Historical Information Research Articles

THE OTTOMAN SIEGE AND CONQUEST OF SHKODRA IN THE 15TH CENTURY ACCORDING TO THE JOURNAL GLAS CRNOGORCA (VOICE OF MONTENEGRO)

The paper examines the appendix on the Ottoman siege of Shkodra in 1474, which was published in two issues of the weekly newspaper Glas Crnogorca (Voice of Montenegro) in December 1896. The appendix is a translation of an article written by the Italian sub-lieutenant Eugenio Barbarich, which was published in the magazine Rivista Militare Italiana at the end of 1896. The historical theme was inspired by the marriage between the heir to the Italian throne and the daughter of the Montenegrin ruler, which resulted in a political alliance between the Kingdom of Italy and the Principality of Montenegro. Under these circumstances, it was important to remind the citizens of the united Venetian and Montenegrin armies that defended Shkodra against Ottoman attacks in the 15th century. The two countries’ insistence on forming an alliance can be explained by the need to prove continuity and draw parallels between historical and contemporary events. It is for this reason that this article has been written, which must be examined to determine the extent to which it provides accurate historical information about a significant event of the 15th century.

Kohelet, Sadducees and Pharisees

Abstract According to my recent research, the book of Kohelet has a link to the emergence of the Sadducees (Mandey, 2023). As a product of a thought movement, Kohelet could be the forerunner of Sadduceism. This paper aims to give a closer look at the link between Kohelet and Sadduceism as well as examine their relationship with the Pharisees as another movement that emerged alongside the Sadducees. Despite the challenges of historical information about the emergence of both the Sadducees and the Pharisees, a socio-historical analysis is conducted using literary sources.

Unit information Dirichlet process prior.

Prior distributions, which represent one's belief in the distributions of unknown parameters before observing the data, impact Bayesian inference in a critical and fundamental way. With the ability to incorporate external information from expert opinions or historical datasets, the priors, if specified appropriately, can improve the statistical efficiency of Bayesian inference. In survival analysis, based on the concept of unit information (UI) under parametric models, we propose the unit information Dirichlet process (UIDP) as a new class of nonparametric priors for the underlying distribution of time-to-event data. By deriving the Fisher information in terms of the differential of the cumulative hazard function, the UIDP prior is formulated to match its prior UI with the weighted average of UI in historical datasets and thus can utilize both parametric and nonparametric information provided by historical datasets. With a Markov chain Monte Carlo algorithm, simulations and real data analysis demonstrate that the UIDP prior can adaptively borrow historical information and improve statistical efficiency in survival analysis.

대형언어모델(LLM)의 역사지리 지식과 AI 역사지도 제작 가능성의 모색

The purpose of this study is to analyze the current state of historical geographic knowledge of Large Language Model (LLM) and to explore whether it is possible to create AI historical maps using LLM historical geographic knowledge. First, I analyzed the answers to historical geographic queries by point, line, and area geometry type for OpenAPI's ChatGPT, Google's Gemini, and Naver's ClovaX, which are major LLM-based GPT services, and estimated the causes of errors. Second, to explore the possibility of AI historical mapping, I created a map of Eupchi(邑治, administrative center) in Gyeonggi-do during the Joseon Dynasty. Then, I compared the current location information of the Eupchi provided by LLM with the results of the Eupchi restored by historical GIS for each county. The results showed that LLM is capable of answering a limited number of queries related to historical geographic information in Korea. However, various errors were found, the main reasons for which are, first, that the characteristics of geographic data are difficult to describe in text alone, and second, that the current LLM technology has limitations in handling historical geographic information consisting of multiple time layers, and third, there is a lack of publicly available historical geographic information. To improve these issues, I propose the construction of historical GIS (HGIS) layers on an ongoing basis and the knowledge expansion of LLM models through semantic data of historical geography.

The possibilities of using historical data on Tambov church monuments of the late 18th – first half of the 19th century in the development of an interactive map

Importance. A number of factors are considered: the possibility of providing relevant historical information to a wide audience, the use of modern technologies for analyzing and distributing historical information, and the significant interest of historians in working within the framework of the methodology used. The purpose of the study is to offer a resource for popularizing the church history of the region. The main sources are used in the work are plans of the city of Tambov and documents from the funds of the Tambov City Duma (16) and the Mezhevaya Chancellery (29) of the State Archive of the Tambov Region, some reference and visual materials, as well as a view of the city of Tambov in 1799.Research Methods. Both classical historical methods and the methodology of historical informatics are used.Results and Discussion. The relevance of modern information technologies use in scientific and educational activities is substantiated. A historiographical analysis of the problem has been carried out, which relates to the theoretical part of the study. The problems associateы with the localization of lost objects on modern maps and their solutions are described, which can be attributed to the practical part. Variants of references of the church history objects of Tambov city for an interactive map of the church history objects of Tambov at the end of the 18th – first half of the 19th century are proposed for consideration. The process of collecting and systematizing information for the formation of historical references of ancient religious buildings in Tambov: the Znamenskaya Church, the Church in the name of the Great Martyr Barbara and the Church of the Life-Giving Trinity is described.Conclusion. The main result of the study is the images demonstration of attaching cartographic, visual and descriptive data on the history of specific monuments of church history to maps.

CONTEXTUAL APPROACH TO TEACHING THE ELECTIVE DISCIPLINE “THEORY OF MASS COM- MUNICATION” TO BACHELORS OF PEDAGOGICAL UNIVERSITIES (SPECIALITIES “GEOGRAPHY” AND “MUSICAL ART”)

The article covers the main principles of the contextual approach in studying the elective course “Theory of Mass Communication” in pedagogical universities. The aim of the article is to substantiate the effectiveness of applying the contextual approach to teaching the elective course “Theory of Mass Communication” to undergraduate students in pedagogical universities (specialties “Geography” and “Music Art”); to develop situational tasks aimed at fostering media literacy, the ability to codify, and the creation of informational sectoral blocks for dissemination in educational and media spaces. In the research, methods of content analysis, specification, problem-posing, as well as task-based and contextual approaches were used. It has been found that the study of university-wide elective courses appeals to interdisciplinarity in thematic correlation. On the one hand, it involves developing a system of situational tasks that contribute to improving the professional training of students in the specialties “Geography” and “Music Art”. It has been substantiated that the contextual approach is oriented towards teaching material based on methodological foundations, theoretical sectoral knowledge, and forms of activity. The context in the study of academic disciplines involves transforming didactic material, where the objective meanings and significance of sectoral knowledge are transformed into the personal experience of the future teacher. The integral platform allows for the design of situational tasks, the resolution of which combines educational and educational-professional experience. Situational tasks, based on the contextual approach to teaching the course “Theory of Mass Communication”, are built considering the professional training of students in higher pedagogical institutions in the specified specialties (“Geography” and “Music Art”). The didactically processed field of mass communication as a university-wide discipline encompasses thematic blocks such as “Basics of Mass Communication”, “Artistic and Aesthetic Parameters of Mass Com- munication”, “Sociological and Psychological Dimensions of Mass Communication”, and “Mass Communi- cation in the Conditions of Digital Society”. A diachronic consideration of the development of mass communications allows for identifying the cul- tural and historical factors that shape the transmission paths of channels aimed at the recipients of certain knowledge. Addressing the diachronic consideration of mass media information significantly expands the un- derstanding of its essence and the processes of information transmission within mass communication models. It has been outlined that the social and psychological aspects of mass communication determine the language behaviour of professional communicators. This specific feature was taken as the basis in develop- ing situational tasks for communicators – future geographers and musicians. The prepared tasks were cor- related with the normative disciplines studied at the stage of professional training. It has been concluded that studying the elective course “Theory of Mass Communication” based on the contextual approach contributes to the development of professional competencies of teachers who transmit sec- toral information in the conditions of the informational educational environment. It has been proved that the study of semiotics of mass communication should be considered at the level of modelling cultural codes (since geographical names, musical and artistic works contain cultural and historical information, which is actualized in educational discourse at the stage of transmitting sectoral knowledge). Situational tasks, aimed at transmitting sectoral information at the level of a professional communicator (manifestation of language culture), should ap- peal to conducting press conferences as a type of communication, building one’s professional image. The expe- rience of students working with advertising material considering the professional training direction is positive.

A Robust Monocular and Binocular Visual Ranging Fusion Method Based on an Adaptive UKF.

Visual ranging technology holds great promise in various fields such as unmanned driving and robot navigation. However, complex dynamic environments pose significant challenges to its accuracy and robustness. Existing monocular visual ranging methods are susceptible to scale uncertainty, while binocular visual ranging is sensitive to changes in lighting and texture. To overcome the limitations of single visual ranging, this paper proposes a fusion method for monocular and binocular visual ranging based on an adaptive Unscented Kalman Filter (AUKF). The proposed method first utilizes a monocular camera to estimate the initial distance based on the pixel size, and then employs the triangulation principle with a binocular camera to obtain accurate depth. Building upon this foundation, a probabilistic fusion framework is constructed to dynamically fuse monocular and binocular ranging using the AUKF. The AUKF employs nonlinear recursive filtering to estimate the optimal distance and its uncertainty, and introduces an adaptive noise-adjustment mechanism to dynamically update the observation noise based on fusion residuals, thus suppressing outlier interference. Additionally, an adaptive fusion strategy based on depth hypothesis propagation is designed to autonomously adjust the noise prior of the AUKF by combining current environmental features and historical measurement information, further enhancing the algorithm's adaptability to complex scenes. To validate the effectiveness of the proposed method, comprehensive evaluations were conducted on large-scale public datasets such as KITTI and complex scene data collected in real-world scenarios. The quantitative results demonstrate that the fusion method significantly improves the overall accuracy and stability of visual ranging, reducing the average relative error within an 8 m range by 43.1% and 40.9% compared to monocular and binocular ranging, respectively. Compared to traditional methods, the proposed method significantly enhances ranging accuracy and exhibits stronger robustness against factors such as lighting changes and dynamic targets. The sensitivity analysis further confirmed the effectiveness of the AUKF framework and adaptive noise strategy. In summary, the proposed fusion method effectively combines the advantages of monocular and binocular vision, significantly expanding the application range of visual ranging technology in intelligent driving, robotics, and other fields while ensuring accuracy, robustness, and real-time performance.

Dynamic constrained multi-objective optimization algorithm based on co-evolution and diversity enhancement

Dynamic constrained multi-objective optimization problems (DCMOPs) involve objectives, constraints, and parameters that change over time. This kind of problem presents a greater challenge for evolutionary algorithms because it requires the population to quickly track the changing pareto-optimal set (PS) under constrained conditions while maintaining the feasibility and good distribution of the population. To address these challenges, this paper proposes a dynamic constrained multi-objective optimization algorithm based on co-evolution and diversity enhancement (CEDE), in which we have made improvements to both the static optimization and dynamic response parts, innovatively utilizing the valuable information latent in the optimization process to help the population evolve more comprehensively. The static optimization involves the co-evolution of three populations, through which their mutual synergy can more comprehensively identify potential true PS and provide more useful historical information for dynamic response. Additionally, to prevent the elimination of potentially valuable infeasible individuals (i.e., individuals that are not dominated by feasible individuals) due to pareto domination, we employ an archive set to store and update these individuals. When the environment changes, to effectively enhance population diversity under complex dynamic constraints and help the population to respond quickly to changes, we propose a diversity enhancement strategy, which includes a diversity maintenance strategy and a center point-based exploration strategy. This strategy effectively enhances population diversity in complex and changing environments, helping the population respond quickly to changes. The effectiveness of the algorithm is validated through two test sets. The experimental results show that CEDE can effectively use valuable information to cope with complex dynamic constraint environments. Compared with several of the most advanced algorithms, it is superior in 94% of the test problems, demonstrating strong competitiveness in handling DCMOPs.

Khūrigān: a Recently Discovered Post-Achaemanid Rock-Cut Tomb near Naqsh-e Rostam, Iran

Abstract Near the northwestern-southeastern foothills of the Marvdasht plain in Fars province, lie a range of ancient necropoleis which date from the reign of Darius I, the Achaemenid king and until the first century after the Muslim conquest. The well-known necropoleis of Naqsh-e Rostam and Persepolis have the most complex tombs among them. However, there are other burials in this region, although smaller and simpler or even imitative, which have considerable archeological importance, since they provide information for the social and political understanding of their time of creation, often known as the dark ages. The present study aims to introduce and analyze the structural-chronological features of the rock-cut tomb of Khūrigān, one of the recent discoveries near Naqsh-e Rostam. Regarding the architectural and stylistic characteristics of the tomb and its context, as well as considering its archeological landscape and using historical information, the period from the last century of the Achaemenid reign until the beginning of the Sassanid dynasty is considered for the general chronology of this tomb; however, through applying a more detailed perspective, we can attribute the chronology of this tomb to the first half of the 3rd until the 1st century BC.

STRUCTURAL AND SEMANTIC FEATURES OF BRITISH TOPONYMS

The article is devoted to the review of structural and semantic features of British toponyms. The study of toponyms helps to understand the linguistic image of the world, highlighting ethnic experience and culture. Toponyms are important as means of transmitting historical, cultural, and other information across generations, which makes their study relevant in linguistics. The proper names of British territories are very diverse, as the country has been home to various civilizations and peoples for many centuries, each of which contributed to the language through their own names. In this work, 200 toponyms from three regions of Great Britain were investigated. According to the origin, the researched toponyms are divided into native and borrowed. Native proper names predominate in England, while toponyms of Scandinavian origin are found in the northern regions and the west of the country. Wales and Scotland are characterized mainly by Celtic names. Borrowed toponyms are distinguished according to four linguistic sources: Celtic, Latin, Scandinavian and Norman-French. English contains more loanwords because it is open to receiving words from other languages due to contact with other cultures and colonial heritage. In general, people who named geographical objects were guided by the features of the landscape where this object was located. This category of toponyms occurs in all three parts of Britain and has many subgroups. The emergence of this group is a logical consequence of the fact that the ancestors of the British named their surroundings according to what they saw. When creating and choosing toponyms, a certain pragmatic orientation can be observed, which depends on various factors, such as the historical context of naming, the level of cultural development, social, political, religious or patriotic motives of persons who give certain names to geographical objects. This layer of vocabulary is of great interest to researchers because it can collect linguistic, sociocultural and historical experience.

Point cloud registration via sampling-based evolutionary multitasking

Point cloud registration (PCR) is an important task in both computer vision and pattern recognition. However, since the success of most existing two-stage PCR methods largely depends on the implicit assumption that the first coarse registration stage can provide an approximately optimal initial transformation for the second fine stage, these methods suffer from low success rate when the assumption is not satisfied. Evolutionary multitasking can find better solutions for multiple tasks simultaneously by transferring knowledge among multiple related tasks. Inspired by evolutionary multitasking, this study proposes a sampling-based multitask optimization method for PCR, which solves the problem of low registration success rate by sharing knowledge between two related tasks generated by a dataset. Specifically, one task is for roughly aligning the sampled point cloud, and the other is for the original unsampled point cloud. The main purpose of the first task is to continuously provide useful knowledge to the second task so that it can achieve precise alignment. Then, a new knowledge transfer mechanism guided by historical information is proposed, which can effectively adjust the search behavior of the original unsampled task. In addition, we develop a dynamic task complement strategy to complement the accuracy that may be lost by downsampling. The results on five different datasets show that the proposed method can achieve higher registration accuracy with higher success rate compared to other state-of-the-art PCR methods.

Risk analysis of lithium-ion battery accidents based on physics-informed data-driven Bayesian networks

The catastrophic consequences of lithium-ion battery (LIB) accidents have attracted high attention from society and industry. Accordingly, risk analysis is indispensable for the risk prevention and control of LIBs. Nevertheless, it is difficult to establish a physics-informed risk analysis model due to the complex material characteristics and aging mechanisms of LIBs. Meanwhile, the data-driven approach requires historical information of LIBs and does not merely rely on knowledge of the internal mechanisms of LIBs. This study proposes a method integrating the physics-informed Bayesian network (BN) (i.e., mapping from fault tree) and data-driven BN (i.e., learning from data) to conduct risk analysis of LIBs. First, we establish physics-informed and data-driven BNs. Subsequently, we bridge physics-informed and data-driven BNs to establish a Bayesian network for risk analysis of LIB accidents. Second, we set up safety barriers in the system, including detectors, emergency response, and firefighting facilities. Third, we evaluate the performance of safety barriers. We validate the proposed model using data from LIBs in air transportation. The results indicate that safety barriers can reduce the accidental risk of LIBs. Eventually, we propose suggestions for the risk control of LIBs in air transportation. This study is supposed to provide theoretical basis for the risk prevention and control of LIB accidents.

Trip Planner (using Generative AI)

The aim of this project is to develop an AI based travel planner that intends to alter planning and excursion encounters for people. Using sophisticated models and instructions for computers, such as statistical techniques applied in learning how humans learn best from their past experiences so they can anticipate future instances on them even when these are unknown for sure beforehand; data showing different types of transportation methods including those involving moving oneself put up for sale together with lodging places like hotels; field trips or tours where individuals can go out and participate in other events besides just sitting at home – all serving as input sources yielding recommendations specific enough standalone resources without being overly complex through averaging available data over time (Hong 2012). The In this regard, the trip planner will evaluate the personal user tastes, historical information concerning the destinations, as well as the contemporary pieces of advice on where to go today, where to get an accommodation or how to move by different types of vehicles, what to do. Besides, the system will support the natural language communication.

Dynamic memory-based event-triggered security control for networked control systems subjected to false-injection-data attack

This study addresses the security control problem for networked control systems that are subjected to false-data-injection attacks. The designed controller rests on a dynamic memory-based event-triggered mechanism, which exploits historically transmitted data and an auxiliary term to improve transmission efficiency and ensure satisfactory control performance. Then, a controller that defends against the false-data-injection attacks is proposed by making full use of the historical information. With the aid of Cauchy–Schwarz and Gronwall–Bellman inequalities, the existence of such a controller is validated through a novel Lyapunov-based method, which allows the Lyapunov function to be nonpositive. Further, a test on a dynamic power system is provided to verify the effectiveness and superiority of the proposed method.

Персуазивная роль этнонимов в испанском электоральном дискурсе

The article examines the persuasive impact of ethnonyms and ethnic categories on the voters in Spanish electoral discourse. In the modern world, the mechanisms of political communication are generating a growing interest. It is explained by the influence of political processes on all spheres of society, the fate of peoples and entire states, and the interests of every citizen. Therefore, political problems remain relevant at all times. The important role of electoral discourse, which has a pronounced persuasive effect on the voters, should be highlighted. When struggling for power, leaders and representatives of Spanish political parties, naturally, strive to establish trust, exert a certain emotional impact on potential voters and induce them to make the “correct” electoral decision, i.e. to vote for their party. It should be noted that persuasiveness has not only an argumentative, but also a manipulative component, forcing an addressee to act in the interests of the sender of the message. One of the persuasive speech mechanisms of Spanish electoral discourse is the use of ethnonyms in the election programmes of political parties. Ethnonyms contain valuable historical, ethnographic, cultural and linguistic information and, accordingly, cover the religious, cultural and historical spheres, as well as play an important role in intercultural communication. Ethnic identity includes the desire of peoples to preserve their identity, the uniqueness of their culture, language and worldview. Ethnonyms allow native speakers to identify their own traits and stereotypes. The essence of cultural, spiritual and political life is revealed through language. Thus, the study of ethnonyms and ethnic categories, as well as their functions in political discourse, is an urgent task of modern linguistics.

Original or post-war paintings? The fixed wooden scenery of the Teatro Olimpico in Vicenza: a guided multidisciplinary approach based on scientific analyses and HBIM

Archival resources, a photogrammetric survey, analysis of materials and techniques, and evaluation of the state of conservation were interconnected phases in the interdisciplinary research on the perspective scenery of the Teatro Olimpico in Vicenza. To fill existing gaps related to the history of this unique artefact and to the undocumented retouching of paint layers on the scenery during post-war reconstruction work, a broad analytical approach (optical microscopy, XRPD, SEM–EDX, μFTIR and μRaman) was applied to micro-samples, the selection of which was guided by consolidated geometrical and archival data. The aims were to obtain a characterisation of the pigments and binders and to evaluate the microstratigraphic sequence, the state of conservation of the scenery flats, and the deterioration processes involved. The findings unveiled a discernible variability in the production techniques of the finishes, frequently lacking the classic microstratigraphic sequence associated with the traditional method for painting on wooden panels from the sixteenth century. Moreover, by identifying many pigments that could be used as temporal markers we were able unequivocally to establish, for the first time, that a significant part of the scenery designed by the architect Vincenzo Scamozzi was heavily repainted in the post-WWII period. These analytical results and all the data collected on the artefacts over time were related through an HBIM model, enabling the historical and technical-analytical information to be linked to the geometrical survey and thus to provide guidance for actions based on current and future knowledge for the maintenance and monitoring of the Teatro Olimpico.

Borrowing Historical Information Across All Concentration Groups with an Application of Potency Estimation in Aquatic Toxicity Assessment

AbstractAquatic toxicity tests assess the negative impact of toxicants on survival, reproduction, and growth of organisms. Since the tests are often repeated in the same laboratory, borrowing historical experimental outcomes that are congruent would increase the precision of potency estimation with current data. In this paper, we extend the historical borrowing from control only to historical data from all concentration levels in toxicity assessments with current data using the calibrated power prior. We assume the transportability (i.e., identical concentration–response relationship) between historical and current experimental outcomes while penalizing the historical data borrowing in each concentration group independently with a modified distribution-informed calibration process. This modified calibration process prevents the over/underfitting issues by sufficiently exploring the distribution of congruence level and allows researchers to determine the level of historical information borrowing, either conservatively or aggressively, from a data-driven perspective. The effectiveness and flexibility of our proposed method are demonstrated via simulation studies. As shown in the simulation study, in scenarios when the transportability assumption fails, the proposed method still tremendously aids in the precision of toxicity assessment. The proposed method is applied in a $$\textit{Ceriodaphnia dubia}$$ Ceriodaphnia dubia test.

Adversarial Robustness Enhancement for Deep Learning-Based Soft Sensors: An Adversarial Training Strategy Using Historical Gradients and Domain Adaptation.

Despite their high prediction accuracy, deep learning-based soft sensor (DLSS) models face challenges related to adversarial robustness against malicious adversarial attacks, which hinder their widespread deployment and safe application. Although adversarial training is the primary method for enhancing adversarial robustness, existing adversarial-training-based defense methods often struggle with accurately estimating transfer gradients and avoiding adversarial robust overfitting. To address these issues, we propose a novel adversarial training approach, namely domain-adaptive adversarial training (DAAT). DAAT comprises two stages: historical gradient-based adversarial attack (HGAA) and domain-adaptive training. In the first stage, HGAA incorporates historical gradient information into the iterative process of generating adversarial samples. It considers gradient similarity between iterative steps to stabilize the updating direction, resulting in improved transfer gradient estimation and stronger adversarial samples. In the second stage, a soft sensor domain-adaptive training model is developed to learn common features from adversarial and original samples through domain-adaptive training, thereby avoiding excessive leaning toward either side and enhancing the adversarial robustness of DLSS without robust overfitting. To demonstrate the effectiveness of DAAT, a DLSS model for crystal quality variables in silicon single-crystal growth manufacturing processes is used as a case study. Through DAAT, the DLSS achieves a balance between defense against adversarial samples and prediction accuracy on normal samples to some extent, offering an effective approach for enhancing the adversarial robustness of DLSS.

Application of Fashion Element Trend Prediction Model Integrating AM and EfficientNet-b7 Models in Art Design

With the rapid development of the fashion industry and the increasing diversification of consumer needs, accurately predicting the fashion trends of clothing elements has become an urgent problem in the field of art design. In order to solve these problems, this paper uses deep learning technology for fashion trend prediction and optimization of prediction models. Firstly, the EfficientNet-b7 model is constructed as an attribute predictor to accurately extract the attributes of clothing image elements. Then, based on user information, popular elements are grouped and counted to solve the problem of different populations having different opinions on popular trends. The prediction model is constructed based on the bidirectional long short-term memory network encoder decoder framework, which trains trend information as a whole and utilizes element coexistence relationships to assist in trend prediction. Meanwhile, the study uses random sampling method for clothing original adoption, and the experimental results show that the model considering coexistence relationship performs the best in terms of mean absolute error and mean absolute percentage error, which are 0.0132 and 14.68%, respectively. In addition, the model that introduces attention mechanism based on trend similarity has improved by 5.09% and 4.54% on two indicators compared to the latest model. The experimental results indicate that coexistence relationships can help improve the performance of prediction models. The attention mechanism based on trend similarity can further improve model performance by similarity comparison between historical information and changing trend, and selecting similar historical information as an important influencing factor for future trends.

Fault Detection and Prediction for a Wood Chip Screw Conveyor

Equipment maintenance is a key aspect to maximize its availability. The present work focuses on data analysis of a screw conveyor of a biomass industry. The screw velocity and load were monitored and analysed, in order to detect and predict possible faults. A machine learning approach was used to detect anomalies, where different algorithms were tested with the data available, in order to train an anomaly classifier. The anomaly classifier was able to accurately identify most anomalies, based on historical data, temporal patterns and information of the maintenance interventions performed. The research carried out allowed to conclude that the Extra Trees Classifier algorithm achieved the best performance, among all algorithms tested, with 0.7974 F-score in the test set. The anomaly classifier has been shown to achieve remarkable accuracy in identifying anomalies. This research not only improves understanding of the performance of screw conveyors in biomass industries, but also highlights the practical utility of employing machine learning for proactive fault detection.