Intelligent Evaluation Research Articles

Decision support system to evaluate a vandalized and deteriorated oil pipeline transportation system using artificial intelligence techniques. Part 2: analysis of the operational and economic risk

Abstract The changing supply and demand of hydrocarbons in recent years, generated by inflation, pandemics, and wars, have impacted its price considerably, developing limitations in maintenance processes in the oil industry worldwide; however, the mechanical deterioration of facilities due to corrosion does not stop. This article contributes original to the knowledge and management of a pipeline transportation system (PTS) without an immediate high impact that would help reduce property loss due to corrosion through the development of intelligent evaluation models that combine field data, laboratory, and cognitive knowledge in a case study in Mexico. The research is divided into Part 1 (Modeling; https://doi.org/10.1515/corrrev-2021-0080) and Part 2 (Operational and economic risk analysis of PTS under corrosive effects, using Monte Carlo simulation, MCS), supported by information and knowledge of 564 km of soils, from cathodic protection studies, essential to determine corrosive profiles of the PTS, considering supply and demand effects, with 1095 data on the price of the Mexican mixture from 2016 to 2019, as well as data monthly inflation rates for the same period, to generate financial estimates representative of the system, in search of replicable exchange actions and practices in international fields.

Retracted: A Convolutional Network-Based Intelligent Evaluation Algorithm for the Quality of Spoken English Pronunciation

Retracted: A Convolutional Network-Based Intelligent Evaluation Algorithm for the Quality of Spoken English Pronunciation

Dialect identification, intelligibility ratings, and acceptability ratings of dysarthric speech in two American English dialects

ABSTRACT The current study explored the intelligibility and acceptability ratings of dysarthric speakers with African American English (AAE) and General American English (GAE) dialects by listeners who identify as GAE or AAE speakers, as well as listener ability to identify dialect in dysarthric speech. Eighty-six listeners rated the intelligibility and acceptability of sentences extracted from a passage read by speakers with dysarthria. Samples were used from the Atlanta Motor Speech Disorders Corpus and ratings were collected via self-report. The listeners identified speaker dialect in a forced-choice format. Listeners self-reported their dialect and exposure to AAE. AAE dialect was accurately identified in 63.43% of the the opportunities; GAE dialect was accurately identified in 70.35% of the opportunities. Listeners identifying as AAE speakers rated GAE speech as more acceptable, whereas, listeners identifying as GAE speakers rated AAE speech as more acceptable. Neither group of listeners demonstrated a difference in intelligibility ratings. Exposure to AAE had no effect on intelligibility or acceptability ratings. Listeners can identify dialect (AAE and GAE) with a better than chance degree of accuracy. One’s dialect may have an effect on intelligibility and acceptability ratings. Exposure to a dialect did not affect listener ratings of intelligibility or acceptability.

KASP-IEva: an intelligent typing evaluation model for KASP primers.

KASP marker technology has been used in molecular marker-assisted breeding because of its high efficiency and flexibility, and an intelligent evaluation model of KASP marker primer typing results is essential to improve the efficiency of marker development on a large scale. To this end, this paper proposes a gene population delineation method based on NTC identification module and data distribution judgment module to improve the accuracy of K-Means clustering, and introduces a decision tree to construct the KASP-IEva primer typing evaluation model. The model firstly designs the NTC identification module and data distribution judgment module to extract four types of data, grouping and categorizing to achieve the improvement of the distinguishability of amplification product signals; secondly, the K-Means algorithm is used to aggregate and classify the data, to visualize the five aggregated clusters and to obtain the morphology location eigenvalues; lastly, the evaluation criteria for the typing effect level are constructed, and the logical decision tree is used to make conditional discrimination on the eigenvalues in order to realize the score prediction. The performance of the model was tested by the KASP marker typing test results of 2519 groups of cotton varieties, and the following conclusions were obtained: the model is able to visualize the aggregation and classification effects of the amplification products of NTC, pure genotypes, heterozygous genotypes, and untyped genotypes, enabling rapid and accurate KASP marker typing evaluation. Comparing and analyzing the model evaluation results with the expert evaluation results, the average accuracy rate of the four grades evaluated by the model was 87%, and the overall evaluation results showed an uneven distribution of the grades with significant differential characteristics. When evaluating 2519 KASP fractal maps, the expert evaluation consumes 15 hours, and the model evaluation only uses 8min27.45s, which makes the model intelligent evaluation significantly better than the expert evaluation from the perspective of time. The establishment of the model will further enhance the application of KASP markers in molecular marker-assisted breeding and provide technical support for the large-scale screening and identification of excellent genotypes.

A framework for quantifying individual and collective common sense

The notion of common sense is invoked so frequently in contexts as diverse as everyday conversation, political debates, and evaluations of artificial intelligence that its meaning might be surmised to be unproblematic. Surprisingly, however, neither the intrinsic properties of common sense knowledge (what makes a claim commonsensical) nor the degree to which it is shared by people (its "commonness") have been characterized empirically. In this paper, we introduce an analytical framework for quantifying both these elements of common sense. First, we define the commonsensicality of individual claims and people in terms of the latter's propensity to agree on the former and their awareness of one another's agreement. Second, we formalize the commonness of common sense as a clique detection problem on a bipartite belief graph of people and claims, defining [Formula: see text] common sense as the fraction [Formula: see text] of claims shared by a fraction [Formula: see text] of people. Evaluating our framework on a dataset of [Formula: see text] raters evaluating [Formula: see text] diverse claims, we find that commonsensicality aligns most closely with plainly worded, fact-like statements about everyday physical reality. Psychometric attributes such as social perceptiveness influence individual common sense, but surprisingly demographic factors such as age or gender do not. Finally, we find that collective common sense is rare: At most, a small fraction [Formula: see text] of people agree on more than a small fraction [Formula: see text] of claims. Together, these results undercut universalistic beliefs about common sense and raise questions about its variability that are relevant both to human and artificial intelligence.

Should left- and right-sided unilateral cleft lip and palate patients be grouped together when reporting the outcomes?

Investigate associations between cleft laterality in patients with non-syndromic unilateral cleft lip and palate (UCLP) and oral-health, dental-arch, speech, audiological, psychological and nasolabial-aesthetic outcomes. Secondary data analysis of the outcomes of 5-year-old children with non-syndromic complete UCLP identified from three studies: Cleft Collective (n = 155), Cleft Care UK (CCUK) (n = 266) and Clinical Standards Advisory Group (CSAG) study (n = 238). Outcome measures included occlusal assessment using the 5-year-old's index score, speech intelligibility rating using the CAPS-A Audit tool, audiological assessment using pure tone audiometry, nasolabial aesthetic assessment using the Asher-McDade tool, oral-health assessment using decayed, missing, filled teeth scores and parent-reported outcomes. Logistic regression with adjustment for age, sex and index-of-multiple-deprivation scores were performed. No differences were found in patient-reported outcomes between the left and right clefts in the Cleft Collective study. From the CCUK study, right clefts had poorer speech (n = 236; 95% CI 1.09, 3.42; and P = .03) and hearing outcomes (n = 211; 95% CI 1.03, 3.43; P = .04). In the CSAG study, patients with left clefts were more likely to be teased (n = 213; 95% CI 0.26, 0.85; and P = .01). Weak associations between cleft laterality, speech, hearing and psychological outcomes were found, however the findings were inconsistent across the studies. This study contributes to evidence of associations between laterality and outcomes in children born with UCLP.

The Optimization of the STOI Algorithm Parameters in Presence of the White Gaussian Noise (WGN)

The first part of the paper describes the Short Time Objective Intelligibility - STOI algorithm, which makes an objective evaluation of intelligibility, as well as an algorithm for estimating the optimal parameters of the STOI algorithm, N and . Second part of the paper, described an experiment that examines the intelligibility of the sentences formed from the Serbian Matrix Sentence Test - SMST base using: a). subjective MOS (Mean Opinion Score) test and b). objective test STOI algorithm. Subsequently, a comparative analysis of the results were made and it was determinate an analytical formula which connecting optimal pairs (N, ). Using the results of the MOS test as a reference, a mean absolute error of estimation of the STOI algorithm was determined.

Can Mandarin-speaking prelingual deaf adults benefit from cochlear implant?

Background With advances in cochlear implant (CI) technology, prelingual deaf adults may experience improved speech perception and quality of life (QoL). It is still a challenge for Mandarin-speaking CI user with tone recognition due to CI technology focused on intonation language. Objectives To evaluate the long-term post-CI auditory performance and social-emotional benefits in prelingual deaf Mandarin-speaking adults and the difference between them and post-lingual deaf adults. Material and Methods Fifty-five adult implanted ears were included (forty-six postlingual deaf group; nine prelingual deaf group). Post-CI long-term outcomes were using vowels, consonants, disyllabic words, Mandarin monosyllable words, categories of audiology performance, speech intelligibility rating, subjective social-emotional questionnaires. Results Post-CI auditory performance and speech intelligibility of prelingual deafness adults was significantly inferior to that of those with postlingual deafness. However, both groups presented improved social-emotional benefits, with no significant difference between both groups. Conclusions Adult CI recipients who deaf before the age of 4 can experience benefits in social-emotional life functioning, regardless of their limited auditory performance and speech intelligibility. Therefore, prelingual Mandarin-speaking deaf adults, especially those using oral communication, can be considered as relative indications for cochlear implantation. Significance To clarify and validate the benefits among Mandarin-speaking prelingual deaf adult recipients.

Smart Classroom: A Review and Research Agenda

The presented systematic review aims to adopt a methodological approach of providing quantitative and qualitative knowledge on the emerging notion of the smart classroom. The analysis is based on an assessment of 572 publications published in peer-reviewed journals between 2000 and 2021. Citation networks, cocitation analysis, and publishing patterns have been used to identify important research works, characterize the intellectual structure of the domains, and highlight research gaps. Bibliometric analysis is used to identify the most notable journals, authors, nations, articles, and themes, which was followed by a comprehensive analysis of various disciplines using standard terminology and taxonomy of the papers. Emerging topics including smart interaction and positive engagement, intelligent evaluation, and inter-connected physical surroundings have been explored. Following the exploration of a conceptual framework, potential topics of research have been identified. This research will assist practitioners, educators, administrators, and academic researchers in understanding the fundamentals of smart classrooms and identifying pertinent topics for future research exploration.

Simulación de niveles de hipernasalidad con actores entrenados: Una comunicación breve

ABSTRACT Purpose: to report an experience of simulation applied to a research context and assess the feasibility of using trained actors’ audio recordings to simulate nasality levels. Methods: two clinical simulation actors selected and subsequently trained to simulate three nasality levels (non-nasal, mild to moderate hypernasal and severe hypernasal), resulting in a total of 6 audios. These files were analysed through a Praat script to obtain the measures A1-P0 compensated and the first formant’s bandwidth. Afterwards, they were rated by two expert SLPs, according to their nasality and intelligibility, using perceptual scales. Results: according to A1-P0 and F1 bandwidth values in most conditions and the expert SLP’s nasality and intelligibility ratings, the actors were able to simulate the previously defined nasality levels. Final Considerations: based on the preliminary data, it can be concluded that the use of clinical simulation in experimental contexts, offering new opportunities and benefits for researchers, is feasible. In this experience, the actors were able to simulate different nasality levels corroborated by acoustic analysis and experts’ ratings.

High-capacity steganography through audio fusion and fission

<span>Information security is required for two reasons, either to conceal the information completely or to prevent the misuse of the information by adding watermarks or metadata. Audio steganography uses audio signals to hide secret information. In the proposed audio steganography technique, cover audio files and secret audio files are transformed from time domain to wavelet domain using discrete wavelet transform, the secret audio file is transformed in two levels, leading to secure and high-capacity data hiding. 1% of the 2-level compressed secret is fused to 99% of the 1-level compressed cover. “Peak signal to noise ratio and mean squared error, Pearson’s correlation coefficient, spearman’s correlation coefficient, perceptual evaluation of speech quality and short-time objective intelligibility” are considered to assess the similarity of cover audio and stego audio and similarity of secret audio embedded, and secret audio retrieved. Results show that the stego audio signal is perceptually indistinguishable from the cover audio signal. The approach also passed the robustness test.</span>

Assessing artificial intelligence and professors’ calibration in English as a foreign language writing courses at a Costa Rican public university

This article paper explores the evaluation of artificial intelligence (AI) in English as a Foreign Language (EFL) writing courses and the importance of calibration in writing evaluations. The role of calibration has received little attention in language contexts, while the role of artificial intelligence has gained increased attention in the last couple of years. This investigation, conducted from August 2022 to March 2023, involved eight TESOL students enrolled in an English as a Foreign Language (EFL) major at a Costa Rican public university, ten TESOL university professors, and one AI piece of software. It used a quantitative, quasi-experimental design, and a language elicitation data collection process. Data was collected by means of a rubric-based writing assessment. Quantitative data were analyzed using descriptive statistics. Data analyses indicate that: 1) human-created paragraphs (X̄ = 7,56) and AI writing (X̄ = 7,61) yield similar results when evaluated; 2) some criteria may favor human creativity or computer, rule-oriented writing; and 3) professors’ ratings reveal inconsistencies when grading human writing in particular. These findings demonstrate that AI matches, at least to a basic level, human writing skills. Furthermore, data show that students may be falling behind in aspects such as grammar, vocabulary, and mechanics. Finally, the analysis indicates that professors’ grading lacks consistency, and a calibration model should be incorporated as part of regular training workshops.

Strategic Integration of Artificial Intelligence in Health-care Systems: Assessing Costs, Technological Upgrades, and Training Timelines

BACKGROUND: In recent years, the evaluation of artificial intelligence (AI) in health-care sector has undergone significant growth and is substantially helpful in supporting clinical decision-making based on evidence. The primary aim of the study is to investigate the strategic integration of AI in health-care systems, specifically focusing on assessing costs, technological upgrades, and training timelines. MATERIALS AND METHODS: This study followed quantitative techniques to explore the AI integration’s importance in the systems of health care highlighting training timelines, upgradation of technology, and associated costs. Using descriptive statistics, data were evaluated and a survey was performed on the professionals of emergency medical care. The study employed a combination of descriptive statistics analysis, such as mean and median calculations, to analyze the data. To select participants, this study applied purposive sampling. The selected sample size of the study was 242 from the Indian health-care context. RESULT: The results of this study indicated that clear training timelines establishment, technological upgradation, and cost assessments are important for successfully integrating AI technologies. In addition, the discussion explored the acceptance of the significance of stakeholders’ collaboration, cost-effective strategies for training, and information technology infrastructure enhancements. The training costs for AI implementation in health care, with 66.12%–69.83% of respondents selecting “strongly agree” and 25.21%–29.75% selecting “agree.” Strong consensus on the necessity of providing specific timelines for AI implementation in emergency departments, with “strongly agree” responses ranging from 66.12% to 68.60%, and “agree” responses from 26.45% to 29.75%. Issues including timeline adherence and funding constraints were discovered, focusing on the necessity for proactive management. CONCLUSION: This research highlighted comprehensive planning’s major role in the integration of AI. Health-care organizations by addressing training timelines, technological upgradation, and cost optimize the incorporation of AI. However, engagement with different financial experts and collaboration with stakeholders are necessary for successfully achieving organizational goals.

User‐Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review

Researchers have developed a variety of approaches to evaluate explainable artificial intelligence (XAI) systems using human–computer interaction (HCI) user‐centered techniques. This systematic literature review has been conducted to understand how these approaches are used to achieve XAI goals. The aim of this review is to explore the methods used to evaluate XAI systems in studies involving human subjects. A total of 101 full‐text studies were systematically selected and analyzed from a sample of 3414 studies obtained from four renowned databases between 2018 and 2023. The analysis focuses on prominent XAI goals achieved across 10 domains and the machine learning (ML) models utilized to create these XAI systems. The analysis also explores explanation methods and detailed study methodologies used by researchers in previous work. The analysis is concluded by categorizing the challenges experienced by researchers into three types. Exploring the methodologies employed by researchers, the review discusses the benefits and shortcomings of the data collection methods and participant recruitment. In conclusion, this review offers a framework that consists of six pillars that researchers can follow for evaluating user‐centered studies in the field of XAI.

An analysis of the relationship between servant leadership and organizational citizenship behavior: The effect of emotional intelligence as a mediating role

The current study's primary goal is to ascertain the impact of servant leadership on organizational citizenship behavior as being affected by emotional intelligence as the mediating variable. This descriptive study was applied to the academic staff of private and public universities. The questionnaire was used for data collection. The dimensions of servant leadership (SL) were nine, the dimensions of emotional intelligence were nine while five dimensions of organizational citizenship behavior were used and collected from literature review. The questionnaire was distributed to 304 of the academic staff. The findings indicate a moderate degree of the servant leadership practice. Also, the evaluation of organizational citizenship behavior practice and emotional intelligence was negative in academic institutions. The results showed that servant leadership affects positively organizational citizenship behavior using emotional intelligence as a mediator. Servant leadership is very important in higher educational organizations when followed properly and affects organizational citizenship behavior by considering the emotional aspects of the academic staff.

Development and Evaluation of Competitive Intelligence Based on Export Market Orientation

Objective: This research aims to develop and evaluate competitive intelligence based on export market orientation in exemplary exporting companies. Methodology: The current study is qualitative and has been conducted using grounded theory. In this study, 15 managers, professors, and researchers in the field of exports were interviewed through semi-structured deep interviews. Subsequently, the data obtained were analyzed through open, axial, and selective coding. Utilizing the results from the theoretical foundations review and the research background and content analysis of the interviews conducted, indicators were identified to enhance export market orientation and competitive intelligence. Findings: The development model for enhancing export market orientation includes three stages of open, axial, and selective coding, comprising six main categories: causal conditions, central phenomenon, strategies, intervening conditions, and consequences of enhancing export market orientation based on the development of competitive intelligence in exemplary exporting companies. Conclusion: The final model shows that a holistic approach and attention to various aspects of export market orientation based on competitive intelligence, considering causal, contextual, and intervening conditions, are essential.

SASEGAN-TCN: Speech enhancement algorithm based on self-attention generative adversarial network and temporal convolutional network.

Traditional unsupervised speech enhancement models often have problems such as non-aggregation of input feature information, which will introduce additional noise during training, thereby reducing the quality of the speech signal. In order to solve the above problems, this paper analyzed the impact of problems such as non-aggregation of input speech feature information on its performance. Moreover, this article introduced a temporal convolutional neural network and proposed a SASEGAN-TCN speech enhancement model, which captured local features information and aggregated global feature information to improve model effect and training stability. The simulation experiment results showed that the model can achieve 2.1636 and 92.78% in perceptual evaluation of speech quality (PESQ) score and short-time objective intelligibility (STOI) on the Valentini dataset, and can accordingly reach 1.8077 and 83.54% on the THCHS30 dataset. In addition, this article used the enhanced speech data for the acoustic model to verify the recognition accuracy. The speech recognition error rate was reduced by 17.4%, which was a significant improvement compared to the baseline model experimental results.

Evaluation of artificial intelligence for detecting periapical lesions on panoramic radiographs

Background/Aim: The aim of this study is to evaluate the function of diagnostic computer software designed for the detection of periapical lesions on panoramic images with deep learning methods. Material and Methods: In our study, more than 500 adult retrospective panoramic radiography images obtained randomly were evaluated, and periapical lesions were labeled on the radiographs with the ResultLab.Ai labeling program (ResultLab.AI, Istanbul, Turkey). All images have been rechecked and verified by Oral, Dental and Maxillofacial Radiology experts. The model used is a U-Net based architecture customized for dental radiographs and optimized for fast operation. What is meant by customization is the structures called "Attention Gate" added to the architecture to draw the model's attention to the lesions. Results: Mask estimation was made separately for each image and F1 and IoU scores were calculated by comparing them with the marked masks. A list was created from the calculated F1 and IoU scores. The F1 and IoU score of the entire data set was calculated by taking the average of the values in this list. In IoU score calculation, Keras library's Mean IoU metric was used to calculate for 2 classes. In the F1 score calculation, the F1 score metric of the SKLearn library was used to calculate the unweighted average for 2 classes. As a result, the IoU-Score was obtained as 0.8578 and the F1-Score as 0.8587. Conclusions: Detection of periapical lesions on panoramic radiographs with an artificial intelligence approach will help practitioners reach definitive conclusions even in lesions that are likely to be overlooked. In addition, success rates for deep learning methods improve as data set size grows. As the number of images rises, the training models' success rates will follow.

Application and Effect Evaluation of Artificial Intelligence in We-Media Marketing

Application and Effect Evaluation of Artificial Intelligence in We-Media Marketing

A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence

A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence