Pub Date : 2023-10-21DOI: 10.5121/csit.2023.131802
Linfeng Jiang, Yuan Zhu
Single-cell RNA sequencing (scRNA-seq) determines RNA expression at single-cell resolution. It provides a powerful tool for studying immunity, regulation, and other life activities of cells. However, due to the limitations of the sequencing technique, the scRNA-seq data are represented with sparsity, which contains missing gene values, i.e., zero values, called dropout. Therefore, it is necessary to impute missing values before analyzing scRNA-seq data. However, existing imputation computation methods often only focus on the identification of technical zeros or imputing all zeros based on cell similarity. This study proposes a new method (SFAG) to reconstruct the gene expression relationship matrix by using graph regularization technology to preserve the high-dimensional manifold information of the data, and to mine the relationship between genes and cells in the data, and then uses a method of averaging the clustering results to fill in the identified technical zeros. Experimental results show that SFAG can help improve downstream analysis and reconstruct cell trajectory.
{"title":"Data Smoothing Filling Method based on ScRNA-Seq Data Zero-Value Identification","authors":"Linfeng Jiang, Yuan Zhu","doi":"10.5121/csit.2023.131802","DOIUrl":"https://doi.org/10.5121/csit.2023.131802","url":null,"abstract":"Single-cell RNA sequencing (scRNA-seq) determines RNA expression at single-cell resolution. It provides a powerful tool for studying immunity, regulation, and other life activities of cells. However, due to the limitations of the sequencing technique, the scRNA-seq data are represented with sparsity, which contains missing gene values, i.e., zero values, called dropout. Therefore, it is necessary to impute missing values before analyzing scRNA-seq data. However, existing imputation computation methods often only focus on the identification of technical zeros or imputing all zeros based on cell similarity. This study proposes a new method (SFAG) to reconstruct the gene expression relationship matrix by using graph regularization technology to preserve the high-dimensional manifold information of the data, and to mine the relationship between genes and cells in the data, and then uses a method of averaging the clustering results to fill in the identified technical zeros. Experimental results show that SFAG can help improve downstream analysis and reconstruct cell trajectory.","PeriodicalId":91205,"journal":{"name":"Artificial intelligence and applications (Commerce, Calif.)","volume":"85 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135514079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sign constraints are a handy representation of domain-specific prior knowledge that can be incorporated to machine learning. Under the sign constraints, the signs of the weight coefficients for linear predictors cannot be flipped from the ones specified in advance according to the prior knowledge. This paper presents new stochastic dual coordinate ascent (SDCA) algorithms that find the minimizer of the empirical risk under the sign constraints. Generic surrogate loss functions can be plugged into the proposed algorithm with the strong convergence guarantee inherited from the vanilla SDCA. A technical contribution of this work is the finding of an efficient algorithm that performs the SDCA update with a cost linear to the number of input features which coincides with the SDCA update without the sign constraints. Eventually, the computational cost O(nd) is achieved to attain an ϵ-accuracy solution. Pattern recognition experiments were carried out using a classification task for microbiological water quality analysis. The experimental results demonstrate the powerful prediction performance of the sign constraints.
{"title":"Stochastic Dual Coordinate Ascent for Learning Sign Constrained Linear Predictors","authors":"Miya Nakajima, Rikuto Mochida, Yuya Takada, Tsuyoshi Kato","doi":"10.5121/csit.2023.131801","DOIUrl":"https://doi.org/10.5121/csit.2023.131801","url":null,"abstract":"Sign constraints are a handy representation of domain-specific prior knowledge that can be incorporated to machine learning. Under the sign constraints, the signs of the weight coefficients for linear predictors cannot be flipped from the ones specified in advance according to the prior knowledge. This paper presents new stochastic dual coordinate ascent (SDCA) algorithms that find the minimizer of the empirical risk under the sign constraints. Generic surrogate loss functions can be plugged into the proposed algorithm with the strong convergence guarantee inherited from the vanilla SDCA. A technical contribution of this work is the finding of an efficient algorithm that performs the SDCA update with a cost linear to the number of input features which coincides with the SDCA update without the sign constraints. Eventually, the computational cost O(nd) is achieved to attain an ϵ-accuracy solution. Pattern recognition experiments were carried out using a classification task for microbiological water quality analysis. The experimental results demonstrate the powerful prediction performance of the sign constraints.","PeriodicalId":91205,"journal":{"name":"Artificial intelligence and applications (Commerce, Calif.)","volume":"33 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135514078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-21DOI: 10.5121/csit.2023.131804
Julia Koifman
It is hard to disagree that reading is one of the most important skills in learning. Children learn to read very early, and before they start school, they are supposed to be able to read. Nevertheless, some of them struggle. For instance, some of them confuse letters or may have difficulty reading comprehension, while others may have difficulty remembering, which might be the consequence of learning difficulties (LD), for instance, dyslexia, one of the most common cognitive disorders. It often affects reading and language skills. Researchers have found out that about 40 million people in the USA suffer from dyslexia, but only about 2 million of them have been diagnosed with such a disorder. At the same time, about 30% of people diagnosed with dyslexia also suffer from autism spectrum disorders (ASD) and attention deficit hyperactivity disorder (ADHD) to one degree or another
{"title":"Teaching Reading Skills More Effectively","authors":"Julia Koifman","doi":"10.5121/csit.2023.131804","DOIUrl":"https://doi.org/10.5121/csit.2023.131804","url":null,"abstract":"It is hard to disagree that reading is one of the most important skills in learning. Children learn to read very early, and before they start school, they are supposed to be able to read. Nevertheless, some of them struggle. For instance, some of them confuse letters or may have difficulty reading comprehension, while others may have difficulty remembering, which might be the consequence of learning difficulties (LD), for instance, dyslexia, one of the most common cognitive disorders. It often affects reading and language skills. Researchers have found out that about 40 million people in the USA suffer from dyslexia, but only about 2 million of them have been diagnosed with such a disorder. At the same time, about 30% of people diagnosed with dyslexia also suffer from autism spectrum disorders (ASD) and attention deficit hyperactivity disorder (ADHD) to one degree or another","PeriodicalId":91205,"journal":{"name":"Artificial intelligence and applications (Commerce, Calif.)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135514081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-21DOI: 10.5121/csit.2023.131805
Svetlana Prokopchina, Veronika Zaslavskaia
Modern measurement tasks are confronted with inherent uncertainty. This significant uncertainty arises due to incomplete and imprecise knowledge about the models of measurement objects, influencing factors, measurement conditions, and the diverse nature of experimental data. This article provides a concise overview of the historical development of methodologies aimed at intellectualizing measurement processes in the context of uncertainty. It also discusses the classification of measurements and measurement systems. Furthermore, the fundamental requirements for intelligent measurement systems and technologies are outlined. The article delves into the conceptual aspects of intelligent measurements, which are rooted in the integration of metrologically certified data and knowledge. It defines intelligent measurements and establishes their key properties. Additionally, the article explores the main characteristics of soft measurements and highlights their distinctions from traditional deterministic measurements of physical quantities. The emergence of cognitive, systemic, and global measurements as new measurement types is discussed. In this paper, we offer a comprehensive examination of the methodology and technologies underpinning Bayesian intelligent measurements, with a foundation in the regularizing Bayesian approach. This approach introduces a novel concept of measurement, where the measurement problem is framed as an inverse problem of pattern recognition, aligning with Bayesian principles. Within this framework, innovative models and coupled scales with dynamic constraints are proposed. These dynamic scales facilitate the development of measurement technologies for enhancing the cognition and interpretation of measurement results by measurement systems. This novel type of scale enables the integration of numerical data (for quantifiable information) and linguistic information (for knowledge-based information) to enhance the quality of measurement solutions. A new set of metrological characteristics for intelligent measurements is introduced, encompassing accuracy, reliability (including error levels of the 1st and 2nd kind), dependability, risk assessment, and entropy characteristics. The paper provides explicit formulas for implementing the measurement process, complete with a metrological justification of the solutions. The article concludes by outlining the advantages and prospects of employing intelligent measurements. These benefits extend to solving practical problems, as well as advancing and integrating artificial intelligence and measurement theory technologies.
{"title":"Methodology of Measurement Intellectualization based on Regularized Bayesian Approach in Uncertain Conditions","authors":"Svetlana Prokopchina, Veronika Zaslavskaia","doi":"10.5121/csit.2023.131805","DOIUrl":"https://doi.org/10.5121/csit.2023.131805","url":null,"abstract":"Modern measurement tasks are confronted with inherent uncertainty. This significant uncertainty arises due to incomplete and imprecise knowledge about the models of measurement objects, influencing factors, measurement conditions, and the diverse nature of experimental data. This article provides a concise overview of the historical development of methodologies aimed at intellectualizing measurement processes in the context of uncertainty. It also discusses the classification of measurements and measurement systems. Furthermore, the fundamental requirements for intelligent measurement systems and technologies are outlined. The article delves into the conceptual aspects of intelligent measurements, which are rooted in the integration of metrologically certified data and knowledge. It defines intelligent measurements and establishes their key properties. Additionally, the article explores the main characteristics of soft measurements and highlights their distinctions from traditional deterministic measurements of physical quantities. The emergence of cognitive, systemic, and global measurements as new measurement types is discussed. In this paper, we offer a comprehensive examination of the methodology and technologies underpinning Bayesian intelligent measurements, with a foundation in the regularizing Bayesian approach. This approach introduces a novel concept of measurement, where the measurement problem is framed as an inverse problem of pattern recognition, aligning with Bayesian principles. Within this framework, innovative models and coupled scales with dynamic constraints are proposed. These dynamic scales facilitate the development of measurement technologies for enhancing the cognition and interpretation of measurement results by measurement systems. This novel type of scale enables the integration of numerical data (for quantifiable information) and linguistic information (for knowledge-based information) to enhance the quality of measurement solutions. A new set of metrological characteristics for intelligent measurements is introduced, encompassing accuracy, reliability (including error levels of the 1st and 2nd kind), dependability, risk assessment, and entropy characteristics. The paper provides explicit formulas for implementing the measurement process, complete with a metrological justification of the solutions. The article concludes by outlining the advantages and prospects of employing intelligent measurements. These benefits extend to solving practical problems, as well as advancing and integrating artificial intelligence and measurement theory technologies.","PeriodicalId":91205,"journal":{"name":"Artificial intelligence and applications (Commerce, Calif.)","volume":"30 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135514077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-21DOI: 10.5121/csit.2023.131806
KasimuJuma Ahmed
Mean Absolute Error (MAE) and Mean Square Error (MSE) are machine learning loss functions that not only estimates the discrepancy between prediction and true label but also guide the optimal parameter of the model.Gradient is used in estimating MSE model and Sub-gradient in estimating MAE model. Batch and stochastic are two of the many variations of sub-gradient method but the former considers the entire dataset per iteration while the latter considers one data point per iteration. Batch-stochastic Sub-gradient method that learn based on the inputted data and gives stable estimated loss value than that of stochastic and memory efficient than that of batch has been developed by considering defined collection of data-point per iteration. The stability and memory efficiency of the method was tested using structured query language (SQL). The new method shows greater stability, accuracy, convergence, memory efficiencyand computational efficiency than any other existing method of finding optimal feasible parameter(s) of a continuous data.
{"title":"Batch-Stochastic Sub-Gradient Method for Solving Non-Smooth Convex Loss Function Problems","authors":"KasimuJuma Ahmed","doi":"10.5121/csit.2023.131806","DOIUrl":"https://doi.org/10.5121/csit.2023.131806","url":null,"abstract":"Mean Absolute Error (MAE) and Mean Square Error (MSE) are machine learning loss functions that not only estimates the discrepancy between prediction and true label but also guide the optimal parameter of the model.Gradient is used in estimating MSE model and Sub-gradient in estimating MAE model. Batch and stochastic are two of the many variations of sub-gradient method but the former considers the entire dataset per iteration while the latter considers one data point per iteration. Batch-stochastic Sub-gradient method that learn based on the inputted data and gives stable estimated loss value than that of stochastic and memory efficient than that of batch has been developed by considering defined collection of data-point per iteration. The stability and memory efficiency of the method was tested using structured query language (SQL). The new method shows greater stability, accuracy, convergence, memory efficiencyand computational efficiency than any other existing method of finding optimal feasible parameter(s) of a continuous data.","PeriodicalId":91205,"journal":{"name":"Artificial intelligence and applications (Commerce, Calif.)","volume":"101 7-8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135514080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.47852/bonviewaia3202660
Rasha G Mohammed Helali
Higher education is grappling with challenges from globalization. The competition between worldwide universities depends not only on the availability of infrastructure and faculty members' teaching quality, but also on their research performance. The research produced by faculty members has a significant impact on a university's standing, ability to acquire funds, and ability to enroll both domestic and international students. The objective of this paper is to identify factors affecting scientific research productivity in selected higher educational institutes. The paper reports the views of academic staff from different educational institutes on such issues as the determinants of research performance. A quantitative analysis approach, including correlation and regression, in addition to deep learning, was utilized to achieve the aim of the paper. The findings of this research demonstrate that the support of academic institutes for enhancing research and providing facilities and funds for such purpose has a great impact on research performance. The allocation of hours of scientific research to the faculty member also had a positive impact on the improvement of scientific research. Linking career promotion and scientific research encourages faculty members to publish more papers. Moreover, the level of qualification for faculty members has a great impact on their rate of publishing papers.
{"title":"An Exploratory Study of Factors Affecting Research Productivity in Higher Educational Institutes Using Regression and Deep Learning Techniques","authors":"Rasha G Mohammed Helali","doi":"10.47852/bonviewaia3202660","DOIUrl":"https://doi.org/10.47852/bonviewaia3202660","url":null,"abstract":"Higher education is grappling with challenges from globalization. The competition between worldwide universities depends not only on the availability of infrastructure and faculty members' teaching quality, but also on their research performance. The research produced by faculty members has a significant impact on a university's standing, ability to acquire funds, and ability to enroll both domestic and international students. The objective of this paper is to identify factors affecting scientific research productivity in selected higher educational institutes. The paper reports the views of academic staff from different educational institutes on such issues as the determinants of research performance. A quantitative analysis approach, including correlation and regression, in addition to deep learning, was utilized to achieve the aim of the paper. The findings of this research demonstrate that the support of academic institutes for enhancing research and providing facilities and funds for such purpose has a great impact on research performance. The allocation of hours of scientific research to the faculty member also had a positive impact on the improvement of scientific research. Linking career promotion and scientific research encourages faculty members to publish more papers. Moreover, the level of qualification for faculty members has a great impact on their rate of publishing papers.","PeriodicalId":91205,"journal":{"name":"Artificial intelligence and applications (Commerce, Calif.)","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75013070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
COVID-19 outbreak ravaged the whole world starting from the early part of 2020. The rapid spread of the pandemic accounts for the major reason the world was thrown into panic mode and pervasive confusion. However, COVID-19’s greatest strength is its virility but its severity on an individual is mostly ambiguous, which is dependent on the particular individual. This, combined with the increasingly limited capacity of the global healthcare infrastructure warrants some mechanism that can predict the prognosis of an individual to better determine if the patient would require hospital resources or be better treated as an outpatient. The lack of such a mechanism leads to suboptimal utilization of valuable hospital resources leading to unnecessary loss of life. However, often at the onset of a pandemic such as it was experienced during the outbreak of COVID-19, ample and appropriately labelled dataset to build accurate deep learning models to assist in this respect was limited. In this vein, frantic efforts were made to acquire dataset to train deep learning models for the stated objectives, unfortunately only a small dataset from a single source was available at the time of the study. Consequently, deep learning models based on the ResNet-18 architecture were trained on a small dataset of chest X-rays of patients infected with COVID-19 to predict mortality risk. The models exhibit considerable accuracy with high sensitivity. The appropriateness of the techniques proposed in this study for predictive modelling maybe particularly suited when only small datasets are available especially at the onset of similar pandemics. From existing literature, models with low complexity such as ResNet perform better with small dataset. Hence, this study utilised ResNet-18 as the baseline to evaluate the performance of other popular models on small datasets. The performance of the baseline models based on ResNet-18 with an accuracy of 0.89 compared favourably with those of the several other models including AlexNet, MobileNetV3, EfficientNetV2, SwinTransformer, and ConvNeXt using the same datasets and similar parameters.
{"title":"Covid-19 Mortality Risk Prediction Using Small Dataset of Chest X-Ray Images","authors":"Akeem Olowolayemo, Wafaa Khazaal Shams, Abubakar Yagoub Ibrahim Omer, Yasin Mohammed, Raashid Salih Batha","doi":"10.47852/bonviewaia3202819","DOIUrl":"https://doi.org/10.47852/bonviewaia3202819","url":null,"abstract":"COVID-19 outbreak ravaged the whole world starting from the early part of 2020. The rapid spread of the pandemic accounts for the major reason the world was thrown into panic mode and pervasive confusion. However, COVID-19’s greatest strength is its virility but its severity on an individual is mostly ambiguous, which is dependent on the particular individual. This, combined with the increasingly limited capacity of the global healthcare infrastructure warrants some mechanism that can predict the prognosis of an individual to better determine if the patient would require hospital resources or be better treated as an outpatient. The lack of such a mechanism leads to suboptimal utilization of valuable hospital resources leading to unnecessary loss of life. However, often at the onset of a pandemic such as it was experienced during the outbreak of COVID-19, ample and appropriately labelled dataset to build accurate deep learning models to assist in this respect was limited. In this vein, frantic efforts were made to acquire dataset to train deep learning models for the stated objectives, unfortunately only a small dataset from a single source was available at the time of the study. Consequently, deep learning models based on the ResNet-18 architecture were trained on a small dataset of chest X-rays of patients infected with COVID-19 to predict mortality risk. The models exhibit considerable accuracy with high sensitivity. The appropriateness of the techniques proposed in this study for predictive modelling maybe particularly suited when only small datasets are available especially at the onset of similar pandemics. From existing literature, models with low complexity such as ResNet perform better with small dataset. Hence, this study utilised ResNet-18 as the baseline to evaluate the performance of other popular models on small datasets. The performance of the baseline models based on ResNet-18 with an accuracy of 0.89 compared favourably with those of the several other models including AlexNet, MobileNetV3, EfficientNetV2, SwinTransformer, and ConvNeXt using the same datasets and similar parameters.","PeriodicalId":91205,"journal":{"name":"Artificial intelligence and applications (Commerce, Calif.)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135440530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.47852/bonviewaia3202751
Andy E. Williams
In this paper, we present an analysis of ChatGPT, a language model developed by OpenAI, through the lens of Human-Centric Functional Modeling (HCFM). ChatGPT is designed to interact through a chat interface in a conversational manner, with the ability to answer follow-up questions, admit mistakes, challenge incorrect premises, and reject inappropriate requests. Since HCFM is hypothesized to provide a functional model for assessing the existence and magnitude of general problem-solving ability (intelligence), and since according to ChatGPT itself HCFM is the only such functional model in existence, the purpose of the paper is to demonstrate the usefulness of HCFM in determining whether an AI like ChatGPT is an AGI. Using Human-Centric Functional Modeling, we aim to determine whether ChatGPT exhibits narrow problem-solving ability, classifying it as an artificial intelligence (AI), or whether it exhibits general problem-solving ability, classifying it as AGI. We also consider the magnitude of ChatGPT's problem-solving ability within the conceptual space defined by HCFM. Finally, this paper also explores the issue from the perspective of the “collective social brain” hypothesis, which predicts which AI behavior the majority of humans will find to be intelligent, as well as predicting that true machine intelligence lies outside such narrow human definitions of intelligent behavior.
{"title":"Has OpenAI Achieved Artificial General Intelligence in ChatGPT?","authors":"Andy E. Williams","doi":"10.47852/bonviewaia3202751","DOIUrl":"https://doi.org/10.47852/bonviewaia3202751","url":null,"abstract":"In this paper, we present an analysis of ChatGPT, a language model developed by OpenAI, through the lens of Human-Centric Functional Modeling (HCFM). ChatGPT is designed to interact through a chat interface in a conversational manner, with the ability to answer follow-up questions, admit mistakes, challenge incorrect premises, and reject inappropriate requests. Since HCFM is hypothesized to provide a functional model for assessing the existence and magnitude of general problem-solving ability (intelligence), and since according to ChatGPT itself HCFM is the only such functional model in existence, the purpose of the paper is to demonstrate the usefulness of HCFM in determining whether an AI like ChatGPT is an AGI. Using Human-Centric Functional Modeling, we aim to determine whether ChatGPT exhibits narrow problem-solving ability, classifying it as an artificial intelligence (AI), or whether it exhibits general problem-solving ability, classifying it as AGI. We also consider the magnitude of ChatGPT's problem-solving ability within the conceptual space defined by HCFM. Finally, this paper also explores the issue from the perspective of the “collective social brain” hypothesis, which predicts which AI behavior the majority of humans will find to be intelligent, as well as predicting that true machine intelligence lies outside such narrow human definitions of intelligent behavior.","PeriodicalId":91205,"journal":{"name":"Artificial intelligence and applications (Commerce, Calif.)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135357604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.47852/bonviewaia3202441
Kavita Bhosle, Vijaya Musande
Devanagari character and digit recognition are a difficult undertaking because writing style depends on a person’s traits and differs from person to person. We get more precise results in digit recognition, thanks to deep learning convolutional neural networks (CNNs), which function similarly to the human brain. In this study, the CNN method was put into practice and contrasted with the feed-forward neural network and random forest approaches. In comparison to previous methods, CNN has reportedly provided an accuracy rating of up to 99.2%. CNN is effective with both organized and unstructured data, including pictures, video, and audio.
{"title":"Evaluation of Deep Learning CNN Model for Recognition of Devanagari Digit","authors":"Kavita Bhosle, Vijaya Musande","doi":"10.47852/bonviewaia3202441","DOIUrl":"https://doi.org/10.47852/bonviewaia3202441","url":null,"abstract":"Devanagari character and digit recognition are a difficult undertaking because writing style depends on a person’s traits and differs from person to person. We get more precise results in digit recognition, thanks to deep learning convolutional neural networks (CNNs), which function similarly to the human brain. In this study, the CNN method was put into practice and contrasted with the feed-forward neural network and random forest approaches. In comparison to previous methods, CNN has reportedly provided an accuracy rating of up to 99.2%. CNN is effective with both organized and unstructured data, including pictures, video, and audio.","PeriodicalId":91205,"journal":{"name":"Artificial intelligence and applications (Commerce, Calif.)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135534454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Classification of arbitrary moving objects including vehicles and human beings in a real environment (such as protected and sensitive areas) is challenging due to arbitrary deformation and directions caused by shaky camera and wind. This work aims at adopting a spatio-temporal approach for classifying arbitrarily moving objects. The intuition to propose the approach is that the behavior of the arbitrary moving objects caused by wind and shaky camera are inconsistent and unstable while for static objects, the behavior is consistent and stable. The proposed method segments foreground objects from background using the frame difference between median frame and individual frame. This step outputs several different foreground information. The method finds static and dynamic edges by subtracting Canny of foreground information from the Canny edges of respective input frames. The ratio of the number of static and dynamic edges of each frame is considered as features. The features are normalized to avoid the problems of imbalanced feature size and irrelevant features. For classification, the work uses 10-fold cross-validation to choose the number of training and testing samples and the random forest classifier is used for the final classification of frames with static objects and arbitrary movement objects. For evaluating the proposed method, we construct our own dataset, which contains video of static and arbitrarily moving objects caused by shaky camera and wind. The results on the video dataset show that the proposed method achieves the state-of-the-art performance (76% classification rate) which is 14% better than the best existing method.
{"title":"Spatiotemporal Edges for Arbitrarily Moving Video Classification in Protected and Sensitive Scenes","authors":"Maryam Asadzadehkaljahi, Arnab Halder, Umapada Pal, Palaiahnakote Shivakumara","doi":"10.47852/bonviewaia3202526","DOIUrl":"https://doi.org/10.47852/bonviewaia3202526","url":null,"abstract":"Classification of arbitrary moving objects including vehicles and human beings in a real environment (such as protected and sensitive areas) is challenging due to arbitrary deformation and directions caused by shaky camera and wind. This work aims at adopting a spatio-temporal approach for classifying arbitrarily moving objects. The intuition to propose the approach is that the behavior of the arbitrary moving objects caused by wind and shaky camera are inconsistent and unstable while for static objects, the behavior is consistent and stable. The proposed method segments foreground objects from background using the frame difference between median frame and individual frame. This step outputs several different foreground information. The method finds static and dynamic edges by subtracting Canny of foreground information from the Canny edges of respective input frames. The ratio of the number of static and dynamic edges of each frame is considered as features. The features are normalized to avoid the problems of imbalanced feature size and irrelevant features. For classification, the work uses 10-fold cross-validation to choose the number of training and testing samples and the random forest classifier is used for the final classification of frames with static objects and arbitrary movement objects. For evaluating the proposed method, we construct our own dataset, which contains video of static and arbitrarily moving objects caused by shaky camera and wind. The results on the video dataset show that the proposed method achieves the state-of-the-art performance (76% classification rate) which is 14% better than the best existing method.","PeriodicalId":91205,"journal":{"name":"Artificial intelligence and applications (Commerce, Calif.)","volume":"218 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135534597","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：