Search results

Automatic anatomical therapeutic chemical (ATC) classification is progressing at a rapid pace because of its potential in drug development. Predicting an unknown compound's therapeutic and chemical characteristics in terms of how it affects multiple organs and physiological systems makes automatic ATC classification a vital yet challenging multilabel problem. The aim of this paper is to experimentally derive an ensemble of different feature descriptors and classifiers for ATC classification that outperforms the state-of-the-art.

The proposed method is an ensemble generated by the fusion of neural networks (i.e. a tabular model and long short-term memory networks (LSTM)) and multilabel classifiers based on multiple linear regression (hMuLab). All classifiers are trained on three sets of descriptors. Features extracted from the trained LSTMs are also fed into hMuLab. Evaluations of ensembles are compared on a benchmark data set of 3883 ATC-coded pharmaceuticals taken from KEGG, a publicly available drug databank.

Experiments demonstrate the power of the authors’ best ensemble, EnsATC, which is shown to outperform the best methods reported in the literature, including the state-of-the-art developed by the fast.ai research group. The MATLAB source code of the authors’ system is freely available to the public at https://github.com/LorisNanni/Neural-networks-for-anatomical-therapeutic-chemical-ATC-classification.

This study demonstrates the power of extracting LSTM features and combining them with ATC descriptors in ensembles for ATC classification.

Diagnosing pain in neonates is difficult but critical. Although approximately thirty manual pain instruments have been developed for neonatal pain diagnosis, most are complex, multifactorial, and geared toward research. The goals of this work are twofold: 1) to develop a new video dataset for automatic neonatal pain detection called iCOPEvid (infant Classification Of Pain Expressions videos), and 2) to present a classification system that sets a challenging comparison performance on this dataset. The iCOPEvid dataset contains 234 videos of 49 neonates experiencing a set of noxious stimuli, a period of rest, and an acute pain stimulus. From these videos 20 s segments are extracted and grouped into two classes: pain (49) and nopain (185), with the nopain video segments handpicked to produce a highly challenging dataset. An ensemble of twelve global and local descriptors with a Bag-of-Features approach is utilized to improve the performance of some new descriptors based on Gaussian of Local Descriptors (GOLD). The basic classifier used in the ensembles is the Support Vector Machine, and decisions are combined by sum rule. These results are compared with standard methods, some deep learning approaches, and 185 human assessments. Our best machine learning methods are shown to outperform the human judges.

Automatic DNA-binding protein (DNA-BP) classification is now an essential proteomic technology. Unfortunately, many systems reported in the literature are tested on only one or two datasets/tasks. The purpose of this study is to create the most optimal and universal system for DNA-BP classification, one that performs competitively across several DNA-BP classification tasks.

Efficient DNA-BP classifier systems require the discovery of powerful protein representations and feature extraction methods. Experiments were performed that combined and compared descriptors extracted from state-of-the-art matrix/image protein representations. These descriptors were trained on separate support vector machines (SVMs) and evaluated. Convolutional neural networks with different parameter settings were fine-tuned on two matrix representations of proteins. Decisions were fused with the SVMs using the weighted sum rule and evaluated to experimentally derive the most powerful general-purpose DNA-BP classifier system.

The best ensemble proposed here produced comparable, if not superior, classification results on a broad and fair comparison with the literature across four different datasets representing a variety of DNA-BP classification tasks, thereby demonstrating both the power and generalizability of the proposed system.

Most DNA-BP methods proposed in the literature are only validated on one (rarely two) datasets/tasks. In this work, the authors report the performance of our general-purpose DNA-BP system on four datasets representing different DNA-BP classification tasks. The excellent results of the proposed best classifier system demonstrate the power of the proposed approach. These results can now be used for baseline comparisons by other researchers in the field.

This work presents a system based on an ensemble of Convolutional Neural Networks (CNNs) and descriptors for bioimage classification that has been validated on different datasets of color images. The proposed system represents a very simple yet effective way of boosting the performance of trained CNNs by composing multiple CNNs into an ensemble and combining scores by sum rule. Several types of ensembles are considered, with different CNN topologies along with different learning parameter sets. The proposed system not only exhibits strong discriminative power but also generalizes well over multiple datasets thanks to the combination of multiple descriptors based on different feature types, both learned and handcrafted. Separate classifiers are trained for each descriptor, and the entire set of classifiers is combined by sum rule. Results show that the proposed system obtains state-of-the-art performance across four different bioimage and medical datasets. The MATLAB code of the descriptors will be available at https://github.com/LorisNanni.

As the workforce becomes increasingly diversified, it becomes increasingly important for managers to understand the conflict resolution attitudes brought to information systems (IS) by both men and women. This research was designed to investigate assumptions that may exist regarding the relationship between gender and conflict resolution. Specifically, the intent of this study was to compare the conflict resolution strategies of males and females majoring in IS in order to determine if gender‐based differences exist.

The Thomas‐Kilmann Conflict Mode Instrument was utilized to assess the conflict resolution styles of 163 traditional‐age (18‐22) students enrolled in undergraduate IS courses at a large Midwestern university. Both ANOVA and t‐test analyses were utilized to investigate the relationship between gender and conflict resolution style.

Results of this study indicate that, when compared with their male counterparts, women are more likely to utilize a collaborative conflict resolution style and men are more likely to avoid conflict. As collaboration is generally considered more productive and avoidance more disruptive in the conflict resolution process, the study suggests that women may possess more effective conflict resolution attributes than their male counterparts.

The results of this paper lend support to the theory that an individual's gender may be related to the development of conflict resolution styles. These findings also support the premise that female students in IS are highly adapted with regard to their ability to work collaboratively (and thereby successfully) in situations where conflict is likely to occur.

While videoconferencing has allowed for meetings to continue in a virtual space without the need for face-to-face interaction, there have been increasing reports of individuals affected by a phenomenon colloquially known as videoconference fatigue (VF). This paper presents a systematic review of existing literature to understand the empirical manifestations of the phenomenon, the causes behind it and potential theoretical explanations behind its effects.

A comprehensive search on four academic databases was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and produced 34,574 results, with 14 articles meeting the eligibility criteria.

Analyses showed that VF can be classified into four dimensions: physical, emotional, cognitive and social. Antecedents of VF can be organized into psychological, social, technical, chronemic and productivity factors. Potential theoretical explanations applied in existing studies were described and elaborated upon. The authors also highlight the importance of addressing social concerns as a key priority in alleviating VF.

To our knowledge, this is the first comprehensive systematic review of existing research on VF. The contribution of this paper is twofold: First, the authors described VF in a systematic and rigorous manner and provide theoretical insights, as much of the current discourse around VF tends to be based on anecdotal evidence and reports. Second, the authors explore potential theoretical explanations surrounding the phenomena, to address the lack of understanding behind the processes by which VF affects individuals.

In Southeast Asia, auditors play a crucial role in the quality of financial reports. With the introduction of a new format of auditors’ report that requires disclosure of key audit matters (KAM), the disclosure practice of auditors is, thus, of great interest. Specifically, this study aims to investigate the factors that auditors take into consideration when issuing KAMs.

The research design is quantitative, with a focus on the number of KAM disclosures issued by auditors. As existing studies rely on the number of KAM disclosures in the analysis, this current research, thus, uses the quantity of KAM disclosures for comparison purposes. The analysis relies on secondary data and multiple regression analysis is used to establish the association between the number of KAM disclosures and three groups of determining factors, namely, auditor characteristics, corporate governance mechanisms and firm characteristics.

The significant determining factors of KAM disclosure include auditor’s litigation risk, firm complexity, profitability and industry type. Firms using a Big 4 audit firm, firms with many subsidiaries and firms in the technology, property and construction and finance industries have higher numbers of KAMs, while highly profitable firms issue lower numbers of KAMs. As for corporate governance mechanisms, the number of KAMs is significantly positively correlated with the number of independent directors (p < 0.10).

This research includes key corporate governance parties in the examination, including external auditors, independent directors and audit committees. The finding affirms the influence of Big 4 on KAM disclosure in Southeast Asia, while their roles are not significant in Western samples. The result also unearths the monitoring role of independent directors in KAM disclosure. The role of the audit committee in KAM disclosure is insignificant in Thai samples, while the committee role is statistically significant in the Western samples. Variations in the findings between this study and previous research could be attributed to differences in institutional settings between both regions.