166,075 results
Search Results
2. Content-based quality evaluation of scientific papers using coarse feature and knowledge entity network
- Author
-
Zhongyi Wang, Haoxuan Zhang, Haihua Chen, Yunhe Feng, and Junhua Ding
- Subjects
Paper quality evaluation ,Knowledge entity ,Network analysis ,Machine learning ,Novelty ,Structural entropy ,Electronic computers. Computer science ,QA75.5-76.95 - Abstract
Pre-evaluating scientific paper quality aids in alleviating peer review pressure and fostering scientific advancement. Although prior studies have identified numerous quality-related features, their effectiveness and representativeness of paper content remain to be comprehensively investigated. Addressing this issue, we propose a content-based interpretable method for pre-evaluating the quality of scientific papers. Firstly, we define quality attributes of computer science (CS) papers as integrity, clarity, novelty, and significance, based on peer review criteria from 11 top-tier CS conferences. We formulate the problem as two classification tasks: Accepted/Disputed/Rejected (ADR) and Accepted/Rejected (AR). Subsequently, we construct fine-grained features from metadata and knowledge entity networks, including text structure, readability, references, citations, semantic novelty, and network structure. We empirically evaluate our method using the ICLR paper dataset, achieving optimal performance with the Random Forest model, yielding F1 scores of 0.715 and 0.762 for the two tasks, respectively. Through feature analysis and case studies employing SHAP interpretable methods, we demonstrate that the proposed features enhance the performance of machine learning models in scientific paper quality evaluation, offering interpretable evidence for model decisions.
- Published
- 2024
- Full Text
- View/download PDF
3. 'Paper, Meet Code': A Deep Learning Approach to Linking Scholarly Articles With GitHub Repositories
- Author
-
Prahyat Puangjaktha, Morakot Choetkiertikul, and Suppawong Tuarob
- Subjects
Academic code repository mining ,paper-repository relationship ,text representation ,machine learning ,Electrical engineering. Electronics. Nuclear engineering ,TK1-9971 - Abstract
Computer scientists often publish their source code accompanying their publications, prominently using code repositories across various domains. Despite the concurrent existence of scholarly articles and their associated official code repositories, explicit references linking the two are often missing. Traditionally, identifying whether scholarly content and code repositories pertain to the same research project requires manual inspection, a time-consuming task. This paper proposes a deep learning-based algorithm for automatically matching scholarly articles with their corresponding official code repositories. Our findings indicate that the most common linking information includes the paper title and BibTeX entries, typically found in the repository’s readme document. In this study, we employed SPECTER for vector embedding of paper and repository metadata. Utilizing these embedding representations with the Light Gradient Boosting Machine (LGBM), our method achieved an F1 score of 0.94. Moreover, combining our best model with a rule-based approach improved performance by 5.31%. This study successfully delineates a connection between academic papers and associated official code repositories, minimizing reliance on explicit bibliographic information in repositories.
- Published
- 2024
- Full Text
- View/download PDF
4. Text-based paper-level classification procedure for non-traditional sciences using a machine learning approach
- Author
-
Moctezuma, Daniela, López-Vázquez, Carlos, Lopes, Lucas, Trevisan, Norton, and Pérez, José
- Published
- 2024
- Full Text
- View/download PDF
5. Development of Paper Temperature Prediction Method in Electrophotographic Processes by Using Machine Learning and Thermal Network Model.
- Author
-
Takamasa Hase, Takumi Ishikura, Shinichi Kuramoto, Koichi Kato, and Kazuyoshi Fushinobu
- Subjects
MACHINE learning ,THERMOPHYSICAL properties ,THERMAL conductivity ,THERMAL properties ,TEMPERATURE ,SPECIFIC heat - Abstract
Since the fusing process in electrophotography has a significant impact not only on printing quality but also on machine internal temperature and toner blocking on outlet tray, accurate paper temperature prediction for various types of papers is essential, especially in the production printing. To develop the thermophysical model of fusing process to predict the paper temperature after the fusing process, thermal properties such as thermal conductivity, specific heat, and thermal contact resistance of several types of papers are necessary. However, paper is composed of complex fiber, surface coating, filler, and moisture, making it difficult to measure thermophysical properties of paper accurately. This work developed a machine learning (ML) model that can predict the thermophysical properties of paper based on a conventionally used 1D thermal network model of the fusing process and experiment results. The thermophysical properties of each paper obtained by ML and the thermophysical properties obtained by the conventional method were input to the thermal network model to predict the paper temperature after the fusing process and compared with the measured paper temperatures of the experiment. The results showed that the paper temperature was predicted with higher accuracy by using thermophysical properties obtained by ML than that by the conventional method. Although the method for predicting paper temperature by using only ML had been proposed, it had the disadvantage of requiring a large number of training experiments. In contrast, this method trained under the conditions of one fusing temperature and two printing speeds, and was able to predict under five fusing temperatures and four printing speeds. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
6. Research Progress and Prospect of Condition Assessment Techniques for Oil–Paper Insulation Used in Power Systems: A Review.
- Author
-
Jiang, Zaijun, Li, Xin, Zhang, Heng, Zhang, Enze, Liu, Chuying, Fan, Xianhao, and Liu, Jiefeng
- Subjects
ELECTRICAL injuries ,ADSORPTION isotherms ,MACHINE learning ,GAS analysis ,RATIO analysis - Abstract
Oil–paper insulation is the critical insulation element in the modern power system. Under a harsh operating environment, oil–paper insulation will deteriorate gradually, resulting in electrical accidents. Thus, it is important to evaluate and monitor the insulation state of oil–paper insulation. Firstly, this paper introduces the geometric structure and physical components of oil–paper insulation and shows the main reasons and forms of oil–paper insulation's degradation. Then, this paper reviews the existing condition assessment techniques for oil–paper insulation, such as the dissolved gas ratio analysis, aging kinetic model, cellulose–water adsorption isotherm, oil–paper moisture balance curve, and dielectric response technique. Additionally, the advantages and limitations of the above condition assessment techniques are discussed. In particular, this paper highlights the dielectric response technique and introduces its evaluation principle in detail: (1) collecting the dielectric response data, (2) extracting the feature parameters from the collected dielectric response data, and (3) establishing the condition assessment models based on the extracted feature parameters and the machine learning techniques. Finally, two full potential studies are proposed, which research hotspots' oil–paper insulation and the electrical–chemical joint evaluation technique. In summary, this paper concludes the principles, advantages and limitation of the existing condition assessment techniques for oil–paper insulation, and we put forward two potential research avenues. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
7. Prediction of Values of Borsa Istanbul Forest, Paper, and Printing Index Using Machine Learning Methods
- Author
-
İlker Akyüz, Kinyas Polat, Selahattin Bardak, and Nadir Ersen
- Subjects
machine learning ,forest industry ,index prediction ,xkagt ,Biotechnology ,TP248.13-248.65 - Abstract
It is difficult to predict index values or stock prices with a single financial formula. They are affected by many factors, such as political conditions, global economy, unexpected events, market anomalies, and the characteristics of the relevant companies, and many computer science techniques are being used to make more accurate predictions about them. This study aimed to predict the values of the XKAGT index by using the monthly closing values of the Borsa Istanbul (BIST) Forestry, Paper and Printing (XKAGT) index between 2002 and 2023, and the machine learning techniques artificial neural networks (ANN), random forest (RF), k-nearest neighbor (KNN), and gradient boosting machine (GBM). Furthermore, the performances of four machine learning techniques were compared. Factors affecting stock prices are generally classified as macroeconomic and microeconomic factors. As a result of examining the studies on determining the macroeconomic factors affecting the stock markets, 10 macroeconomic factors were determined as input. The macroeconomic variables used were crude oil price, exchange rate of USD/TRY, dollar index, BIST100 index, gold price, money supply (M2), S&P 500 index, US 10-year bond interest, export-import coverage rate in the forest products sector, and deposits interest rate. It was determined that all machine learning techniques used in the study performed successfully in predicting the index value, but the k-nearest neighbor algorithm showed the best performance with R2=0.996, RMSE=71.36, and a MAE of 40.8. Therefore, in line with the current variables, investors can make analyzes using any of the ANN, RF, KNN, and GBM techniques to predict the future index value, which will lead them to accurate results.
- Published
- 2024
8. Assessment of Published Papers on the Use of Machine Learning in Diagnosis and Treatment of Mastitis.
- Author
-
Bourganou, Maria V., Kiouvrekis, Yiannis, Chatzopoulos, Dimitrios C., Zikas, Sotiris, Katsafadou, Angeliki I., Liagka, Dimitra V., Vasileiou, Natalia G. C., Fthenakis, George C., and Lianou, Daphne T.
- Subjects
MACHINE learning ,ARTIFICIAL intelligence ,SUPPORT vector machines ,COMPUTERS in agriculture ,MASTITIS - Abstract
The present study is an evaluation of published papers on machine learning as employed in mastitis research. The aim of this study was the quantitative evaluation of the scientific content and the bibliometric details of these papers. In total, 69 papers were found to combine machine learning in mastitis research and were considered in detail. There was a progressive yearly increase in published papers, which originated from 23 countries (mostly from China or the United States of America). Most original articles (n = 59) referred to work involving cattle, relevant to mastitis in individual animals. Most articles described work related to the development and diagnosis of the infection. Fewer articles described work on the antibiotic resistance of pathogens isolated from cases of mastitis and on the treatment of the infection. In most studies (98.5% of published papers), supervised machine learning models were employed. Most frequently, decision trees and support vector machines were employed in the studies described. 'Machine learning' and 'mastitis' were the most frequently used keywords. The papers were published in 39 journals, with most frequent publications in Computers and Electronics in Agriculture and Journal of Dairy Science. The median number of cited references in the papers was 39 (interquartile range: 31). There were 435 co-authors in the papers (mean: 6.2 per paper, median: 5, min.–max.: 1–93) and 356 individual authors. The median number of citations received by the papers was 4 (min.–max.: 0–70). Most papers (72.5%) were published in open-access mode. This study summarized the characteristics of papers on mastitis and artificial intelligence. Future studies could explore using these methodologies at farm level, and extending them to other animal species, while unsupervised learning techniques might also prove to be useful. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
9. Cover papers of top journals are reliable source for emerging topics detection: a machine learning based prediction framework
- Author
-
Wei, Wenjie, Liu, Hongxu, and Sun, Zhuanlan
- Published
- 2022
- Full Text
- View/download PDF
10. Research Paper Screening Tool: Automating Conference Paper Evaluation and Enhancement.
- Author
-
Rathnasiri, Hansani Upeksha, Ishara Lakshani, L. A., Amarasinghe, Nipuni Nilakna, Dissanayake, Oshan Asinda, Nawinna, Dasuni, and Attanayaka, Buddima
- Subjects
TECHNOLOGICAL innovations ,ARTIFICIAL neural networks ,MACHINE learning ,ARTIFICIAL intelligence ,NATURAL language processing - Abstract
In this era of knowledge, academic researchers are growing every day, this also spikes a growth in published literature on the new innovations and findings. This leads to a problem where the reviewers at the conferences must go through many research papers to determine whether they are suitable for the conference or not. This problem has caused the necessity of an effective paper screening tool for optimizing the literature review process. This research presents a development of a new Paper Screening Tool (PST) aimed at increasing the efficiency and accuracy of the literature screening phase. Leveraging the NPL processing techniques this PST and reduces a lot of manual efforts. Through comprehensive evaluation using a diverse dataset, the tools provide high precision. The PST also has user friendly interfaces and customizable report generation which empowers the researchers screening process to their specific needs. This paper contributes to literature by solving the challenge of information overloading during the literature review. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
11. Intelligent Detection and Odor Recognition of Cigarette Packaging Paper Boxes Based on a Homemade Electronic Nose
- Author
-
Xingguo Wang, Hao Li, Yunlong Wang, Bo Fu, and Bin Ai
- Subjects
electronic nose ,gas sensor array ,cigarette packaging paper ,odor detection ,machine learning ,Mechanical engineering and machinery ,TJ1-1570 - Abstract
The printing process of box packaging paper can generate volatile organic compounds, resulting in odors that impact product quality and health. An efficient, objective, and cost-effective detection method is urgently needed. We utilized a self-developed electronic nose system to test four different cigarette packaging paper samples. Employing multivariate statistical methods like Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Statistical Quality Control (SQC), and Similarity-based Independent Modeling of Class Analogy (SIMCA), we analyzed and processed the collected data. Comprehensive evaluation and quality control models were constructed to assess sample stability and distinguish odors. Results indicate that our electronic nose system rapidly detects odors and effectively performs quality control. By establishing models for quality stability control, we successfully identified samples with acceptable quality and those with odors. To further validate the system’s performance and extend its applications, we collected two types of cigarette packaging paper samples with odor data. Using data augmentation techniques, we expanded the dataset and achieved an accuracy rate of 0.9938 through classification and discrimination. This highlights the significant potential of our self-developed electronic nose system in recognizing cigarette packaging paper odors and odorous samples.
- Published
- 2024
- Full Text
- View/download PDF
12. Review paper on research direction towards cancer prediction and prognosis using machine learning and deep learning models
- Author
-
Murthy, Nimmagadda Satyanarayana and Bethala, Chaitanya
- Published
- 2023
- Full Text
- View/download PDF
13. Classification Analysis of Copy Papers Using Infrared Spectroscopy and Machine Learning Modeling
- Author
-
Yong-Ju Lee, Tai-Ju Lee, and Hyoung Jin Kim
- Subjects
attenuated-total-reflection infrared spectroscopy (atr-ir) ,partial least squares-discriminant analysis (pls-da) ,support vector machine (svm) ,k-nearest neighbor (knn) ,machine learning ,document forgery ,forensic document analysis ,Biotechnology ,TP248.13-248.65 - Abstract
The evaluation and classification of chemical properties in different copy-paper products could significantly help address document forgery. This study analyzes the feasibility of utilizing infrared spectroscopy in conjunction with machine learning algorithms for classifying copy-paper products. A dataset comprising 140 infrared spectra of copy-paper samples was collected. The classification models employed in this study include partial least squares-discriminant analysis, support vector machine, and K-nearest neighbors. The key findings indicate that a classification model based on the use of attenuated-total-reflection infrared spectroscopy demonstrated good performance, highlighting its potential as a valuable tool in accurately classifying paper products and ensuring assisting in solving criminal cases involving document forgery.
- Published
- 2023
14. Assessment of Published Papers on the Use of Machine Learning in Diagnosis and Treatment of Mastitis
- Author
-
Maria V. Bourganou, Yiannis Kiouvrekis, Dimitrios C. Chatzopoulos, Sotiris Zikas, Angeliki I. Katsafadou, Dimitra V. Liagka, Natalia G. C. Vasileiou, George C. Fthenakis, and Daphne T. Lianou
- Subjects
algorithm ,artificial intelligence ,cattle ,machine learning ,mammary infection ,mastitis ,Information technology ,T58.5-58.64 - Abstract
The present study is an evaluation of published papers on machine learning as employed in mastitis research. The aim of this study was the quantitative evaluation of the scientific content and the bibliometric details of these papers. In total, 69 papers were found to combine machine learning in mastitis research and were considered in detail. There was a progressive yearly increase in published papers, which originated from 23 countries (mostly from China or the United States of America). Most original articles (n = 59) referred to work involving cattle, relevant to mastitis in individual animals. Most articles described work related to the development and diagnosis of the infection. Fewer articles described work on the antibiotic resistance of pathogens isolated from cases of mastitis and on the treatment of the infection. In most studies (98.5% of published papers), supervised machine learning models were employed. Most frequently, decision trees and support vector machines were employed in the studies described. ‘Machine learning’ and ‘mastitis’ were the most frequently used keywords. The papers were published in 39 journals, with most frequent publications in Computers and Electronics in Agriculture and Journal of Dairy Science. The median number of cited references in the papers was 39 (interquartile range: 31). There were 435 co-authors in the papers (mean: 6.2 per paper, median: 5, min.–max.: 1–93) and 356 individual authors. The median number of citations received by the papers was 4 (min.–max.: 0–70). Most papers (72.5%) were published in open-access mode. This study summarized the characteristics of papers on mastitis and artificial intelligence. Future studies could explore using these methodologies at farm level, and extending them to other animal species, while unsupervised learning techniques might also prove to be useful.
- Published
- 2024
- Full Text
- View/download PDF
15. Detection of fake papers in the era of artificial intelligence.
- Author
-
Dadkhah, Mehdi, Oermann, Marilyn H., Hegedüs, Mihály, Raman, Raghu, and Dávid, Lóránt Dénes
- Subjects
- *
ARTIFICIAL intelligence , *MACHINE learning , *DECISION trees , *PAPER mills - Abstract
Paper mills, companies that write scientific papers and gain acceptance for them, then sell authorships of these papers, present a key challenge in medicine and other healthcare fields. This challenge is becoming more acute with artificial intelligence (AI), where AI writes the manuscripts and then the paper mills sell the authorships of these papers. The aim of the current research is to provide a method for detecting fake papers. The method reported in this article uses a machine learning approach to create decision trees to identify fake papers. The data were collected from Web of Science and multiple journals in various fields. The article presents a method to identify fake papers based on the results of decision trees. Use of this method in a case study indicated its effectiveness in identifying a fake paper. This method to identify fake papers is applicable for authors, editors, and publishers across fields to investigate a single paper or to conduct an analysis of a group of manuscripts. Clinicians and others can use this method to evaluate articles they find in a search to ensure they are not fake articles and instead report actual research that was peer reviewed prior to publication in a journal. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
16. Paper‐Based Wearable Patches for Real‐Time, Quantitative Lactate Monitoring
- Author
-
Elisabetta Ruggeri, Giusy Matzeu, Andrea Vergine, Giuseppe De Nicolao, and Fiorenzo G. Omenetto
- Subjects
colorimetric sensors ,lactate ,machine learning ,silk fibroin ,wearable interfaces ,Technology (General) ,T1-995 ,Science - Abstract
Abstract Wearable sensors are establishing themselves as options for real‐time continuous health monitoring in health care and wellness. In particular, the use of flexible interfaces that conform to the skin have attracted considerable interest for the extraction of meaningful pathophysiological information through continuous and painless sampling and analysis of biofluids. In contrast, conventional techniques for biomarkers analysis are difficult to adapt to real‐time portable monitoring due to their invasive sampling protocols, biosample preparation and reagent stabilization. Here a shelf‐stable, non‐invasive, paper‐based colorimetric wearable lactate sensor is reported. This sensor exploits the ability of silk to control the concentration, print, and functionally preserve labile transducing biomolecules in the format of a shelf‐stable digital patch for optical readout. This novel approach overcomes major challenges associated with the commercialization of colorimetric wearable sensors (e.g., enzyme thermal instability, narrow sensing range, low sensitivity, and qualitative response) by showing a combination of unprecedented stability (i.e., up to 2 years in refrigerated conditions), wide sensing range, and high sensitivity. Additionally, real‐time quantitative signal readouts are achieved using machine learning‐driven image analysis enabling physiological status evaluation with a simple smartphone camera.
- Published
- 2024
- Full Text
- View/download PDF
17. Advanced imaging for earlier diagnosis and morbidity prevention in multiple myeloma: A British Society of Haematology and UK Myeloma Society Good Practice Paper.
- Author
-
Kaiser, Martin, Goh, Vicky, Stern, Simon, Spencer, Nicholas, Rabin, Neil, Ramasamy, Karthik, Lawless, Sarah, Soutar, Richard, Ashcroft, John, Pratt, Guy, Messiou, Christina, and Bygrave, Ceri
- Subjects
- *
MULTIPLE myeloma , *COMORBIDITY , *EARLY diagnosis , *MACHINE learning , *HEMATOLOGY - Abstract
Summary This Good Practice Paper provides recommendations for the use of advanced imaging for earlier diagnosis and morbidity prevention in multiple myeloma. It describes how advanced imaging contributes to optimal healthcare resource utilisation by in newly diagnosed and relapsed myeloma, and provides a perspective on future directions of myeloma imaging, including machine learning assisted reporting. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
18. Prediction of Values of Borsa Istanbul Forest, Paper, and Printing Index Using Machine Learning Methods.
- Author
-
Akyüz, İlker, Polat, Kinyas, Bardak, Selahattin, and Ersen, Nadir
- Subjects
- *
ARTIFICIAL neural networks , *STOCK price indexes , *GOLD sales & prices , *STOCK index futures , *MONEY supply - Abstract
It is difficult to predict index values or stock prices with a single financial formula. They are affected by many factors, such as political conditions, global economy, unexpected events, market anomalies, and the characteristics of the relevant companies, and many computer science techniques are being used to make more accurate predictions about them. This study aimed to predict the values of the XKAGT index by using the monthly closing values of the Borsa Istanbul (BIST) Forestry, Paper and Printing (XKAGT) index between 2002 and 2023, and the machine learning techniques artificial neural networks (ANN), random forest (RF), k-nearest neighbor (KNN), and gradient boosting machine (GBM). Furthermore, the performances of four machine learning techniques were compared. Factors affecting stock prices are generally classified as macroeconomic and microeconomic factors. As a result of examining the studies on determining the macroeconomic factors affecting the stock markets, 10 macroeconomic factors were determined as input. The macroeconomic variables used were crude oil price, exchange rate of USD/TRY, dollar index, BIST100 index, gold price, money supply (M2), S&P 500 index, US 10-year bond interest, export-import coverage rate in the forest products sector, and deposits interest rate. It was determined that all machine learning techniques used in the study performed successfully in predicting the index value, but the k-nearest neighbor algorithm showed the best performance with R2=0.996, RMSE=71.36, and a MAE of 40.8. Therefore, in line with the current variables, investors can make analyzes using any of the ANN, RF, KNN, and GBM techniques to predict the future index value, which will lead them to accurate results. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
19. Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT
- Author
-
Slart, Riemer H. J. A., Williams, Michelle C., Juarez-Orozco, Luis Eduardo, Rischpler, Christoph, Dweck, Marc R., Glaudemans, Andor W. J. M., Gimelli, Alessia, Georgoulias, Panagiotis, Gheysens, Olivier, Gaemperli, Oliver, Habib, Gilbert, Hustinx, Roland, Cosyns, Bernard, Verberne, Hein J., Hyafil, Fabien, Erba, Paola A., Lubberink, Mark, Slomka, Piotr, Išgum, Ivana, Visvikis, Dimitris, Kolossváry, Márton, and Saraste, Antti
- Published
- 2021
- Full Text
- View/download PDF
20. User Behavior Analysis for Detecting Compromised User Accounts: A Review Paper
- Author
-
Jurišić M., Tomičić I., and Grd P.
- Subjects
machine learning ,account takeover ,ato ,user behavior analysis ,literature review ,Cybernetics ,Q300-390 - Abstract
The rise of online transactions has led to a corresponding increase in online criminal activities. Account takeover attacks, in particular, are challenging to detect, and novel approaches utilize machine learning to identify compromised accounts. This paper aims to conduct a literature review on account takeover detection and user behavior analysis within the cybersecurity domain. By exploring these areas, the goal is to combat account takeovers and other fraudulent attempts effectively.
- Published
- 2023
- Full Text
- View/download PDF
21. Do papers (really) match journals’ “aims and scope”? A computational assessment of innovation studies
- Author
-
Santos, Ana Teresa and Mendonça, Sandro
- Published
- 2022
- Full Text
- View/download PDF
22. The 100 most influential papers in medical artificial intelligence; a bibliometric analysis
- Author
-
Fatima Zahoor, Muhammad Abdullah, Muhammad Waleed Tahir, and Asif Islam
- Subjects
Artificial intelligence ,Machine learning ,Computer reasoning ,Machine intelligence ,Medicine - Abstract
Objective: To assess the current trends in the field of artificial intelligence in medicine by analysing 100 most cited original articles relevant to the field. Methods: The systematic review was conducted in September 2022, and comprised literature search on Scopus database for original articles only. Google and Medical Subject Headings databases were used as resources to extract key words. In order to cover a broad range of articles, original studies comprising human as well as non-human subjects, studies without abstract and studies in languages other than English were part of the inclusion criteria. There was no specific time period applied to the search and no specific selection was done regarding the journals in the database. The screening was done using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines to extract the top 100 most cited articles in the field of artificial intelligence usage in medicine. Data was analysed using SPSS 23. Results: Of the 11,571 studies identified, 100(0.86%) were analysed in detail. The studies were published between 1986 and 2021, with a median of 43 citations (IQR 53) per article. The journal ‘Artificial Intelligence in Medicine’ accounted for the highest number 9(9%)) of articles, and the United States was the country of origin for most of the articles 36(36%). Conclusion: The trends, development and shortcomings in field of artificial intelligence usage in medicine need to be understood to conduct an effective research in areas that still need attention, and to guide the authorities to direct their funding accordingly.
- Published
- 2024
- Full Text
- View/download PDF
23. Centrifugal Pump Reliability Improvement in the Pulp and Paper Industry.
- Author
-
Shabane, Nontuthuko, Makhanya, Bheki B. S., and Pretorius, Jan-Harm
- Subjects
PAPER industry ,CENTRIFUGAL pumps ,PRODUCTION losses ,MAINTENANCE ,MACHINE learning ,LUBRICATION & lubricants ,TRAINING - Abstract
South African pulp and paper mills have encountered frequent breakdowns of centrifugal pumps, resulting in considerable production losses. A case study was conducted to determine the factors contributing to these failures and devise ways to enhance pump reliability. Data were collected through questionnaires and operational records. The study revealed that inadequate maintenance, misalignment of pump components, lack of lubrication, improper baseplate installation, subpar sealing arrangements, inadequate design of the pumping system, and foreign materials entering the system were the primary causes of pump failure. To improve reliability, this study suggests employing machine learning methods to select the optimal maintenance strategy and provide internal maintenance personnel with training in condition monitoring systems. This will enable both pulp and paper mills and pump manufacturers to identify blind spots and improve the dependability of centrifugal pumps. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
24. An Overview of Machine Learning in Orthopedic Surgery: An Educational Paper.
- Author
-
Padash, Sirwa, Mickley, John P., Vera Garcia, Diana V., Nugen, Fred, Khosravi, Bardia, Erickson, Bradley J., Wyles, Cody C., and Taunton, Michael J.
- Abstract
The growth of artificial intelligence combined with the collection and storage of large amounts of data in the electronic medical record collection has created an opportunity for orthopedic research and translation into the clinical environment. Machine learning (ML) is a type of artificial intelligence tool well suited for processing the large amount of available data. Specific areas of ML frequently used by orthopedic surgeons performing total joint arthroplasty include tabular data analysis (spreadsheets), medical imaging processing, and natural language processing (extracting concepts from text). Previous studies have discussed models able to identify fractures in radiographs, identify implant type in radiographs, and determine the stage of osteoarthritis based on walking analysis. Despite the growing popularity of ML, there are limitations including its reliance on "good" data, potential for overfitting, long life cycle for creation, and ability to only perform one narrow task. This educational article will further discuss a general overview of ML, discussing these challenges and including examples of successfully published models. [Display omitted] [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
25. An Approach to Automate the Scientific Paper's Evaluation Based on NLP Technologies: the Experience in the Russian Segment of Financial Technologies Field.
- Author
-
Terentieva, Elena, Zheltova, Kristina, and Dukhanov, Alexey
- Subjects
MACHINE learning ,FINANCIAL technology ,LANGUAGE models - Abstract
This paper reflects the research to design and application the complex method to evaluate the quality of the paper written in the IMRaD format. As a field we choose Russian segment of the financial technologies area since we had interest to use multilingual language model. The method covers paper's relevance to the chosen field and internal topics, the actuality, relation between parts, text borrowing, and experiment part. The clustering and classifying algorithms, and language machine learning model were used. The experimental part based on corpus of Russian papers shows the deviation of method's recommendations from expert opinion not more than 20%. The results may be interested not only reviewers but student as authors of futures papers to avoid common mistakes during paper's writing. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
26. Rapid segmentation and sensitive analysis of CRP with paper-based microfluidic device using machine learning
- Author
-
Ning, Qihong, Zheng, Wei, Xu, Hao, Zhu, Armando, Li, Tangan, Cheng, Yuemeng, Feng, Shaoqing, Wang, Li, Cui, Daxiang, and Wang, Kan
- Published
- 2022
- Full Text
- View/download PDF
27. The Future of Heritage Science and Technologies: Papers from Florence Heri-Tech 2022.
- Author
-
Furferi, Rocco, Colombini, Maria Perla, Seymour, Kate, Pelagotti, Anna, and Gherardini, Francesco
- Subjects
- *
GEOGRAPHIC information systems , *SCIENTIFIC literature , *SPECTRAL imaging , *ARTIFICIAL intelligence , *ULTRASONIC testing , *WORLD Heritage Sites , *MACHINE learning - Abstract
The article discusses the potential of advanced technologies in the field of cultural heritage. It highlights how these technologies, such as virtual reality, artificial intelligence, and 3D printing, can be used to understand, preserve, and enhance cultural heritage. The article also presents scientific papers from the Florence Heri-Tech International Conference, showcasing the various applications of these technologies. The papers cover topics such as the use of hyperspectral imaging for hieroglyph recognition, the enhancement of user experience in cultural spaces through advanced systems, and the use of non-invasive techniques for conservation. Overall, the article emphasizes the significant impact of technology on the research, preservation, and promotion of cultural heritage. [Extracted from the article]
- Published
- 2024
- Full Text
- View/download PDF
28. ElmNet: a benchmark dataset for generating headlines from Persian papers
- Author
-
Shenassa, Mohammad E. and Minaei-Bidgoli, Behrouz
- Published
- 2022
- Full Text
- View/download PDF
29. ChatGPT and scientific papers in veterinary neurology; is the genie out of the bottle?
- Author
-
Samira Abani, Holger Andreas Volk, Steven De Decker, Joe Fenn, Clare Rusbridge, Marios Charalambous, Rita Goncalves, Rodrigo Gutierrez-Quintana, Shenja Loderstedt, Thomas Flegel, Carlos Ros, Thilo von Klopmann, Henning Christian Schenk, Marion Kornberg, Nina Meyerhoff, Andrea Tipold, and Jasmin Nicole Nessler
- Subjects
ChatGPT ,artificial intelligence (AI) ,machine learning ,generative AI ,scientific writing ,ethics ,Veterinary medicine ,SF600-1100 - Published
- 2023
- Full Text
- View/download PDF
30. Intelligent Detection and Odor Recognition of Cigarette Packaging Paper Boxes Based on a Homemade Electronic Nose.
- Author
-
Wang, Xingguo, Li, Hao, Wang, Yunlong, Fu, Bo, and Ai, Bin
- Subjects
ODORS ,ELECTRONIC noses ,CIGARETTE packaging ,CARTONS ,FISHER discriminant analysis ,ELECTRONIC systems - Abstract
The printing process of box packaging paper can generate volatile organic compounds, resulting in odors that impact product quality and health. An efficient, objective, and cost-effective detection method is urgently needed. We utilized a self-developed electronic nose system to test four different cigarette packaging paper samples. Employing multivariate statistical methods like Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Statistical Quality Control (SQC), and Similarity-based Independent Modeling of Class Analogy (SIMCA), we analyzed and processed the collected data. Comprehensive evaluation and quality control models were constructed to assess sample stability and distinguish odors. Results indicate that our electronic nose system rapidly detects odors and effectively performs quality control. By establishing models for quality stability control, we successfully identified samples with acceptable quality and those with odors. To further validate the system's performance and extend its applications, we collected two types of cigarette packaging paper samples with odor data. Using data augmentation techniques, we expanded the dataset and achieved an accuracy rate of 0.9938 through classification and discrimination. This highlights the significant potential of our self-developed electronic nose system in recognizing cigarette packaging paper odors and odorous samples. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
31. Advancement in Paper-Based Electrochemical Biosensing and Emerging Diagnostic Methods.
- Author
-
Benjamin, Stephen Rathinaraj, de Lima, Fábio, Nascimento, Valter Aragão do, de Andrade, Geanne Matos, and Oriá, Reinaldo Barreto
- Subjects
THREE-dimensional printing ,POINT-of-care testing ,MACHINE learning ,MACHINE tools ,BIOSENSORS ,MACHINE theory - Abstract
The utilization of electrochemical detection techniques in paper-based analytical devices (PADs) has revolutionized point-of-care (POC) testing, enabling the precise and discerning measurement of a diverse array of (bio)chemical analytes. The application of electrochemical sensing and paper as a suitable substrate for point-of-care testing platforms has led to the emergence of electrochemical paper-based analytical devices (ePADs). The inherent advantages of these modified paper-based analytical devices have gained significant recognition in the POC field. In response, electrochemical biosensors assembled from paper-based materials have shown great promise for enhancing sensitivity and improving their range of use. In addition, paper-based platforms have numerous advantageous characteristics, including the self-sufficient conveyance of liquids, reduced resistance, minimal fabrication cost, and environmental friendliness. This study seeks to provide a concise summary of the present state and uses of ePADs with insightful commentary on their practicality in the field. Future developments in ePADs biosensors include developing novel paper-based systems, improving system performance with a novel biocatalyst, and combining the biosensor system with other cutting-edge tools such as machine learning and 3D printing. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
32. One-Dimensional Convolutional Neural Networks with Infrared Spectroscopy for Classifying the Origin of Printing Paper.
- Author
-
Sung-Wook Hwang, Geungyong Park, Jinho Kim, Kwang-Ho Kang, and Won-Hee Lee
- Subjects
- *
CONVOLUTIONAL neural networks , *INFRARED spectroscopy , *SUPPORT vector machines , *MACHINE learning - Abstract
Herein, the challenge of accurately classifying the manufacturing origin of printing paper, including continent, country, and specific product, was addressed. One-dimensional convolutional neural network (1D CNN) models trained on infrared (IR) spectrum data acquired from printing paper samples were used for the task. The preprocessing of the IR spectra through a second-derivative transformation and the restriction of the spectral range to 1800 to 1200 cm-1 improved the classification performance of the model. The outcomes were highly promising. Models trained on second-derivative IR spectra in the 1800 to 1200-cm-1 range exhibited perfect classification for the manufacturing continent and country, with an impressive F1 score of 0.980 for product classification. Notably, the developed 1D CNN model outperformed traditional machine learning classifiers, such as support vector machines and feed-forward neural networks. In addition, the application of data point attribution enhanced the transparency of the decision-making process of the model, offering insights into the spectral patterns that affect classification. This study makes a considerable contribution to printing paper classification, with potential implications for accurate origin identification in various fields. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
33. SENSOR FOR AN AUTOMATIC MEASUREMENT OF MECHANICAL PROPERTIES OF RECOVERED PAPER OBJECTS
- Author
-
KREBS, Tobias and SCHABEL, Samuel
- Subjects
automation ,machine learning ,mechanical properties ,paper object classification ,recovered paper ,sensor technology ,recovered paper quality ,Engineering (General). Civil engineering (General) ,TA1-2040 ,Electronic computers. Computer science ,QA75.5-76.95 - Abstract
Recovered paper is the most important raw material for paper industry today and paper industry is one of the forerunners of circular economy. However, despite the long history with recycling the characterization of recovered paper quality is still not solved sufficiently. Here the automatic classification of paper objects can bring significant progress. Up to now, most technical approaches use NIR sensors and visual cameras, which can only “see” the surface of the objects. This often leads to misclassifications, since, for example, many packages look like graphic papers due to their printed surface. To improve these challenging classification tasks, sensors for mechanical properties of the paper objects can make an important contribution. In this paper, an automatic sensor is presented which can measure force characteristics when penetrating paper objects with specially shaped measuring tips. These force characteristics show good correlations to the mechanical properties determined in the laboratory according to standardized methods.
- Published
- 2020
- Full Text
- View/download PDF
34. Comparison of Different Features and Neural Networks for Predicting Industrial Paper Press Condition.
- Author
-
Rodrigues, João Antunes, Farinha, José Torres, Mendes, Mateus, Mateus, Ricardo J. G., and Cardoso, António J. Marques
- Subjects
- *
MACHINE learning , *PAPER pulp , *ELECTRIC currents , *ARTIFICIAL neural networks - Abstract
Forecasting has extreme importance in industry due to the numerous competitive advantages that it provides, allowing to foresee what might happen and adjust management decisions accordingly. Industries increasingly use sensors, which allow for large-scale data collection. Big datasets enable training, testing and application of complex predictive algorithms based on machine learning models. The present paper focuses on predicting values from sensors installed on a pulp paper press, using data collected over three years. The variables analyzed are electric current, pressure, temperature, torque, oil level and velocity. The results of XGBoost and artificial neural networks, with different feature vectors, are compared. They show that it is possible to predict sensor data in the long term and thus predict the asset's behaviour several days in advance. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
35. Unveiling Recent Trends in Biomedical Artificial Intelligence Research: Analysis of Top-Cited Papers
- Author
-
Benjamin S. Glicksberg and Eyal Klang
- Subjects
AI ,machine learning ,multiomics ,medical imaging ,personal medicine ,health informatics ,Technology ,Engineering (General). Civil engineering (General) ,TA1-2040 ,Biology (General) ,QH301-705.5 ,Physics ,QC1-999 ,Chemistry ,QD1-999 - Abstract
This review analyzes the most influential artificial intelligence (AI) studies in health and life sciences from the past three years, delineating the evolving role of AI in these fields. We identified and analyzed the top 50 cited articles on AI in biomedicine, revealing significant trends and thematic categorizations, including Drug Development, Real-World Clinical Implementation, and Ethical and Regulatory Aspects, among others. Our findings highlight a predominant focus on AIs application in clinical settings, particularly in diagnostics, telemedicine, and medical education, accelerated by the COVID-19 pandemic. The emergence of AlphaFold marked a pivotal moment in protein structure prediction, catalyzing a cascade of related research and signifying a broader shift towards AI-driven approaches in biological research. The review underscores AIs pivotal role in disease subtyping and patient stratification, facilitating a transition towards more personalized medicine strategies. Furthermore, it illustrates AIs impact on biology, particularly in parsing complex genomic and proteomic data, enhancing our capabilities to disentangle complex, interconnected molecular processes. As AI continues to permeate the health and life sciences, balancing its rapid technological advancements with ethical stewardship and regulatory vigilance will be crucial for its sustainable and effective integration into healthcare and research.
- Published
- 2024
- Full Text
- View/download PDF
36. Increased Accuracy on Image Classification of Game Rock Paper Scissors using CNN
- Author
-
Muhammad Nur Ichsan, Nur Armita, Agus Eko Minarno, Fauzi Dwi Setiawan Sumadi, and Hariyady
- Subjects
cnn ,deep learning ,image classification ,machine learning ,neural network ,Systems engineering ,TA168 ,Information technology ,T58.5-58.64 - Abstract
Rock Paper Scissors is one of the most popular games in the world, because of their easy and simple way to play among young and elderly people. The point of this game is to do the draw or just to find out who loses or wins. The pandemic conditions made people unable to meet face-to-face and could only play this game virtually. To carry out this activity in a virtual way, this research facilitates a model in the form of image classification to distinguish the hand gestures s in the form of rock, paper, and scissors. This classification process utilizes the Convolutional Neural Network (CNN) method. This method is one type of artificial neural network in terms of image classification. CNN uses three stages, namely convolutional layer, pooling layer, and fully connected layer. The implementation of this method for hand gesture classification in the form of rock, scissors, and paper images in this study shows an increased average accuracy towards the previous study from 97.66% to 99%.
- Published
- 2022
- Full Text
- View/download PDF
37. COVID-19 disease diagnosis from paper-based ECG trace image data using a novel convolutional neural network model
- Author
-
Irmak, Emrah
- Published
- 2022
- Full Text
- View/download PDF
38. Factors associating with or predicting more cited or higher quality journal articles: An Annual Review of Information Science and Technology (ARIST) paper.
- Author
-
Kousha, Kayvan and Thelwall, Mike
- Subjects
- *
ABSTRACTING , *PUBLISHING , *READABILITY (Literary style) , *SERIAL publications , *METADATA , *BIBLIOGRAPHY , *CONFERENCES & conventions , *REGRESSION analysis , *MACHINE learning , *CITATION analysis , *INFORMATION science , *BIBLIOGRAPHICAL citations , *INTERPROFESSIONAL relations , *PERIODICAL articles , *IMPACT factor (Citation analysis) , *INFORMATION technology , *ABSTRACTING & indexing services , *MEDICAL research - Abstract
Identifying factors that associate with more cited or higher quality research may be useful to improve science or to support research evaluation. This article reviews evidence for the existence of such factors in article text and metadata. It also reviews studies attempting to estimate article quality or predict long‐term citation counts using statistical regression or machine learning for journal articles or conference papers. Although the primary focus is on document‐level evidence, the related task of estimating the average quality scores of entire departments from bibliometric information is also considered. The review lists a huge range of factors that associate with higher quality or more cited research in some contexts (fields, years, journals) but the strength and direction of association often depends on the set of papers examined, with little systematic pattern and rarely any cause‐and‐effect evidence. The strongest patterns found include the near universal usefulness of journal citation rates, author numbers, reference properties, and international collaboration in predicting (or associating with) higher citation counts, and the greater usefulness of citation‐related information for predicting article quality in the medical, health and physical sciences than in engineering, social sciences, arts, and humanities. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
39. Classification Analysis of Copy Papers Using Infrared Spectroscopy and Machine Learning Modeling.
- Author
-
Yong-Ju Lee, Tai-Ju Lee, and Hyoung Jin Kim
- Subjects
- *
MACHINE learning , *INFRARED spectroscopy , *ATTENUATED total reflectance , *FORGERY , *K-nearest neighbor classification , *SUPPORT vector machines , *NEAR infrared spectroscopy - Abstract
The evaluation and classification of chemical properties in different copypaper products could significantly help address document forgery. This study analyzes the feasibility of utilizing infrared spectroscopy in conjunction with machine learning algorithms for classifying copy-paper products. A dataset comprising 140 infrared spectra of copy-paper samples was collected. The classification models employed in this study include partial least squares-discriminant analysis, support vector machine, and K-nearest neighbors. The key findings indicate that a classification model based on the use of attenuated-total-reflection infrared spectroscopy demonstrated good performance, highlighting its potential as a valuable tool in accurately classifying paper products and ensuring assisting in solving criminal cases involving document forgery. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
40. Phishing Website Detection Using Several Machine Learning Algorithms: A Review Paper
- Author
-
Alexander M. Veach and Munther Abualkibash
- Subjects
artificial intelligence ,data science ,machine learning ,phishing ,Information technology ,T58.5-58.64 ,Computer engineering. Computer hardware ,TK7885-7895 - Abstract
Phishing is one of the major web social engineering attacks. This has led to demand for a better way to predict and stop them in a commercial environment. This paper seeks to understand the research done in the field and analyse the next steps forward. This is done by focusing on what goes into the selection of proper features, from manual selection to the use of Genetic Algorithms such as ADABoost and MultiBoost. Then a look into the classifiers in use, Neural Networks and Ensemble algorithms which were prominent alongside some novel approaches. This information is then processed into a framework for cloud-based and client-based phishing website detection, alongside suggestions for possible future research and experiments that could help progress the field.
- Published
- 2022
- Full Text
- View/download PDF
41. State of the art paper: Cardiac computed tomography of the left atrium in atrial fibrillation.
- Author
-
Bodagh, Neil, Williams, Michelle C., Vickneson, Keeran, Gharaviri, Ali, Niederer, Steven, and Williams, Steven E.
- Abstract
The clinical spectrum of atrial fibrillation means that a patient-individualized approach is required to ensure optimal treatment. Cardiac computed tomography can accurately delineate atrial structure and function and could contribute to a personalized care pathway for atrial fibrillation patients. The imaging modality offers excellent spatial resolution and has been utilised in pre-, peri- and post-procedural care for patients with atrial fibrillation. Advances in temporal resolution, acquisition times and analysis techniques suggest potential expanding roles for cardiac computed tomography in the future management of patients with atrial fibrillation. The aim of the current review is to discuss the use of cardiac computed tomography in atrial fibrillation in pre-, peri- and post-procedural settings. Potential future applications of cardiac computed tomography including atrial wall thickness assessment and epicardial fat volume quantification are discussed together with emerging analysis techniques including computational modelling and machine learning with attention paid to how these developments may contribute to a personalized approach to atrial fibrillation management. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
42. Paper quality enhancement and model prediction using machine learning techniques
- Author
-
T. Kalavathi Devi, E.B. Priyanka, and P. Sakthivel
- Subjects
Moisture ,Weight ,Caliper ,Steam ,Machine learning ,Error ,Technology - Abstract
A machine learning approach demonstrated in the proposed study predicts the parameters involved in paper quality enhancement in real time. To control the steam pressure during paper manufacture, machine learning algorithms have been used to model different parameters such as moisture, caliper, and weight (grammage). The training and testing data sets were obtained to develop several machine learning models through several data from the parameters of the paper-making process. The inputs considered were moisture, weight, and grammage. As a result, the developed model showed better results by showing less execution time, fewer error values such as root mean squared error, mean squared error, mean absolute error, and R squared score. In addition, modeling was carried out based on model interpretation and cross-validation results, showing that the developed model could be a more useful tool in predicting the performance of the steam pressure and input parameters in the paper-making process. A comparison of results shows that the k-Nearest Neighbor algorithm outperforms the other machine learning techniques. Machine learning is also used to predict the efficiency of steam pressure reduction.
- Published
- 2023
- Full Text
- View/download PDF
43. A Graph-Based Topic Modeling Approach to Detection of Irrelevant Citations.
- Author
-
Pham, Phu, Le, Hieu, Tam, Nguyen Thanh, and Tran, Quang-Dieu
- Subjects
NATURAL language processing ,DEEP learning ,MACHINE learning ,INFORMATION retrieval - Abstract
In the recent years, the academic paper influence analysis has been widely studied due to its potential applications in the multiple areas of science information metric and retrieval. By identifying the academic influence of papers, authors, etc., we can directly support researchers to easily reach academic papers. These recommended candidate papers are not only highly relevant with their desired research topics but also highly-attended by the research community within these topics. For very recent years, the rapid developments of academic networks, like Google Scholar, Research Gate, CiteSeerX, etc., have significantly boosted the number of new published papers annually. It also helps to strengthen the borderless cooperation between researchers who are interested on the same research topics. However, these current academic networks still lack the capabilities of provisioning researchers deeper into most-influenced papers. They also largely ignore quite/irrelevant papers, which are not fully related with their current interest topics. Moreover, the distributions of topics within these academic papers are considered as varying and it is difficult to extract the main concentrated topics in these papers. Thus, it leads to challenges for researchers to find their appropriated/high-qualified reference resources while doing researches. To overcome this limitation, in this paper, we proposed a novel approach of paper influence analysis through their content-based and citation relationship-based analyses within the biographical network. In order to effectively extract the topic-based relevance from papers, we apply the integrated graph-based citation relationship analysis with topic modeling approach to automatically learn the distributions of keyword-based labeled topics in forms of unsupervised learning approach, named as TopCite. Then, we base on the constructed graph-based paper–topic structure to identify their relevancy levels. Upon the identified relevancy levels between papers, we can support for improving the accuracy performance of other bibliographic network mining tasks, such as paper similarity measurement, recommendation, etc. Extensive experiments in real-world AMiner bibliographic dataset demonstrate the effectiveness of our proposed ideas in this paper. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
44. SMIAltmetric: A comprehensive metric for evaluating social media impact of scientific papers on Twitter (X).
- Author
-
Wang, Zuzheng, Lu, Yongxu, Zhou, Yuanyuan, and Ji, Jiaojiao
- Subjects
MACHINE learning ,SOCIAL impact ,SCHOLARLY communication ,SOCIAL classes ,ALTMETRICS ,SOCIAL media - Abstract
• A new indicator, SMIAltmetric, for measuring scientific paper's social media impact. • Key impact factors: Followers, retweets, mentions, and Citation. • SMIAltmetric outperforms Altmetric in finer differentiation. The rise of social media has significantly influenced scholarly communication, knowledge dissemination, and research evaluation, leading to the enrichment of alternative metrics (altmetrics) for evaluating academic papers' social impact, which assesses the social impact of academic papers through online activities, including reading, bookmarking, downloading, and commenting. However, these altmetrics often focus on the number of mentions on social media rather than thoroughly evaluating the source, content, and dissemination of these mentions. To address this gap, this study introduces the social media impact altmetric (SMIAltmetric), which is based on 44,087 publications and 860,680 tweets (now "posts"), a comprehensive scoring system for evaluating scientific papers on Twitter (now "X"), using diverse features, including literature-related, social media engagement-related, user-related, and content-related features. Employing Altmetric Attention Acores (AAS) as labels, we tested eight machine learning algorithms, with XGBoost demonstrating the highest accuracy at 0.8672. Crucial factors influencing SMIAltmetric, as identified by the SHAP value, were followers, retweets, mentions, and citation. Furthermore, consistency analysis and convergent validation between the proposed SMIAltmetric and AAS confirm the reliability and finer differentiation of SMIAltmetric. The proposed SMIAltmetric provides a more comprehensive understanding of a paper's social media impact, enhancing the evaluation of scientific discourse and its engagement with society. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
45. Content-based quality evaluation of scientific papers using coarse feature and knowledge entity network.
- Author
-
Wang, Zhongyi, Zhang, Haoxuan, Chen, Haihua, Feng, Yunhe, and Ding, Junhua
- Subjects
MACHINE learning ,SCIENCE education ,COMPUTER science ,PEER pressure ,RANDOM forest algorithms - Abstract
Pre-evaluating scientific paper quality aids in alleviating peer review pressure and fostering scientific advancement. Although prior studies have identified numerous quality-related features, their effectiveness and representativeness of paper content remain to be comprehensively investigated. Addressing this issue, we propose a content-based interpretable method for pre-evaluating the quality of scientific papers. Firstly, we define quality attributes of computer science (CS) papers as integrity , clarity , novelty , and significance , based on peer review criteria from 11 top-tier CS conferences. We formulate the problem as two classification tasks: Accepted/Disputed/Rejected (ADR) and Accepted/Rejected (AR). Subsequently, we construct fine-grained features from metadata and knowledge entity networks, including text structure, readability, references, citations, semantic novelty, and network structure. We empirically evaluate our method using the ICLR paper dataset, achieving optimal performance with the Random Forest model, yielding F1 scores of 0.715 and 0.762 for the two tasks, respectively. Through feature analysis and case studies employing SHAP interpretable methods, we demonstrate that the proposed features enhance the performance of machine learning models in scientific paper quality evaluation, offering interpretable evidence for model decisions. • Define four criteria for quality evaluation of scientific papers: integrity, clarity, novelty, and significance. • Propose a framework for quality evaluation of scientific papers based on coarse features and knowledge entity network. • An effective algorithm for measuring the novelty and significance of scientific papers based on knowledge entity networks. • Create and release a rigorous dataset, which could serve as the gold standard for quality evaluation of scientific papers. • Conduct extensive experiments to validate the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
46. Attribute-based quality classification of academic papers
- Author
-
Nakatoh, Tetsuya, Hirokawa, Sachio, Minami, Toshiro, Nanri, Takeshi, and Funamori, Miho
- Published
- 2018
- Full Text
- View/download PDF
47. PaperNet: A Dataset and Benchmark for Fine-Grained Paper Classification
- Author
-
Tan Yue, Yong Li, Xuzhao Shi, Jiedong Qin, Zijiao Fan, and Zonghai Hu
- Subjects
artificial intelligence application ,dataset ,multi-modal information processing ,machine learning ,paper classification ,Technology ,Engineering (General). Civil engineering (General) ,TA1-2040 ,Biology (General) ,QH301-705.5 ,Physics ,QC1-999 ,Chemistry ,QD1-999 - Abstract
Document classification is an important area in Natural Language Processing (NLP). Because a huge amount of scientific papers have been published at an accelerating rate, it is beneficial to carry out intelligent paper classifications, especially fine-grained classification for researchers. However, a public scientific paper dataset for fine-grained classification is still lacking, so the existing document classification methods have not been put to the test. To fill this vacancy, we designed and collected the PaperNet-Dataset that consists of multi-modal data (texts and figures). PaperNet 1.0 version contains hierarchical categories of papers in the fields of computer vision (CV) and NLP, 2 coarse-grained and 20 fine-grained (7 in CV and 13 in NLP). We ran current mainstream models on the PaperNet-Dataset, along with a multi-modal method that we propose. Interestingly, none of these methods reaches an accuracy of 80% in fine-grained classification, showing plenty of room for improvement. We hope that PaperNet-Dataset will inspire more work in this challenging area.
- Published
- 2022
- Full Text
- View/download PDF
48. Data-driven microstructure sensitivity study of fibrous paper materials
- Author
-
Binbin Lin, Yang Bai, and Bai-Xiang Xu
- Subjects
Paper fiber network ,Structure-property relation ,Cohesive zone finite element simulation ,Machine learning ,Sensitivity study ,Materials of engineering and construction. Mechanics of materials ,TA401-492 - Abstract
Nowadays, Machine Learning (ML) model of the structure-property relation based on large data from reliable physical models becomes a new and promising approach for material design. The present work demonstrates such approach to examine the variation in microstructure features on mechanical properties of paper materials. After the generation of a “big” dataset of fiber network samples, morphological feature data, including interfiber contact properties were extracted and statistically evaluated. By performing cohesive finite element simulations, the mechanical properties including failure strain, effective stiffness, and maximal stress of fiber networks under tensile test were determined and served along with structural feature data for the ML analysis. Gradient Boosting method achieved a performance score of approx. 0.9 for all mechanical properties of such complex fibrous structure. It was found that “disorderness” represented by the variation of fiber network orientation and the mean contact area size to be the most influential factors to the failure strain and effective stiffness. Whereas the failure strength was driven by the homogeneous distribution of the contact areas. The results validated the strong orientation dependence of fibrous materials in experimental observations and enlighten the importance of sensitivity as feature parameters and the striking potential of ML for material optimization.
- Published
- 2021
- Full Text
- View/download PDF
49. Deep Learning for 3D Reconstruction, Augmentation, and Registration: A Review Paper.
- Author
-
Vinodkumar, Prasoon Kumar, Karabulut, Dogus, Avots, Egils, Ozcinar, Cagri, and Anbarjafari, Gholamreza
- Subjects
- *
DEEP learning , *COMPUTER vision , *GRAPH neural networks , *ARTIFICIAL intelligence , *MACHINE learning , *GENERATIVE adversarial networks - Abstract
The research groups in computer vision, graphics, and machine learning have dedicated a substantial amount of attention to the areas of 3D object reconstruction, augmentation, and registration. Deep learning is the predominant method used in artificial intelligence for addressing computer vision challenges. However, deep learning on three-dimensional data presents distinct obstacles and is now in its nascent phase. There have been significant advancements in deep learning specifically for three-dimensional data, offering a range of ways to address these issues. This study offers a comprehensive examination of the latest advancements in deep learning methodologies. We examine many benchmark models for the tasks of 3D object registration, augmentation, and reconstruction. We thoroughly analyse their architectures, advantages, and constraints. In summary, this report provides a comprehensive overview of recent advancements in three-dimensional deep learning and highlights unresolved research areas that will need to be addressed in the future. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
50. Special Invited Paper. Additive Logistic Regression: A Statistical View of Boosting: Discussion
- Author
-
Buhlmann, Peter and Yu, Bin
- Published
- 2000
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.