK, stem cell enumeration, and lymphoid screening tube assays.

Automated analysis of flow cytometry data can improve objectivity and reduce analysis time but has generally required work by software and algorithm experts. Here, we investigated the performance of BD ElastiGate™ Software (hereafter ElastiGate), which allows users to automate gating by selecting gated training files, then uses elastic image registration to gate new files. Three assays of increasing complexity were examined: TBNK, stem cell enumeration (SCE), and lymphoid screening tube (LST). For TBNK analysis, 60 peripheral blood (PB) samples from normal, HIV+, and controls were tested with ground truth analysis by an existing automated method. For SCE, 128 samples including bone marrow (BM), cord blood (CB), and apheresis were tested with analysis by multiple manual analysts. For LST, 80 PB and 28 BM samples were tested with manual analysis. For ElastiGate, a minimal number of training files was selected. Results were compared by Bland-Altman or F1 score analysis. For TBNK, ElastiGate using three training files (1 control, 1 normal, 1 HIV+) showed mean %bias across all reported populations between -1.48% and 7.13% (average 2.08%). For SCE, ElastiGate using three BM and two CB training files showed median F1 scores >0.93 in comparison to >0.94 and >0.92 for two other manual analysts. For LST, ElastiGate using four training files for each of PB and BM showed median F1 scores >0.945 for 13 of 14 PB populations and 10 of 14 BM populations, with generally similar or better performance for normal samples compared to abnormal; populations with lower scores were often associated with lower agreement between manual analysts. Based on analysis of three assays with four sample types of increasing complexity, ElastiGate with minimal training files may perform as an automated gating assistant. The results reported here are for research use only, not for use in diagnostic or therapeutic procedures.

Recommendations for the creation of benchmark datasets for reproducible artificial intelligence in radiology

Various healthcare domains have witnessed successful preliminary implementation of artificial intelligence (AI) solutions, including radiology, though limited generalizability hinders their widespread adoption. Currently, most research groups and industry have limited access to the data needed for external validation studies. The creation and accessibility of benchmark datasets to validate such solutions represents a critical step towards generalizability, for which an array of aspects ranging from preprocessing to regulatory issues and biostatistical principles come into play. In this article, the authors provide recommendations for the creation of benchmark datasets in radiology, explain current limitations in this realm, and explore potential new approaches.Clinical relevance statementBenchmark datasets, facilitating validation of AI software performance can contribute to the adoption of AI in clinical practice.Key PointsBenchmark datasets are essential for the validation of AI software performance.Factors like image quality and representativeness of cases should be considered.Benchmark datasets can help adoption by increasing the trustworthiness and robustness of AI.Graphical

Measuring code efficiency optimization capabilities with ACEOB

As Moore’s Law gains diminish, software performance and efficiency become increasingly vital. Optimizing code efficiency is challenging, even for professional programmers. However, related research remains relatively scarce, and rigorously assessing models’ abilities to optimize code efficiency is fraught with difficulties. In response to this challenge, we first conduct an in-depth analysis of “code patterns” in the model training dataset, meticulously exploring human-written code. Secondly, we define a task for optimizing code efficiency and introduce the Automatic Code Efficiency Optimization Benchmark (ACEOB), which consists of 95,359 pairs of efficient–inefficient code aimed at assessing code efficiency optimization capabilities. To our knowledge, ACEOB is the first dataset specifically targeting Python code efficiency optimization. To evaluate models’ ability in optimizing code efficiency, we propose two new metrics: the Isomorphic Optimal Comparison CodeBLEU (IOCCB) metric and the Normalized Performance Index (NPI) metric, to assess the efficiency of model-generated code. We also evaluate several advanced code models, such as PolyCoder and CodeT5, after fine-tuning them on ACEOB and demonstrate that the efficiency of each model improves after introducing the NPI filter. However, it was observed that even ChatGPT does not perform optimally in code efficiency optimization tasks. Our dataset and models are available at: https://github.com/CodeGeneration2/ACEOB.Editor’s note: Open Science material was validated by the Journal of Systems and Software Open Science Board.

Automated quality control analysis for American College of Radiology (ACR) digital mammography (DM) phantom images.

To develop and validate an automated software analysis method for mammography image quality assessment of the American College of Radiology (ACR) digital mammography (DM) phantom images. Twenty-seven DICOM images were acquired using Fuji mammography systems. All images were evaluated by three expert medical physicists using the Royal Australian and New Zealand College of Radiologists (RANZCR) mammography quality control guideline. To enhance the robustness and sensitivity assessment of our algorithm, an additional set of 12 images from a Hologic mammography system was included to test various phantom positional adjustments. The software automatically chose multiple regions of interest (ROIs) for analysis. A template matching method was primarily used for image analysis, followed by an additional method that locates and scores each target object (speck groups, fibers, and masses). The software performance shows a good to excellent agreement with the average scoring of observers (intraclass correlation coefficient [ICC] of 0.75, 0.79, 0.82 for speck groups, fibers, and masses, respectively). No significant differences were found in the scoring of target objects between human observers and the software. Both methods achieved scores meeting the pass criteria for speck groups and masses. Expert observers allocated lower scores to fiber objects, with diameters less than 0.61mm, when compared to the software. The software was able to accurately score objects when the phantom position changed by up to 25mm laterally, up to 5 degrees rotation, and overhanging the chest wall edge by up to 15mm. Automated software analysis is a feasible method that may help improve the consistency and reproducibility of mammography image quality assessment with reduced reliance on human interaction and processing time.

Quantum state tomography with locally purified density operators and local measurements

Understanding quantum systems is of significant importance for assessing the performance of quantum hardware and software, as well as exploring quantum control and quantum sensing. An efficient representation of quantum states enables realizing quantum state tomography with minimal measurements. In this study, we propose an alternative approach to state tomography that uses tensor network representations of mixed states through locally purified density operators and employs a classical data postprocessing algorithm requiring only local measurements. Through numerical simulations of one-dimensional pure and mixed states and two-dimensional pure states up to size 8 × 8, we demonstrate the efficiency, accuracy, and robustness of our proposed methods. Experiments on the IBM and Quafu Quantum platforms complement these numerical simulations. Our study opens avenues in quantum state tomography for two-dimensional systems using tensor network formalism.

Enhancing Software Performance and Reliability through Observability in DevOps

Enhancing Software Performance and Reliability through Observability in DevOps

A unified active learning framework for annotating graph data for regression tasks

In many domains, effectively applying machine learning models requires a large number of annotations and labelled data, which might not be available in advance. Acquiring annotations often requires significant time, effort, and computational resources, making it challenging. Active learning strategies are pivotal in addressing these challenges, particularly for diverse data types such as graphs. Although active learning has been extensively explored for node-level classification, its application to graph-level learning, especially for regression tasks, is not well-explored. We develop a unified active learning framework specializing in graph annotating and graph-level learning for regression tasks on both standard and expanded graphs, which are more detailed representations. We begin with graph collection and construction. Then, we construct various graph embeddings (unsupervised and supervised) into a latent space. Given such an embedding, the framework becomes task agnostic and active learning can be performed using any regression method and query strategy suited for regression. Within this framework, we investigate the impact of using different levels of information for active and passive learning, e.g., partially available labels and unlabelled test data. Despite our framework being domain agnostic, we validate it on a real-world application of software performance prediction, where the execution time of the source code is predicted. Thus, the graph is constructed as an intermediate source code representation. We support our methodology with a real-world dataset to underscore the applicability of our approach. Our real-world experiments reveal that satisfactory performance can be achieved by querying labels for only a small subset of all the data. A key finding is that Graph2Vec (an unsupervised embedding approach for graph data) performs the best, but only when all train and test features are used. However, Graph Neural Networks (GNNs) are the most flexible embedding techniques when used for different levels of information with and without label access. In addition, we find that the benefit of active learning increases for larger datasets (more graphs) and when the graphs are more complex, which is arguably when active learning is the most important.

Simulation and performance characteristics of rock with borehole using Visual Finite Element Analysis

Purpose. This study aims to investigate fluid flow and heat transfer within rocks containing boreholes, focusing on the complex mechanisms within hot reservoirs. Non-commercial finite element (FE) software is used to visualize and present the results. Methods. The study involved the use of FE method with Visual Finite Element Analysis (VisualFEA) software to analyze the coupled phenomena of fluid flow and heat transfer in a rock sample. Special attention was given to incorporating material structure and geotechnical analysis in the software, as well as the treatment of cracked elements. In addition, the validation was done by comparing the current numerical solution using VisualFEA with the numerical solution using ANSYS Software. Findings. The study findings highlight the capabilities of VisualFEA software to accurately represent fluid flow, stress, and heat transfer in borehole-containing rocks. The results include insights into flow direction within the borehole, temperature distribution, and the validation of the software performance against expected system behavior. The study demonstrates the effectiveness of VisualFEA in handling complex loading and its ability to visualize multiple flow directions within a 2D model. The results are presented in the form of contours and curves. Originality. This study contributes to the field demonstrating the application of VisualFEA software in analyzing fluid flow and heat transfer in rocks with boreholes. The focus on incorporating material structure, geotechnical analysis, and treatment of cracked elements adds originality to the study, providing a comprehensive understanding of the coupled phenomena in hot reservoirs. Practical implications. The practical significance of this study is in the validation and benchmarking of VisualFEA software for studying fluid flow and heat transfer in geotechnical application. The findings can be utilized by geotechnical engineers and researchers to better understand the behavior of borehole-containing rocks under specific pressure and thermal loading conditions. The insights gained from this study can be used in decision-making processes related to resource mining, reservoir engineering, and geothermal energy use.

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.

Identifying the Factors Influencing Youths Decision in Afghanistan for the Purpose of Smartphone Purchasing

The current study aims to investigate the variables influencing customer intent to purchase smartphones and to smooth the way and increase investor interest in investing in Afghanistan considering the identified factors (Subjective Norm, Personal Factor, Operational Factor, Software Performance, and Product Physical Features). Data was collected through a Google Forms structured questionnaire, which was developed from previous studies, using a 5-point Likert scale. This study determined that a sample size of 800–1000 respondents would be appropriate for the survey; 892 replies in all were gathered. The factor analysis test was applied to test the variables' validity. In the study, Binary Logistic Regression Analysis (LR) was performed to assess whether there is a significant relationship between smartphone purchasing decisions and the following factors: Subjective Norm, Personal Factor, Operational Factor, Software Performance, and Product Physical Features. The research showed that there is a significant relationship between the mentioned factors and smartphone purchase decisions. There are a variety of elements that influence consumers' intentions to buy smartphones, but subjective norms, personal factors, operational factors, software performance, and physical features are the factors that drive consumers to purchase.