Machine Learning

Accurate and early prediction of a disease allows to plan and improve a patient's quality of future life. During pandemic situations, the medical decision becomes a speed challenge in which physicians have to act fast to diagnose and predict the risk of the severity of the disease, moreover this is also of high priority for neurodegenerative diseases like Parkinson's disease. Machine Learning (ML) models with Features Selection (FS) techniques can be applied to help physicians to quickly diagnose a disease. FS optimally subset features that improve a model performance and help reduce the number of needed tests for a patient and hence speeding up the diagnosis. This study shows the result of three Feature Selection (FS) techniques pre-applied to a classifier algorithm, Logistic Regression, on non-invasive test results data. The three FS are Analysis of Variance (ANOVA) as filter based method, Least Absolute Shrinkage and Selection Operator (LASSO) as embedded method and Sequential Feature Selection (SFS) as wrapper method. The outcome shows that FS technique can help to build an efficient and effective classifier, hence improving the performance of the classifier while reducing the computation time.

Deep learning methods used for retinal diagnosis are typically "black boxes" that cannot explain how the system made its decision. In this study multiple explainability methods that highlight anomalous regions in OCT scans are compared for their clinical significance.

The accuracy and flexibility of Deep Convolutional Neural Networks (DCNNs) have been highly validated over the past years. However, their intrinsic opaqueness is still affecting their reliability and limiting their application in critical production systems, where the black-box behavior is difficult to be accepted. This work proposes EBAnO, an innovative explanation framework able to analyze the decision-making process of DCNNs in image classification by providing prediction-local and class-based model-wise explanations through the unsupervised mining of knowledge contained in multiple convolutional layers. EBAnO provides detailed visual and numerical explanations thanks to two specific indexes that measure the features' influence and their influence precision in the decision-making process. The framework has been experimentally evaluated, both quantitatively and qualitatively, by (i) analyzing its explanations with four state-of-the-art DCNN architectures, (ii) comparing its results with three state-of-the-art explanation strategies and (iii) assessing its effectiveness and easiness of understanding through human judgment, by means of an online survey. EBAnO has been released as open-source code and it is freely available online.

Despite the high accuracy offered by state-of-the-art deep natural-language models (e.g., LSTM, BERT), their application in real-life settings is still widely limited, as they behave like a black-box to the end-user. Hence, explainability is rapidly becoming a fundamental requirement of future-generation data-driven systems based on deep-learning approaches. Several attempts to fulfill the existing gap between accuracy and interpretability have been made. However, robust and specialized eXplainable Artificial Intelligence solutions, tailored to deep natural-language models, are still missing. We propose a new framework, named T-EBAnO, which provides innovative prediction-local and class-based model-global explanation strategies tailored to deep learning natural-language models. Given a deep NLP model and the textual input data, T-EBAnO provides an objective, human-readable, domain-specific assessment of the reasons behind the automatic decision-making process. Specifically, the framework extracts sets of interpretable features mining the inner knowledge of the model. Then, it quantifies the influence of each feature during the prediction process by exploiting the normalized Perturbation Influence Relation index at the local level and the novel Global Absolute Influence and Global Relative Influence indexes at the global level. The effectiveness and the quality of the local and global explanations obtained with T-EBAnO are proved on an extensive set of experiments addressing different tasks, such as a sentiment-analysis task performed by a fine-tuned BERT model and a toxic-comment classification task performed by an LSTM model. The quality of the explanations proposed by T-EBAnO, and, specifically, the correlation between the influence index and human

Pemrograman Linier Parametrik merupakan model pengembangan analisis sensitivitas dimana koefisien input berubah secara simultan. Model ini mengembangkan pemecahan masalah dimana nilai koefisien input tidak diketahui dengan pasti, namun dapat dilakukan estimasi dalam interval tertentu sesuai dengan tingkat kepercayaan yang diharapkan. Dalam tulisan ini diuraikan manfaat Pemrograman Linier Parametrik untuk menganalisis dampak fluktuasi koefisien fungsi objektif dan konstanta terhadap solusi optimal. Terbukti bahwa perubahan koefisien input dalam interval tertentu tidak mengubah solusi optimal yang telah diperoleh sebelumnya.

Biomarkers able to characterise and predict multifactorial diseases are still one of the most important targets for all the "omics" investigations. In this context, Matrix-Assisted Laser Desorption/Ionisation-Mass Spectrometry Imaging (MALDI-MSI) has gained considerable attention in recent years, but it also led to a huge amount of complex data to be elaborated and interpreted. For this reason, computational and machine learning procedures for biomarker discovery are important tools to consider, both to reduce data dimension and to provide predictive markers for specific diseases. For instance, the availability of protein and genetic markers to support thyroid lesion diagnoses would impact deeply on society due to the high presence of undetermined reports (THY3) that are generally treated as malignant patients. In this paper we show how an accurate classification of thyroid bioptic specimens can be obtained through the application of a state-of-the-art machine learning approach (i.e., Support Vector Machines) on MALDI-MSI data, together with a particular wrapper feature selection algorithm (i.e., recursive feature elimination). The model is able to provide an accurate discriminatory capability using only 20 out of 144 features, resulting in an increase of the model performances, reliability, and computational efficiency. Finally, tissue areas rather than average proteomic profiles are classified, highlighting potential discriminating areas of clinical interest.

Planning, scheduling and Resource levelling plays an important role in any construction project maybe it is construction of building or construction of road. In absence of proper planning, scheduling and resource levelling construction industry does not get profit over the project. For this purpose, proper software's and techniques must be utilize. This paper is focussing on the advantages of Oracle Primavera P6 Software. The latest version of Primavera is P6-17. In any construction work huge amount of paperwork is needed, which makes the management very burdensome. By using Oracle's Primavera P6 Software paperwork can be reduce, resulting in reduction of burden. Primavera P6 give improvement in construction management. Primavera P6 is the time redeemable tool, with proper resource optimization.

Decision trees are probably the most popular and commonly used classification model. They are built recursively following a top-down approach (from general concepts to particular examples) by repeated splits of the training dataset. The chosen splitting criterion may affect the accuracy of the classifier, but not significantly. In fact, none of the proposed splitting criteria in the literature has proved to be universally better than the rest. Although they all yield similar results, their complexity varies significantly, and they are not always suitable for multi-way decision trees. Here we propose two new splitting rules which obtain similar results to other well-known criteria when used to build multi-way decision trees, while their simplicity makes them ideal for non-expert users.

In recent years, the global e-commerce landscape has witnessed rapid growth, with sales reaching a new peak in the past year and expected to rise further in the coming years. Amid this e-commerce boom, accurately predicting user purchase behavior has become crucial for commercial success. We introduce a novel framework integrating three innovative approaches to enhance the prediction model's effectiveness. First, we integrate an eventbased timestamp encoding within a time-series attention model, effectively capturing the dynamic and temporal aspects of user behavior. This aspect is often neglected in traditional user purchase prediction methods, leading to suboptimal accuracy. Second, we incorporate Graph Neural Networks (GNNs) to analyze user behavior. By modeling users and their actions as nodes and edges within a graph structure, we capture complex relationships and patterns in user behavior more effectively than current models, offering a nuanced and comprehensive analysis. Lastly, our framework transcends traditional learning strategies by implementing advanced meta-learning techniques. This enables the model to autonomously adjust learning parameters, including the learning rate, in response to new and evolving data environments, thereby significantly enhancing its adaptability and learning efficiency. Through extensive experiments on diverse real-world e-commerce datasets, our model demonstrates superior performance, particularly in accuracy and adaptability in large-scale data scenarios. This study not only overcomes the existing challenges in analyzing e-commerce user behavior but also sets a foundation for future exploration in this dynamic field. We believe our contributions provide significant insights and tools for e-commerce platforms to better understand and cater to their users, ultimately driving sales and improving user experiences.

Administrative services in Indonesia present complex issues that demand comprehensive attention and resolution. It is crucial to acknowledge that government services provided to the community must constantly evolve to incorporate creative thinking from the public and adapt to the increasing demands of the community and changes within the government itself. The purpose of this study is to analyze public trust in population administration services at the Makassar City Population and Civil Registry Office. The research method employed in this study was qualitative, with data analysis conducted using descriptive qualitative techniques. The unit of analysis was individual, and data collection involved observation, interviews, and documentation to gather information about public trust in services at the Makassar City Population and Civil Registry Office. The data sources used in this study included both primary and secondary data. The data were analyzed using Miles and Huberman's analysis model (1994), with data reduction techniques, data presentation, and conclusion drawing. The study's results revealed that public trust in the government regarding public administration services was categorized as good. However, the researchers observed several aspects and shortcomings that require improvement, such as empathy and service ethics. It is important to ensure that people providing services feel respected and are not treated differently from one another.

Acquiring a functional comprehension of the deregulation of cell signaling networks in disease allows progress in the development of new therapies and drugs. Computational models are becoming increasingly popular as a systematic tool to analyze the functioning of complex biochemical networks, such as those involved in cell signaling. CellNOpt is a framework to build predictive logic-based models of signaling pathways by training a prior knowledge network to biochemical data obtained from perturbation experiments. This training can be formulated as an optimization problem that can be solved using metaheuristics. However, the genetic algorithm used so far in CellNOpt presents limitations in terms of execution time and quality of solutions when applied to large instances. Thus, in order to overcome those issues, in this paper we propose the use of a method based on ant colony optimization, adapted to the problem at hand and parallelized using a hybrid approach. The performance of this novel method is illustrated with several challenging benchmark problems in the study of new therapies for liver cancer.

Acquiring a functional comprehension of the deregulation of cell signaling networks in disease allows progress in the development of new therapies and drugs. Computational models are becoming increasingly popular as a systematic tool to analyze the functioning of complex biochemical networks, such as those involved in cell signaling. CellNOpt is a framework to build predictive logic-based models of signaling pathways by training a prior knowledge network to biochemical data obtained from perturbation experiments. This training can be formulated as an optimization problem that can be solved using metaheuristics. However, the genetic algorithm used so far in CellNOpt presents limitations in terms of execution time and quality of solutions when applied to large instances. Thus, in order to overcome those issues, in this paper we propose the use of a method based on ant colony optimization, adapted to the problem at hand and parallelized using a hybrid approach. The performance of this novel method is illustrated with several challenging benchmark problems in the study of new therapies for liver cancer.

Three probabilistic methodologies are developed for predicting the long-term creep rupture life of 9–12 wt%Cr ferritic-martensitic steels using their chemical and processing parameters. The framework developed in this research strives to simultaneously make efficient inference along with associated risk, i.e., the uncertainty of estimation. The study highlights the limitations of applying probabilistic machine learning to model creep life and provides suggestions as to how this might be alleviated to make an efficient and accurate model with the evaluation of epistemic uncertainty of each prediction. Based on extensive experimentation, Gaussian Process Regression yielded more accurate inference ($$Pearson\;correlation\;coefficent> 0.95$$ P e a r s o n c o r r e l a t i o n c o e f f i c e n t > 0.95 for the holdout test set) in addition to meaningful uncertainty estimate (i.e., coverage ranges from 94 to 98% for the test set) as compared to quantile regression and natural grad...

Three probabilistic methodologies are developed for predicting the long-term creep rupture life of 9−12 𝑤𝑡% 𝐶𝑟 ferritic-martensitic steels using their chemical and processing parameters. The framework developed in this research strives to simultaneously make efficient inference along with associated risk, i.e., the uncertainty of estimation. The study highlights the limitations of applying probabilistic machine learning to model creep life and provides suggestions as to how this might be alleviated to make an efficient and accurate model with the evaluation of epistemic uncertainty of each prediction. Based on extensive experimentation, Gaussian Process Regression yielded more accurate inference (𝑃𝑒𝑎𝑟𝑠𝑜𝑛 𝑐𝑜𝑟𝑟𝑒𝑙𝑎𝑡𝑖𝑜𝑛 𝑐𝑜𝑒𝑓𝑓𝑖𝑐𝑒𝑛𝑡> 0.95 for the holdout test set) in addition to meaningful uncertainty estimate (i.e., coverage ranges from 94 – 98% for the test set) as compared to quantile regression and natural gradient boosting algorithm. Furthermore, the possibility of an active learn...

Early fault detection and fault prognosis are crucial to ensure efficient and safe operations of complex engineering systems such as the Spallation Neutron Source (SNS) and its power electronics (high voltage converter modulators). Following an advanced experimental facility setup that mimics SNS operating conditions, the authors successfully conducted 21 fault prognosis experiments, where fault precursors are introduced in the system to a degree enough to cause degradation in the waveform signals, but not enough to reach a real fault. Nine different machine learning techniques based on ensemble trees, convolutional neural networks, support vector machines, and hierarchical voting ensembles are proposed to detect the fault precursors. Although all 9 models have shown a perfect and identical performance during the training and testing phase, the performance of most models has decreased in the prognosis phase once they got exposed to real-world data from the 21 experiments. The hierarchical voting ensemble, which features multiple layers of diverse models, maintains a distinguished performance in early detection of the fault precursors with 95% success rate (20/21 tests), followed by adaboost and extremely randomized trees with 52% and 48% success rates, respectively. The support vector machine models were the worst with only 24% success rate (5/21 tests). The study concluded that a successful implementation of machine learning in the SNS or particle accelerator power systems would require a major upgrade in the controller and the data acquisition system to facilitate streaming and handling big data for the machine learning models. In addition, this study shows that the best performing models were diverse and based on the ensemble concept to reduce the bias and hyperparameter sensitivity of individual models.

Semi-supervised learning is a machine learning approach that integrates supervised and unsupervised learning mechanisms. In this learning, most of labels in the training set are unknown, while there is a small part of data that has known labels. The semi-supervised learning is attractive due to its potential to use labeled and unlabeled data to perform better than supervised learning. This paper consists of a study in the field of semi-supervised learning and implements changes on two well-known semi-supervised learning algorithms: self-training and co-training. In the literature, it is common to develop researches that change the structure of these algorithms, however, none of them proposes automating the labeling process of unlabeled instances, which is the main purpose of this work. In order to achieve this goal, three methods are proposed: FlexCon-G, FlexCon and FlexCon-C. The main difference among these methods is the way in which the confidence rate is calculated and the strategy used to select a label in each iteration. In order to evaluate the proposed methods' performance, an empirical analysis is conducted, in which the performance of these methods has been evaluated on 30 datasets with different characteristics. The obtained results indicate that all three proposed methods perform better than the original self-training and co-training methods, in most analysed cases.

Semi-supervised learning (SSL) is a paradigm that has been continuously used in data classification tasks in datasets that do not have enough labeled instances to train a supervised model with a minimum acceptable accuracy. In this context, data stream classification in dynamic environments appears as a natural application for this approach, because changes in data distribution contribute to decrease the performance of the classification algorithms. In this paper, we have proposed a framework, refered to as Dynamic Data Stream Learning (DyDaSL), that implements an auto-adaptive classifier ensemble -which is able to evaluate and replace classifiers with decreasing performance. This platform uses the FlexCon-C method, which is a variant of the self-training SSL algorithm that adjusts a confidence threshold dynamically, in each iteration, to define which instances will be labeled. Experimental tests on synthetic and real datasets show that the proposed approach obtains better results than traditional approaches using four evaluation metrics: accuracy, F-score, precision, and recall.

The study aims to test the effect of the performance of the internal supervision unit, organizational culture, and organizational commitment toward the internal control system implementation for the implementation of good governance at the higher education service institution. Data analysis techniques using path analysis using data obtained from the distribution of questionnaires in 150 respondents. The results showed that the implementation of the internal control system in an effort to realize good governance was influenced by the performance of the internal supervision unit, organizational culture, and organizational commitment. The performance of the internal supervision unit has a very high influence on the implementation of the internal control system so that it is able to realize good governance in Higher Education Service Institutions.

This research addressed the challenge of recognizing emotions from speech by developing a deep learning-based speechemotion recognition (SER) system. A key focus of the study is the creation of a new Hausa emotional speech dataset, aimed at addressing the linguistic and cultural imbalance in existing SER datasets, which predominantly feature Western languages. This study captured four emotions: happy, sad, angry, and surprise among native Hausa speakers. The selfcaptured dataset was recorded in an environment that is devoid of noise to ensure high quality and uniformity in the audio data. A public dataset; RAVDESS was used for benchmarking the proposed technique. CNN and Bi-Directional Long Short-Term Memory (BiLSTM) architectures were combined and used as proposed model for the SER experiment. The developed CNN architecture helped in extracting spatial features, while the BiLSTM without the attention mechanism captured temporal dependencies from the audio data. The approach reduced time complexity and improved performance to 100% and 96% recognition accuracies against 94% and 90% of the benchmark model for the local and benchmark datasets respectively. The results demonstrate the proposed approach's robustness to generalize across linguistic contexts.

Estimating the bearing capacity of piles is an essential point when seeking for safe and economic geotechnical structures. However, the traditional methods employed in this estimation are time-consuming and costly. The current study aims at elaborating a new alternative model for predicting the pile-bearing capacity based on eleven new advanced machine-learning methods in order to overcome these limitations. The modeling phase used a database of 100 samples collected from different countries. Additionally, eight relevant factors were selected in the input layer based on the literature recommendations. The optimal inputs were modeled using the machine-learning methods and their performance was assessed through six performance measures using a K-fold cross-validation approach. The comparative study proved the effectiveness of the DNN model, which displayed a higher performance in predicting the pile-bearing capacity. This elaborated model provided the optimal prediction, i.e., the clo...

Background. Diabetic kidney disease (DKD), one of the complications of diabetes in patients, leads to progressive loss of kidney function. Timely intervention is known to improve outcomes. erefore, screening patients to identify high-risk populations is important. Machine learning classification techniques can be applied to patient datasets to identify high-risk patients by building a predictive model. Objective. is study aims to identify a suitable classification technique for predicting DKD by applying different classification techniques to a DKD dataset and comparing their performance using WEKA machine learning software. Methods. e performance of nine different classification techniques was analyzed on a DKD dataset with 410 instances and 18 attributes. Data preprocessing was carried out using the PartitionMembershipFilter. A 10-fold cross validation was performed on the dataset. e performance was assessed on the basis of the execution time, accuracy, correctly and incorrectly classified instances, kappa statistics (K), mean absolute error, root mean squared error, and true values of the confusion matrix. Results. With an accuracy of 93.6585% and a higher K value (0.8731), IBK and random tree classification techniques were found to be the best performing techniques. Moreover, they also exhibited the lowest root mean squared error rate (0.2496). ere were 15 false-positive instances and 11 false-negative instances with these prediction models. Conclusions. is study identified IBK and random tree classification techniques as the best performing classifiers and accurate prediction methods for DKD.

The present study aims to measure the prevalence of non-disabled frailty and its associated factors among Bangladeshi older adults. This cross-sectional study was conducted during September and October 2021 among 1,045 Bangladeshi older adults (�60 years). Telephone interviews, using a semi-structured questionnaire, were undertaken to collect data on participants' characteristics and level of frailty. The non-disabled frailty was measured using the 'Frail Non-Disabled (FiND)' questionnaire. A multinomial logistic regression model assessed the factors associated with frailty among the participants. Around a quarter of the participants (24.8%) were frail. The multinomial regression analysis showed that older participants aged �80 years (RRR = 3.23, 95% CI: 1.41-7.37) were more likely to be frail compared to participants aged 60-69 years. Likewise, the participants living in a large family with �4 members (RRR = 1.39, 95% CI: 1.01-1.92) were more likely to be frail compared to those living in smaller families. Also, participants having memory or

redistribute this paper in full or in part, you need to provide proper attribution to it to ensure that others can later locate this work (and to ensure that others do not accuse you of plagiarism). You may (and we encourage you to) adapt, remix, transform, and build upon the material for any non-commercial purposes. This license does not permit you to use this material for commercial purposes.

Regularisation has become an important tool in statistical modelling. In particular the challenge of high dimensional data boosted the fitting of more and more complex models that can not be fitted without appropriate regularisation. The need for regularisation, however, is not restricted to the modelling of high dimensional data, it is mainly driven by the complexity of the model. When the model includes nonparametric function estimation regularisation restricts the class of functions that are fitted. In regression and classification complexity of the model is usually determined by the structuring of the predictor. Regularisation helps to identify the relevant parts, which can consist of simple linear terms, functions, parametric or nonparametric interaction terms, or complex spatially and temporally structured terms. Regularisation can be made explicit by using penalty terms that restrict estimates or can be implicitly determined by the algorithm as for example in boosting methods. This issue of Statistics and Computing collects ten papers that focus on regularisation methods in different areas and with different methodology. Two papers are devoted to the extension of boosting techniques. In the paper "Twin Boosting: Improved Feature Selection and Prediction" P. Bühlmann and T. Hothorn propose a boosting method that consists of two rounds of common boosting with the second boosting process being forced to resemble the first round of boosting. The method shows much better feature selection behaviour than common boosting, in particular as far as false positives are concerned. The paper "Estimation and Regularization Techniques for Regression Models with Multidimensional Prediction Functions

The seminar "Promoting the Green Transition via University Education with Green Standards" presents the approach and concept of the international project Boosting the Green Future via University Micro-Credentials (B-Green-ED), funded by the Erasmus+ program KA220-HED -Cooperation partnerships in higher education, aiming to contribute to the achievement of the sustainable, green and digital goals of the European Union by providing innovative university micro-credentials related to environmental and management standards to improve the digital and green capabilities of the higher education sector. Some findings and results of the B-Green-ED research conducted in four EU countries -Bulgaria, Lithuania, Spain, and Romania are presented.

Automatic classification of blog entries is generally treated as a semi-supervised machine learning task, in which the blog entries are automatically assigned to one of a set of pre-defined classes based on the features extracted from their textual content. This paper attempts automatic classification of unstructured blog entries by following pre-processing steps like tokenization, stop-word elimination and stemming; statistical techniques for feature set extraction, and feature set enhancement using semantic resources followed by modeling using two alternative machine learning models-the naïve Bayesian model and the artificial neural network model. Empirical evaluations indicate that this multi-step classification approach has resulted in good overall classification accuracy over unstructured blog text datasets with both machine learning model alternatives. However, the naïve Bayesian classification model clearly out-performs the ANN based classification model when a smaller feature-set is available which is usually the case when a blog topic is recent and the number of training datasets available is restricted.

This paper describes the system developed for SemEval 2017 task 6: #HashTagWars -Learning a Sense of Humor. Learning to recognize sense of humor is the important task for language understanding applications. Different set of features based on frequency of words, structure of tweets and semantics are used in this system to identify the presence of humor in tweets. Supervised machine learning approaches, Multilayer perceptron and Naïve Bayes are used to classify the tweets in to three levels of sense of humor. For given Hashtag, the system finds the funniest tweet and predicts the amount of funniness of all the other tweets. In official submitted runs, we have achieved 0.506 accuracy using multilayer perceptron in subtask-A and 0.938 distance in subtask-B. Using Naïve bayes in subtask-B, the system achieved 0.949 distance. Apart from official runs, this system have scored 0.751 accuracy in subtask-A using SVM.

Automatic short answer grading (ASAG) has become part of natural language processing problems. Modern ASAG systems start with natural language preprocessing and end with grading. Researchers started experimenting with machine learning in the preprocessing stage and deep learning techniques in automatic grading for English. However, little research is available on automatic grading for Arabic. Datasets are important to ASAG, and limited datasets are available in Arabic. In this research, we have collected a set of questions, answers, and associated grades in Arabic. We have made this dataset publicly available. We have extended to Arabic the solutions used for English ASAG. We have tested how automatic grading works on answers in Arabic provided by schoolchildren in 6th grade in the context of serious games. We found out those schoolchildren providing answers that are 5.6 words long on average. On such answers, deep learning-based grading has achieved high accuracy even with limited training data. We have tested three different recurrent neural networks for grading. With a transformer, we have achieved an accuracy of 95.67%. ASAG for school children will help detect children with learning problems early. When detected early, teachers can solve learning problems easily. This is the main purpose of this research.

In recent times, malware visualization has become very popular for malwareclassification in cybersecurity. Existing malware features can easily identifyknown malware that have been already detected, but they cannot identify newand infrequent malwares accurately. Moreover, deep learning algorithmsshow their power in term of malware classification topic. However, we foundthe use of imbalanced data; the Malimg database which contains 25 malwarefamilies don’t have same or near number of images per class. To address theseissues, this paper proposes an effective malware classifier, based on costsensitive deep learning. When performing classification on imbalanced data, some classes get less accuracy than others. Cost-sensitive is meant to solve this issue, however in our case of 25 classes, classical cost-sensitive weights wasn’t effective is giving equal attention to all classes. The proposed approach improves the performance of malware classification, and we demonstrate this improvement...

Machine learning (ML) is a large field of study that overlaps with and inherits ideas from many related fields such as artificial intelligence (AI). The main focus of the field is learning from previous experiences. Classification in ML is a supervised learning method, in which the computer program learns from the data given to it and make new classifications. There are many different types of classification tasks in ML and dedicated approaches to modeling that may be used for each. For example, classification predictive modeling involves assigning a class label to input samples, binary classification refers to predicting one of two classes and multi-class classification involves predicting one of more than two categories. Recurrent Neural Networks (RNNs) are very powerful sequence models for classification problems, however, in this paper, we will use RNNs as generative models, which means they can learn the sequences of a problem and then generate entirely a new sequence for the p...

Dogs and laboratory mice are commonly trained to perform complex tasks by guiding them through a curriculum of simpler tasks ('shaping'). What are the principles behind effective shaping strategies? Here, we propose a machine learning framework for shaping animal behavior, where an autonomous teacher agent decides its student's task based on the student's transcript of successes and failures on previously assigned tasks. Using autonomous teachers that plan a curriculum in a common sequence learning task, we show that near-optimal shaping algorithms adaptively alternate between simpler and harder tasks to carefully balance reinforcement and extinction. Based on this intuition, we derive an adaptive shaping heuristic with minimal parameters, which we show is near-optimal on the sequence learning task and robustly trains deep reinforcement learning agents on navigation tasks that involve sparse, delayed rewards. Extensions to continuous curricula are explored. Our work provides a starting point towards a general computational framework for shaping animal behavior. I.

Intelligence (AI) is a rapidly evolving subset of AI technologies that involves creating new content, such as text, images, and audio, using algorithms trained on large datasets. Well-known examples of generative AI technologies include Generative Adversarial Networks (GANs) and Generative Pre-trained Transformers (GPT). These innovations are increasingly being integrated into various business applications, from automating content creation and enhancing customer interactions to driving product development and innovation. The importance of generative AI in a business context lies in its potential to augment human creativity, improve operational efficiency, and unlock new business opportunities, making it a critical tool for enterprises aiming to maintain a competitive edge in the digital age. Despite its transformational potential, the implementation of generative AI in businesses faces significant challenges. High implementation costs, the complexity of integrating AI systems into existing infrastructures, a shortage of skilled specialists, and ethical issues related to data privacy and AI-generated content are among the primary obstacles. Additionally, businesses often struggle to align AI initiatives with their strategic goals and ensure that AI outputs meet high standards of quality and compliance. These barriers complicate the large-scale and effective adoption of generative AI, limiting its potential to revolutionize business operations and innovation. The research encompasses a comprehensive review of existing literature, analysis of real-world cases, and synthesis of best practices in the strategic implementation of generative AI. It explores strategic models for the deployment of generative AI in enterprises, identifies key drivers and barriers to its adoption in business environments, and examines the strategic approaches businesses use to integrate generative AI into their operations. Insights and recommendations are provided for enterprises considering the adoption of generative AI technologies. The importance of the research lies in its potential to help businesses overcome implementation challenges and maximize the benefits of generative AI. Understanding strategic models and approaches to AI integration will enable businesses to better navigate the complexities of AI deployment, enhance their innovative capabilities, and ensure sustainable growth in an increasingly competitive market. The conclusions drawn from the research aim to bridge the gap between theoretical insights and practical applications of generative AI, providing a valuable resource for business leaders, technology strategists, and policymakers seeking to leverage AI for competitive advantage.

Flooding is a natural occurrence hazardous to people and properties and produces environmental and economic losses, especially in flood-prone areas. This study will be used to assess flood risk in the Bangko and Masjid watersheds. To analyze it, flood hazard mapping is arranged by slope, land cover, elevation, rainfall, buffer zone, and soil type, which is done with the help of a Geographic Information System (GIS), specifically QuantumGIS (QGIS). This system tool assesses each variable utilizing satellite spatial data and categorizes the vulnerability being very high, high, medium, low, and very low. Each map arrangement value is combined using an overlay value to determine the flood susceptibility. According to the mapping results, the Bangko and Masjid watersheds are highly vulnerable to flooding. Based on the results of the mapping, in the Bangko watershed 61% of the total area is vulnerable to flooding, and 20% has high to very high vulnerability, while in the Mosque watershed ...

The term Morphologically Rich Languages (MRLs) refers to languages in which significant information concerning syntactic units and relations is expressed at word-level. There is ample evidence that the application of readily available statistical parsing models to such languages is susceptible to serious performance degradation. The first workshop on statistical parsing of MRLs hosts a variety of contributions which show that despite languagespecific idiosyncrasies, the problems associated with parsing MRLs cut across languages and parsing frameworks. In this paper we review the current state-of-affairs with respect to parsing MRLs and point out central challenges. We synthesize the contributions of researchers working on parsing Arabic, Basque, French, German, Hebrew, Hindi and Korean to point out shared solutions across languages. The overarching analysis suggests itself as a source of directions for future investigations.

Signature matching, which includes packet classification and content matching, is the most expensive operation of a signature-based network intrusion detection system (NIDS). In this paper, we present a technique to improve the performance of packet classification of Snort, a popular open-source NIDS, based on generating native code from Snort signatures. 1 An obvious way to generate native code for packet classification is to use a low-level language like C to access the contents of a packet by treating it as a sequence of bytes. Generating such low-level code manually can be cumbersome and error prone. Use of a high-level specification language can simplify the task of writing packet classification code. Such a language needs features that minimize the likelihood of common errors as errors in the packet processing code can crash the intrusion detection system, which may leave it open to attacks. To overcome these problems, we use a rule-based specification language with a type system for specifying the structure and contents of packets. The compiler for the specification language generates C code for packet classification. This code can be compiled into native code using a C-compiler and loaded into Snort as shared library. Our experiments using real and synthetic traces show that the use of native code results in a speedup of the packet classification of Snort up to a factor of five.

In India, approximately 4 million people are being suffered from some form of dementia. 44 million people are affected with dementia worldwide, so it becomes the global health crisis that must be resolved. Identification of pre-MCI and MCI patients at higher level of risk before conversion to AD is very effective for patient treatment. Before the content-based image retrieval (CBIR) system only clinical inputs were taken with some relevant data from genetic analysis where the diagnosis is totally dependent on knowledge and experience of doctor, which can be biased also. Multi-modality, network structure, and measures of classification play very important role to predict AD and its prodromal stages. Neuroimaging scanners like MRI, PET, CT scan; biomarkers like CSF, cerebral glucose, tau proteins, amyloid precursor proteins, apolipoproteins E (APOE); and clinical scores like ADAS-Cog, MMSE are being used as multi-modality inputs to predict disease and its prodromal stages. These imaging techniques along with clinical inputs and biomarkers have their own level of mechanisms to refine classification technique. AI techniques like machine learning, deep learning, and artificial neural network play an important role to diagnose and predict the AD and its prodromal stages. KNN, SVM, RF, naïve Bayes classifier, and CNN are techniques which are used for feature selection as well as for classification. Different combinations of these techniques are being used for optimal prediction. Somebody used them as multi-stage classifier and others used them as multi-view classifier.

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Breast cancer has the highest incidence and second-highest mortality rate among all cancers. The management of breast cancer is being revolutionized by artificial intelligence (AI), which is improving early detection, pathological diagnosis, risk assessment, individualized treatment recommendations, and treatment response prediction. Nuclear medicine has used artificial intelligence (AI) for over 50 years, but more recent advances in machine learning (ML) and deep learning (DL) have given AI in nuclear medicine additional capabilities. AI accurately analyzes breast imaging scans for early detection, minimizing false negatives while offering radiologists reliable, swift image processing assistance. It smoothly fits into radiology workflows, which may result in early treatments and reduced expenditures. In pathological diagnosis, artificial intelligence improves the quality of diagnostic data by ensuring accurate diagnoses, lowering inter-observer variability, speeding up the review process, and identifying errors or poor slides. By taking into consideration nutritional, genetic, and environmental factors, providing individualized risk assessments, and recommending more regular tests for higher-risk patients, AI aids with the risk assessment of breast cancer. The integration of clinical and genetic data into individualized treatment recommendations by AI facilitates collaborative decision-making and resource allocation optimization while also enabling patient progress monitoring, drug interaction consideration, and alignment with clinical guidelines. AI is used to analyze patient data, imaging, genomic data, and pathology reports in order to forecast how a treatment would respond. These models anticipate treatment outcomes, make sure that clinical recommendations are followed, and learn from historical data. The implementation of AI in medicine is hampered by issues with data quality, integration with healthcare IT systems, data protection, bias reduction, and ethical considerations, necessitating transparency and constant surveillance. Protecting patient privacy, resolving biases, maintaining transparency, identifying fault for mistakes, and ensuring fair access are just a few examples of ethical considerations. To preserve patient trust and address the effect on the healthcare workforce, ethical frameworks must be developed. The amazing potential of AI in the treatment of breast cancer calls for careful examination of its ethical and practical implications. We aim to review the comprehensive role of artificial intelligence in breast cancer management.

Background: Prediction of low Apgar score for vaginal deliveries following labor induction intervention is critical for improving neonatal health outcomes. We set out to investigate important attributes and train popular machine learning (ML) algorithms to correctly classify neonates with a low Apgar scores from an imbalanced learning perspective. We analyzed 7716 induced vaginal deliveries from the electronic birth registry of the Kilimanjaro Christian Medical Centre (KCMC). 733 (9.5%) of which constituted of low (< 7) Apgar score neonates. The 'extra-tree classifier' was used to assess features' importance. We used Area Under Curve (AUC), recall, precision, F-score, Matthews Correlation Coefficient (MCC), balanced accuracy (BA), bookmaker informedness (BM), and markedness (MK) to evaluate the performance of the selected six (6) machine learning classifiers. To address class imbalances, we examined three widely used resampling techniques: the Synthetic Minority Oversampling Technique (SMOTE) and Random Oversampling Examples (ROS) and Random undersampling techniques (RUS). We applied Decision Curve Analysis (DCA) to evaluate the net benefit of the selected classifiers. Results: Birth weight, maternal age, and gestational age were found to be important predictors for the low Apgar score following induced vaginal delivery. SMOTE, ROS and and RUS techniques were more effective at improving "recalls" among other metrics in all the models under investigation. A slight improvement was observed in the F1 score, BA, and BM. DCA revealed potential benefits of applying Boosting method for predicting low Apgar scores among the tested models. There is an opportunity for more algorithms to be tested to come up with theoretical guidance on more effective rebalancing techniques suitable for this particular imbalanced ratio. Future research should prioritize a debate on which performance indicators to look up to when dealing with imbalanced or skewed data.

Dialectometry is a discipline devoted to studying the variations of a language around a geographical region. One of their goals is the creation of linguistic atlases capturing the similarities and differences of the language under study around the area in question. For instance, Spanish is one of the most spoken languages across the world, but not necessarily Spanish is written and spoken in the same way in different countries. This manuscript presents a broad analysis describing lexical and semantic relationships among 26 Spanish-speaking countries around the globe. For this study, we analyze four-year of the Twitter geotagged public stream to provide an extensive survey of the Spanish language vocabularies of different countries, its distributions, semantic usage of terms, and emojis. We also offer open regional word-embedding resources for Spanish Twitter to help other researchers and practitioners take advantage of regionalized models.

The present statistical models used for forecasting cannot effectively handle uncertainty and instability nature of foreign exchange data. In this work, an artificial neural network foreign exchange rate forecasting model (AFERFM) was designed for foreign exchange rate forecasting to correct some of these problems. The design was divided into two phases, namely: training and forecasting. In the training phase, back propagation algorithm was used to train the foreign exchange rates and learn how to approximate input. Sigmoid Activation Function (SAF) was used to transform the input into a standard range [0, 1]. The learning weights were randomly assigned in the range [-0.1, 0.1] to obtain the output consistent with the training. SAF was depicted using a hyperbolic tangent in order to increase the learning rate and make learning efficient. Feed forward Network was used to improve the efficiency of the back propagation. Multilayer Perceptron Network was designed for forecasting. The datasets from oanda website were used as input in the back propagation for the evaluation and forecasting of foreign exchange rates. The design was implemented using matlab7.6 and visual studio because of their supports for implementing forecasting system. The system was tested using mean square error and standard deviation with learning rate of 0.10, an input layer, 3 hidden layers and an output layer. The best known related work, Hidden Markov foreign exchange rate forecasting model (HFERFM) showed an accuracy of 69.9% as against 81.2% accuracy of AFERFM. This shows that the new approach provided an improved technique for carrying out foreign exchange rate forecasting.

Solving mechanical problems in large structures with rich localized behaviors remains a challenging issue despite the enormous advances in numerical procedures and computational performance. In particular, these localized behaviors need for extremely fine descriptions, and this has an associated impact in the number of degrees of freedom from one side, and the decrease of the time step employed in usual explicit time integrations, whose stability scales with the size of the smallest element involved in the mesh. In the present work we propose a data-driven technique for learning the rich behavior of a local patch and integrate it into a standard coarser description at the structure level. Thus, localized behaviors impact the global structural response without needing an explicit description of that fine scale behaviors.

Elías Cueto. Aragon Institute of Engineering Research, Universidad de Zaragoza. Zaragoza, Spain Corresponding author: ecueto@unizar.es David González. Aragon Institute of Engineering Research, Universidad de Zaragoza. Zaragoza, Spain Alberto Badías. Aragon Institute of Engineering Research, Universidad de Zaragoza. Zaragoza, Spain Francisco Chinesta. ESI Group Chair, Arts et Metiers Institute of Technology. Paris, France Nicolas Hascoet. ESI Group Chair, Arts et Metiers Institute of Technology. Paris, France Jean-Louis Duval. ESI Group, Bâtiment Seville, 3bis. Rue Saarinen. Rungis, France

The present work aims at proposing a new methodology for learning reduced models from a small amount of data. It is based on the fact that discrete models, or their transfer function counterparts, have a low rank and then they can be expressed very efficiently using few terms of a tensor decomposition. An efficient procedure is proposed as well as a way for extending it to nonlinear settings while keeping limited the impact of data noise. The proposed methodology is then validated by considering a nonlinear elastic problem and constructing the model relating tractions and displacements at the observation points.

The series "Studies in Big Data" (SBD) publishes new developments and advances in the various areas of Big Data-quickly and with a high quality. The intent is to cover the theory, research, development, and applications of Big Data, as embedded in the fields of engineering, computer science, physics, economics and life sciences. The books of the series refer to the analysis and understanding of large, complex, and/or distributed data sets generated from recent digital sources coming from sensors or other physical instruments as well as simulations, crowd sourcing, social networks or other internet transactions, such as emails or video click streams and other. The series contains monographs, lecture notes and edited volumes in Big Data spanning the areas of computational intelligence including neural networks, evolutionary computation, soft computing, fuzzy systems, as well as artificial intelligence, data mining, modern statistics and Operations research, as well as self-organizing systems. Of particular value to both the contributors and the readership are the short publication timeframe and the world-wide distribution, which enable both wide and rapid dissemination of research output.

Latest advances in hardware technology and state of the art of computer vision and artiÿcial intelligence research can be employed to develop autonomous and distributed monitoring systems. The paper proposes a multi-agent architecture for the understanding of scene dynamics merging the information streamed by multiple cameras. A typical application would be the monitoring of a secure site, or any visual surveillance application deploying a network of cameras. Modular software (the agents) within such architecture controls the di erent components of the system and incrementally builds a model of the scene by merging the information gathered over extended periods of time. The role of distributed artiÿcial intelligence composed of separate and autonomous modules is justiÿed by the need for scalable designs capable of co-operating to infer an optimal interpretation of the scene. Decentralizing intelligence means creating more robust and reliable sources of interpretation, but also allows easy maintenance and updating of the system. Results are presented to support the choice of a distributed architecture, and to prove that scene interpretation can be incrementally and e ciently built by modular software.