Search

Chickpea (Cicer arietinum L.) is a major grain legume grown worldwide as a staple protein source. Traditionally, it is a rain-fed crop, but supplemental irrigation can increase yields and counteract the challenges posed by the changing climate worldwide. A fast and non-destructive plant water status assessment method may streamline irrigation management. The main objective of this study was to remotely assess the leaf water potential (LWP) and leaf area index (LAI) of field-grown chickpea. Five irrigation treatments were applied in two farm experiments and two commercial fields. Ground hyperspectral canopy reflectance and Vegetation and Environment monitoring on a New Micro-Satellite (VENµS) images acquired throughout the study. In parallel, LWP and LAI measurements were captured in the field. Vegetation indices (VIs) and machine learning (ML) based on all spectral bands were used to calibrate and validate spectral estimation models. The normalized difference spectral index (NDSI) that used bands on 1600 and 1730 nm (NDSI(1600,1730)) selected in the current study yielded the LWP lowest estimation error on independent validation (RMSE = 0.19 [MPa]) using linear regression. VENµS based VIs resulted in relatively lower LWP estimation accuracy (RMSE = 0.23–0.29 [MPa]) compared to VIs calculated from ground hyperspectral data (RMSE = 0.19–0.21 [MPa]). Artificial neural network (ANN) models for LWP from ground and space spectral data showed similar performances (RMSE = 0.15–0.17 [MPa]), and were both more accurate than VIs. LWP response to the irrigation treatments was faster than the LAI response and was captured by the NDSI(1600,1730). The low correlation found between LWP and LAI (r = 0.08–0.44) supports the conclusion that spectral reflectance of chickpea canopy can be used to estimate LWP per se and is only partially affected by morphological changes induced by irrigation treatments and canopy development. The ability to rapidly estimate chickpea LWP may improve irrigation scheduling in the future. [ABSTRACT FROM AUTHOR]

Optical sensors, mounted on uncrewed aerial vehicles (UAVs), are typically pointed straight downward to simplify structure-from-motion and image processing. High horizontal and vertical image overlap during UAV missions effectively leads to each object being measured from a range of different view angles, resulting in a rich multi-angular reflectance dataset. We propose a method to extract reflectance data, and their associated distinct view zenith angles (VZA) and view azimuth angles (VAA), from UAV-mounted optical cameras; enhancing plant parameter classification compared to standard orthomosaic reflectance retrieval. A standard (nadir) and a multi-angular, 10-band multispectral dataset was collected for maize using a UAV on two different days. Reflectance data was grouped by VZA and VAA (on average 2594 spectra/plot/day for the multi-angular data and 890 spectra/plot/day for nadir flights only, 13 spectra/plot/day for a standard orthomosaic), serving as predictor variables for leaf chlorophyll content (LCC), leaf area index (LAI), green leaf area index (GLAI), and nitrogen balanced index (NBI) classification. Results consistently showed higher accuracy using grouped VZA/VAA reflectance compared to the standard orthomosaic data. Pooling all reflectance values across viewing directions did not yield satisfactory results. Performing multiple flights to obtain a multi-angular dataset did not improve performance over a multi-angular dataset obtained from a single nadir flight, highlighting its sufficiency. Our openly shared code (https://github.com/ReneHeim/proj%5fon%5fuav) facilitates access to reflectance data from pre-defined VZA/VAA groups, benefiting cross-disciplinary and agriculture scientists in harnessing the potential of multi-angular datasets. [ABSTRACT FROM AUTHOR]

Prediction of surface topography in milling usually requires complex kinematics and dynamics modeling of the milling process, plus solving physical models of surface generation is a daunting task. This paper presents a multimodal data-driven machine learning (ML) method to predict milled surface topography. The proposed method predicts the height map of the surface topography by fusing process parameters and in-process acoustic information as model inputs. This method has been validated by comparing the predicted surface topography with the measured data. [ABSTRACT FROM AUTHOR]

In the training process of machine learning, the minimization of the empirical risk loss function is often used to measure the difference between the model’s predicted value and the real value. Stochastic gradient descent is very popular for this type of optimization problem, but converges slowly in theoretical analysis. To solve this problem, there are already many algorithms with variance reduction techniques, such as SVRG, SAG, SAGA, etc. Some scholars apply the conjugate gradient method in traditional optimization to these algorithms, such as CGVR, SCGA, SCGN, etc., which can basically achieve linear convergence speed, but these conclusions often need to be established under some relatively strong assumptions. In traditional optimization, the conjugate gradient method often requires the use of line search techniques to achieve good experimental results. In a sense, line search embodies some properties of the conjugate methods. Taking inspiration from this, we apply the modified three-term conjugate gradient method and line search technique to machine learning. In our theoretical analysis, we obtain the same convergence rate as SCGA under weaker conditional assumptions. We also test the convergence of our algorithm using two non-convex machine learning models. [ABSTRACT FROM AUTHOR]

Vacant cruising is an inevitable part of taxi services caused by spontaneous demand, and the efficiency of cruising strategies has purported impact on the profit of individual drivers. Extensive studies have been conducted to analyze taxi cruising patterns and propose effective cruising strategies. However, existing studies mainly focused on the collective behavior of certain driver groups and failed to capture cruising behavior patterns at the individual driver or trip level. Also, prior studies considered different types of factors affecting taxi cruising, but we still lack an integrated model to compare their relative importance. In this study, we analyze trip-level cruising time and the associated external and internal factors using a taxi trajectory dataset in Shanghai, China. A trajectory annotation technique is introduced to segment taxi trajectories into different phases. Various external (supply and demand, traffic condition and built environment) and internal (cruising strategies and historical driver performance) factors are derived from taxi trajectories and other data sources. A spatiotemporal embedding method is devised to capture unobserved effects over time and space. The impacts of external and internal factors on taxi cruising time are examined using regression and XGBoost—a machine learning model. The results show external and internal factors are both important in determining taxi cruising time. Cruising strategies contribute 49.0% in taxi cruising time, which implies effective cruising strategies can greatly reduce vacant cruising time. Additionally, nonlinear associations of some variables (e.g., supply–demand patterns, traffic speed) with taxi cruising time are discussed. [ABSTRACT FROM AUTHOR]

Ride-hailing services such as Lyft, Uber, and Cabify operate through smartphone apps and are a popular and growing mobility option in cities around the world. These companies can adjust their fares in real time using dynamic algorithms to balance the needs of drivers and riders, but it is still scarcely known how prices evolve at any given time. This research analyzes ride-hailing fares before and during the COVID-19 pandemic, focusing on applications of time series forecasting and machine learning models that may be useful for transport policy purposes. The Lyft Application Programming Interface was used to collect data on Lyft ride supply in Atlanta and Boston over 2 years (2019 and 2020). The Facebook Prophet model was used for long-term prediction to analyze the trends and global evolution of Lyft fares, while the Random Forest model was used for short-term prediction of ride-hailing fares. The results indicate that ride-hailing fares are affected during the COVID-19 pandemic, with values in the year 2020 being lower than those predicted by the models. The effects of fare peaks, uncontrollable events, and the impact of COVID-19 cases are also investigated. This study comes up with crucial policy recommendations for the ride-hailing market to better understand, regulate and integrate these services. [ABSTRACT FROM AUTHOR]

For market players and policy officials, commodity price forecasts are crucial problems that are challenging to address due to the complexity of price time series. Given its strategic importance, corn crops are hardly an exception. The current paper evaluates the forecasting issue for China's weekly wholesale price index for yellow corn from January 1, 2010 to January 10, 2020. We develop a Gaussian process regression model using cross validation and Bayesian optimizations over various kernels and basis functions that could effectively handle this sophisticated commodity price forecast problem. The model provides precise out-of-sample forecasts from January 4, 2019 to January 10, 2020, with a relative root mean square error, root mean square error, and mean absolute error of 1.245%, 1.605, and 0.936, respectively. The models developed here might be used by market players for market evaluations and decision-making as well as by policymakers for policy creation and execution. [ABSTRACT FROM AUTHOR]

The rapid discrimination of bacteria is currently an emerging trend in the fields of food safety, medical detection, and environmental observation. Traditional methods often require lengthy culturing processes, specialized analytical equipment, and bacterial recognition receptors. In response to this need, we have developed a paper-based fluorescence sensor array platform for identifying different bacteria. The sensor array is based on three unique carbon quantum dots (CQDs) as sensing units, each modified with a different antibiotic (polymyxin B, ampicillin, and gentamicin). These antibiotic-modified CQDs can aggregate on the bacterial surface, triggering aggregation-induced fluorescence quenching. The sensor array exhibits varying fluorescent responses to different bacterial species. To achieve low-cost and portable detection, CQDs were formulated into fluorescent ink and used with an inkjet printer to manufacture paper-based sensor arrays. A smartphone was used to collect the responses generated by the bacteria and platform. Diverse machine learning algorithms were utilized to discriminate bacterial types. Our findings showcase the platform's remarkable capability to differentiate among five bacterial strains, within a detection range spanning from 1.0 × 103 CFU/mL to 1.0 × 107 CFU/mL. Its practicality is further validated through the accurate identification of blind bacterial samples. With its cost-effectiveness, ease of fabrication, and high degree of integration, this platform holds significant promise for on-site detection of diverse bacteria. [ABSTRACT FROM AUTHOR]

This paper surveys some of the most important recent works related to micro-expression analysis. It includes discussions on algorithms for spotting and recognizing micro-expressions, their performances, databases, and new feature descriptor frameworks. Here, we use a reverse chronological order to discuss the state-of-the-art in a work-specific fashion. We provide a questionnaire-based comparative study of the literature and discuss future directions of micro-expression analysis. We expect this survey to expose micro-expressions to those interested in pursuing research in this emerging field. [ABSTRACT FROM AUTHOR]

Plant leaf diseases have become a serious concern for the agricultural industry, yet timely diagnosis and recognition are challenging in numerous regions of the globe owing to a shortage of automated crop disease identification methods. If plant diseases are not recognized in a prompt way, food insecurity will rise, affecting the country's income. Plant disease identification is critical for successful crop prevention and control of diseases, as well as farm production management and decision-making. Plant disease detection technologies aid in finding infected plants in their early phases and also help the user in cost-effectively expanding plant disease identification system to a variety of plants. This paper's major contribution is a stacked ensemble technique based on Machine learning and Deep learning techniques. This research article also elaborates on how plant disease detection framework will be realized using novel segmentation and feature extraction strategies for extracting significant features for classification. Once the features are extracted, they are transmitted to the cloud platform to implement web enabled automated monitoring system. The proposed stacked ensemble learning is evaluated by comparing different machine learning and Deep learning techniques models utilizing precision, recall, and F_score. When compared to traditional machine learning and deep learning techniques approaches, the findings show that the proposed technique achieves about 99% accuracy. [ABSTRACT FROM AUTHOR]

Long gone is the time when people preferred using only cash. In recent years, cashless transactions have gained much popularity, be it using UPI apps or credit and debit cards. The same has even led to a significant increase in the number of credit card fraud cases. Detecting fraudulent transactions is a challenging task as the fraudsters disguise the ordinary conduct of clients in order to perform fraud. Automated intelligent credit card fraud detection can be employed for detecting fraudulent transactions. In this paper, we proposed a credit card fraud detection approach involving an arrangement of supervised machine learning algorithms called ensemble learning. One of the difficulties looked at during the time spent to distinguish fraud transactions in datasets is the imbalanced class distribution. In this work, we employed an ensemble learning model in combination with two data-level techniques for handling class imbalance problems. The proposed approach is the ensemble of three base classifiers including random forest, logistic regress and K-nearest neighbour along with two data-level algorithms namely random oversampling and random undersampling. To combine the predictions of the base classifiers, the weighted voting ensemble approach is used. The proposed approach is evaluated using a highly imbalanced credit card transaction dataset. The proposed approach is evaluated using various sets of weights in order to identify the best possible outcomes in terms of accuracy and minimise the misclassification of fraudulent transactions. [ABSTRACT FROM AUTHOR]

Environmental sound classification(ESC) is one of the challenging issues in the area of audio recognition. Classifying the sounds such as glass breaking, gunshots, dog barking can aid in a variety of applications like audio surveillance, smart homes, robotic navigation, and other crime investigation systems. Environmental sounds are more complicated as compared to speech and music due to their unstructured nature. Environ- mental sounds are classified using machine learning algorithms such as Support Vector Machines, K-Nearest Neighbour, and various deep learn- ing algorithms such as Convolutional Neural Networks, Recurrent Neural Networks, Long Short Term Memory Neural Networks. In this paper, a robust approach is proposed for ESC on the UrbanSound8k dataset. Cep- stral features Mel Frequency Cepstral Coefficients are extracted from the audios and fed to the Convolutional Recurrent Neural Network (CRNN). The effect of varying various hyperparameters such as the number of layers, batch size, and filter count are analyzed to determine the ade- quate combination of parameters that can give considerable accuracy for ESC. The proposed approach is compared to the baseline models and it attains the best accuracy of 93.58% which is higher than the previ- ous research results of ESC. The proposed model gives the best results using one LSTM layer, 0.3 momentum value, 512 number of filters, 512 neurons in LSTM layer and 256 batch size. The proposed framework can be ameliorated by using novel neural networks and combinations. [ABSTRACT FROM AUTHOR]

Mackenzie and Alexander Mathis were still early in their careers when their software created a sensation. Now they’re using it to support other young scientists. [ABSTRACT FROM AUTHOR]

The acceleration of global climate change poses enormous challenges to the automotive manufacturing industry, a key sector in reducing greenhouse gas (GHG) emissions. Particularly, Scope 3 emissions, encompassing indirect emissions, often constitute the largest carbon footprint component in this sector, yet their quantification and management remain challenging. This paper proposes an interdisciplinary approach that integrates cloud computing, text analysis, and machine learning, and systematically details its implementation, key benefits, and potential applications. Through this methodology, the paper seeks to provide the automotive industry with innovative and actionable insights to tackle the complexities of Scope 3 emissions. It focuses on enhancing the accuracy of emission quantification and optimizing supply chains, aiming to reduce the overall carbon footprint. Moreover, this paper outlines the future challenges and directions for these technologies and methodologies in sustainable development and environmental management. This work underlines the critical role of interdisciplinary approaches in resolving environmental challenges, setting the stage for the automotive industry to forge paths towards a greener future. Highlights: • The article explores the challenges of managing Scope 3 emissions, emphasizing the importance of strengthened quantitative analysis and strategic oversight. • The research promotes interdisciplinary integration, combining cloud computing, text analysis, and machine learning to establish a comprehensive framework for emission data management and reduction. • The development of a specialized SaaS platform is proposed to refine data collection practices, enhance stakeholder interaction, and streamline emission management workflow. • The adoption of text analysis in supply chain management optimization is advocated to improve operational efficiency and support decision-making processes. • The discussion covers technological, policy, and market developments potentially affecting Scope 3 emissions management strategies, offering a long-term orientation for future research and industry practices. [ABSTRACT FROM AUTHOR]

The Smart Grid operates autonomously, facilitating the smooth integration of diverse power generation sources into the grid, thereby ensuring a continuous, reliable, and high-quality supply of electricity to end users. One key focus within the realm of smart grid applications is the Home Energy Management System (HEMS), which holds significant importance given the fluctuating availability of generation and the dynamic nature of loading conditions. This paper presents an overview of HEMS and the methodologies utilized for load forecasting. It introduces a novel approach employing Quantum Support Vector Machine (QSVM) for predicting periodic power consumption, leveraging the AMPD2 dataset. In the establishment of a microgrid, various factors such as energy consumption patterns of household appliances, solar irradiance, and overall load are taken into account in dataset creation. In the realm of load forecasting in Home Energy Management Systems (HEMS), the Quantum Support Vector Machine (QSVM) stands out from other methods due to its unique approach and capabilities. Unlike traditional forecasting methods, QSVM leverages quantum computing principles to handle complex and nonlinear electricity consumption patterns. QSVM demonstrates superior accuracy by effectively capturing intricate relationships within the data, leading to more precise predictions. Its ability to adapt to diverse datasets and produce significantly low error values, such as RMSE and MAE, showcases its efficiency in forecasting electricity load consumption in smart grids. Moreover, the QSVM model's exceptional flexibility and performance, as evidenced by achieving an accuracy of 97.3% on challenging datasets like AMpds2, highlight its distinctive edge over conventional forecasting techniques, making it a promising solution for enhancing forecasting accuracy in HEMS.The article provides a brief summary of HEMS and load forecasting techniques, demonstrating and comparing them with deep learning models to showcase the efficacy of the proposed algorithms. [ABSTRACT FROM AUTHOR]

With the popularity of smart devices and online social media platforms, people are expressing their views in various modalities like text, images, and audio. Thus, recent research in sentiment analysis is no more limited to one modality of information only, rather it compiles all the available modalities to predict more correct sentiment. Multimodal sentiment analysis (MSA) is the process of extracting sentiment from various modalities such as text, images, and audio. Existing research works predict the sentiment of individual modalities independently and these predictions leverage the final sentiment. This paper presents an MSA approach for obtaining the final sentiment of an image-text tweet using multimodal decision-level fusion by incorporating features of individual modalities and inter-modal semantic relations. A dataset is prepared from an existing benchmark MSA dataset by annotating the final sentiment to tweets as a whole after assessing all the modalities. The proposed approach is experimented on this dataset and compared with state-of-the-art MSA methods. The in-depth analysis of the comparison results shows that the proposed approach outperforms existing methods in terms of accuracy, and F1-score. [ABSTRACT FROM AUTHOR]

Sentiment analysis involves extracting sentiments from various forms of text, including customer reviews, tweets, blogs, and news clips expressing opinions on diverse subjects, even populist events. The advent of tools supporting regional languages has resulted in a substantial surge of regional language texts. As Hindi ranks fourth in terms of native speakers, the development of sentiment analysis mechanisms for Hindi text becomes crucial. This paper provides a comprehensive review of specific approaches used in Hindi sentiment analysis, encompassing negation handling and the evolution of SentiWordNet for the Hindi Language. Moreover, it offers an overview of available Hindi lexicons and insights into diverse stemmers and morphological analyzers designed for the language. Additionally, the paper conducts an in-depth literature review of various sentiment analysis tasks carried out in Hindi, thereby opening avenues for future research in sentiment analysis and opinion mining in the Hindi language. [ABSTRACT FROM AUTHOR]

Forensic identification of vulnerabilities in Ethereum based smart contract has received significant interest among security agencies and researchers because it normally manages a lot of cryptocurrencies worth billions of dollars. Recalling the fact that smart contracts, a small set of instruction or programmes especially designed towards user verification, authentication and access control in Blockchain, can have the different vulnerabilities including Denial of Services (DoS), access control, Arithmetic integer overflow, arithmetic bad-randomness, re-entrancy, unchecked low-level calls, etc. In this paper a novel methodology using natural language processing and machine learning based vulnerability detection system is developed. The overall proposed model was designed towards Ethereum based Smart Contracts, where the standard benchmark data with the different vulnerability types has been taken into consideration. Though, classical methods apply SolMatrix tool to extract the features from Ethereum Solidarity vulnerability matrix however, they are confined to address feature variations, data imbalance which eventually impacts overall (vulnerability) classification performance. Considering this fact, in this research the overall methodology was defined in such manner that it assesses a Ethereum Solidity Smart Contract towards the probability of any (aforesaid) vulnerability types.To examine the performance of the proposed vulnerability detection model, we obtained results in terms of Accuracy, F-Measure, and Area and ROC Curve (AUC). The extensive performance analysis in terms of intra-model comparison, the average accuracy with SMOTE sampled data resulted near 90% of accuracy using Random Forest Algorithm. AUC performance too was found near 0.7, confirming acceptability of the proposed model. With Random Forest algorithm the average F-Measure was found to be near 0.86. [ABSTRACT FROM AUTHOR]

Due to the uncertainty of geological conditions during the tunneling process, advanced prediction of TBM tunneling parameters is significant for evaluating operational safety and efficiency, especially for real-time prediction of key tunneling parameters during the steady phase of TBM operation. At present, although there are studies on constructing predictive models based on machine learning algorithms, multiparameter prediction consistent with the actual tunneling process remains challenging due to the complexity of the TBM tunneling process and the numerous tunneling parameters. Therefore, this paper proposes a real-time multiple tunneling parameters prediction method of TBM steady phase based on dual recurrent neural networks. Firstly, the irregular multidimensional time series of tunneling parameters are analyzed and processed, which are divided into an idle-push phase, a rising phase, and a steady phase; secondly, the parameters of rising phase are analyzed using a recurrent neural network, and the parameters relevant for constructing a real-time prediction model are screened; then, based on the screened parameters, the Bayesian-optimized gated recurrent unit (GRU, a kind of recursive neural network) is proposed to construct a real-time prediction model for the four key tunneling parameters during the steady phase. Finally, the effectiveness and practicality of the proposed method are demonstrated by verification on real TBM tunnel datasets and comparing it with the models constructed by six commonly used machine learning algorithms. The results of this paper show that the designed prediction method is able to achieve a good combination of performance in terms of accuracy and computational time-consumption, with an average prediction accuracy of 91.1% for the four parameters for different rock grades of geology, the multiparameter prediction time for 100 samples is only 11 ms. In addition, three current similar studies using deep learning methods were compared to demonstrate the superiority of this proposal. As a method more closer to practical application, this work provides guidance for the forward-looking prediction of TBM tunneling parameters. [ABSTRACT FROM AUTHOR]

The utilization of artificial intelligence (AI) in healthcare is on the rise, demanding increased accessibility to (public) medical data for benchmarking. The digitization of healthcare in recent years has facilitated medical data scientists' access to extensive hospital data, fostering AI-based research. A notable addition to this trend is the Salzburg Intensive Care database (SICdb), made publicly available in early 2023. Covering over 27 thousand intensive care admissions at the University Hospital Salzburg from 2013 to 2021, this dataset presents a valuable resource for AI-driven investigations. This article explores the SICdb and conducts a comparative analysis with the widely recognized Medical Information Mart for Intensive Care - version IV (MIMIC-IV) database. The comparison focuses on key aspects, emphasizing the availability and granularity of data provided by the SICdb, particularly vital signs and laboratory measurements. The analysis demonstrates that the SICdb offers more detailed information with higher data availability and temporal resolution for signal data, especially for vital signs, compared to the MIMIC-IV. This is advantageous for longitudinal studies of patients' health conditions in the intensive care unit. The SICdb provides a valuable resource for medical data scientists and researchers. The database offers comprehensive and diverse healthcare data in a European country, making it well suited for benchmarking and enhancing AI-based healthcare research. The importance of ongoing efforts to expand and make public datasets available for advancing AI applications in the healthcare domain is emphasized by the findings. [ABSTRACT FROM AUTHOR]

Wind power forecasting techniques have been well developed over the last half-century. There has been a large number of research literature as well as review analyses. Over the past 5 decades, considerable advancements have been achieved in wind power forecasting. A large body of research literature has been produced, including review articles that have addressed various aspects of the subject. However, these reviews have predominantly utilized horizontal comparisons and have not conducted a comprehensive analysis of the research that has been undertaken. This survey aims to provide a systematic and analytical review of the technical progress made in wind power forecasting. To accomplish this goal, we conducted a knowledge map analysis of the wind power forecasting literature published in the Web of Science database over the last 2 decades. We examined the collaboration network and development context, analyzed publication volume, citation frequency, journal of publication, author, and institutional influence, and studied co-occurring and bursting keywords to reveal changing research hotspots. These hotspots aim to indicate the progress and challenges of current forecasting technologies, which is of great significance for promoting the development of forecasting technology. Based on our findings, we analyzed commonly used traditional machine learning and advanced deep learning methods in this field, such as  classical neural networks, and recent Transformers, and discussed emerging technologies like large language models. We also provide quantitative analysis of the advantages, disadvantages, forecasting accuracy, and computational costs of these methods. Finally, some open research questions and trends related to this topic were discussed, which can help improve the understanding of various power forecasting methods. This survey paper provides valuable insights for wind power engineers. [ABSTRACT FROM AUTHOR]

The article discusses the potential of advanced technologies in the field of cultural heritage. It highlights how these technologies, such as virtual reality, artificial intelligence, and 3D printing, can be used to understand, preserve, and enhance cultural heritage. The article also presents scientific papers from the Florence Heri-Tech International Conference, showcasing the various applications of these technologies. The papers cover topics such as the use of hyperspectral imaging for hieroglyph recognition, the enhancement of user experience in cultural spaces through advanced systems, and the use of non-invasive techniques for conservation. Overall, the article emphasizes the significant impact of technology on the research, preservation, and promotion of cultural heritage. [Extracted from the article]

Determining acute ischemic stroke (AIS) etiology is fundamental to secondary stroke prevention efforts but can be diagnostically challenging. We trained and validated an automated classification tool, StrokeClassifier, using electronic health record (EHR) text from 2039 non-cryptogenic AIS patients at 2 academic hospitals to predict the 4-level outcome of stroke etiology adjudicated by agreement of at least 2 board-certified vascular neurologists' review of the EHR. StrokeClassifier is an ensemble consensus meta-model of 9 machine learning classifiers applied to features extracted from discharge summary texts by natural language processing. StrokeClassifier was externally validated in 406 discharge summaries from the MIMIC-III dataset reviewed by a vascular neurologist to ascertain stroke etiology. Compared with vascular neurologists' diagnoses, StrokeClassifier achieved the mean cross-validated accuracy of 0.74 and weighted F1 of 0.74 for multi-class classification. In MIMIC-III, its accuracy and weighted F1 were 0.70 and 0.71, respectively. In binary classification, the two metrics ranged from 0.77 to 0.96. The top 5 features contributing to stroke etiology prediction were atrial fibrillation, age, middle cerebral artery occlusion, internal carotid artery occlusion, and frontal stroke location. We designed a certainty heuristic to grade the confidence of StrokeClassifier's diagnosis as non-cryptogenic by the degree of consensus among the 9 classifiers and applied it to 788 cryptogenic patients, reducing cryptogenic diagnoses from 25.2% to 7.2%. StrokeClassifier is a validated artificial intelligence tool that rivals the performance of vascular neurologists in classifying ischemic stroke etiology. With further training, StrokeClassifier may have downstream applications including its use as a clinical decision support system. [ABSTRACT FROM AUTHOR]

Few published data science tools are ever translated from academia to real-world clinical settings for which they were intended. One dimension of this problem is the software engineering task of turning published academic projects into tools that are usable at the bedside. Given the complexity of the data ecosystem in large health systems, this task often represents a significant barrier to the real-world deployment of data science tools for prospective piloting and evaluation. Many information technology companies have created Machine Learning Operations (MLOps) teams to help with such tasks at scale, but the low penetration of home-grown data science tools in regular clinical practice precludes the formation of such teams in healthcare organizations. Based on experiences deploying data science tools at two large academic medical centers (Beth Israel Deaconess Medical Center, Boston, MA; Mayo Clinic, Rochester, MN), we propose a strategy to facilitate this transition from academic product to operational tool, defining the responsibilities of the principal investigator, data scientist, machine learning engineer, health system IT administrator, and clinician end-user throughout the process. We first enumerate the technical resources and stakeholders needed to prepare for model deployment. We then propose an approach to planning how the final product will work from data extraction and analysis to visualization of model outputs. Finally, we describe how the team should execute on this plan. We hope to guide health systems aiming to deploy minimum viable data science tools and realize their value in clinical practice. [ABSTRACT FROM AUTHOR]

Background: Suicide is one of the leading causes of death among young people and university students. Research has identified numerous socio-demographic, relational, and clinical factors as potential predictors of suicide risk, and machine learning techniques have emerged as promising ways to improve risk assessment. Objective: This cross-sectional observational study aimed at identifying predictors and college student profiles associated with suicide risk through a machine learning approach. Methods: A total of 3102 students were surveyed regarding potential suicide risk, socio-demographic characteristics, academic career, and physical/mental health and well-being. The classification tree technique and the multiple correspondence analysis were applied to define students' profiles in terms of suicide risk and to detect the main predictors of such a risk. Results: Among the participating students, 7% showed high potential suicide risk and 3.8% had a history of suicide attempts. Psychological distress and use of alcohol/substance were prominent predictors of suicide risk contributing to define the profile of high risk of suicide: students with significant psychological distress, and with medium/high-risk use of alcohol and psychoactive substances. Conversely, low psychological distress and low-risk use of alcohol and substances, together with religious practice, represented the profile of students with low risk of suicide. Conclusions: Machine learning techniques could hold promise for assessing suicide risk in college students, potentially leading to the development of more effective prevention programs. These programs should address both risk and protective factors and be tailored to students' needs and to the different categories of risk. [ABSTRACT FROM AUTHOR]

Latest version of the AI models how proteins interact with other molecules — but DeepMind restricts access to the tool. [ABSTRACT FROM AUTHOR]

Autonomous weapons guided by artificial intelligence are already in use. Researchers, legal experts and ethicists are struggling with what should be allowed on the battlefield. [ABSTRACT FROM AUTHOR]

Automated disease diagnosis and prediction, powered by AI, play a crucial role in enabling medical professionals to deliver effective care to patients. While such predictive tools have been extensively explored in resource-rich languages like English, this manuscript focuses on predicting disease categories automatically from symptoms documented in the Afaan Oromo language, employing various classification algorithms. This study encompasses machine learning techniques such as support vector machines, random forests, logistic regression, and Naïve Bayes, as well as deep learning approaches including LSTM, GRU, and Bi-LSTM. Due to the unavailability of a standard corpus, we prepared three data sets with different numbers of patient symptoms arranged into 10 categories. The two feature representations, TF-IDF and word embedding, were employed. The performance of the proposed methodology has been evaluated using accuracy, recall, precision, and F1 score. The experimental results show that, among machine learning models, the SVM model using TF-IDF had the highest accuracy and F1 score of 94.7%, while the LSTM model using word2vec embedding showed an accuracy rate of 95.7% and F1 score of 96.0% from deep learning models. To enhance the optimal performance of each model, several hyper-parameter tuning settings were used. This study shows that the LSTM model verifies to be the best of all the other models over the entire dataset. [ABSTRACT FROM AUTHOR]

Internet of Medical Things (IoMT) can be leveraged for periodic sensing and recording of different health parameters using sensors, wireless communications, and computation platforms. Health care systems can be enhanced by using IoMT for remote patient monitoring and data-driven diagnosis powered by machine learning algorithms. In the context of IoMT, federated learning (FL) is an excellent choice to manage machine learning (ML) algorithms to drive this analysis. This is because FL models can be trained in a distributed manner on local heterogeneous datasets that all contribute to the "collective wisdom". The model parameters can be regulated and shared without sharing the actual health data, ensuring confidentiality and security. This paper makes a case for the viability of FL-based analysis of data acquired via IoMT by presenting some use cases and recent work in this area and proposing a novel framework for data analysis using FL specifically in the context of mental stress detection. It shows that FL-based methods can significantly reduce the required communication overhead for each local device from 10.02MB/day up to only 754B/day as compared to non-FL techniques. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is a collaborative artificial intelligence (AI) approach that enables distributed training of AI models without data sharing, thereby promoting privacy by design. However, it is essential to acknowledge that FL only offers a partial solution to safeguard the confidentiality of AI and machine learning (ML) models. Unfortunately, many studies fail to report the results of privacy measurement when applying FL, mainly due to assumptions that privacy is implicitly achieved as FL is a privacy-by-design approach. This trend can also be attributed to the complexity of understanding privacy measurement metrics and methods. This paper presents a survey of privacy measurement in FL, aimed at evaluating its effectiveness in protecting the privacy of sensitive data during the training of AI and ML models. While FL is a promising approach for preserving privacy during model training, ensuring privacy is genuinely achieved in practice is crucial. By evaluating privacy measurement metrics and methods in FL, we can identify the gaps in existing approaches and propose new techniques to enhance FL's privacy. A comprehensive study investigating "privacy measurement and metrics" in FL is therefore required to support the field's growth. Our survey provides a critical analysis of the current state of privacy measurement in FL, identifies gaps in existing research, and offers insights into potential research directions. Moreover, this paper presents a case study that evaluates the effectiveness of various privacy techniques in a specific FL scenario. This case study serves as tangible evidence of the real-world implications of privacy measurements, providing insightful and practical guidelines for researchers and practitioners to optimize privacy preservation while balancing other crucial factors such as communication overhead and accuracy. Finally, our paper outlines a future roadmap for advancing privacy in FL, combining traditional techniques with innovative technologies such as quantum computing and Trusted Execution Environments to fortify data protection. [ABSTRACT FROM AUTHOR]

Social media sites are now quite popular among internet users for sharing news and opinions. This has become possible due to the inexpensive Internet, easy availability of digital devices, and the no-cost policy to create a user account on social media platforms. People are fascinated by social media sites because they can easily connect with others to share their interests, news, and opinions. According to studies, someone who lacks credibility is more likely to spread false information in order to achieve goals of any kind, be it influencing political opinions, earning attention, or making money. The automatic detection of social media related fake news has thus emerged as a highly anticipated research area in recent years. This paper offers a comprehensive review of the automatic detection of fake news on social media platforms. It contains details of the key models or techniques related to machine/deep learning proposed (or developed) during the period of the year 2011 to the year 2022 along with the performance metrics of each model or technique. The paper discusses (a). the key challenges faced during the development of an effective and efficient fake news detection system, (b). some popular datasets for carrying out fake news detection related research, and (c). the major research gaps, and future research directions in the area of automatic fake news detection on social media. [ABSTRACT FROM AUTHOR]

In recent years, drones have brought about numerous conveniences in our work and daily lives due to their advantages of low cost and ease of use. However, they have also introduced significant hidden threats to public safety and personal privacy. Effectively and promptly detecting drone is thus a crucial task to ensure public safety and protect individual privacy. This paper proposes a method that combines beamforming algorithm with Deep Learning neural network to achieve the detection of drone acoustic event using microphone array technology. The aim is to achieve maximum coverage and accuracy in drone detection. The proposed approach utilizes beamforming algorithm to perform directional audio capture of the drone sound signal acquired by the microphone array. It then extracts features such as Log-Mel spectrogram and Mel-Frequency Cepstral Coefficients from the audio signal, which are subsequently input to a Convolutional Neural Network for classification. The final detection result is obtained through this process. The study also incorporates experimental analysis to assess the impact of different frontend processing algorithms, dataset compositions and feature selections on the detection performance. To provide a more specific and pronounced indication of the accomplishment of the drone sound event detection task, a novel evaluation criterion is introduced, termed as the Machine- Human Ultimate Distance Ratio. This criterion is employed to assess the detection effectiveness of the drone sound event detection task. The results demonstrate that the detection range and accuracy of the drone sound event detection system based on Deep Learning and microphone array surpass those of single-microphone sound event detection method. The proposed detection approach achieves effective detection within a range of up to 135 m in the surrounding environment. [ABSTRACT FROM AUTHOR]

Music streaming services have transformed the way people listen to music in recent years. The current streaming services majorly rely on collaborative and hybrid filtering techniques, which predominantly recommend popular songs. However, most present systems lack musical contents, user taste changes, and novelty parameters. In this paper, we propose a music recommendation using reinforcement learning with personalizing the individual results. The proposed method implements a Q-learning model derived from the incremental reinforcement learning algorithm based on the cumulative reward from similar songs played and liked during the session. The user profile is modeled using implicit and explicit feedback from the individual musical interactions with the system. The cumulative reward obtained from the experimental outcomes demonstrates that a combination of reinforcement learning and personalized recommendation potentially broadens the scope of recommendations by including freshness and novelty. The experimental result shows average interaction time improvement of 35% compared with existing apps. [ABSTRACT FROM AUTHOR]

Researchers can examine numerous ailments and forecast improved treatments using a huge number of medical databases. The Michael Fox PPMI data sets provide a baseline evaluation of the disease using the Unified Parkinson's Disease Rating Scales, the most prevalent sequential scales for identifying Parkinson's conditions. Existing research uses a Gaussian mixture model to predict PD disease using min–max normalization and dimensionality reduction based on principal component analysis. It significantly improved the findings, but it required more data to make predictions. This may be developed by decreasing the numbers of features utilized for prediction utilizing optimization algorithms. As a result, the ant-colony optimizations approach is suggested in this paper to enhance the classifier with few features. The ant colony approach uses this information to select the lowest features to use in training the regression neural network for disease prediction. When compared to various dimensionality reductions methods including Fast-ICA, PCAs, Kernel-PCA, as well as NMF, the findings suggest that the suggested optimization approaches performing-well. The neural regression network also reveals that the suggested strategy outperforms the Gaussian mixture model with the least patient information on the UPDRSs dataset. [ABSTRACT FROM AUTHOR]

Sentiment analysis is a part of natural language processing, along with text mining. Over the years, sentiment analysis has become a key study area for researchers and industries all over the world. The major goal of this review is to overview the papers that have found the sentiment of the data under study over the past few years. Also, the various techniques and methods that have enabled us to solve the problem of sentiment analysis are looked into and put forward briefly. The articles are looked into considering the area of sentiment analysis in which the contributions are made, be it sentiment detection, dataset creation, or transfer learning. This would help the researchers to curate advanced and accurate models and methods for analyzing sentiment. Additionally, they would be given a quick rundown of current developments in this area of research. With this in mind, the literature study is conducted taking into account various applications, various machine learning algorithms, the type of data utilized for analysis purposes, and various performance measurements. Challenges and gaps based on all the contributions studied are summarized. [ABSTRACT FROM AUTHOR]

The evolution of sophisticated deep learning algorithms such as Generative Adversarial Networks has made it possible to create deepfakes videos with convincing reality. Deepfake identification is important to address internet disinformation campaigns and lessen negative social media effects. Existing studies either use handcrafted features or deep learning-based models for deepfake detection. To effectively combine the attributes of both approaches, this paper presents a fusion of deep features with handcrafted texture features to create a powerful fused feature vector for accurate deepfakes detection. We propose a Directional Magnitude Local Hexadecimal Pattern (DMLHP) to extract the 320-D texture features and extract the deep feature vector of 2048-D using inception V3. Next, we employ the Principal Component Analysis to reduce the feature dimensions to 320 for a balanced representation of features after fusion. The deep and handcrafted features are combined to form a fused feature vector of 640-D. Further, we employ the proposed features to train the XGBoost model for the classification of frames as genuine or forged. We evaluated our proposed model on Faceforensic + + and Deepfake Detection Challenge Preview (DFDC-P) datasets. Our method achieved the accuracy and area under the curve of 97.7% and 99.3% on Faceforensic + + , whereas 90.8% and 93.1% on the DFDC-P dataset, respectively. Moreover, we performed a cross-set and cross-dataset evaluation to show the generalization capability of our model. [ABSTRACT FROM AUTHOR]

Recently, Electrocardiography (ECG) signals are commonly used in diagnosing the cardiac arrhythmia that shows up with the loss of the regular movement of the heart. Approximately 5% of the world population have cardio motor disorders. Therefore, usage of the ECG signals in biomedical signal processing algorithms and machine learning methods for automated diagnosis of this widespread health problem is a popular research topic. In this paper, the Particle Swarm Optimization (PSO) technique is implemented to tune the parameters of Tunable Q-Factor Wavelet Transform (TQWT) and the new generation feature generator Hamsi Hash Function (Hamsi-Pat) is used to obtain the characteristics of the signal. Sub-signals of 10 s obtained from the original ECG signal are divided into their sub-bands of 25 levels with PSO and TQWT. Each of these low pass filters generates 536 dimensional features by applying Hamsi-Pat and statistical methods. Then, all these features are combined and 536 × 25 = 13400-dimensional feature set is obtained. The features in the set are reduced and the best of them are selected by using the Iterative Neighborhood Component Analysis (INCA) method. Finally, the k-Nearest Neighbors (kNN) classification method is applied to the best features according to the City Block measurement criterion. All studies cited to compare the results in this paper also use the MIT-BIH Arrhythmia ECG database. Hence, the difference could be observed in the used techniques. In contrast to the existing studies, this study shows its superior performance by classifying all 17 classes simultaneously by applying a "fused" approach. The method in the paper reached 98.5% classification accuracy on the 17 classes of the MIT-BIH Arrhythmia ECG database. The results indicate that the proposed method showed better rates from the existing studies related to arrhythmia diagnosis using ECG signals in the literature. [ABSTRACT FROM AUTHOR]

Dermoscopy is a noninvasive way to examine and diagnose skin lesions, e.g. nevus and melanoma, and is a critical step for skin cancer detection. Accurate classification of dermoscopic images can detect skin cancer at an early stage and bring social and economic impact to patients and communities. Using deep learning methods to classify dermoscopic images has shown superior performance, but existing research often overlooks the class imbalance in the data. In addition, although a handful of public datasets are available for skin cancer research, these datasets are generally not large enough for deep learning algorithms to produce accurate results. In this paper, we propose to use data augmentation and generative adversarial networks (GAN) to tackle class-imbalanced dermoscopic image classification. Our main objectives are to determine (1) how state-of-the-art fine-tuned deep learning models perform on class-imbalanced dermoscopic images, (2) whether data augmentation and GAN can help alleviate class imbalances to improve classification accuracy, and (3) which method is more effective in addressing the class imbalance. By using public datasets and a carefully designed framework to generate augmented images and synthetic images, our research provides clear answers to these questions. Code and data used in the study are available at: https://github.com/mjan2021/Dermoscopic-image-classification.git [ABSTRACT FROM AUTHOR]

Student engagement is positively related to learning outcomes. The student engagement measurement is studied in varied settings, from the traditional classroom to online learning. Artificial intelligence and machine learning advancements have fueled automatic student engagement analysis. The automated student engagement measurement employed several sensor data such as audio, video, and physiological signals in different settings. This paper presents a literature review of automatic student engagement measurement in the classroom and online learning settings, including data collection and annotation techniques, methods, and evaluation metrics. First, a generalized methodology for automatic student engagement analysis is discussed. Then we describe various data collection techniques and annotation methods widely used in the literature and detail the limitations and advantages. The state-of-the-art machine learning methods and the evaluation metrics used to test those methods are reviewed. Additionally, we extend our literature review to the insight into the existing datasets for evaluating the automatic student engagement methods and recent developments in the machine learning methods on open-source datasets. Finally, we present a comprehensive comparison of the methods proposed on various public datasets based on evaluation metrics and engagement types. [ABSTRACT FROM AUTHOR]

This paper introduces a new learning-based approach for approximately solving the Kidney-Exchange Problem (KEP), an NP-hard problem on graphs. The KEP consists of, given a pool of kidney donors and patients waiting for kidney donations, optimally selecting a set of donations to optimize the quantity and quality of transplants performed while respecting a set of constraints about the arrangement of these donations. The proposed technique consists of two major steps: the first is a Graph Neural Network (GNN) trained without supervision; the second is a deterministic non-learned search heuristic that uses the output of the GNN to find a valid solution. To allow for comparisons, we also implemented and tested an exact solution method using integer programming, two greedy search heuristics without the machine learning module, and the GNN alone without a heuristic. We analyze and compare the methods and conclude that the learning-based two-stage approach is the best solution quality, outputting approximate solutions on average 1.1 times more valuable than the ones from the deterministic heuristic alone. [ABSTRACT FROM AUTHOR]

Language models (LMs) such as BERT and GPT have revolutionized natural language processing (NLP). However, the medical field faces challenges in training LMs due to limited data access and privacy constraints imposed by regulations like the Health Insurance Portability and Accountability Act (HIPPA) and the General Data Protection Regulation (GDPR). Federated learning (FL) offers a decentralized solution that enables collaborative learning while ensuring data privacy. In this study, we evaluated FL on 2 biomedical NLP tasks encompassing 8 corpora using 6 LMs. Our results show that: (1) FL models consistently outperformed models trained on individual clients' data and sometimes performed comparably with models trained with polled data; (2) with the fixed number of total data, FL models training with more clients produced inferior performance but pre-trained transformer-based models exhibited great resilience. (3) FL models significantly outperformed pre-trained LLMs with few-shot prompting. [ABSTRACT FROM AUTHOR]

Overall quality of radiomics research has been reported as low in literature, which constitutes a major challenge to improve. Consistent, transparent, and accurate reporting is critical, which can be accomplished with systematic use of reporting guidelines. The CheckList for EvaluAtion of Radiomics research (CLEAR) was previously developed to assist authors in reporting their radiomic research and to assist reviewers in their evaluation. To take full advantage of CLEAR, further explanation and elaboration of each item, as well as literature examples, may be useful. The main goal of this work, Explanation and Elaboration with Examples for CLEAR (CLEAR-E3), is to improve CLEAR's usability and dissemination. In this international collaborative effort, members of the European Society of Medical Imaging Informatics−Radiomics Auditing Group searched radiomics literature to identify representative reporting examples for each CLEAR item. At least two examples, demonstrating optimal reporting, were presented for each item. All examples were selected from open-access articles, allowing users to easily consult the corresponding full-text articles. In addition to these, each CLEAR item's explanation was further expanded and elaborated. For easier access, the resulting document is available at https://radiomic.github.io/CLEAR-E3/. As a complementary effort to CLEAR, we anticipate that this initiative will assist authors in reporting their radiomics research with greater ease and transparency, as well as editors and reviewers in reviewing manuscripts. Relevance statement Along with the original CLEAR checklist, CLEAR-E3 is expected to provide a more in-depth understanding of the CLEAR items, as well as concrete examples for reporting and evaluating radiomic research. Key points • As a complementary effort to CLEAR, this international collaborative effort aims to assist authors in reporting their radiomics research, as well as editors and reviewers in reviewing radiomics manuscripts. • Based on positive examples from the literature selected by the EuSoMII Radiomics Auditing Group, each CLEAR item explanation was further elaborated in CLEAR-E3. • The resulting explanation and elaboration document with examples can be accessed at https://radiomic.github.io/CLEAR-E3/. [ABSTRACT FROM AUTHOR]

Carbon nanotubes (CNTs), hollow cylinders of carbon, hold great promise for advanced technologies, provided their structure remains uniform throughout their length. Their growth takes place at high temperatures across a tube-catalyst interface. Structural defects formed during growth alter CNT properties. These defects are believed to form and heal at the tube-catalyst interface but an understanding of these mechanisms at the atomic-level is lacking. Here we present DeepCNT-22, a machine learning force field (MLFF) to drive molecular dynamics simulations through which we unveil the mechanisms of CNT formation, from nucleation to growth including defect formation and healing. We find the tube-catalyst interface to be highly dynamic, with large fluctuations in the chiral structure of the CNT-edge. This does not support continuous spiral growth as a general mechanism, instead, at these growth conditions, the growing tube edge exhibits significant configurational entropy. We demonstrate that defects form stochastically at the tube-catalyst interface, but under low growth rates and high temperatures, these heal before becoming incorporated in the tube wall, allowing CNTs to grow defect-free to seemingly unlimited lengths. These insights, not readily available through experiments, demonstrate the remarkable power of MLFF-driven simulations and fill long-standing gaps in our understanding of CNT growth mechanisms. There is a lack of atomic level insight on the role of defects on carbon nanotubes' growth. Here, authors present a machine learning force field to drive near-microsecond simulations the entire growth process of this material, unveiling mechanisms of defect formation and healing. [ABSTRACT FROM AUTHOR]

Materials synthesis platforms that are designed for autonomous experimentation are capable of collecting multimodal diagnostic data that can be utilized for feedback to optimize material properties. Pulsed laser deposition (PLD) is emerging as a viable autonomous synthesis tool, and so the need arises to develop machine learning (ML) techniques that are capable of extracting information from in situ diagnostics. Here, we demonstrate that intensified-CCD image sequences of the plasma plume generated during PLD can be used for anomaly detection and the prediction of thin film growth kinetics. We develop multi-output (2 + 1)D convolutional neural network regression models that extract deep features from plume dynamics that not only correlate with the measured chamber pressure and incident laser energy, but more importantly, predict parameters of an auto-catalytic film growth model derived from in situ laser reflectivity experiments. Our results demonstrate how ML with in situ plume diagnostics data in PLD can be utilized to maintain deposition conditions in an optimal regime. Further, the predictive capabilities of plume dynamics on the kinetics of film growth or other film properties prior to deposition provides a means for rapid pre-screening of growth conditions for the non-expert, which promises to accelerate materials optimization with PLD. [ABSTRACT FROM AUTHOR]

Scientific research of artificial intelligence (AI) in dermatology has increased exponentially. The objective of this study was to perform a systematic review and meta-analysis to evaluate the performance of AI algorithms for skin cancer classification in comparison to clinicians with different levels of expertise. Based on PRISMA guidelines, 3 electronic databases (PubMed, Embase, and Cochrane Library) were screened for relevant articles up to August 2022. The quality of the studies was assessed using QUADAS-2. A meta-analysis of sensitivity and specificity was performed for the accuracy of AI and clinicians. Fifty-three studies were included in the systematic review, and 19 met the inclusion criteria for the meta-analysis. Considering all studies and all subgroups of clinicians, we found a sensitivity (Sn) and specificity (Sp) of 87.0% and 77.1% for AI algorithms, respectively, and a Sn of 79.78% and Sp of 73.6% for all clinicians (overall); differences were statistically significant for both Sn and Sp. The difference between AI performance (Sn 92.5%, Sp 66.5%) vs. generalists (Sn 64.6%, Sp 72.8%), was greater, when compared with expert clinicians. Performance between AI algorithms (Sn 86.3%, Sp 78.4%) vs expert dermatologists (Sn 84.2%, Sp 74.4%) was clinically comparable. Limitations of AI algorithms in clinical practice should be considered, and future studies should focus on real-world settings, and towards AI-assistance. [ABSTRACT FROM AUTHOR]

With the development of Non-Intrusive Load Monitoring (NILM), it has become feasible to perform device identification, energy consumption decomposition, and load switching detection using Deep Learning (DL) methods. Similar to other machine learning problems, the research and validation of NILM necessitate substantial data support. Moreover, different regions exhibit distinct characteristics in their electricity environments. Therefore, there is a need to provide open datasets tailored to different regions. In this paper, we introduce the Transient Dataset of Household Appliances with Intensive Switching Events (TDHA25). This dataset comprises switch instantaneous data from 10 typical household appliances in China. The TDHA dataset features a high sampling rate, accurate labelling, and realistic representation of actual appliance start-up waveforms. Additionally, appliance switching is achieved through precise control of relay switches, thus mitigating interference caused by mechanical switches. By furnishing such a dataset, we aim not only to enhance the recognition accuracy of existing NILM algorithms but also to facilitate the application of NILM algorithms in regions sharing similar electricity consumption characteristics to those of China. [ABSTRACT FROM AUTHOR]

This study investigates the application of cavitation in non-invasive abdominal fat reduction and body contouring, a topic of considerable interest in the medical and aesthetic fields. We explore the potential of cavitation to alter abdominal fat composition and delve into the optimization of fat prediction models using advanced hyperparameter optimization techniques, Hyperopt and Optuna. Our objective is to enhance the predictive accuracy of abdominal fat dynamics post-cavitation treatment. Employing a robust dataset with abdominal fat measurements and cavitation treatment parameters, we evaluate the efficacy of our approach through regression analysis. The performance of Hyperopt and Optuna regression models is assessed using metrics such as mean squared error, mean absolute error, and R-squared score. Our results reveal that both models exhibit strong predictive capabilities, with R-squared scores reaching 94.12% and 94.11% for post-treatment visceral fat, and 71.15% and 70.48% for post-treatment subcutaneous fat predictions, respectively. Additionally, we investigate feature selection techniques to pinpoint critical predictors within the fat prediction models. Techniques including F-value selection, mutual information, recursive feature elimination with logistic regression and random forests, variance thresholding, and feature importance evaluation are utilized. The analysis identifies key features such as BMI, waist circumference, and pretreatment fat levels as significant predictors of post-treatment fat outcomes. Our findings underscore the effectiveness of hyperparameter optimization in refining fat prediction models and offer valuable insights for the advancement of non-invasive fat reduction methods. This research holds important implications for both the scientific community and clinical practitioners, paving the way for improved treatment strategies in the realm of body contouring. [ABSTRACT FROM AUTHOR]

Liquefaction is a devastating consequence of earthquakes that occurs in loose, saturated soil deposits, resulting in catastrophic ground failure. Accurate prediction of such geotechnical parameter is crucial for mitigating hazards, assessing risks, and advancing geotechnical engineering. This study introduces a novel predictive model that combines Extreme Learning Machine (ELM) with Dingo Optimization Algorithm (DOA) to estimate strain energy-based liquefaction resistance. The hybrid model (ELM-DOA) is compared with the classical ELM, Adaptive Neuro-Fuzzy Inference System with Fuzzy C-Means (ANFIS-FCM model), and Sub-clustering (ANFIS-Sub model). Also, two data pre-processing scenarios are employed, namely traditional linear and non-linear normalization. The results demonstrate that non-linear normalization significantly enhances the prediction performance of all models by approximately 25% compared to linear normalization. Furthermore, the ELM-DOA model achieves the most accurate predictions, exhibiting the lowest root mean square error (484.286 J/m3), mean absolute percentage error (24.900%), mean absolute error (404.416 J/m3), and the highest correlation of determination (0.935). Additionally, a Graphical User Interface (GUI) has been developed, specifically tailored for the ELM-DOA model, to assist engineers and researchers in maximizing the utilization of this predictive model. The GUI provides a user-friendly platform for easy input of data and accessing the model's predictions, enhancing its practical applicability. Overall, the results strongly support the proposed hybrid model with GUI serving as an effective tool for assessing soil liquefaction resistance in geotechnical engineering, aiding in predicting and mitigating liquefaction hazards. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel pricing model for delivery insurance in a food delivery company in Latin America, with the aim of reducing the high costs associated with the premium paid to the insurer. To achieve this goal, a thorough analysis was conducted to estimate the probability of losses based on delivery routes, transportation modes, and delivery drivers' profiles. A large amount of data was collected and used as a database, and various statistical models and machine learning techniques were employed to construct a comprehensive risk profile and perform risk classification. Based on the risk classification and the estimated probability associated with it, a new pricing model for delivery insurance was developed using advanced mathematical algorithms and machine learning techniques. This new pricing model took into account the pattern of loss occurrence and high and low-risk behaviors, resulting in a significant reduction of insurance costs for both the contracting company and the insurer. The proposed pricing model also allowed for greater flexibility in insurance contracting, making it more accessible and appealing to delivery drivers. The use of estimated loss probabilities and a risk score for the pricing of delivery insurance proved to be a highly effective and efficient alternative for reducing the high costs associated with insurance, while also improving the profitability and competitiveness of the food delivery company in Latin America. [ABSTRACT FROM AUTHOR]