Purpose Wafer foundries face numerous challenges in localizing the semiconductor supply chain, necessitating various measures to overcome these challenges. Given their limited funding, time and resources, these measures require prioritization. Design/methodology/approach To prioritize these measures, this study proposes a dynamic fuzzy compromise planning (DFCP) approach, which dynamically allocates resources across a limited budget based on the priority of measures within each time period. The DFCP approach embeds a fuzzy technique for order preference by similarity to ideal solution mechanism into a fuzzy mixed binary-nonlinear programming model. Findings The DFCP approach has been applied to a real-world case. Experimental results demonstrated that the DFCP approach satisfied the three objectives of wafer foundries, while existing methods either over-concentrated resources on a few possible measures or produced discontinuous planning fragments. Originality/value Semiconductor supply chain localization is undoubtedly one of the most advanced manufacturing models in the semiconductor industry, yet it has received little discussion to date. The DFCP approach combines multi-criteria decision-making practices with fuzzy optimization models, which is quite different from most existing fuzzy compromise programming methods.
Purpose This study aims to develop and validate a quantum-enhanced behavioral security framework that integrates a lightweight quantum obfuscation layer into classical intrusion detection systems (IDSs). The primary objective is to harden these models against post-quantum threats, specifically model extraction and feature inversion attacks, while maintaining high detection accuracy across both traditional machine learning and deep learning architectures. Design/methodology/approach A quantum feature obfuscation layer was designed using 6-qubit parameterized circuits with angle encoding and variational ansatz to nonlinearly transform behavioral features. This layer was integrated with classical classifiers (random forest, support vector machine, logistic regression) and a deep learning model multi-layer perceptron (MLP). The framework was evaluated on UNSW-NB15 and NSL-KDD datasets using Qiskit Aer simulators in Google Colab, measuring accuracy, precision, recall, F1-score, model extraction error (MEE) and feature inversion error (FIE). Findings Quantum-assisted models maintained detection performance comparable to classical baselines, with accuracy degradation of 0.7% across all architectures. Security resilience significantly improved, with a 3–4× increase in both MEE and FIE, indicating substantially enhanced resistance to model theft and feature reconstruction. The framework demonstrated improved noise tolerance under Gaussian perturbations. The MLP achieved 92.5% accuracy (classical) versus 91.8% (quantum-assisted), with 3.3× and 3.5× improvements in MEE and FIE, respectively. Research limitations/implications The evaluation was conducted entirely on quantum simulators, not capturing real hardware noise, decoherence and fidelity limitations. The threat model assumes secrecy of quantum circuit parameters, representing a form of model-level security through obscurity. Scalability is constrained by exponential simulation costs, limiting current experiments to 6 qubits. Only feedforward neural networks (MLP) were tested; advanced architectures like CNNs, LSTMs and transformers require future validation. The framework’s resilience against adversaries with partial knowledge of the ansatz structure remains unexplored. Practical implications The framework provides a pragmatic, classifier-agnostic defense layer deployable on freely accessible cloud platforms (Google Colab) without specialized quantum hardware. With only 15–25 ms inference overhead and 40–60% training overhead, it offers viable post-quantum hardening for security-critical applications. Resource-constrained environments such as edge computing nodes and IoT deployments can benefit from this approach. The demonstration that meaningful security gains (3–4× improvement) are achievable using only 6 qubits lowers the barrier for organizations to adopt quantum-assisted security measures today. Social implications As quantum computing threatens classical cryptography, protecting behavioral analytics becomes crucial for critical infrastructure, financial systems and healthcare networks. This research contributes to building resilient cyber defense mechanisms that protect sensitive data and privacy even when encryption is compromised. By democratizing access to quantum-enhanced security through cloud-based simulation platforms, the framework helps bridge the gap between institutions with varying resources, promoting more equitable cybersecurity preparedness for the post-quantum era across both developed and developing nations. Originality/value This work shifts the focus of quantum-enhanced security from pure cryptographic replacement to model-hardening, harnessing quantum state complexity as a defensive mechanism rather than pursuing quantum advantage for classification speed. It introduces a novel quantum obfuscation layer specifically designed for IDS, validated across both traditional ML and deep learning architectures. The consistent security improvements (3–4×) across classifier types confirm the approach is classifier-agnostic. The Colab-based implementation ensures reproducibility and accessibility, providing a practical foundation for future quantum-aware cyber defense research and deployment.
PurposeWith the rapid proliferation of Internet-connected devices, software-defined networking (SDN) has become an attractive paradigm for efficient network management compared to traditional network infrastructure. Nevertheless, SDN networks remain susceptible to distributed denial-of-service (DDoS) attacks, significantly degrading network performance and reliability. This research seeks to overcome the current limitation posed by the absence of realistic SDN-based datasets for DDoS detection and proposes an enhanced detection methodology tailored explicitly for SDN networks.Design/methodology/approachThis research introduces SDN-DDoS2025, a novel dataset developed by adapting the CIC-DDoS2019 dataset to an SDN environment while preserving flow- and traffic-level characteristics unique to SDN. Comprehensive exploratory data analysis (EDA) is performed to thoroughly investigate feature distributions, trends and correlations within the dataset. Furthermore, a hybrid deep learning model integrating one-dimensional convolutional neural networks with long short-term memory layers (CNN-LSTM) is proposed, demonstrating enhanced efficiency and effectiveness in detecting DDoS attacks.FindingsThe experimental results reveal that the proposed CNN-LSTM hybrid model outperforms recent benchmark methods on both the original CIC-DDoS2019 and the newly introduced SDN-DDoS2025 datasets. The model attains superior detection accuracy and demonstrates robust generalization capabilities, handling real-world SDN traffic patterns.Originality/valueThis research presents the first SDN-specific dataset derived from the CIC-DDoS2019 benchmark, incorporating realistic SDN-oriented features and proposes a robust deep learning architecture specifically designed for effective DDoS detection in SDN contexts. By integrating dataset generation, comprehensive EDA and advanced deep learning modeling, this research addresses a significant research gap within the SDN security domain.
Purpose - This paper aims to present a modular pipeline approach by combining extractive and abstractive summarisation methods in order to improve the accuracy of automatic text summarisation (ATS). Design/methodology/approach - In our framework we have used LangChain [20], a large language model integration platform, to orchestrate an extractive algorithm (LexRank) and an abstractive algorithm (Bidirectional and Auto-Regressive Transformers (BART)). LexRank identifies key sentences from the input text, ensuring core information is retained without redundancy, BART is used for refining these extracted sentences into human-like, concise summaries. Findings - We evaluated the performance of our framework by using CNN/Daily Mail, Newsroom and XSum datasets, which are widely used benchmark for summarisation tasks. Evaluation results demonstrate that this modular approach improves accuracy of generated summaries in two ways, (1) word level similarities between reference summary and generated summary and (2) semantic similarity between reference summary and generated summary. Research limitations/implications - In our experiments, we used datasets that have short length documents (within 7,000 characters). We need to perform more experiments with long documents to evaluate the robustness of our pipeline. We have not investigated error propagation from extractive phase to abstractive phase that may have an impact on the performance of our framework. Originality/value - The primary contribution of this study is the development and evaluation of a modular pipeline combining LexRank, an extractive summarisation technique, and BART, an advanced abstractive model, using LangChain. The results indicate that the hybrid approach outperforms traditional single-model methods and other existing hybrid models, as evidenced by higher Recall-Oriented Understudy for Gisting Evaluation and BERTScores across various examples.
PurposeThis study aims to develop a data-driven Deep Koopman-based model predictive control (DK-MPC) framework for real-time trajectory tracking and stabilization of quadrotor systems. The objective is to overcome the computational limitations of conventional nonlinear model predictive control (NMPC) while preserving high-accuracy control performance.Design/methodology/approachA deep neural network-based Koopman operator is employed to map the nonlinear quadrotor dynamics into a globally linear latent space, enabling the formulation of a computationally efficient linear model predictive control (MPC) problem. The Koopman embeddings are trained using the publicly available WaveLab Pelican dataset to capture the coupled and nonlinear dynamics of the quadrotor. The proposed DK-MPC framework is evaluated through numerical simulations involving point stabilization and trajectory tracking tasks, including previously unseen helical trajectories. Performance is assessed in terms of tracking accuracy, computational efficiency and real-time feasibility, with comparisons made against conventional NMPC.FindingsSimulation results demonstrate that the proposed DK-MPC framework achieves high-precision control with a coefficient of determination (R2) of 99%. The method requires approximately 10% of the computation time per control step compared to NMPC. For a prediction horizon of H = 50, DK-MPC maintains real-time feasibility with an average computation time of 15 ms per control step, while NMPC frequently fails to converge within the required time constraints. These findings confirm the effectiveness of the Koopman-based linear embedding in reducing computational burden without compromising control accuracy.Originality/valueThe study presents a scalable and computationally efficient integration of deep Koopman operator learning with MPC for quadrotor systems. By combining data-driven nonlinear system representation with linear MPC optimization, the proposed framework bridges the gap between advanced learning-based modeling and real-time predictive control implementation.
PurposeThis study investigates the integration of quantum-enhanced machine learning (QML) into medical image analysis, focusing on classification and feature extraction tasks. It aims to evaluate whether hybrid quantum-classical models can overcome the limitations of traditional machine learning in handling high-dimensional, clinically relevant imaging data.Design/methodology/approachHybrid architectures combining classical preprocessing with quantum components, specifically variational quantum circuits (VQCs) and quantum kernel methods, were developed and implemented in simulated quantum environments using Qiskit and PennyLane on Google Colab. Publicly available datasets (ChestX-ray14, Brain Tumor MRI and CT Hemorrhage) were preprocessed and encoded into quantum states. Model performance was evaluated against classical baselines (MLP and CNN) using accuracy, precision, recall, F1-score, convergence speed and trainable parameters.FindingsQuantum-enhanced models achieved competitive or superior performance compared to classical models with significantly fewer trainable parameters and faster convergence. The Quantum Kernel SVM demonstrated the highest precision (89.1%) and F1-score (88.5%) using only 8 parameters, while VQC models converged up to 2x faster than classical baselines. These results highlight the potential of QML to improve efficiency, robustness and scalability in diagnostic imaging workflows, particularly in resource-constrained or data-limited settings.Research limitations/implicationsThe study relies on simulated quantum environments, which do not capture hardware noise or qubit limitations. Future work will extend to real quantum devices, multimodal data integration and interpretability strategies.Practical implicationsQuantum kernel methods and lightweight VQC architectures enable faster, resource-efficient diagnostic modeling, making them suitable for clinical environments with limited computational capacity or time-sensitive decision-making needs.Social implicationsImproving the efficiency and accessibility of medical image analysis has the potential to support faster diagnosis and enhance healthcare delivery, particularly in underserved or resource-limited regions.Originality/valueThis study provides a practical evaluation of hybrid quantum-classical models applied to multiple real medical imaging datasets in a reproducible simulated environment. It offers an early-stage framework demonstrating how QML techniques can be integrated into existing machine learning pipelines for medical image analysis.
PurposeTo detect academic misconduct in students' assessment score trajectories under severe class imbalance. The paper compares tabular learners, gradient-boosting models, and sequence-aware deep networks, and proposes a precision-recall-centric evaluation and deployment protocol (calibration, threshold selection and Recall@Top-k%) tailored to rare-event screening in educational settings.Design/methodology/approachA cohort of 1,527 students (2021-2024) is modeled using ten algorithms: LR, DT, RF, SVM, MLP, XGBoost, CatBoost, LightGBM, GRU-RNN and 1D-CNN. Features encode sequential score dynamics and metadata. Models are tuned via cross-validation; probabilities are calibrated (Platt/Isotonic); operating thresholds are chosen on validation to maximize minority-class F1 or a cost-sensitive utility. Performance is assessed on a hold-out test set with PR-AUC (headline), F1(+), Recall@Top-k%, ROC-AUC, calibration curves, Brier, and bootstrap CIs.FindingsSequence-aware models dominate: GRU-RNN and 1D-CNN achieve ROC-AUC 0.97-0.98 and the highest F1(+) and Recall@Top-5%. Tabular/boosting baselines show 0.90 accuracy yet miss most positives at the default 0.5 threshold, highlighting the necessity of calibration and threshold optimization. With PR-centric selection and tuned operating points, deep temporal models yield strong screening utility for limited human review budgets.Research limitations/implicationsLabels reflect suspected-not adjudicated-cheating, introducing noise. The single-institution cohort may limit external validity; temporal shift across semesters can degrade performance. Future work should include multi-site evaluation, collusion/graph modeling, semi-/weak-supervision for noisy labels and governance topics (fairness audits, drift monitoring and uncertainty reporting).Practical implicationsThis study highlights how educational institutions can leverage machine learning for early detection of academic dishonesty based on historical performance data. CNN and RNN models are promising tools for identifying anomalous learning patterns. However, practical deployment requires preprocessing techniques to manage class imbalance and threshold optimization to reduce false negatives. The findings provide a roadmap for building automated cheating detection systems in both online and traditional assessment environments.Social implicationsBy improving the ability to detect cheating, this research contributes to fairer academic environments, upholding educational integrity and credibility of credentials. However, ethical considerations must be taken into account to avoid false accusations and ensure student rights. Human-in-the-loop systems are crucial for verifying algorithmic predictions before disciplinary action, thereby fostering transparency and accountability in automated decision-making processes.Originality/valueThe study unifies a minority-focused evaluation protocol with a comprehensive comparison of tabular, boosting, and sequence-aware models for cheating detection from score trajectories. It demonstrates the decisive value of temporal representation learning and provides a reproducible pipeline and operational metrics that align model performance with real investigative workflows.
Purpose In time and accurate detection of cancer can save the life of the person affected. According to the World Health Organization (WHO), breast cancer occupies the most frequent incidence among all the cancers whereas breast cancer takes fifth place in the case of mortality numbers. Out of many image processing techniques, certain works have focused on convolutional neural networks (CNNs) for processing these images. However, deep learning models are to be explored well. Design/methodology/approach In this work, multivariate statistics-based kernel principal component analysis (KPCA) is used for essential features. KPCA is simultaneously helpful for denoising the data. These features are processed through a heterogeneous ensemble model that consists of three base models. The base models comprise recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU). The outcomes of these base learners are fed to fuzzy adaptive resonance theory mapping (ARTMAP) model for decision making as the nodes are added to the F_2ˆa layer if the winning criteria are fulfilled that makes the ARTMAP model more robust. Findings The proposed model is verified using breast histopathology image dataset publicly available at Kaggle. The model provides 99.36% training accuracy and 98.72% validation accuracy. The proposed model utilizes data processing in all aspects, i.e. image denoising to reduce the data redundancy, training by ensemble learning to provide higher results than that of single models. The final classification by a fuzzy ARTMAP model that controls the number of nodes depending upon the performance makes robust accurate classification. Research limitations/implications Research in the field of medical applications is an ongoing method. More advanced algorithms are being developed for better classification. Still, the scope is there to design the models in terms of better performance, practicability and cost efficiency in the future. Also, the ensemble models may be chosen with different combinations and characteristics. Only signal instead of images may be verified for this proposed model. Experimental analysis shows the improved performance of the proposed model. This method needs to be verified using practical models. Also, the practical implementation will be carried out for its real-time performance and cost efficiency. Originality/value The proposed model is utilized for denoising and to reduce the data redundancy so that the feature selection is done using KPCA. Training and classification are performed using heterogeneous ensemble model designed using RNN, LSTM and GRU as base classifiers to provide higher results than that of single models. Use of adaptive fuzzy mapping model makes the final classification accurate. The effectiveness of combining these methods to a single model is analyzed in this work.
PurposeThe aim of this study is to investigate subject independent emotion recognition capabilities of EEG and peripheral physiological signals namely: electroocoulogram (EOG), electromyography (EMG), electrodermal activity (EDA), temperature, plethysmograph and respiration. The experiments are conducted on both modalities independently and in combination. This study arranges the physiological signals in order based on the prediction accuracy obtained on test data using time and frequency domain features.Design/methodology/approachDEAP dataset is used in this experiment. Time and frequency domain features of EEG and physiological signals are extracted, followed by correlation-based feature selection. Classifiers namely – Naïve Bayes, logistic regression, linear discriminant analysis, quadratic discriminant analysis, logit boost and stacking are trained on the selected features. Based on the performance of the classifiers on the test set, the best modality for each dimension of emotion is identified.Findings The experimental results with EEG as one modality and all physiological signals as another modality indicate that EEG signals are better at arousal prediction compared to physiological signals by 7.18%, while physiological signals are better at valence prediction compared to EEG signals by 3.51%. The valence prediction accuracy of EOG is superior to zygomaticus electromyography (zEMG) and EDA by 1.75% at the cost of higher number of electrodes. This paper concludes that valence can be measured from the eyes (EOG) while arousal can be measured from the changes in blood volume (plethysmograph). The sorted order of physiological signals based on arousal prediction accuracy is plethysmograph, EOG (hEOG + vEOG), vEOG, hEOG, zEMG, tEMG, temperature, EMG (tEMG + zEMG), respiration, EDA, while based on valence prediction accuracy the sorted order is EOG (hEOG + vEOG), EDA, zEMG, hEOG, respiration, tEMG, vEOG, EMG (tEMG + zEMG), temperature and plethysmograph.Originality/valueMany of the emotion recognition studies in literature are subject dependent and the limited subject independent emotion recognition studies in the literature report an average of leave one subject out (LOSO) validation result as accuracy. The work reported in this paper sets the baseline for subject independent emotion recognition using DEAP dataset by clearly specifying the subjects used in training and test set. In addition, this work specifies the cut-off score used to classify the scale as low or high in arousal and valence dimensions. Generally, statistical features are used for emotion recognition using physiological signals as a modality, whereas in this work, time and frequency domain features of physiological signals and EEG are used. This paper concludes that valence can be identified from EOG while arousal can be predicted from plethysmograph.
PurposeConsumers increasingly rely on organisations for online services and data storage while these same institutions seek to digitise the information assets they hold to create economic value. Cybersecurity failures arising from malicious or accidental actions can lead to significant reputational and financial loss which organisations must guard against. Despite having some critical weaknesses, qualitative cybersecurity risk analysis is widely used in developing cybersecurity plans. This research explores these weaknesses, considers how quantitative methods might address the constraints and seeks the insights and recommendations of leading cybersecurity practitioners on the use of qualitative and quantitative cyber risk assessment methods.Design/methodology/approachThe study is based upon a literature review and thematic analysis of in-depth qualitative interviews with 16 senior cybersecurity practitioners representing financial services and advisory companies from across the world.FindingsWhile most organisations continue to rely on qualitative methods for cybersecurity risk assessment, some are also actively using quantitative approaches to enhance their cybersecurity planning efforts. The primary recommendation of this paper is that organisations should adopt both a qualitative and quantitative cyber risk assessment approach.Originality/valueThis work provides the first insight into how senior practitioners are using and combining qualitative and quantitative cybersecurity risk assessment, and highlights the need for in-depth comparisons of these two different approaches.
PurposeThis research work aims to arise from developing new communication channels for customer service in micro, small and medium enterprises (MSMEs), such as chatbots. In particular, the results of the usability testing of three chatbots implemented in MSMEs are presented.Design/methodology/approachThe methodology employed includes participants, chatbot development platform, research methodology, software development methodology and usability test to contextualize the study's results.FindingsBased on the results obtained from the System Usability Scale (SUS) and considering the accuracy of the chatbot's responses, it is concluded that the level of satisfaction in using chatbots is high; therefore, if the chatbot is well integrated with the communication systems/channels of the MSMEs, the client receives an excellent, fast and efficient service.Originality/valueThe paper analyzes chatbots for customer service and presents the usability testing results of three chatbots implemented in MSMEs.
PurposeThis paper aims to propose a solution for detecting and grading diabetic retinopathy (DR) in retinal images using a convolutional neural network (CNN)-based approach. It could classify input retinal images into a normal class or an abnormal class, which would be further split into four stages of abnormalities automatically.Design/methodology/approachThe proposed solution is developed based on a newly proposed CNN architecture, namely, DeepRoot. It consists of one main branch, which is connected by two side branches. The main branch is responsible for the primary feature extractor of both high-level and low-level features of retinal images. Then, the side branches further extract more complex and detailed features from the features outputted from the main branch. They are designed to capture details of small traces of DR in retinal images, using modified zoom-in/zoom-out and attention layers.FindingsThe proposed method is trained, validated and tested on the Kaggle dataset. The regularization of the trained model is evaluated using unseen data samples, which were self-collected from a real scenario from a hospital. It achieves a promising performance with a sensitivity of 98.18% under the two classes scenario.Originality/valueThe new CNN-based architecture (i.e. DeepRoot) is introduced with the concept of a multi-branch network. It could assist in solving a problem of an unbalanced dataset, especially when there are common characteristics across different classes (i.e. four stages of DR). Different classes could be outputted at different depths of the network.
PurposeThe purpose of this paper is to create an automatic interpretation of the results of the method of multiple correspondence analysis (MCA) for categorical variables, so that the nonexpert user can immediately and safely interpret the results, which concern, as the authors know, the categories of variables that strongly interact and determine the trends of the subject under investigation.Design/methodology/approachThis study is a novel theoretical approach to interpreting the results of the MCA method. The classical interpretation of MCA results is based on three indicators: the projection (F) of the category points of the variables in factorial axes, the point contribution to axis creation (CTR) and the correlation (COR) of a point with an axis. The synthetic use of the aforementioned indicators is arduous, particularly for nonexpert users, and frequently results in misinterpretations. The current study has achieved a synthesis of the aforementioned indicators, so that the interpretation of the results is based on a new indicator, as correspondingly on an index, the well-known method principal component analysis (PCA) for continuous variables is based.FindingsTwo (2) concepts were proposed in the new theoretical approach. The interpretative axis corresponding to the classical factorial axis and the interpretative plane corresponding to the factorial plane that as it will be seen offer clear and safe interpretative results in MCA.Research limitations/implicationsIt is obvious that in the development of the proposed automatic interpretation of the MCA results, the authors do not have in the interpretative axes the actual projections of the points as is the case in the original factorial axes, but this is not of interest to the simple user who is only interested in being able to distinguish the categories of variables that determine the interpretation of the most pronounced trends of the phenomenon being examined.Practical implicationsThe results of this research can have positive implications for the dissemination of MCA as a method and its use as an integrated exploratory data analysis approach.Originality/valueInterpreting the MCA results presents difficulties for the nonexpert user and sometimes lead to misinterpretations. The interpretative difficulty persists in the MCA's other interpretative proposals. The proposed method of interpreting the MCA results clearly and accurately allows for the interpretation of its results and thus contributes to the dissemination of the MCA as an integrated method of categorical data analysis and exploration.
Purpose The goal of this study is to test the real-world use of an emotion recognition system. Design/methodology/approach The researchers chose an existing algorithm that displayed high accuracy and speed. Four emotions: happy, sadness, anger and surprise, are used from six of the universal emotions, associated by their own mood markers. The mood-matrix interface is then coded as a web application. Four guidance counselors and 10 students participated in the testing of the mood-matrix. Guidance counselors answered the technology acceptance model (TAM) to assess its usefulness, and the students answered the general comfort questionnaire (GCQ) to assess their comfort levels. Findings Results from TAM found that the mood-matrix has significant use for the guidance counselors and the GCQ finds that the students were comfortable during testing. Originality/value No study yet has tested an emotion recognition system applied to counseling or any mental health or psychological transactions.
PurposeThis study aims to validate the content of an instrument which identifies the organizational, sociocultural and technological characteristics that foster digital transformation (DT) in higher education institutions (HEIs) through the Delphi method.Design/methodology/approachThe methodology is quantitative, non-experimental, and descriptive in scope. First, expert judges were selected; Second, Aiken'sVcoefficients were obtained. Nine experts were considered for the validation.FindingsThis study’s findings show that the instrument has content validity and there was strong consensus among the judges. The instrument consists of 29 questions; 13 items adjusted and 2 merged.Originality/valueA novel instrument for measuring the DT at HEIs was designed and has content validity, evidenced by Aiken'sVcoefficients of 0.91 with a 0.05 significance, and consensus among judges evidenced by consensus coefficient of 0.81.
PurposeThe authors propose the concept of “Autonomic Cycle for innovation processes,” which defines a set of tasks of data analysis, whose objective is to improve the innovation process in micro-, small and medium-sized enterprises (MSMEs).Design/methodology/approachThe authors design autonomic cycles where each data analysis task interacts with each other and has different roles: some of them must observe the innovation process, others must analyze and interpret what happens in it, and finally, others make decisions in order to improve the innovation process.FindingsIn this article, the authors identify three innovation sub-processes which can be applied to autonomic cycles, which allow interoperating the actors of innovation processes (data, people, things and services). These autonomic cycles define an innovation problem, specify innovation requirements, and finally, evaluate the results of the innovation process, respectively. Finally, the authors instance/apply the autonomic cycle of data analysis tasks to determine the innovation problem in the textile industry.Research limitations/implicationsIt is necessary to implement all autonomous cycles of data analysis tasks (ACODATs) in a real scenario to verify their functionalities. Also, it is important to determine the most important knowledge models required in the ACODAT for the definition of the innovation problem. Once determined this, it is necessary to define the relevant everything mining techniques required for their implementations, such as service and process mining tasks.Practical implicationsACODAT for the definition of the innovation problem is essential in a process innovation because it allows the organization to identify opportunities for improvement.Originality/valueThe main contributions of this work are: For an innovation process is specified its ACODATs in order to manage it. A multidimensional data model for the management of an innovation process is defined, which stores the required information of the organization and of the context. The ACODAT for the definition of the innovation problem is detailed and instanced in the textile industry. The Artificial Intelligence (AI) techniques required for the ACODAT for the innovation problem definition are specified, in order to obtain the knowledge models (prediction and diagnosis) for the management of the innovation process for MSMEs of the textile industry.
Purpose Sorting is a very important algorithm to solve problems in computer science. The most well-known divide and conquer sorting algorithm is quicksort. It starts with dividing the data into subarrays and finally sorting them. Design/methodology/approach In this paper, the algorithm named Dual Parallel Partition Sorting ( DPPSort ) is analyzed and optimized. It consists of a partitioning algorithm named Dual Parallel Partition ( DPPartition ). The DPPartition is analyzed and optimized in this paper and sorted with standard sorting functions named qsort and STLSort which are quicksort, and introsort algorithms, respectively. This algorithm is run on any shared memory/multicore systems. OpenMP library which supports multiprocessing programming is developed to be compatible with C/C++ standard library function. The authors’ algorithm recursively divides an unsorted array into two halves equally in parallel with Lomuto's partitioning and merge without compare-and-swap instructions. Then, qsort/STLSort is executed in parallel while the subarray is smaller than the sorting cutoff. Findings In the authors’ experiments, the 4-core Intel i7-6770 with Ubuntu Linux system is implemented. DPPSort is faster than qsort and STLSort up to 6.82× and 5.88× on Uint64 random distributions, respectively. Originality/value The authors can improve the performance of the parallel sorting algorithm by reducing the compare-and-swap instructions in the algorithm. This concept can be used to develop related problems to increase speedup of algorithms.
PurposeThis paper purposed a multi-facet sentiment analysis system.Design/methodology/approachHence, This paper uses multidomain resources to build a sentiment analysis system. The manual lexicon based features that are extracted from the resources are fed into a machine learning classifier to compare their performance afterward. The manual lexicon is replaced with a custom BOW to deal with its time consuming construction. To help the system run faster and make the model interpretable, this will be performed by employing different existing and custom approaches such as term occurrence, information gain, principal component analysis, semantic clustering, and POS tagging filters.FindingsThe proposed system featured by lexicon extraction automation and characteristics size optimization proved its efficiency when applied to multidomain and benchmark datasets by reaching 93.59% accuracy which makes it competitive to the state-of-the-art systems.Originality/valueThe construction of a custom BOW. Optimizing features based on existing and custom feature selection and clustering approaches.
PurposeThe amount of features in handwritten digit data is often very large due to the different aspects in personal handwriting, leading to high-dimensional data. Therefore, the employment of a feature selection algorithm becomes crucial for successful classification modeling, because the inclusion of irrelevant or redundant features can mislead the modeling algorithms, resulting in overfitting and decrease in efficiency.Design/methodology/approachThe minimum redundancy and maximum relevance (mRMR) and the recursive feature elimination (RFE) are two frequently used feature selection algorithms. While mRMR is capable of identifying a subset of features that are highly relevant to the targeted classification variable, mRMR still carries the weakness of capturing redundant features along with the algorithm. On the other hand, RFE is flawed by the fact that those features selected by RFE are not ranked by importance, albeit RFE can effectively eliminate the less important features and exclude redundant features.FindingsThe hybrid method was exemplified in a binary classification between digits “4” and “9” and between digits “6” and “8” from a multiple features dataset. The result showed that the hybrid mRMR + support vector machine recursive feature elimination (SVMRFE) is better than both the sole support vector machine (SVM) and mRMR.Originality/valueIn view of the respective strength and deficiency mRMR and RFE, this study combined both these methods and used an SVM as the underlying classifier anticipating the mRMR to make an excellent complement to the SVMRFE.
Cardiovascular disease is a global public health challenge, with its rising prevalence severely impacting quality of life and leading to chronic conditions and fatalities. Monitoring heart rate (HR) is a crucial indicator of cardiac health. Remote photoplethysmography (rPPG) and HR monitoring through videos have shown promise for remote healthcare applications. Various deep learning approaches have reported state-of-the-art results on different datasets. While these results are encouraging, their applicability to real-world deployment is limited due to the presence of different types of biases present in these datasets. We conducted a thorough search on various scholarly databases (e.g., Google Scholar and IEEE Xplore) with keywords “rPPG” or “remote photoplethysmography”, datasets “heart rate” and similar variants. This led us to identify 32 public and private commonly used rPPG datasets. By doing an extensive literature review on 32 commonly used rPPG datasets, we showed that most of the available datasets do not consider important demographic factors along the dimensions of age, sex, ethnicity and including patients during data collection. The most underrepresented category was patients, as only one dataset included them in the study. This could be related to the ease of data collection; however, it could lead to models that may not be generalizable to other groups, demographics or subsets of populations. Overall, our findings reveal that representation bias is present across various rPPG datasets. Our findings are limited to these 32 rPPG datasets, and further investigation of more datasets could reveal insights into the representation bias problem. Biased rPPG datasets could lead to biased deep learning models that may not generalize in real-world conditions, leading to misdiagnosis and under- or over-estimation of HR estimation. Our in-depth analysis provides key insights to researchers to collect inclusive and diverse datasets and develop algorithms to mitigate biases in estimating HR and rPPG among different demographics. This is one of the first literature reviews that delves deeper into common rPPG datasets and evaluates them for the presence of representation bias along the dimensions of age, sex, ethnicity and including patients.
