Research Interest Research Articles

Broadband and tunable fiber polarizer based on a graphene photonic crystal fiber.

The recent flourishing development of two-dimensional (2D) graphene has sparked considerable interest and extensive research on graphene-based optical fiber polarizers. However, studies on graphene-optical fiber polarizers focused on the structure with graphene films attached to side-polished fibers, which face challenges such as low birefringence of 10-6, low polarization extinction ratio (PER), and narrow polarizing window of tens of nanometers. Here, a fiber polarizer based on a graphene-photonic crystal fiber (Gr-PCF) is proposed firstly, which exhibits high birefringence of ∼2.5 × 10-3, high PER of ∼111 dB/mm, broad polarizing window of >400 nm, and tunable polarization states. Graphene or graphene/hBN/graphene (Gr/hBN/Gr) heterojunctions are attached to the surface of two square holes in the PCF to make one of the polarizing modes attenuate significantly. The tunability of the Fermi level (EF) in Gr/hBN/Gr enables the proposed device to function as a polarizer or a polarization-maintaining fiber. The combination of PCF's endless single-mode feature and graphene's broadband optical response feature enables the fiber polarizer to exhibit a wide spectrum range with single-mode transmission characteristics.

Unveiling Global Trends in Reactive and Proactive Aggression: A Cutting-Edge Bibliometric Analysis

This bibliometric mapping discusses the research landscape of proactive and reactive aggression, key authors, collaborative networks, and trends in scholarly publishing for the past two decades. The study, using tools like VOSviewer, shows important patterns in co-authorship, citation networks, and keyword co-occurrence. The leading personalities include Adrian Raine, Paula J. Fite, Richard E. Tremblay, and Paul J. Frick. Heavy contributors to the knowledge about aggression from biological, psychological, and developmental perspectives are identified. Co-authorship is intense, especially on topics dealing with neuro-criminology, childhood and adolescent behavior, and the role of psychopathy in violent behavior. The analysis shows that from the year 2009, the publication of works has grown rapidly to their peak in the year 2022, reflecting an upward spiral of interest and interdisciplinary research on aggression. Dominant keywords like "aggression," "reactive," "proactive," "psychopathy," and "conduct disorder" point to the core themes of research on emotional regulation, developmental trajectories, and clinical interventions. This review has come to a close that studies in the field of aggression have now developed into a multi-disciplinary science, embracing neuroscience, psychology, criminology, and social science knowledge to further advance the understanding of the underlying mechanisms of aggressive behavior and develop various treatments. Future research will have to go on filling in areas of investigation that are underrepresented, including but not limited to aggression at the interface with particular demographic variables and newer approaches to intervention.

Facile synthesis of MOF-derived carbon-supported LaZn@C nanocomposite as an efficient electrode material for supercapacitor

MOF-derived transition metal alloys have attracted researcher's interest in energy storage devices due to their vast surface area, high porosity, adjustable pore sizes, ease of modification, abundant active sites, and 3D tunable structure. Metal alloys covered with carbon can stabilize conductivity and ease charge accumulation, and they are suitable candidates for electrode materials for supercapacitor application. In this research article, core-shell LaZn@C nanocomposites were fabricated at different pyrolysis times via a hydrothermal approach. The materials that pyrolysis for two hours have a remarkable specific capacitance of 1024 F g−1 at 1 A g−1 and an impressive energy density of 36.9 Whkg−1. In addition, it has lower Rp∼0.8 Ω and Rs∼0.2 Ω resistance due to the large surface area's high carbon content with cylindrical particles. Moreover, it shows an outstanding retention rate of (94.5 % over 4500 cycles at 1 A g−1). Finally, this research showed the novelty of advanced MOF-derived materials that suggest an efficient electrode material for the electrochemical performance of energy storage devices and supercapacitor applications.

ANALISIS BIBLIOMETRIK: APPROACHING MATHEMATICS FOR SLOW LEARNERS BERBASIS VOS VIEWER

This research presents a bibliometric analysis of mathematical approaches for slow learners using the VOS Viewer analysis tool. Slow learners often encounter difficulties in understanding mathematical concepts, which are key components of the education curriculum. This study aims to explore trends, patterns, and research focus in this domain and to identify key contributors in the field. Bibliometric methods were employed to analyze a dataset consisting of indexed journals relevant to the chosen topic. The bibliometric method involved collecting journal data from 2019 to 2024 via Google Scholar using the Publish or Perish software, yielding 1,000 journals. Variables related to Approaching Mathematics for Slow Learners that have potential and novelty for future research include gamification, e-learning, critical thinking, student perception, student interest, machine learning, mathematical models, STEM, e-modules, digital literacy, science learning, blended learning, contextual teaching, mathematical formulations, artificial intelligence, scoping review, self-efficacy, intervention approaches, mathematics achievement, mathematical concepts, and action research.

Exploring the structural landscape of DNA maintenance proteins

Evolutionary annotation of genome maintenance (GM) proteins has conventionally been established by remote relationships within protein sequence databases. However, often no significant relationship can be established. Highly sensitive approaches to attain remote homologies based on iterative profile-to-profile methods have been developed. Still, these methods have not been systematically applied in the evolutionary annotation of GM proteins. Here, by applying profile-to-profile models, we systematically survey the repertoire of GM proteins from bacteria to man. We identify multiple GM protein candidates and annotate domains in numerous established GM proteins, among other PARP, OB-fold, Macro, TUDOR, SAP, BRCT, KU, MYB (SANT), and nuclease domains. We experimentally validate OB-fold and MIS18 (Yippee) domains in SPIDR and FAM72 protein families, respectively. Our results indicate that, surprisingly, despite the immense interest and long-term research efforts, the repertoire of genome stability caretakers is still not fully appreciated.

A bibliometric analysis of the application of physical therapy in knee osteoarthritis from 2013 to 2022.

Knee osteoarthritis (KOA) is one of the most common chronic joint diseases. Physical therapy, a non-invasive approach, is extensively used in its treatment. Although bibliometrics is a reliable method to evaluate the significance and impact of research fields, systematic bibliometric analyses in this area are lacking. This study aims to perform a bibliometric analysis covering 2013 to 2022, to highlight the current state, key focuses, and trends in physical therapy for KOA. This study utilizes the Web of Science Core Collection to gather relevant literature on physical therapy and KOA from 2013 to 2022. CiteSpace and VOSviewer software facilitated the visual analysis of the annual publications, geographic and institutional distributions, journals, authors, references, and keywords in this field. The study analyzed 1,357 articles, showing an overall increase in publications over time from 71 countries and 2,302 institutions. The United States and Australia emerged as leaders in this field. The analysis identified 6,046 authors, with Kim L. Bennell as the most prolific and Bellamy N. receiving the most citations. BMC Musculoskeletal Disorders published the most articles, while Osteoarthritis and Cartilage received the most citations. High-impact articles were authored notably by McAlindon TE, Bannuru RR, Fernandes L, and Bennell KL. Keyword analysis highlighted a strong focus on patient self-management, exercise therapy, physical factor therapy, and remote rehabilitation. The bibliometric analysis confirms significant interest and ongoing research in physical therapy for KOA treatment from 2013 to 2022, indicating a growing field. Journals and authors in this area show influential and collaborative dynamics. Future research should focus on enhancing international and institutional collaboration and explore emerging trends like internet-guided treatments.

Towards Fairness-Aware Federated Learning.

Recent advances in federated learning (FL) have brought large-scale collaborative machine learning opportunities for massively distributed clients with performance and data privacy guarantees. However, most current works focus on the interest of the central controller in FL and overlook the interests of the FL clients. This may result in unfair treatment of clients, which discourages them from actively participating in the learning process and damages the sustainability of the FL ecosystem. Therefore, the topic of ensuring fairness in FL is attracting a great deal of research interest. In recent years, diverse fairness-aware FL (FAFL) approaches have been proposed in an effort to achieve fairness in FL from different perspectives. However, there is no comprehensive survey that helps readers gain insight into this interdisciplinary field. This article aims to provide such a survey. By examining the fundamental and simplifying assumptions, as well as the notions of fairness adopted by the existing literature in this field, we propose a taxonomy of FAFL approaches covering major steps in FL, including client selection, optimization, contribution evaluation, and incentive distribution. In addition, we discuss the main metrics for experimentally evaluating the performance of FAFL approaches and suggest promising future research directions toward FAFL.

Representasi Tokoh Sri Asih dalam Film dan Komik Sri Asih

The comic Sri Asih which was produced after the screening of the film Sri Asih, is an innovation in de-ecranization research because de-ecranization tends to focus on changing the vehicle from a film to a novel. The selection of this object was based on the researcher's interest in the character Sri Asih, who is the first female superhero in Indonesia and is no less great than foreign superheroes, as well as to appreciate the new genre of Indonesian cinema that is packaged in the Bumilangit Cinematic Universe. This research aims to describe the characterization of Sri Asih in the film Sri Asih by Upi Avianto and the comic Sri Asih by Rizqi R. Mosmarth and Dody Eka. The research method used is a qualitative descriptive method. This method produces descriptive data originating from personal speech. The intertextuality approach and de-ecranization studies are used to analyze the structure of the film and comic Sri Asih, which focuses on analyzing the plot, setting, characters, and characterization. Meanwhile, the study of de-ecranization serves to add and change variations in the comparison of the two works. The results of the research conducted show that the film and comic Sri Asih both have superhero themes and use a forward plot as a component to form the storyline. Meanwhile, other building elements in the two works are relatively the same. As for the form of transformation from the film Sri Asih into the comic Sri Asih, there are additional variations and changes.

ARTIFICIAL INTELLIGENCE FOR INNOVATION: A BIBLIOMETRIC ANALYSIS AND STRUCTURAL VARIATION APPROACH

Artificial intelligence (AI) has gained significant popularity in recent years. This study critically examines the existing literature on the role and potential of AI, machine learning (ML) and big data in driving innovation. To the best of our knowledge, no existing survey has provided a comprehensive overview of this topic. The aim of this paper is thus to provide a coherent overview of theoretical cornerstones as well as recent trends in research on AI and data analytics for innovation. Using various bibliometric analyses of themes including publication counts and trends, co-citations, co-authorship, and keyword co-occurrence, we infer the thematic structure of AI research in innovation for the period from 1991 to 2021. The publications are grouped into three major clusters, with Cluster 1 remaining a constantly dominant theme in the digital innovation publication landscape. Cluster 2 includes published studies on big data, which also received much research attention. Cluster 3, which is the most prominent, includes business performance, business analytics, and information systems. We also analyse publication citation counts in the literature using Poisson and negative binomial regressions. The results show that the structural variation approach provides a new method for tracking and evaluating the potential of freshly published studies in context. The findings of the current study will be significant in identifying new areas of research of potential interest to scholars and practitioners in the field of AI for innovation worldwide. We conclude this review with limitations and theoretical and practical orientations.

From Simple to Complex Scenes: Learning Robust Feature Representations for Accurate Human Parsing.

Human parsing has attracted considerable research interest due to its broad potential applications in the computer vision community. In this paper, we explore several useful properties, including high-resolution representation, auxiliary guidance, and model robustness, which collectively contribute to a novel method for accurate human parsing in both simple and complex scenes. Starting from simple scenes: we propose the boundary-aware hybrid resolution network (BHRN), an advanced human parsing network. BHRN utilizes deconvolutional layers and multi-scale supervision to generate rich high-resolution representations. Additionally, it includes an edge perceiving branch designed to enhance the fineness of part boundaries. Building on BHRN, we construct a dual-task mutual learning (DTML) framework. It not only provides implicit guidance to assist the parser by incorporating boundary features, but also explicitly maintains the high-order consistency between the parsing prediction and the ground truth. Toward complex scenes: we develop a domain transform method to enhance the model robustness. By transforming the input space from the spatial domain to the polar harmonic Fourier moment domain, the mapping relationship to the output semantic space is highly stable. This transformation yields robust representations for both clean and corrupted data. When evaluated on standard benchmark datasets, our method achieves superior performance compared to state-of-the-art human parsing methods. Furthermore, our domain transform strategy significantly improves the robustness of DTML dramatically in most complex scenes.

Global Trends in Research Related to Emergence Agitation From 1978 to 2023: A Bibliometric Analysis

PurposeEmergence agitation (EA) is a postoperative behavioral disorder characterized by a lack of connection between consciousness and behavior. Despite its clinical importance and prevalence in the postoperative setting, the research focus and knowledge structure remain to be systematically mapped. Therefore, we conducted a bibliometric analysis from 1978 to 2023 to address this gap. This study aims to excavate research hotspots, map knowledge structure, uncover emerging trends, and provide invaluable insights for guiding future research endeavors. DesignA bibliometric analysis of emergency agitation. MethodsWe conducted a literature search in the Web of Science Core Collection for articles on EA published between 1978 and 2023. We collected data on countries, institutions, journals, authors, citations, and keywords. Subsequently, we comprehensively analyzed the gathered knowledge units using three tools, including VOSviewer, HistCite Pro, and ArcGIS Pro. FindingsFrom 1978 to 2023, we retrieved 948 pieces of literature on EA, with the number of publications increasing yearly. China ranked first in the number of publications (n = 253, 26.69%). The United States was the most cited and influential country, closely collaborating with other countries (5,661 citations, H-index 57, citations per publication 37.99, total link strength [TLS] 24). Yonsei University was the most productive and influential institution (n = 18, 1.9%, 427 citations, H-index 12, citations per publication 23.72). Shanghai Jiao Tong University had close collaborative relationships with other universities (TLS 7). The journal with the most publications and influence was Pediatric Anaesthesia (n = 46, 4.92%, H-index 32). Anaesthesia and Analgesia was the most cited journal (2,849 citations). M.T. Aouad was the most influential and productive author devoted to studying EA (n = 6, 0.63%, 173 citations, TLS 3,002). The most influential reference was “Greater incidence of delirium during recovery from sevoflurane anaesthesia in preschool boys” (author J. Aono, No. 19, IF = 8.8, Q1, local citation score 147). Hot research directions in EA include EA and emergence delirium, propofol and EA, risk factors of EA, EA in pediatric anaesthesia, dexmedetomidine, and EA induced by sevoflurane. Esketamine, nalbuphine, sugammadex, and dezocine are drugs that have received increased attention in recent years. ConclusionsThe study mapped the knowledge structure of EA and identified six prominent research directions, four drugs of significant research interest, and emerging thematic trends. These findings offer insights into the current state of research on EA, providing a comprehensive view of the field's landscape.

Critical Thinking Skills and Reading Proficiency among the English Language Students of Public Higher Education Institutions (HEIs) in Sulu

The sobering realization of the critical thinking and the difficulty in the language comprehension, specifically in English language piques the researcher's interest in learning more about the experiences of tertiary students majoring in English language studies at other public HEIs in Sulu. This study sought to investigate the significant difference in the extent of critical thinking skills and reading proficiency among the English language students. This study employed a variety of statistical techniques, including the adopted weighted mean, standard deviation, t-Test for independent samples, One-way ANOVA, and Pearson’s r test of correlation to analyze the reading comprehension and critical thinking skills among English language learners in Sulu's public HEIs throughout the 2023–2024 academic year. A surveyed has been conducted on 200 female students aged 20-21 from public Higher Education Institutions (HEIs) in Sulu, revealing high critical thinking abilities and average reading proficiency ratings. Students' demographic profiles did not significantly influence their assessment of critical thinking or perceived reading proficiency. The study supports Anderson's Theory of Schema, which suggests that comprehension is an interactive process involving the reader's background knowledge and the text, requiring the ability to relate the material to one's own knowledge. The school administration will partner with language teachers to provide reading materials that enhance students' critical thinking skills and reading proficiency. Teachers must guide students to comprehend texts thoroughly, while parents play a crucial role in their children's future. Students will develop the ability to comprehend texts thorough through books and other reading materials provided by teachers. The objective of this study is to offer a foundation for upcoming researchers to enhance their own investigations on critical thinking abilities and reading competence within their field of study. The study will be conducted during the Academic Year 2023-2024 in Sulu province.

Efektivitas Metode Resitasi Terhadap Hasil Belajar Matematika Siswa Kelas VIII Mtsn 4 Bojonegoro

Mathematics learning in MTsN 4 Bojonegoro is less effective, especially on the subject of circles. This is because in the learning process they still use conventional methods or lectures. So that this study is based on the researcher's interest in applying the recitation method to the learning process in MTsN 4 Bojonegoro. The problem in this study is: which is more effective between learning with the recitation method or conventional learning on the mathematics learning outcomes of grade VIII students on the subject of the MTsN 4 Bojonegoro circle for the 2023/2024 academic year. This research aims to find out: the effectiveness of the recitation method on learning outcomes mathematics for class VIII students on the subject of the MTsN 4 Bojonegoro circle for the 2023/2024 academic year. The population of this study were class VIII students in semester 2 of MTsN 4 Bojonegoro who were divided into seven classes. Sampling was carried out using a cluster random sampling technique, class VIII A students were obtained as the experimental class, while the control class was class VIII D. In the experimental group learning used the recitation method, while the control group used the conventional method (lecture).

AMARL: An Attention-Based Multiagent Reinforcement Learning Approach to the Min-Max Multiple Traveling Salesmen Problem.

In recent years, the multiple traveling salesmen problem (MTSP or multiple TSP) has received increasing research interest and one of its main applications is coordinated multirobot mission planning, such as cooperative search and rescue tasks. However, it is still challenging to solve MTSP with improved inference efficiency as well as solution quality in varying situations, e.g., different city positions, different numbers of cities, or agents. In this article, we propose an attention-based multiagent reinforcement learning (AMARL) approach, which is based on the gated transformer feature representations for min-max multiple TSPs. The state feature extraction network in our proposed approach adopts the gated transformer architecture with reordering layer normalization (LN) and a new gate mechanism. It aggregates fixed-dimensional attention-based state features irrespective of the number of agents and cities. The action space of our proposed approach is designed to decouple the interaction of agents' simultaneous decision-making. At each time step, only one agent is assigned to a non-zero action so that the action selection strategy can be transferred across tasks with different numbers of agents and cities. Extensive experiments on min-max multiple TSPs were conducted to illustrate the effectiveness and advantages of the proposed approach. Compared with six representative algorithms, our proposed approach achieves state-of-the-art performance in solution quality and inference efficiency. In particular, the proposed approach is suitable for tasks with different numbers of agents or cities without extra learning, and experimental results demonstrate that the proposed approach realizes powerful transfer capability across tasks.

Investigasi Sistem Pemasaran Produk Halal Olahan Edamame Mitratani 27 Kabupaten Jember

Marketing is very important in the world of business or entrepreneurship, whether large scale or small, medium or large scale. Marketing is an accomplice of leading companies. As the company's front line in achieving profits, of course, the people in this section must have reliable abilities, be active, and also not give up easily when facing business competition to win market share of the business they rely on. In this case, it is very important to implement marketing strategies at PT Mitratani Dua Tujuh in order to meet the needs and desires of customers on a national and international scale. This type of research uses field research. This research is based on the researcher's interest in Edamame Processed Products PT. Mitra Tani Dua Tujuh, especially in marketing strategies for halal products (PT. Mitra Tani Dua Tujuh) PT. Mitratani Dua Tujuh begins with the production process to the edamame marketing process which involves many parties. With collaboration between business partners, edamame has been successfully marketed to local and international markets. The network involved in the production process is all PT employees. Mitratani is involved in the process of providing raw materials, the edamame cultivation process, and the edamame processing process in the factory. The network involved in the marketing process is all parties or institutions involved in the marketing process of PT Mitratani products, such as Mitratani 27 Outlate distributors, IKBI (Wives' Extended Family Association) Mitra Tani 27 employees, PT Perkebunan Nusantara, PT Rolas Medika Nusantara, UPTPS Tresna Werdha Jember, the Agro-Industry Workers Union (SPA) and several agencies that collaborate with Mitra Tani 27 Jember.

HISTORICAL SPECIAL INTEREST TOURISM: THE EVOLUTION OF MOUNTAINEERING IN SOUTH AFRICA

Scholarship on special interest tourism has burgeoned since the 1980s. Although this expanding research interest is relatively new, the phenomenon of special interest tourism is not of recent origin as many of its forms, such as mountaineering, exhibit a long historical record. Most research on special interest tourism concentrates on contemporary issues. The objective is to present a historical perspective on special interest tourism. Using archival sources an analysis is undertaken of the evolution of mountaineering in South Africa as a recreational sport and incipient form of special interest tourism. Cape Town’s Table Mountain and the Drakensberg mountains provide the geographical focus of discussion. The results demonstrate that during the 1920s and 1930s tourism promoters in South Africa acknowledged the potential of special interest mountaineers to contribute to tourism growth. The documented experience of early mountaineering in South Africa provides an example of racism in recreation by showing that the country’s recreational practices became constructed around politicallyimposed racial hierarchies.

Bifunctional Catalysts for CO2 Reduction and O2 Evolution: A Pivotal for Aqueous Rechargeable Zn-CO2 Batteries.

The quest for the advancement of green energy storage technologies and reduction of carbon footprint is determinedly rising toward carbon neutrality. Aqueous rechargeable Zn-CO2 batteries (ARZCBs) hold the great potential to encounter both the targets simultaneously, i.e., green energy storage and CO2 conversion to value-added chemicals/fuels. The major descriptor of ARZCBs efficiency is allied with the reactions occurring at cathode during discharging (CO2 reduction) and charging (O2 evolution) which own different fundamental mechanisms and hence mandate the employment of two different catalysts. This presents an overall complex and expensive battery system which requires a concrete solution, while the development and application of a bifunctional cathode catalyst toward both reactions could reduce the complexity and cost and thus can be a pivotal for ARZCBs. However, despite the increasing research interest and ongoing research, a systematic evaluation of bifunctional catalysts is rarely reported. In this review, the need of bifunctional cathode catalysts for ARZCBs and associated challenges with strategies have been critically assessed. A detailed progress examination and understanding toward designing of bifunctional catalyst for ARZCBs have been provided. This review will enlighten the future research approaching boosted performance of ARZCBs through the development of efficient bifunctional cathode catalysts.

Homestay Tourism as Tourism Development in Pemuteran Traditional Village

Homestay tourism is an activity in a homestay located in a traditional village environment. Homestay tourism is a special attraction for visiting tourists. Homestay tourism has not been widely utilised by homestay owners and managers. Homestay tourism is a new challenge for residents in meeting the needs of tourists. This is one of the causes of the researcher's interest in conducting research related to Homestay Tourism as a tourism development. The research aims to obtain information on the needs of homestay tourism in facing the challenges of tourism development, contributing to improving the economy of local communities, preserving local culture, preserving local culture and the surrounding environment, and being able to find novelty in the world of hospitality to increase the economic value of local communities. This research uses a qualitative action research method using a problem approach by mapping tourism objects, making observations, and taking documentation of homestay owners and managers. The results of the study show that homestay tourism is capable of standardised tourism development, increasing the economic value of local communities, helping local economic development, and preserving their cultural heritage. The researcher hopes that there will be ongoing and continuous research

Meta-Analysis: Investigating the Emotional Intelligence among Undergraduate Students

The concept of emotional intelligence has long been a subject of keen interest and extensive research. The present study aims to find the level of EI of students in Pakistan by conducting meta-analysis emphasizing gender differences and educational impact. Utilizing a meta-analysis of peer-reviewed studies from multiple Database like Google scholar, SCOPUS, Mendeley were searched published between January 2020 to June 2024. The findings revealed that EI significantly influences performance in academics, personal development, and social interactions. Despite minimal gender differences, EI competencies such as self-awareness, empathy, and emotional regulation are very important for students' holistic development. The study indicates the integration of EI training into university curricula and suggested professional development for teachers, provide counseling services to students, and engage students in extracurricular activities to cultivate EI. Suggestion to conduct Longitudinal research is for further understand the long-term benefits of EI development were given. This comprehensive analysis provides information to educators and policy makers on the EI’s importance in cultivating adaptable, empathetic and resilient individuals.

Automatic Generation of Insights From Workers’ Actions in Industrial Workflows With Explainable Machine Learning: A Proposed Architecture With Validation

New technologies, such as machine learning (ML), have provided great potential for evaluating industry workflows and automatically generating key performance indicators (KPIs). However, despite established standards for measuring the efficiency of industrial machinery, there is no precise equivalent for workers’ productivity, which would be highly desirable given the lack of a skilled workforce for the next generation of industry workflows. Therefore, an ML solution combining data from manufacturing processes and workers’ performance for that goal is required. Additionally, in recent times intense effort has been devoted to explainable ML approaches that can automatically explain their decisions to a human operator, thus increasing their trustworthiness. We propose to apply explainable ML solutions to differentiate between expert and inexpert workers in industrial workflows, which we validate at a quality assessment industrial workstation. Regarding the methodology used, input data are captured by a manufacturing machine and stored in a NoSQL database. Data are processed to engineer features used in automatic classification and to compute workers’ KPIs to predict their level of expertise (with all classification metrics exceeding 90%). These KPIs and the relevant features in the decisions are textually explained by natural language expansion on an explainability dashboard. These automatic explanations made it possible to infer knowledge from expert workers for inexpert workers. The latter illustrates the interest of research in self-explainable ML for automatically generating insights to improve productivity in industrial workflows.