Pub Date : 2023-08-01DOI: 10.4230/LIPIcs.TIME.2021.9
L. Bozzelli, A. Montanari, A. Peron, P. Sala
In this paper, we establish Pspace-completeness of the finite satisfiability and model checking problems for the fragment of Halpern and Shoham interval logic with modality ⟨E⟩, for the “suffix” relation on pairs of intervals, and modality ⟨D⟩, for the “sub-interval” relation, under the homogeneity assumption. The result significantly improves the Expspace upper bound recently established for the same fragment, and proves the rather surprising fact that the complexity of the considered problems does not change when we add either the modality for suffixes (⟨E⟩) or, symmetrically, the modality for prefixes (⟨B⟩) to the logic of sub-intervals (featuring only ⟨D⟩). 2012 ACM Subject Classification Theory of computation → Logic and verification
{"title":"Pspace-Completeness of the Temporal Logic of Sub-Intervals and Suffixes","authors":"L. Bozzelli, A. Montanari, A. Peron, P. Sala","doi":"10.4230/LIPIcs.TIME.2021.9","DOIUrl":"https://doi.org/10.4230/LIPIcs.TIME.2021.9","url":null,"abstract":"In this paper, we establish Pspace-completeness of the finite satisfiability and model checking problems for the fragment of Halpern and Shoham interval logic with modality ⟨E⟩, for the “suffix” relation on pairs of intervals, and modality ⟨D⟩, for the “sub-interval” relation, under the homogeneity assumption. The result significantly improves the Expspace upper bound recently established for the same fragment, and proves the rather surprising fact that the complexity of the considered problems does not change when we add either the modality for suffixes (⟨E⟩) or, symmetrically, the modality for prefixes (⟨B⟩) to the logic of sub-intervals (featuring only ⟨D⟩). 2012 ACM Subject Classification Theory of computation → Logic and verification","PeriodicalId":13622,"journal":{"name":"Inf. Comput.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82537677","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}
The success of an organization hinges upon the effective utilization of its human resources, which serves as a crucial developmental factor and competitive advantage, and sets the organization apart from others. Evaluating staff productivity involves considering various dimensions, notably structural, behavioral, and circumferential factors. These factors collectively form a three-pronged model that comprehensively encompasses the facets of an organization. However, assessing the productivity of employees poses challenges, due to the inherent complexity of the humanities domain. Fuzzy logic offers a sound approach to address this issue, employing its rationale and leveraging a fuzzy inference system (FIS) as a sophisticated toolbox for measuring productivity. Fuzzy inference systems enhance the flexibility, speed, and adaptability in soft computation. Likewise, their applications, integration, hybridization, and adaptation are also introduced. They also provide an alternative solution to deal with imprecise data. In this study, we endeavored to identify and measure the productivity of human resources within a case study, by developing an alternative framework known as an FIS. Our findings provided evidence to support the validity of the alternative approach. Thus, the utilized approach for assessing employee productivity may provide managers and businesses with a more realistic asset.
{"title":"Employee Productivity Assessment Using Fuzzy Inference System","authors":"M. Nikmanesh, A. Feili, S. Sorooshian","doi":"10.3390/info14070423","DOIUrl":"https://doi.org/10.3390/info14070423","url":null,"abstract":"The success of an organization hinges upon the effective utilization of its human resources, which serves as a crucial developmental factor and competitive advantage, and sets the organization apart from others. Evaluating staff productivity involves considering various dimensions, notably structural, behavioral, and circumferential factors. These factors collectively form a three-pronged model that comprehensively encompasses the facets of an organization. However, assessing the productivity of employees poses challenges, due to the inherent complexity of the humanities domain. Fuzzy logic offers a sound approach to address this issue, employing its rationale and leveraging a fuzzy inference system (FIS) as a sophisticated toolbox for measuring productivity. Fuzzy inference systems enhance the flexibility, speed, and adaptability in soft computation. Likewise, their applications, integration, hybridization, and adaptation are also introduced. They also provide an alternative solution to deal with imprecise data. In this study, we endeavored to identify and measure the productivity of human resources within a case study, by developing an alternative framework known as an FIS. Our findings provided evidence to support the validity of the alternative approach. Thus, the utilized approach for assessing employee productivity may provide managers and businesses with a more realistic asset.","PeriodicalId":13622,"journal":{"name":"Inf. Comput.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80520663","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}
Wen-Chang Cheng, Hung-Chou Hsiao, Yung-Fa Huang, Li-Hua Li
This research proposes a single network model architecture for mask face recognition using the FaceNet training method. Three pre-trained convolutional neural networks of different sizes are combined, namely InceptionResNetV2, InceptionV3, and MobileNetV2. The models are augmented by connecting an otherwise fully connected network with a SoftMax output layer. We combine triplet loss and categorical cross-entropy loss to optimize the training process. In addition, the learning rate of the optimizer is dynamically updated using the cosine annealing mechanism, which improves the convergence of the model during training. Mask face recognition (MFR) experimental results on a custom MASK600 dataset show that proposed InceptionResNetV2 and InceptionV3 use only 20 training epochs, and MobileNetV2 uses only 50 training epochs, but to achieve more than 93% accuracy than the previous works of MFR with annealing. In addition to reaching a practical level, it saves time for training models and effectively reduces energy costs.
{"title":"Combining Classifiers for Deep Learning Mask Face Recognition","authors":"Wen-Chang Cheng, Hung-Chou Hsiao, Yung-Fa Huang, Li-Hua Li","doi":"10.3390/info14070421","DOIUrl":"https://doi.org/10.3390/info14070421","url":null,"abstract":"This research proposes a single network model architecture for mask face recognition using the FaceNet training method. Three pre-trained convolutional neural networks of different sizes are combined, namely InceptionResNetV2, InceptionV3, and MobileNetV2. The models are augmented by connecting an otherwise fully connected network with a SoftMax output layer. We combine triplet loss and categorical cross-entropy loss to optimize the training process. In addition, the learning rate of the optimizer is dynamically updated using the cosine annealing mechanism, which improves the convergence of the model during training. Mask face recognition (MFR) experimental results on a custom MASK600 dataset show that proposed InceptionResNetV2 and InceptionV3 use only 20 training epochs, and MobileNetV2 uses only 50 training epochs, but to achieve more than 93% accuracy than the previous works of MFR with annealing. In addition to reaching a practical level, it saves time for training models and effectively reduces energy costs.","PeriodicalId":13622,"journal":{"name":"Inf. Comput.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81669049","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}
Muhammad Alfian, Umi Laili Yuhana, E. Pardede, Akbar Noto Ponco Bimantoro
Assessment is one benchmark in measuring students’ abilities. However, assessment results cannot necessarily be trusted, because students sometimes cheat or even guess in answering the questions. Therefore, to obtain valid results, it is necessary to separate valid and invalid answers by considering rapid-guessing behaviour. We conducted a test to record exam log data from undergraduate and postgraduate students to model rapid-guessing behaviour by determining the threshold response time. Rapid-guessing behaviour detection is inspired by the common k-second method. However, the method flattens the application of the threshold, thus allowing misclassification. The modified method considers item difficulty in determining the threshold. The evaluation results show that the system can identify students’ rapid-guessing behaviour with a success rate of 71%, which is superior to the previous method. We also analysed various aggregation techniques of response time and compared them to see the effect of selecting the aggregation technique.
{"title":"Correction of Threshold Determination in Rapid-Guessing Behaviour Detection","authors":"Muhammad Alfian, Umi Laili Yuhana, E. Pardede, Akbar Noto Ponco Bimantoro","doi":"10.3390/info14070422","DOIUrl":"https://doi.org/10.3390/info14070422","url":null,"abstract":"Assessment is one benchmark in measuring students’ abilities. However, assessment results cannot necessarily be trusted, because students sometimes cheat or even guess in answering the questions. Therefore, to obtain valid results, it is necessary to separate valid and invalid answers by considering rapid-guessing behaviour. We conducted a test to record exam log data from undergraduate and postgraduate students to model rapid-guessing behaviour by determining the threshold response time. Rapid-guessing behaviour detection is inspired by the common k-second method. However, the method flattens the application of the threshold, thus allowing misclassification. The modified method considers item difficulty in determining the threshold. The evaluation results show that the system can identify students’ rapid-guessing behaviour with a success rate of 71%, which is superior to the previous method. We also analysed various aggregation techniques of response time and compared them to see the effect of selecting the aggregation technique.","PeriodicalId":13622,"journal":{"name":"Inf. Comput.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81040357","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}
Federico Ricci, Luca Petrucci, F. Mariani, C. Grimaldi
To carry out increasingly sophisticated checks, which comply with international regulations and stringent constraints, on-board computational systems are called upon to manipulate a growing number of variables, provided by an ever-increasing number of real and virtual sensors. The optimization phase of an ICE passes through the control of these numerous variables, which often exhibit rapidly changing trends over time. On the one hand, the amount of data to be processed, with narrow cyclical frequencies, entails ever more powerful computational equipment. On the other hand, computational strategies and techniques are required which allow actuation times that are useful for timely and optimized control. In the automotive industry, the ‘machine learning’ approach is becoming one the most used approaches to perform forecasting activities with reduced computational effort, due to both its cost-effectiveness and its simple and compact structure. In the present work, the nonlinear dynamic system we address is related to the torque estimation of an ICE through a nonlinear autoregressive with exogenous inputs (NARX) approach. Preliminary activities were performed to optimize the neural network in terms of neurons, hidden layers, and the number of input parameters to be assessed. A Shapley sensitivity analysis allowed quantification of the impact of each variable on the target prediction, and therefore, a reduction in the amount of data to be processed by the architecture. In all cases analyzed, the optimized structure was able to achieve average percentage errors on the target prediction that were always lower than a critical threshold of 10%. In particular, when the dataset was augmented or the analyzed cases merged, the architecture achieved average prediction errors of about 1%, highlighting its remarkable ability to reproduce the target with fidelity.
{"title":"NARX Technique to Predict Torque in Internal Combustion Engines","authors":"Federico Ricci, Luca Petrucci, F. Mariani, C. Grimaldi","doi":"10.3390/info14070417","DOIUrl":"https://doi.org/10.3390/info14070417","url":null,"abstract":"To carry out increasingly sophisticated checks, which comply with international regulations and stringent constraints, on-board computational systems are called upon to manipulate a growing number of variables, provided by an ever-increasing number of real and virtual sensors. The optimization phase of an ICE passes through the control of these numerous variables, which often exhibit rapidly changing trends over time. On the one hand, the amount of data to be processed, with narrow cyclical frequencies, entails ever more powerful computational equipment. On the other hand, computational strategies and techniques are required which allow actuation times that are useful for timely and optimized control. In the automotive industry, the ‘machine learning’ approach is becoming one the most used approaches to perform forecasting activities with reduced computational effort, due to both its cost-effectiveness and its simple and compact structure. In the present work, the nonlinear dynamic system we address is related to the torque estimation of an ICE through a nonlinear autoregressive with exogenous inputs (NARX) approach. Preliminary activities were performed to optimize the neural network in terms of neurons, hidden layers, and the number of input parameters to be assessed. A Shapley sensitivity analysis allowed quantification of the impact of each variable on the target prediction, and therefore, a reduction in the amount of data to be processed by the architecture. In all cases analyzed, the optimized structure was able to achieve average percentage errors on the target prediction that were always lower than a critical threshold of 10%. In particular, when the dataset was augmented or the analyzed cases merged, the architecture achieved average prediction errors of about 1%, highlighting its remarkable ability to reproduce the target with fidelity.","PeriodicalId":13622,"journal":{"name":"Inf. Comput.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75992486","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}
Image captioning is a challenging task, which generates a sentence for a given image. The earlier captioning methods mainly decode the visual features to generate caption sentences for the image. However, the visual features lack the context semantic information which is vital for generating an accurate caption sentence. To address this problem, this paper first proposes the Attention-Aware (AA) mechanism which can filter out erroneous or irrelevant context semantic information. And then, AA is utilized to constitute a Context Semantic Auxiliary Network (CSAN), which can capture the effective context semantic information to regenerate or polish the image caption. Moreover, AA can capture the visual feature information needed to generate a caption. Experimental results show that our proposed CSAN outperforms the compared image captioning methods on MS COCO “Karpathy” offline test split and the official online testing server.
{"title":"A Context Semantic Auxiliary Network for Image Captioning","authors":"Jianying Li, Xiangjun Shao","doi":"10.3390/info14070419","DOIUrl":"https://doi.org/10.3390/info14070419","url":null,"abstract":"Image captioning is a challenging task, which generates a sentence for a given image. The earlier captioning methods mainly decode the visual features to generate caption sentences for the image. However, the visual features lack the context semantic information which is vital for generating an accurate caption sentence. To address this problem, this paper first proposes the Attention-Aware (AA) mechanism which can filter out erroneous or irrelevant context semantic information. And then, AA is utilized to constitute a Context Semantic Auxiliary Network (CSAN), which can capture the effective context semantic information to regenerate or polish the image caption. Moreover, AA can capture the visual feature information needed to generate a caption. Experimental results show that our proposed CSAN outperforms the compared image captioning methods on MS COCO “Karpathy” offline test split and the official online testing server.","PeriodicalId":13622,"journal":{"name":"Inf. Comput.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80720607","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}
In recent work, various scholars have suggested that large language models can be construed as input-driven theories of language acquisition. In this paper, we propose a way to test this idea. As we will document, there is good reason to think that processing pressures override input at an early point in linguistic development, creating a temporary but sophisticated system of negation with no counterpart in caregiver speech. We go on to outline a (for now) thought experiment involving this phenomenon that could contribute to a deeper understanding both of human language and of the language models that seek to simulate it.
{"title":"Natural Syntax, Artificial Intelligence and Language Acquisition","authors":"W. O'grady, Miseon Lee","doi":"10.3390/info14070418","DOIUrl":"https://doi.org/10.3390/info14070418","url":null,"abstract":"In recent work, various scholars have suggested that large language models can be construed as input-driven theories of language acquisition. In this paper, we propose a way to test this idea. As we will document, there is good reason to think that processing pressures override input at an early point in linguistic development, creating a temporary but sophisticated system of negation with no counterpart in caregiver speech. We go on to outline a (for now) thought experiment involving this phenomenon that could contribute to a deeper understanding both of human language and of the language models that seek to simulate it.","PeriodicalId":13622,"journal":{"name":"Inf. Comput.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82281754","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}
Sentence-level sentiment analysis, as a research direction in natural language processing, has been widely used in various fields. In order to address the problem that syntactic features were neglected in previous studies on sentence-level sentiment analysis, a multiscale graph attention network (MSGAT) sentiment analysis model based on dependent syntax is proposed. The model adopts RoBERTa_WWM as the text encoding layer, generates graphs on the basis of syntactic dependency trees, and obtains sentence sentiment features at different scales for text classification through multilevel graph attention network. Compared with the existing mainstream text sentiment analysis models, the proposed model achieves better performance on both a hotel review dataset and a takeaway review dataset, with 94.8% and 93.7% accuracy and 96.2% and 90.4% F1 score, respectively. The results demonstrate the superiority and effectiveness of the model in Chinese sentence sentiment analysis.
{"title":"MSGAT-Based Sentiment Analysis for E-Commerce","authors":"Tingyao Jiang, Wei Sun, Min Wang","doi":"10.3390/info14070416","DOIUrl":"https://doi.org/10.3390/info14070416","url":null,"abstract":"Sentence-level sentiment analysis, as a research direction in natural language processing, has been widely used in various fields. In order to address the problem that syntactic features were neglected in previous studies on sentence-level sentiment analysis, a multiscale graph attention network (MSGAT) sentiment analysis model based on dependent syntax is proposed. The model adopts RoBERTa_WWM as the text encoding layer, generates graphs on the basis of syntactic dependency trees, and obtains sentence sentiment features at different scales for text classification through multilevel graph attention network. Compared with the existing mainstream text sentiment analysis models, the proposed model achieves better performance on both a hotel review dataset and a takeaway review dataset, with 94.8% and 93.7% accuracy and 96.2% and 90.4% F1 score, respectively. The results demonstrate the superiority and effectiveness of the model in Chinese sentence sentiment analysis.","PeriodicalId":13622,"journal":{"name":"Inf. Comput.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86242410","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}
Aristeidis Karras, Christos N. Karras, K. Giotopoulos, Dimitrios Tsolis, K. Oikonomou, S. Sioutas
Federated learning (FL) has emerged as a promising technique for preserving user privacy and ensuring data security in distributed machine learning contexts, particularly in edge intelligence and edge caching applications. Recognizing the prevalent challenges of imbalanced and noisy data impacting scalability and resilience, our study introduces two innovative algorithms crafted for FL within a peer-to-peer framework. These algorithms aim to enhance performance, especially in decentralized and resource-limited settings. Furthermore, we propose a client-balancing Dirichlet sampling algorithm with probabilistic guarantees to mitigate oversampling issues, optimizing data distribution among clients to achieve more accurate and reliable model training. Within the specifics of our study, we employed 10, 20, and 40 Raspberry Pi devices as clients in a practical FL scenario, simulating real-world conditions. The well-known FedAvg algorithm was implemented, enabling multi-epoch client training before weight integration. Additionally, we examined the influence of real-world dataset noise, culminating in a performance analysis that underscores how our novel methods and research significantly advance robust and efficient FL techniques, thereby enhancing the overall effectiveness of decentralized machine learning applications, including edge intelligence and edge caching.
{"title":"Federated Edge Intelligence and Edge Caching Mechanisms","authors":"Aristeidis Karras, Christos N. Karras, K. Giotopoulos, Dimitrios Tsolis, K. Oikonomou, S. Sioutas","doi":"10.3390/info14070414","DOIUrl":"https://doi.org/10.3390/info14070414","url":null,"abstract":"Federated learning (FL) has emerged as a promising technique for preserving user privacy and ensuring data security in distributed machine learning contexts, particularly in edge intelligence and edge caching applications. Recognizing the prevalent challenges of imbalanced and noisy data impacting scalability and resilience, our study introduces two innovative algorithms crafted for FL within a peer-to-peer framework. These algorithms aim to enhance performance, especially in decentralized and resource-limited settings. Furthermore, we propose a client-balancing Dirichlet sampling algorithm with probabilistic guarantees to mitigate oversampling issues, optimizing data distribution among clients to achieve more accurate and reliable model training. Within the specifics of our study, we employed 10, 20, and 40 Raspberry Pi devices as clients in a practical FL scenario, simulating real-world conditions. The well-known FedAvg algorithm was implemented, enabling multi-epoch client training before weight integration. Additionally, we examined the influence of real-world dataset noise, culminating in a performance analysis that underscores how our novel methods and research significantly advance robust and efficient FL techniques, thereby enhancing the overall effectiveness of decentralized machine learning applications, including edge intelligence and edge caching.","PeriodicalId":13622,"journal":{"name":"Inf. Comput.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76828061","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：