{"title":"A tuned feed-forward deep neural network algorithm for effort estimation","authors":"M. Öztürk","doi":"10.1080/0952813X.2021.1871664","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1871664","url":null,"abstract":"ABSTRACT Software effort estimation (SEE) is a software engineering problem that requires robust predictive models. To establish robust models, the most feasible configuration of hyperparameters of regression methods is searched. Although only a few works, which include hyperparameter optimisation (HO), have been done so far for SEE, there is not any comprehensive study including deep learning models. In this study, a feed-forward deep neural network algorithm (FFDNN) is proposed for software effort estimation. The algorithm relies on a binary-search-based method for finding hyperparameters. FFDNN outperforms five comparison algorithms in the experiment that uses two performance parameters. The results of the study suggest that: 1) Employing traditional methods such as grid and random search increases tuning time remarkably. Instead, sophisticated parameter search methods compatible with the structure of regression method should be developed; 2) The performance of SEE is enhanced when associated hyperparameter search method is devised according to the essentials of chosen deep learning approach; 3) Deep learning models achieve in competitive CPU time compared to the tree-based regression methods such as CART_DE8.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"181 1","pages":"235 - 259"},"PeriodicalIF":2.2,"publicationDate":"2021-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83019660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Collaborative filtering based on multiple attribute decision making","authors":"Yajun Leng, Zong-Yu Wu, Qing Lu, Shuping Zhao","doi":"10.1080/0952813X.2021.1882000","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1882000","url":null,"abstract":"ABSTRACT To address the sparsity problem, a novel collaborative filtering approach based on multiple attribute decision making (MADM-CF) is proposed. In MADM-CF, users in collaborative filtering are treated as decision alternatives, items are treated as attributes. The weight of each item is determined, and the preference similarities between the active user and other users are computed. The preference similarity means that how the users’ preferences are similar on positive ratings and negative ratings. According to the preference similarities, the candidate neighbourhood of the active user is determined. A method to compute overall assessment value is designed, the overall assessment value of each user in the candidate neighbourhood is computed, and users with the smallest overall assessment values are selected as the active user’s nearest neighbours. Finally, the most frequent item recommendation method (MFIR) is used to provide top-N recommendations to the active user. Experimental results based on MovieLens and Netflix datasets show that the proposed approach is superior to existing alternatives.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"98 1","pages":"387 - 397"},"PeriodicalIF":2.2,"publicationDate":"2021-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74971112","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Detection of AAC compression using MDCT-based features and supervised learning","authors":"José Juan García-Hernández, W. Gómez-Flores","doi":"10.1080/0952813X.2021.1882003","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1882003","url":null,"abstract":"ABSTRACT Audio files are frequent targets of malicious users who seek illegal profit trading with fake-quality content. For increasing the confidence in the integrity of audio files, the detection of fake-quality content is an important task. This paper proposes a method for detecting Advanced Audio Coding (AAC) compression on suspicious WAV files, in which the variance of the Modified Discrete Cosine Transform (MDCT) characterises four compression bitrates: uncompressed, 64 kbps, 128 kbps, and 256 kbps. This scheme takes advantage of the reduction of the variance of the high-frequency MDCT coefficients in compressed signals. Data obtained from MDCT coefficients generate a high-dimensional feature space. Hence, Principal Component Analysis, followed by Linear Discriminant Analysis, is used for projecting the high-dimensional data onto a lower-dimensional space. Besides, six supervised learning algorithms are compared for classifying four compression bitrates. The experiments show that using audio samples with 20 seconds and 1024 MDCT coefficients, an accuracy of 93% is reached with a Bayesian classifier. Collaterally, the detection between uncompressed and compressed signals attains an accuracy of 97% with Multinomial Logistic Regression. In conclusion, the proposed approach can detect previous AAC compression and can be potentially used when it is unfeasible to recover the suspicious signal completely.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"22 1","pages":"451 - 468"},"PeriodicalIF":2.2,"publicationDate":"2021-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79059821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ricardo Rios, T. N. Rios, Gabriel R. Palma, R. F. de Mello
{"title":"Brazilian Forest Dataset: A new dataset to model local biodiversity","authors":"Ricardo Rios, T. N. Rios, Gabriel R. Palma, R. F. de Mello","doi":"10.1080/0952813X.2021.1871972","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1871972","url":null,"abstract":"ABSTRACT The Intergovernmental Panel on Climate Change and the Intergovernmental Science-Policy Platform on Biodiversity and Ecosystem Services have emphasised unequivocal evidences about the impact of human actions on climate and biodiversity at alarming rates. In Brazilian terms, 2019 has been marked by controversial discussions among politicians and environmentalists, leading to misinformation and misinterpretations that clearly motivate the continuous collection and scientific analysis of data to support sustainable solutions. Aiming at dealing with this issue, this manuscript brings two contributions: (i) the creation of the Brazilian Forest Dataset, including Brazilian seed plants, Fraction of Absorbed Photosynthetically Active Radiation, meteorological and geographical data composing 8,482 attributes to model and predict 20 vegetation types; and (ii) the feasibility analysis on modelling this dataset in light of supervised machine learning algorithms, so we devise confident results on the Brazilian biodiversity. Experimental results confirm Random Forest and Support Vector Machines successfully adjust models, enabling researchers to predict the occurrence of specific types of vegetation in different regions of Brazil as well as analyse how the prediction accuracy changes along time after the collection of new data. Our contributions bring important tools to support the study on the evolution of the Brazilian biodiversity.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"26 1","pages":"327 - 354"},"PeriodicalIF":2.2,"publicationDate":"2021-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77246816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A hybrid optimizer based on backtracking search and differential evolution for continuous optimization","authors":"Yiğit Çağatay Kuyu, E. Onieva, P. López-García","doi":"10.1080/0952813X.2021.1872109","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1872109","url":null,"abstract":"ABSTRACT This paper introduces a novel hybridisation technique combining the Backtracking Search (BS) and Differential Evolution (DE) algorithms. The proposed hybridisation executes diversity loss and stagnation detection mechanisms to maintain the diversity of the populations, in addition, modifications are done over the mutation operators of the component algorithms in order to improve the search capability of the proposal. These modifications are self-adapted and implemented simultaneously. Extensive experiments to establish the optimal configuration of the parameters are also presented through the introduced technique. The proposed hybridisation approach has been applied to five classical versions and two state-of-the-art variants of DE and tested against 28 well-known benchmark functions with different dimensions, each type of which highlights a different set of characteristics and provides a baseline measurement to validate the performance of the algorithms. In order to further test the proposal, the four outstanding algorithms in the state of the art have also been included in the comparisons. Experimental results show the effectiveness of the proposed hybrid framework over the compared algorithms.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"13 1","pages":"355 - 385"},"PeriodicalIF":2.2,"publicationDate":"2021-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74545263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jinjin Chi, Jihong Ouyang, Ang Zhang, Xinhua Wang, Ximing Li
{"title":"Fast copula variational inference","authors":"Jinjin Chi, Jihong Ouyang, Ang Zhang, Xinhua Wang, Ximing Li","doi":"10.1080/0952813X.2021.1871970","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1871970","url":null,"abstract":"ABSTRACT Mean-field variational inference, built on fully factorisations, can be efficiently solved; however, it ignores the dependencies between latent variables, resulting in lower performance. To address this, the copula variational inference (CVI) method is proposed by using the well-established copulas to effectively capture posterior dependencies, leading to better approximations. However, it suffers from a computational issue, where the optimisation for big models with massive latent variables is quite time-consuming. This is mainly caused by the expensive sampling when forming noisy Monte Carlo gradients in CVI. For CVI speedup, in this paper we propose a novel fast CVI (abbr. FCVI). In FCVI, we derive the gradient of CVI objective by an expectation of the mean-field factorisation. Therefore, we can achieve a much efficient sampling from the -dimensional mean-field factorisation, enabling to reduce the sampling complexity from to . To evaluate FCVI, we compare it against baseline methods on modelling performance and runtime. Experimental results demonstrate that FCVI is on a par with CVI, but runs much faster.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"54 1","pages":"295 - 310"},"PeriodicalIF":2.2,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80717923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Correlation-based Oversampling aided Cost Sensitive Ensemble learning technique for Treatment of Class Imbalance","authors":"D. Devi, S. Biswas, B. Purkayastha","doi":"10.1080/0952813X.2020.1864783","DOIUrl":"https://doi.org/10.1080/0952813X.2020.1864783","url":null,"abstract":"ABSTRACT The issue of class imbalance and its consequences over the conventional learning models is a well-investigated topic, as it highly influences performances of real-life classification tasks. Amongst the available solutions, Synthetic Minority Oversampling Technique (SMOTE) imprints efficacy in balancing the data through synthetic minority instance generation. However, SMOTE suffers from the drawback of redundant data generation owing to uniform oversampling rate in regard to which, SMOTE with a customised oversampling rate has been investigated recently. In parallel to this, ensemble learning approaches are quite effective in improving prediction abilities of a set of weak classifiers through adaptive-weighted training. However, it does not account the imbalanced nature of the data during training. Through this paper, Correlation-based Oversampling aided Cost Sensitive Ensemble learning (CorrOV-CSEn) is proposed by integrating correlation-based oversampling with the AdaBoost ensemble learning model. The correlation-based oversampling entails to define a customised oversampling rate and a suitable oversampling zone while a misclassification ratio-based cost-function is introduced in the AdaBoost model to administer adaptive learning of imbalanced cases. CorrOV-CSEn is evaluated against 13 state-of-the-art methods by using 8 simulation datasets. The experimental results establish CorrOV-CSEn to be effective than the state-of-the-art methods in resolving the concerned issues.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"3 1","pages":"143 - 174"},"PeriodicalIF":2.2,"publicationDate":"2021-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85325931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
E. L. Strugeon, K. Oliveira, Marie Thilliez, Dorian Petit
{"title":"A systematic mapping study on agent mining","authors":"E. L. Strugeon, K. Oliveira, Marie Thilliez, Dorian Petit","doi":"10.1080/0952813X.2020.1864784","DOIUrl":"https://doi.org/10.1080/0952813X.2020.1864784","url":null,"abstract":"ABSTRACT Over the past two decades, many studies have been published in diverse fields of application combining agent abilities (knowledge processing, communication, learning, mobility, etc.) and data mining approaches (clustering, decision trees, ontologies, etc.). We performed a systematic mapping study to quantitatively analyse these contributions about agent mining. We determined that most of the publications were in the field of data mining using agent systems to collect or mine the data. Some used data mining solutions to improve agent behaviour, and very few publications integrated both agent and mining approaches. In the latter case, most were published in the last few years, which highlights the advances in research integrating agents and mining approaches.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"41 1","pages":"189 - 214"},"PeriodicalIF":2.2,"publicationDate":"2021-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81352013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The synchronization and stability analysis of delayed fuzzy Cohen-Grossberg neural networks via nonlinear measure method","authors":"Meryem Abdelaziz, F. Chérif","doi":"10.1080/0952813X.2021.1871663","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1871663","url":null,"abstract":"ABSTRACT This paper examines the problem of master-slave synchronization for a class of fuzzy Cohen-Grossberg neural networks (FCGNNs) subject to fuzzy effects and time-delays (time-varying and distributed). Some sufficient and new conditions are given in order to establish the exponential lag synchronization for the considered model. Also, the existence, the uniqueness, and exponential stability of the equilibrium point are investigated, based on the nonlinear measure method and Halanay inequality. Finally, two examples with numerical simulations are given to show the effectiveness of the derived results.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"25 1","pages":"215 - 234"},"PeriodicalIF":2.2,"publicationDate":"2021-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77693779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Boosting symbiotic organism search algorithm with ecosystem service for dynamic blood allocation in blood banking system","authors":"Prinolan Govender, Ezugwu E. Absalom","doi":"10.1080/0952813X.2021.1871665","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1871665","url":null,"abstract":"ABSTRACT Blood is a valuable commodity in society due to its ability to save lives during crises. Furthermore, because of the scarcity of blood donors, blood assignment by blood banks requires meticulous planning and solid issuing policy. The multiple components of a blood banking system contribute to the complexity of maintaining an efficient structure for such a system. One particular aspect relates to the stochastic nature of the demand for blood units. This paper implements a mathematical model for a blood bank system in South Africa and additionally explores the possible implementation of a hybrid global optimisation metaheuristic approach for the efficient assignment of blood products in the blood bank system. The approximate optimisation method used is the hybridisation of the symbiotic organism search (SOS) algorithm and a pre-processing ecosystem services (PES) techniques. In order to show the practicability of the model and evaluate the accuracy and robustness of the newly proposed hybrid algorithm, several numerical computations were performed using synthetically generated datasets that fall within the initial blood volume bounds of 500 to 20, 000. The experimental results indicate that the hybrid symbiotic organisms search ecosystem services optimisation algorithm offers better solutions for blood allocation under a dynamic environment than does the standard symbiotic organism search algorithm and other previously proposed hybrid versions of the SOS methods.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"20 1","pages":"261 - 293"},"PeriodicalIF":2.2,"publicationDate":"2021-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82597436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}