Data Analysis Algorithms Research Articles

Application of Intelligent Algorithms and Big Data Analysis in Film and Television Creation

With the rapid development of social media, people can access a large amount of data in a short period of time, and big data technology has emerged. With the vigorous development of cloud computing and big data, the method of mining audience interests through a large amount of data to guide film and television creation has attracted more and more attention from experts and scholars. In order to understand the current situation of film and television drama creation in China and provide suggestions for the shortcomings in the industry, this article mainly analyzes the application of intelligent algorithms for traffic prediction models and big data analysis in film and television creation. This intelligent algorithm can predict the potential audience of movies or TV dramas, helping producers and investors make decisions. This system utilizes artificial intelligence technology to select suitable actors for characters based on their matching degree and past work performance. This article applies intelligent algorithms to big data processing to improve the accuracy of data processing. This article explores the application of intelligent algorithms and big data analysis in film and television creation. Using machine learning algorithms to predict the potential audience of a movie or TV series based on historical data, providing decision-making basis for investors and producers. This system utilizes AI technology to select suitable actors for characters based on their matching degree with characters and past work performance, improving the scientific and accurate selection of roles. The application of these technologies helps to improve production efficiency and quality, reduce costs and risks, and inject new impetus into the sustainable development of the film and television industry.

Application of Big Data Analysis and Intelligent Algorithm in Power System Operation Optimization

The power communication system provides powerful technical support for realizing the intelligent operation and information management of the power grid and improving the operation efficiency and power supply quality of the power grid. Quantum key distribution (QKD) is considered one of the most promising technologies for commercialization. QKD uses a single photon to encrypt data to produce a more secure and reliable password. This paper intends to study the hierarchical, centralized control architecture of power dispatching based on quantum essential supply (QKD). The performance indexes of MDI-QKD under symmetric and asymmetric conditions were studied by local optimization. The optimal key formation rate of the algorithm is analyzed. From the perspective of quantum critical utilization, a quantum key utilization scheme for grid backbone dispatching service is proposed. The dynamic adjustment test of multi-node time slot and service key update rate is carried out. Experiments show that the MDI scheme can effectively improve the effectiveness of a multi-node QKD system. Thus, the security of data transmission of the core business of power dispatching data networks can be ensured to the greatest extent. AMDI can effectively reduce the transmission timeout of low-priority data streams because the delay of high-priority data streams reaches the proportion. It can be an excellent solution to the power system and the password requirements.

Selection of reference genes for normalizing gene expression data across seasons in spermatozoa of water buffalo (Bubalus bubalis).

Selection of the most stably expressed reference genes is key to monitoring accurate target gene expression across any tissue or cell type. The mRNA in spermatozoa stores valuable information related to changes in spermatogenesis due to variations in environmental conditions, especially during heat stress, which affects various sperm functions. Semen quality in buffalo bulls is significantly influenced by the seasons. In the study, a panel of nine genes was evaluated to identify the most stably expressed internal control gene (ICG) for the normalization of real-time gene expression data generated across various seasons for Murrah buffalo bulls' spermatozoa. Sperm cells were purified from the semen samples collected during different seasons, with temperature-humidity index (THI) ranging from 80.80 ± 1.47 (hot summer) to 55.88 ± 1.98 (winter), using the BoviPure™ gradient purification method. The RNA isolated from the purified spermatozoa fraction was quality checked prior to reverse transcription and subjected to qPCR (quantitative real-time PCR) based expression analysis. An automated 'endoGene' pipeline was employed to apply the geNorm, NormFinder, and BestKeeper algorithms for data analysis. The result indicated that GAPDH and PP1A were the most stably expressed among the gene panel, whereas ATPSF1 and ACTB were the two least stable expressed reference genes. Further, the most suitable ICGs identified were validated by normalization of real time expression data of heat stress and sperm quality genes, HSFY2 and AKAP4, respectively. The genes identified would help in generating the most reliable results for the expression profiling of the genes dictating sperm quality and heat stress cope-up mechanism in buffalo spermatozoa, collected during different seasons.

Maximizing Electrochemical Information: A Perspective on Background-Inclusive Fast Voltammetry.

This perspective encompasses a focused review of the literature leading to a tipping point in electroanalytical chemistry. We tie together the threads of a "revolution" quietly in the making for years through the work of many authors. Long-held misconceptions about the use of background subtraction in fast voltammetry are addressed. We lay out future advantages that accompany background-inclusive voltammetry, particularly when paired with modern machine-learning algorithms for data analysis.

An Approach to Generating Recommendations for Improving the Performance of Software for Heterogeneous Computing Platforms

The widespread use of heterogeneous computing platforms, as well as the incorporation of computationally expensive implementations of intelligent data analysis algorithms into modern software systems leads to the demand in moving software fragments to most suitable hardware accelerators that are available on a heterogeneous computing platform. In this research, we propose an approach to the generation of recommendations for improving the performance of software systems by finding candidate algorithm implementations for hardware acceleration, and by suggesting the most suitable hardware accelerator among the specialized processors that are available on a given heterogeneous computing platform. The proposed approach is based on a code-to-code search technique, which extracts code fragments from an abstract syntax tree (AST), converts them into vectors containing program features, and compares the vectors with the query program vector. The obtained results confirm that the use of automatically recommended hardware accelerators for the code fragments identified using the proposed approach indeed allows to increase the performance of software systems solving machine learning tasks.

Exploring Stress Detection in Tweets: A Comparative Business Analysis of Classification Algorithms

Abstract: In today's digitally-driven landscape, social media platforms such as Twitter, Facebook, and WordPress have emerged as critical conduits for public discourse, resulting in an overwhelming influx of unprocessed data, particularly on Twitter. Coping with the sheer volume of this data presents a significant challenge. To address this, sentiment analysis, a technique that categorizes sentiments into positive, negative, or neutral, offers a promising solution. This study delves into three main approaches for sentiment analysis: Machine learning-based methods, Sentiment lexicon-based approaches, and Hybrid methods. Its primary research objectives revolve around the identification of suitable algorithms and metrics for evaluating the performance of Machine Learning Classifiers. Additionally, the study aims to compare these metrics with respect to the dataset size, gauging their impact on the most appropriate sentiment analysis algorithm.The research methodology applied is experimental, entailing a rigorous assessment of algorithms using carefully selected metrics. The results of this investigation spotlight Naïve Bayes, Random Forest, XGBoost, and CNN-LSTM as the leading machine learning algorithms under consideration. These algorithms are assessed based on key performance metrics such as precision, accuracy, F1 score, and recall. Notably, the CNN-LSTM model emerges as the optimal choice for sentiment analysis of Twitter data within the specified dataset size, achieving a remarkable accuracy rate of 88%.In summary, this research successfully pinpoints the most suitable algorithm for sentiment analysis of Twitter data, especially in the context of dataset size. The CNN- LSTM model showcases its effectiveness, serving as a robust tool for sentiment analysis and delivering an impressive accuracy rate. This study significantly enhances our comprehension of public sentiment on Twitter, providing valuable insights into the ever-evolving realm of digital discourse and the analysis of vast unprocessed data

Electromagnetic shielding material database and machine learning preparing for laser cladding FeCo-based alloy

The compilation and preprocessing of electromagnetic shielding material databases using machine learning techniques are pivotal in contemporary materials science and engineering. These materials play a crucial role in diverse applications such as electronics, telecommunications, aerospace, and automotive industries, necessitating effective attenuation of electromagnetic interference (EMI). This paper underscores the significance of comprehensive databases in organizing material properties systematically, facilitating the identification of novel materials with enhanced shielding effectiveness. It explores the role of machine learning algorithms in predictive modeling and data analysis, expediting the screening process of candidate materials and uncovering hidden correlations within complex datasets. However, the efficacy of machine learning techniques relies heavily on the quality of input data and preprocessing steps. Thus, this paper discusses methodologies for collecting material data, challenges in data curation and integration, and common preprocessing techniques such as data cleaning, feature extraction, and normalization. The integration of electromagnetic shielding material databases with machine learning preprocessing holds great promise for FeCo-based alloy laser cladding manufacturing and design, leading to innovative solutions for electromagnetic interference mitigation across various technological domains.

Adaptable software tools for searching objects-analogues tasks 
 in NO-CODE concept

The paper is devoted to the problem of methodological and software support for the search of object analogues, performed when solving the problems of modelling and designing the development of oil and gas fields. The article shows that there is no single generally accepted methodology for searching analogues, existing methodologies differ in applied similarity criteria and search algorithms, are adapted to the search conditions, and are modernised. With the inconsistency of methods computer programs for searching analogues are created at a low level of abstraction, for a limited range of tasks, the existing developments are integrated with corporate databases and in general do not solve the problem of providing analysts with pro-software tools. As a solution we propose the development of programs for searching analogues in the concept of "no-code" (without programming) on the basis of analytical platforms. The "no-code" approach will allow analysts without involving programmers to create software tools for searching analogues, implementing their own variant methods. The article presents the authors' algorithm for express analysis of data at the initial stage of analogue search and the software tool that implements it, created "no code" on the basis of the Russian analytical platform Loginom.

Abstract 951: 3D-PREDICT - An ex vivo precision oncology and clinical trial enrichment platform by Nilogen Oncosystems

Abstract Background: Immuno-oncology (IO) therapy with checkpoint inhibitors has demonstrated a higher response rate, duration of response, and overall survival than chemotherapy. However, predicting which FDA approved IO therapies or pharmaceutical agents, as well as best combinations and delivery sequence, will have optimal patient response remains a significant challenge for personalized medicine. Nilogen Oncosystem’s 3D-PREDICT is a novel ex vivo therapeutic investigative platform that provides a functional model of a patient’s tumor to investigate susceptibility to different therapeutic approaches directly. Derived from core biopsies, the 3D-PREDICT model captures the tumor heterogeneity while preserving the tumor microenvironment by retaining stromal components and cell-cell and cell-extracellular matrix interactions. Here, we employed the 3D-PREDICT platform to compare the efficacy of different immunotherapeutic approaches in various solid tumor indications ex vivo. Methods: Tumoroids from 18-gauge core biopsies from solid tumors were generated using Nilogen Oncosystems’s proprietary mechanical process forgoing any enzymatic digestion or propagation while keeping the spatial contexture of stroma intact. Pooled tumoroids were treated ex vivo for 72 hours with various standard-of-care mono or combo therapy (carboplatin, anti-programmed death-ligand 1 (PD-L1) antibody atezolizumab, anti-CD47 antibody magrolimab, anti-programmed cell death receptor-1 (PD-1) antibody nivolumab, or a combination of magrolimab and atezolizumab). Treatment-mediated immune modulation in tumor microenvironment were analyzed to predict patient response to subjected therapies. Results: Treatment-mediated tumor cell killing activity was evaluated using 3D high throughput confocal imaging and Nilogen Oncosystems’s proprietary algorithm for data analysis. The ex vivo response to checkpoint inhibitors was correlated with retrospective patient clinical information. Tumoroid samples treated with atezolizumab and magrolimab demonstrated enhanced tumor cell killing. Approximately 20% of tumors showed increased CD8 T-cell activation upon ex vivo treatment, correlating with proinflammatory cytokine release in conditioned media. Conclusions: The 3D-PREDICT ex vivo tumoroid platform provides a unique resource to predict patients’ response to treatment, potentially serving as a clinical diagnostic to guide clinical care and stratifying patient procurement into clinical trials. This would allow prospective assessment of therapeutic efficacy ex vivo to match each patient to the most effective and least toxic, to improving outcomes, reducing costs, and assigning therapeutics on a more rational basis. Citation Format: Jared Ehrhart, Seth Currlin, Michelle Ataya, Alliyah Humphrey, Rikhia Chakraborty. 3D-PREDICT - An ex vivo precision oncology and clinical trial enrichment platform by Nilogen Oncosystems [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 951.

Digital Technology Applications in the Management of Adverse Drug Reactions: Bibliometric Analysis.

Adverse drug reactions continue to be not only one of the most urgent problems in clinical medicine, but also a social problem. The aim of this study was a bibliometric analysis of the use of digital technologies to prevent adverse drug reactions and an overview of their main applications to improve the safety of pharmacotherapy. The search was conducted using the Web of Science database for the period 1991-2023. A positive trend in publications in the field of using digital technologies in the management of adverse drug reactions was revealed. A total of 72% of all relevant publications come from the following countries: the USA, China, England, India, and Germany. Among the organizations most active in the field of drug side effect management using digital technologies, American and Chinese universities dominate. Visualization of publication keywords using VOSviewer software 1.6.18 revealed four clusters: "preclinical studies", "clinical trials", "pharmacovigilance", and "reduction of adverse drug reactions in order to improve the patient's quality of life". Molecular design technologies, virtual models for toxicity modeling, data integration, and drug repurposing are among the key digital tools used in the preclinical research phase. Integrating the application of machine learning algorithms for data analysis, monitoring of electronic databases of spontaneous messages, electronic medical records, scientific databases, social networks, and analysis of digital device data into clinical trials and pharmacovigilance systems, can significantly improve the efficiency and safety of drug development, implementation, and monitoring processes. The result of combining all these technologies is a huge synergistic provision of up-to-date and valuable information to healthcare professionals, patients, and health authorities.

Inventory Management System for MSMEs

This inquire about points to create a web-based stock framework that centers on reasonableness, user-friendliness, and usefulness custom-made to desires of Miniaturized scale, Little, and Medium Ventures (MSMEs). Through in-depth analysis of MSMEs' specific inventory management requirements, the system not only provides a comprehensive solution for stock management but also integrates the Apriori algorithm for associative analysis of inventory data. The system's development adopts an Agile approach, allowing flexible adaptation to changing needs throughout the development process. Key features include efficient stock management, intuitive Point of Sales (POS) transaction recording, and customizable inventory reporting. The implementation of this system is expected to enhance MSMEs' efficiency in inventory management, provide insightful data to support more informed decision-making, and positively contribute to strengthening competitiveness and growth in the dynamic and competitive business environment.

Real Time Monitoring Research on Rehabilitation Effect of Artificial Intelligence Wearable Equipment on Track and Field Athletes

INTRODUCTION: With the rapid development of artificial intelligence technology, wearable artificial intelligence devices show great potential in medical rehabilitation. This study explores the Real Time monitoring effect of AI wearable devices in the rehabilitation process of track and field athletes. The application of this technology in rehabilitation monitoring was investigated through the introduction of advanced sensing technology and data analysis algorithms to provide track and field athletes with more scientific and personalized rehabilitation programs. OBJECTIVES: A group of track and field athletes was selected as the research object and equipped with an artificial intelligence wearable device, which is capable of Real Time monitoring of the athletes' physiological parameters, sports postures, joint mobility, and other rehabilitation-related data. An individualized rehabilitation model was established through the data collected by these sensors, and advanced artificial intelligence algorithms were used to analyze the data in Real Time. At the same time, the sensor data were combined with the actual performance of the athletes' rehabilitation training to comprehensively assess the effectiveness of AI wearable devices in rehabilitation monitoring. METHODS: This study aims to assess the effect of Real Time monitoring of AI wearable devices in the rehabilitation of track and field athletes and to explore their potential application in the rehabilitation process. Real Time tracking of athletes' physiological status and athletic performance aims to provide more accurate and timely information to rehabilitation doctors and coaches to optimize the rehabilitation training program and promote the rehabilitation process of athletes. RESULTS: The study showed that artificial intelligence wearable devices have significant Real Time monitoring effects in rehabilitating track and field athletes. Through Real Time monitoring of data such as physiological parameters, sports posture, and joint mobility, the rehabilitation team was able to identify potential problems and adjust the rehabilitation program in a more timely manner. Athletes using artificial intelligence wearable devices improved the personalization and targeting of rehabilitation training, and the rehabilitation effect was significantly better than that of traditional monitoring methods. CONCLUSION: This study concludes that artificial intelligence wearable devices perform well in rehabilitating track and field athletes, providing a more scientific and comprehensive means of rehabilitation monitoring. Through Real Time tracking, the rehabilitation team could better understand the rehabilitation progress of the athletes, adjust the rehabilitation program in a targeted manner, and improve the rehabilitation effect. However, future research still needs to optimize the performance of the devices further, expand the sample size, and thoroughly study the monitoring needs at different stages of rehabilitation to better meet the individualized requirements of track and field athletes' rehabilitation process.

Transformational Leadership on Teacher Performance Through the Mediating Role of Motivation

The purpose of this study is to investigate the impact of the principal's transformational leadership on school performance, as mediated by teachers' work motivation at MTsN 1 Merangin. This study employs a quantitative method as well as explanatory research. Primary data is collected using questionnaires for three relevant variables, while secondary data is gathered from school records, textbooks, and periodicals. The sample employed in this study was non-probability purposive sampling, with a total of 51 teachers. Smart PLS v.3 software runs the PLS-SEM data analysis algorithms. This study found that the principal's transformative leadership had a considerable positive direct effect on teacher performance (coefficient 0.208, t-count 1.660, a standard deviation 0.126, p-value 0.045 < 0.05). It demonstrates that transformational principle leadership has a substantial impact on teacher performance. The principal's transformational leadership has a considerable direct and beneficial effect on teachers’ motivation (coefficient 0.675, t-count 12.979, a standard deviation 0.05, p-value 0.000 < 0.05. It indicates a significant effect of transformative leadership on teacher motivation. Next, there was a considerable beneficial direct influence of teachers' motivation on teacher performance (coefficient 0.634, t-count 5.574, a standard deviation 0.114, p-value 0.000 < 0.05). It indicates a statistically significant influence of teacher motivation on performance. Last, motivation can operate as a mediator (coefficient 0.428, standard deviation 0.087, t-count 4.888, p-value 0.000 < 0.05). motivation mediates transformational leadership to teacher performance. So, the school principal was encouraged to have more intellectual stimulation, care, and inspire teachers, as well as other indicators of transformational leadership, to boost teacher motivation and performance.

Investigation of light gas adsorption by microporous materials using data analysis and decision tree machine learning algorithm

This study aimed to extract insights into the adsorption behavior of light gases by microporous materials such as zeolites, MOFs, and activated carbons. Data reported in 22 articles published between 1974 and 2022 were analyzed using a decision tree (DT) machine learning algorithm. A comprehensive database comprising 3297 data points, elucidating the impacts of 8 input variables on adsorption capacity, was constructed. Various exploratory data analysis techniques, including histograms, bar charts, and scatter plots, were employed to discern the relationships among input variables and the performance variable. Additionally, a DT model was employed to regress the adsorbed capacity data. Furthermore, a parametric study of this model facilitated the determination of the relative importance of input variables and their partial dependence, enhancing the interpretability of the model and enabling the deduction of heuristics for high or low adsorption capacity. The exploratory data analysis revealed that pressure and molecular mass of the adsorbate were the most significant variables influencing adsorption capacity.

PREDICTING FIRE ALARMS USING MULTI SENSOR DATA: A BINARY CLASSIFICATION APPROACH

Fires pose significant threats to human life, property, and the environment. Early detection of fire incidents is crucial to prevent extensive damage and to ensure the safety of occupants. Traditional fire alarm systems typically rely on a single type of sensor, such as smoke detectors or heat sensors, to detect specific fire indicators. These systems operate based on predefined thresholds and triggers. However, they can be prone to false alarms triggered by non-fire-related events (e.g., cooking fumes or dust) and may not provide early warning signs in certain scenarios. To address these limitations, researchers and engineers have turned to advanced technologies, such as multi-sensor data analysis and machine learning algorithms, to develop more reliable and efficient fire alarm prediction systems. On the other hand, the need for a more robust and accurate fire alarm prediction system stems from the shortcomings of traditional methods. False alarms not only lead to wasted resources but also desensitize occupants, potentially leading them to ignore genuine alarms. Additionally, a delayed response to a fire incident can result in severe consequences, making it essential to develop an intelligent system that can effectively and timely predict fire events. Therefore, this work presents the utilization of multi-sensor data and binary classification to develop a more reliable fire alarm prediction system. The experiments are conducted using a dataset collected from various sensor inputs, including air temperature, humidity, CO2 concentration, molecular hydrogen, ethanol gas, and air pressure etc. Then applied binary classification algorithm to learn patterns from the data and classify fire-related events accurately. The results showed promising improvements in prediction accuracy, reduced false alarm rates, and early detection of fire incidents.

Online water quality monitoring: a case study in the umbulan drinking water supply system, East Java, Indonesia

Conventional systems that monitor the supply system periodically are considered to be very inadequate. This can cause the water supply distributed to the community to be of poor quality. Therefore, this study aims to evaluate water quality periodically by measuring water parameters such as pH, chlorine and turbidity for 30 days using an online system and portable unit. Portable tools used to measure pH, turbidity and residual chlorine are as follows, namely pH meters (Hanna, HI98017), Turbidity Meters (Hanna, HI 98703), Residual Chlorine meters and measurements with an online system using "Supervisory Control and Data Acquisition”. The average parameter value of the results of online daily monitoring for a month for the pH parameter was a minimum 6.92, a maximum of 7.46, a minimum turbidity of 0.08 nephelometric turbidity unit (NTU) and a maximum of 0.94 NTU. While the residual chlorine minimum of 0.29 mg/L and a maximum of 0.58 mg/L. To determine the accuracy of the offline measurements, measurements were also performed with a portable device four times a month. The comparison of the measurement results is very small, which is the difference in pH parameters is between 0.37-0.50, turbidity is between 0.05-0.21 NTU, and residual chlorine is 0.002-0.006 mg/L. Offline measurements using the portable device are consistent with the online daily monitoring. Future research should focus on optimizing sensor technology for enhanced accuracy and reliability, and developing automated data analysis algorithms to streamline evaluation processes.

An advanced multimodal driver-assistance prototype for emergency-vehicle detection

In the automotive industry, intelligent monitoring systems for advanced human-vehicle interaction aimed at enhancing the safety of drivers and passengers represent a rapidly growing area of research. Safe driving behavior relies on the driver’s awareness of the road context, enabling them to make appropriate decisions and act consistently in anomalous circumstances. A potentially dangerous situation can arise when an emergency vehicle rapidly approaches with sirens blaring. In such cases, it is crucial for the driver to perform the correct maneuvers to prioritize the emergency vehicle. For this purpose, an Advanced Driver Assistance System (ADAS) can provide timely alerts to the driver about an approaching emergency vehicle. In this work, we present a driver-assistance prototype that leverages multimodal information from an integrated audio and video monitoring system. In the initial stage, sound analysis technologies based on computational audio processing are employed to recognize the proximity of an emergency vehicle based on the sound of its siren. When such an event occurs, an in-vehicle monitoring system is activated, analyzing the driver’s facial patterns using deep-learning-based algorithms to assess their awareness. This work illustrates the design of such a prototype, presenting the hardware technologies, the software architecture, and the deep-learning algorithms for audio and video data analysis that make the driver-assistance prototype operational in a commercial car. At this initial experimental stage, the algorithms for analyzing the audio and video data have yielded promising results. The area under the precision-recall curve for siren identification stands at 0.92, while the accuracy in evaluating driver gaze orientation reaches 0.97. In conclusion, engaging in research within this field has the potential to significantly improve road safety by increasing driver awareness and facilitating timely and well-informed reactions to crucial situations. This could substantially reduce risks and ultimately protect lives on the road.

Integration of Augmented Reality and Building Information Modeling for Enhanced Construction Inspection—A Case Study

This research addresses a significant challenge in the construction industry: the traditional reliance on CAD drawings and manual methods for building inspection and monitoring. This article presents a transformative proposal utilizing Augmented Reality (AR) to revolutionize these processes. The proposed model is based on an innovative integration of AR technology with Building Information Modeling (BIM), aiming to enhance data life-cycle management and improve the efficiency of construction management practices. The main goal of the article is to demonstrate the practical feasibility and benefits of this AR-BIM integration in construction management, particularly in the realms of inspection and monitoring. This involves developing and testing an accessible, user-friendly, and affordable AR application prototype for mobile devices, employing multiple markers, as a potential replacement for traditional methods. The research methodology comprises five phases, starting with the conversion of 2D CAD drawings into 3D BIM, followed by the simulation of AR-BIM integration at a construction site using a commercial AR application. This is succeeded by assessing the applicability of the commercial AR app and developing a multiple-marker AR application prototype suitable for general platforms. The final phase encompasses the testing and evaluation of this prototype. The findings suggest that the integration of 3D BIM with AR technology is not only feasible, but also beneficial in replacing paper-based processes, thereby enhancing information sharing, communication, and overall project execution efficiency. However, the accuracy of the superimposition between virtual and actual objects needs improvement to reduce discrepancies between as-built and as-planned scenarios. These results hold significant potential for transforming construction project execution by replacing traditional methods with more efficient digital solutions. Future research directions include extensive testing in various construction scenarios, improving model complexity handling, exploring the application of machine learning algorithms for data analysis, and expanding the study to encompass other stages of the construction lifecycle.

A Review on Wearable Devices for Animal Health Monitoring

Internet of Things has changed everyone's life. It often changes the way people interact with their environment and objects. IoT devices use wearable devices that are used to monitor the activities of animals. The Internet of Things for Animal Health (IoTAH) uses biosensors and software to monitor and manage animal health information. This work concerns the development of a mobile application coupled with a hardware device (called CAHM) attached to an animal’s collar. Companion Animal Health Monitoring App. Equipped with a smart collar, the system feature’s location tracking, heart rate, body temperature measurement, disease detection and isolation, detection of reproductive cycles, as well as monitoring physiological wellbeing of the animal. With further advancements in technology, data analysis algorithms and IoT systems, using these technologies we can improve our understanding of animal health, improve prevention and support healthy, happy animals.

Retraction Note: Fuzzy clustering-based skyline query preprocessing algorithm for large-scale flow data analysis

Retraction Note: Fuzzy clustering-based skyline query preprocessing algorithm for large-scale flow data analysis