Downloads & Free Reading Options - Results

In this dissertation, a series of studies are designed to investigate the brain connectivity patterns (both functional connectivity and effective connectivity), comparing subjects with depression history vs. control and subjects with OCD vs. control. Depression and OCD are examples of trans-diagnostic disorders, which may be more likely due to alteration of connectivity patterns (ex., hyper-connectivity in default mode network or other networks) rather than localized brain abnormality.

Longitudinal EHRs contain a wealth of clinical information and can potentially support diagnostic tasks that target disease prevention. Although the exploding amount of data increases information, clinicians cannot assess this during consultation and, therefore, do not exploit the full potential. There is accumulating evidence that machine learning can assist in analyzing large-scale EHRs, but studies mainly focus on designing techniques and lack healthcare focus. Because machine learning is a black box for clinicians, it is significant to map the generated knowledge and benefits for preventive healthcare.

The delay at signalized intersections is a crucial parameter that determines the performance and level of service (LOS). The estimation models are commonly used to model delay; however, inaccurate predictions from these models can pose a significant limitation. Consequently, this study aimed to compare a wide array of machine learning algorithms, including Artificial Neural Networks (ANN), Random Forest (RF), decision tree, Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), AdaBoost, Gradient Boost, XGBoost, and Partial Least Squares (PLS) regression. A comprehensive evaluation was undertaken across prediction accuracy, training-testing performance discrepancy, sensitivity to outliers, computational time cost, and model robustness. Additionally, the proposed methods were benchmarked against the Highway Capacity Manual (HCM), Webster, and Akçelik models. The results demonstrated that the RF model exhibited the most balanced performance across the specified criteria, with an average error below 4% and a rating of 35 out of 45 according to the proposed criteria. Moreover, the findings revealed that adopted analytical models should not be employed for vehicular delay estimation without calibration, as RMSE values were about 5 to 58 times higher than other models, varying by model.

As the development of machine learning and deep learning, more and more people or organizations use multiple algorithms to analyse large collections of data to produce meaningful results that help to predict behaviour. And this kind of technology is increasingly used in medical field to predict some severe illness in their early stage, for example, cervical cancer. Cervical Cancer is one of the main reasons of deaths in countries having a low capita income. It is the second most common cancer in India in women accounting for 22.86 of all cancer cases in women. It becomes quite complicated while examining a patient on the basis of result obtained from various doctor’s preferred test to determine if the patient is positive with the cancer. There were 96,922 new cases of cervical cancer diagnosed in India in 2018. Around the globe, around a quarter of million people die owing to cervical cancer. Screening and different deterministic tests confuse the available Computed Aided Diagnosis CAD to treat the patient correctly for the cancer. Machine learning and Deep learning algorithms are used in this project and determine if the patient has cancer based on the analyses of the risk factors available in the dataset. Predicting the presence of cervical cancer can help the diagnosis process to start at an early stage and comparing various models will help in finding out the best prediction model for predicting the presence of cervical cancer effectively. Kayalvizhi. K. R | N Kanimozhi "Prediction of Cervical Cancer using Machine Learning and Deep Learning Algorithms" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-6 , October 2020, URL: https://www.ijtsrd.com/papers/ijtsrd33378.pdf Paper Url: https://www.ijtsrd.com/computer-science/artificial-intelligence/33378/prediction-of-cervical-cancer-using-machine-learning-and-deep-learning-algorithms/kayalvizhi-k-r

We prove several results giving new and stronger connections between learning, circuit lower bounds and pseudorandomness. Among other results, we show a generic learning speedup lemma, equivalences between various learning models in the exponential time and subexponential time regimes, a dichotomy between learning and pseudorandomness, consequences of non-trivial learning for circuit lower bounds, Karp-Lipton theorems for probabilistic exponential time, and NC$^1$-hardness for the Minimum Circuit Size Problem.

There are several confounding factors that can reduce the accuracy of gait recognition systems. These factors can reduce the distinctiveness, or alter the features used to characterise gait, they include variations in clothing, lighting, pose and environment, such as the walking surface. Full invariance to all confounding factors is challenging in the absence of high-quality labelled training data. We introduce a simulation-based methodology and a subject-specific dataset which can be used for generating synthetic video frames and sequences for data augmentation. With this methodology, we generated a multi-modal dataset. In addition, we supply simulation files that provide the ability to simultaneously sample from several confounding variables. The basis of the data is real motion capture data of subjects walking and running on a treadmill at different speeds. Results from gait recognition experiments suggest that information about the identity of subjects is retained within synthetically generated examples. The dataset and methodology allow studies into fully-invariant identity recognition spanning a far greater number of observation conditions than would otherwise be possible.

There are several confounding factors that can reduce the accuracy of gait recognition systems. These factors can reduce the distinctiveness, or alter the features used to characterise gait, they include variations in clothing, lighting, pose and environment, such as the walking surface. Full invariance to all confounding factors is challenging in the absence of high-quality labelled training data. We introduce a simulation-based methodology and a subject-specific dataset which can be used for generating synthetic video frames and sequences for data augmentation. With this methodology, we generated a multi-modal dataset. In addition, we supply simulation files that provide the ability to simultaneously sample from several confounding variables. The basis of the data is real motion capture data of subjects walking and running on a treadmill at different speeds. Results from gait recognition experiments suggest that information about the identity of subjects is retained within synthetically generated examples. The dataset and methodology allow studies into fully-invariant identity recognition spanning a far greater number of observation conditions than would otherwise be possible.

Machine learning is recognized as a tool for improving the performance of many kinds of systems, yet most machine learning systems themselves are not well equipped to improve their own learning performance. By emphasizing the role of domain knowledge, learning systems can be crafted as knowledge directed systems, and with the addition of a knowledge store for organizing and maintaining knowledge to assist learning, a learning machine learning (L-ML) algorithm is possible. The necessary components of L-ML systems are presented along with several case descriptions of existing machine learning systems that possess limited L-ML capabilities. Keywords: Algorithms, Artificial intelligence. (SDW)

The concept of algorithm, as used in teaching and learning, is defined. Characteristics of algorithms are identified and described. The elements (operator, discriminator, syntactic structure) are described and illustrated. Methods of representing algorithms are portrayed. Differences between identification algorithms, transformation algorithms, and search algorithms are discussed. Use of algorithms in instruction and training are suggested. Several research and development tasks are proposed. (Author)

Ensembles of climate models are commonly used to improve climate predictions and assess the uncertainties associated with them. Weighting the models according to their performances holds the promise of further improving their predictions. Here, we use an ensemble of decadal climate predictions to demonstrate the ability of sequential learning algorithms (SLAs) to reduce the forecast errors and reduce the uncertainties. Three different SLAs are considered, and their performances are compared with those of an equally weighted ensemble, a linear regression and the climatology. Predictions of four different variables--the surface temperature, the zonal and meridional wind, and pressure--are considered. The spatial distributions of the performances are presented, and the statistical significance of the improvements achieved by the SLAs is tested. Based on the performances of the SLAs, we propose one to be highly suitable for the improvement of decadal climate predictions.

Reinforcement learning agents have traditionally been evaluated on small toy problems. With advances in computing power and the advent of the Arcade Learning Environment, it is now possible to evaluate algorithms on diverse and difficult problems within a consistent framework. We discuss some challenges posed by the arcade learning environment which do not manifest in simpler environments. We then provide a comparison of model-free, linear learning algorithms on this challenging problem set.

Reinforcement learning agents have traditionally been evaluated on small toy problems. With advances in computing power and the advent of the Arcade Learning Environment, it is now possible to evaluate algorithms on diverse and difficult problems within a consistent framework. We discuss some challenges posed by the arcade learning environment which do not manifest in simpler environments. We then provide a comparison of model-free, linear learning algorithms on this challenging problem set.

Reinforcement learning agents have traditionally been evaluated on small toy problems. With advances in computing power and the advent of the Arcade Learning Environment, it is now possible to evaluate algorithms on diverse and difficult problems within a consistent framework. We discuss some challenges posed by the arcade learning environment which do not manifest in simpler environments. We then provide a comparison of model-free, linear learning algorithms on this challenging problem set.

Reinforcement learning agents have traditionally been evaluated on small toy problems. With advances in computing power and the advent of the Arcade Learning Environment, it is now possible to evaluate algorithms on diverse and difficult problems within a consistent framework. We discuss some challenges posed by the arcade learning environment which do not manifest in simpler environments. We then provide a comparison of model-free, linear learning algorithms on this challenging problem set.

Systems, methods and apparatus are provided through which in some embodiments, automata learning algorithms and techniques are implemented to generate a more complete set of scenarios for requirements based programming. More specifically, a CSP-based, syntax-oriented model construction, which requires the support of a theorem prover, is complemented by model extrapolation, via automata learning. This may support the systematic completion of the requirements, the nature of the requirement being partial, which provides focus on the most prominent scenarios. This may generalize requirement skeletons by extrapolation and may indicate by way of automatically generated traces where the requirement specification is too loose and additional information is required.

Information retrieval using probabilistic techniques has attracted significant attention on the part of researchers in information and computer science over the past few decades. In the 1980s, knowledge-based techniques also made an impressive contribution to intelligent information retrieval and indexing. More recently, information science researchers have turned to other newer inductive learning techniques including symbolic learning, genetic algorithms, and simulated annealing. These newer techniques, which are grounded in diverse paradigms, have provided great opportunities for researchers to enhance the information processing and retrieval capabilities of current information systems. In this article, we first provide an overview of these newer techniques and their use in information systems. In this article, we first provide an overview of these newer techniques and their use in information retrieval research. In order to familiarize readers with the techniques, we present three promising methods: The symbolic ID3 algorithm, evolution-based genetic algorithms, and simulated annealing. We discuss their knowledge representations and algorithms in the unique context of information retrieval. An experiment using a 8000-record COMPEN database was performed to examine the performances of these inductive query-by-example techniques in comparison with the performance of the conventional relevance feedback method. The machine learning techniques were shown to be able to help identify new documents which are similar to documents initially suggested by users, and documents which contain similar concepts to each other. Genetic algorithms, in particular, were found to out-perform relevance feedback in both document recall and precision.

We consider the neurologically-inspired hypothesis that higher level cognition is built on the same fundamental building blocks as low-level perception. That is, the same basic algorithm that is able to represent and perform inference on low-level sensor data can also be used to process relational structures. We present a system that represents relational structures as feature bags. Using this representation, our system leverages algorithms inspired by the sensory cortex to automatically create an ontology of relational structures and to efficiently retrieve analogs for new relational structures from long-term memory. We provide a demonstration of our approach that takes as input a set of unsegmented stories, constructs an ontology of analogical schemas (corresponding to plot devices), and uses this ontology to find analogs within new stories in time logarithmic in the total number of stories, yielding significant time-savings over linear analog retrieval with only a small sacrifice in accuracy. We also provide a proof of concept for how our framework allows for cortically-inspired algorithms to perform analogical inference. Finally, we discuss how insights from our system can be used so that a corticallyinspired model can serve as the core mechanism for a full cognitive architecture.

This thesis explores various theoretical aspects of machine learning with particular emphasis on techniques for designing and analyzing computationally efficient learning algorithms. Many of the results in this thesis are concerned with a model of concept learning proposed by Valiant. The thesis begins in Chapter 2 with a proof that any 'weak' learning algorithm in this model that performs slightly better than random guessing can be converted into one whose error can be made arbitrarily small. Several interesting consequences of this result are also described. Chapter 3 next explores in detail a simple but powerful technique for discovering the structure of an unknown read-once formula from random examples. An especially nice feature of this technique is its powerful resistance to noise. Chapter 4 considers a realistic extension of the PAC model to concepts that may exhibit uncertain or probabilistic behavior. A range of techniques are explored for designing efficient algorithms for learning such probabilistic concepts. In the last chapter, we present new algorithms for inferring an unknown finite-state automation from its input-output behavior. This problem is motivated by that faced by a robot in unfamiliar surroundings who must, through experimentation, discover the structure of its environment.

Recent research suggests that algorithms that can learn will mitigate the effects of bad reactions to algorithm errors. We expect that telling participants that the algorithm can learn from mistakes will lessen the negative reactions to errors.

Perma.cc archive of https://arapackelaw.com/patents/softwaremobile-apps/are-machine-learning-algorithms-patentable/ created on 2021-11-15 00:05:01+00:00.

We have constructed an automated learning apparatus to control quantum systems. By directing intense shaped ultrafast laser pulses into a variety of samples and using a measurement of the system as a feedback signal, we are able to reshape the laser pulses to direct the system into a desired state. The feedback signal is the input to an adaptive learning algorithm. This algorithm programs a computer-controlled, acousto-optic modulator pulse shaper. The learning algorithm generates new shaped laser pulses based on the success of previous pulses in achieving a predetermined goal.

This paper presents new and effective algorithms for learning kernels. In particular, as shown by our empirical results, these algorithms consistently outperform the so-called uniform combination solution that has proven to be difficult to improve upon in the past, as well as other algorithms for learning kernels based on convex combinations of base kernels in both classification and regression. Our algorithms are based on the notion of centered alignment which is used as a similarity measure between kernels or kernel matrices. We present a number of novel algorithmic, theoretical, and empirical results for learning kernels based on our notion of centered alignment. In particular, we describe efficient algorithms for learning a maximum alignment kernel by showing that the problem can be reduced to a simple QP and discuss a one-stage algorithm for learning both a kernel and a hypothesis based on that kernel using an alignment-based regularization. Our theoretical results include a novel concentration bound for centered alignment between kernel matrices, the proof of the existence of effective predictors for kernels with high alignment, both for classification and for regression, and the proof of stability-based generalization bounds for a broad family of algorithms for learning kernels based on centered alignment. We also report the results of experiments with our centered alignment-based algorithms in both classification and regression.

We consider the problem of learning the structure of Ising models (pairwise binary Markov random fields) from i.i.d. samples. While several methods have been proposed to accomplish this task, their relative merits and limitations remain somewhat obscure. By analyzing a number of concrete examples, we show that low-complexity algorithms often fail when the Markov random field develops long-range correlations. More precisely, this phenomenon appears to be related to the Ising model phase transition (although it does not coincide with it).

The purpose of this paper is to introduce a concept of equivalence between machine learning algorithms. We define two notions of algorithmic equivalence, namely, weak and strong equivalence. These notions are of paramount importance for identifying when learning prop erties from one learning algorithm can be transferred to another. Using regularized kernel machines as a case study, we illustrate the importance of the introduced equivalence concept by analyzing the relation between kernel ridge regression (KRR) and m-power regularized least squares regression (M-RLSR) algorithms.

The success of machine learning on a given task dependson, among other things, which learning algorithm is selected and its associated hyperparameters. Selecting an appropriate learning algorithm and setting its hyperparameters for a given data set can be a challenging task, especially for users who are not experts in machine learning. Previous work has examined using meta-features to predict which learning algorithm and hyperparameters should be used. However, choosing a set of meta-features that are predictive of algorithm performance is difficult. Here, we propose to apply collaborative filtering techniques to learning algorithm and hyperparameter selection, and find that doing so avoids determining which meta-features to use and outperforms traditional meta-learning approaches in many cases.

We study the problem of dynamic spectrum sensing and access in cognitive radio systems as a partially observed Markov decision process (POMDP). A group of cognitive users cooperatively tries to exploit vacancies in primary (licensed) channels whose occupancies follow a Markovian evolution. We first consider the scenario where the cognitive users have perfect knowledge of the distribution of the signals they receive from the primary users. For this problem, we obtain a greedy channel selection and access policy that maximizes the instantaneous reward, while satisfying a constraint on the probability of interfering with licensed transmissions. We also derive an analytical universal upper bound on the performance of the optimal policy. Through simulation, we show that our scheme achieves good performance relative to the upper bound and improved performance relative to an existing scheme. We then consider the more practical scenario where the exact distribution of the signal from the primary is unknown. We assume a parametric model for the distribution and develop an algorithm that can learn the true distribution, still guaranteeing the constraint on the interference probability. We show that this algorithm outperforms the naive design that assumes a worst case value for the parameter. We also provide a proof for the convergence of the learning algorithm.

We develop fast algorithms for solving regression problems on graphs where one is given the value of a function at some vertices, and must find its smoothest possible extension to all vertices. The extension we compute is the absolutely minimal Lipschitz extension, and is the limit for large $p$ of $p$-Laplacian regularization. We present an algorithm that computes a minimal Lipschitz extension in expected linear time, and an algorithm that computes an absolutely minimal Lipschitz extension in expected time $\widetilde{O} (m n)$. The latter algorithm has variants that seem to run much faster in practice. These extensions are particularly amenable to regularization: we can perform $l_{0}$-regularization on the given values in polynomial time and $l_{1}$-regularization on the initial function values and on graph edge weights in time $\widetilde{O} (m^{3/2})$.

We evaluate the performance of four different machine learning algorithms (ANN, Adaboost, GBC, XGBoost), in the separation of pulsars from radio frequency interference (RFI) and other sources of noise, using a dataset consisting of pulsar candidates obtained from the post-processing of a pulsar search pipeline. This dataset was previously used for cross-validation of the {\tt SPINN}-based machine learning engine, which was used for the re-processing of the HTRU-S survey. We report a variety of quality metrics from all four of these algorithms. We apply a model-independent information theoretic approach to determine the features with the most predictive power, and also compare with the feature importance results from the machine learning algorithms, wherever possible. We find that the RMS distance between the folded profile and sub-integrations is the most important feature in Adaboost and XGBoost. In the case of GBC, we find that the logarithm of the ratio of barycentric period and dispersion measure to be the most important feature. The information theoretic approach to feature importance yields a ranking very well matched to that based on GBC. For all the aforementioned machine learning techniques, we report a recall of 100% with false positive rates of 0.15%, 0.077%, 0.1%, 0.08% for ANN, Adaboost, GBC, and XGBoost respectively. Amongst all four of these algorithms, we find that Adaboost has the minimum overlap between the error rates as a function of threshold for detection of pulsars and RFI, and based on this criterion can be considered to be the best.

Automatically searching for optimal hyperparameter configurations is of crucial importance for applying deep learning algorithms in practice. Recently, Bayesian optimization has been proposed for optimizing hyperparameters of various machine learning algorithms. Those methods adopt probabilistic surrogate models like Gaussian processes to approximate and minimize the validation error function of hyperparameter values. However, probabilistic surrogates require accurate estimates of sufficient statistics (e.g., covariance) of the error distribution and thus need many function evaluations with a sizeable number of hyperparameters. This makes them inefficient for optimizing hyperparameters of deep learning algorithms, which are highly expensive to evaluate. In this work, we propose a new deterministic and efficient hyperparameter optimization method that employs radial basis functions as error surrogates. The proposed mixed integer algorithm, called HORD, searches the surrogate for the most promising hyperparameter values through dynamic coordinate search and requires many fewer function evaluations. HORD does well in low dimensions but it is exceptionally better in higher dimensions. Extensive evaluations on MNIST and CIFAR-10 for four deep neural networks demonstrate HORD significantly outperforms the well-established Bayesian optimization methods such as GP, SMAC, and TPE. For instance, on average, HORD is more than 6 times faster than GP-EI in obtaining the best configuration of 19 hyperparameters.

In this paper, we analyze the spectrum occupancy using different machine learning techniques. Both supervised techniques (naive Bayesian classifier (NBC), decision trees (DT), support vector machine (SVM), linear regression (LR)) and unsupervised algorithm (hidden markov model (HMM)) are studied to find the best technique with the highest classification accuracy (CA). A detailed comparison of the supervised and unsupervised algorithms in terms of the computational time and classification accuracy is performed. The classified occupancy status is further utilized to evaluate the probability of secondary user outage for the future time slots, which can be used by system designers to define spectrum allocation and spectrum sharing policies. Numerical results show that SVM is the best algorithm among all the supervised and unsupervised classifiers. Based on this, we proposed a new SVM algorithm by combining it with fire fly algorithm (FFA), which is shown to outperform all other algorithms.

MM (majorization--minimization) algorithms are an increasingly popular tool for solving optimization problems in machine learning and statistical estimation. This article introduces the MM algorithm framework in general and via three popular example applications: Gaussian mixture regressions, multinomial logistic regressions, and support vector machines. Specific algorithms for the three examples are derived and numerical demonstrations are presented. Theoretical and practical aspects of MM algorithm design are discussed.

Recent emergence of next-generation DNA sequencing technology has enabled acquisition of genetic information at unprecedented scales. In order to determine the genetic blueprint of an organism, sequencing platforms typically employ so-called shotgun sequencing strategy to oversample the target genome with a library of relatively short overlapping reads. The order of nucleotides in the reads is determined by processing the acquired noisy signals generated by the sequencing instrument. Assembly of a genome from potentially erroneous short reads is a computationally daunting task even in the scenario where a reference genome exists. Errors and gaps in the reference, and perfect repeat regions in the target, further render the assembly challenging and cause inaccuracies. In this paper, we formulate the reference-guided sequence assembly problem as the inference of the genome sequence on a bipartite graph and solve it using a message-passing algorithm. The proposed algorithm can be interpreted as the well-known classical belief propagation scheme under a certain prior. Unlike existing state-of-the-art methods, the proposed algorithm combines the information provided by the reads without needing to know reliability of the short reads (so-called quality scores). Relation of the message-passing algorithm to a provably convergent power iteration scheme is discussed. To evaluate and benchmark the performance of the proposed technique, we find an analytical expression for the probability of error of a genie-aided maximum a posteriori (MAP) decision scheme. Results on both simulated and experimental data demonstrate that the proposed message-passing algorithm outperforms commonly used state-of-the-art tools, and it nearly achieves the performance of the aforementioned MAP decision scheme.

Pairwise learning usually refers to a learning task which involves a loss function depending on pairs of examples, among which most notable ones include ranking, metric learning and AUC maximization. In this paper, we study an online algorithm for pairwise learning with a least-square loss function in an unconstrained setting of a reproducing kernel Hilbert space (RKHS), which we refer to as the Online Pairwise lEaRning Algorithm (OPERA). In contrast to existing works \cite{Kar,Wang} which require that the iterates are restricted to a bounded domain or the loss function is strongly-convex, OPERA is associated with a non-strongly convex objective function and learns the target function in an unconstrained RKHS. Specifically, we establish a general theorem which guarantees the almost surely convergence for the last iterate of OPERA without any assumptions on the underlying distribution. Explicit convergence rates are derived under the condition of polynomially decaying step sizes. We also establish an interesting property for a family of widely-used kernels in the setting of pairwise learning and illustrate the above convergence results using such kernels. Our methodology mainly depends on the characterization of RKHSs using its associated integral operators and probability inequalities for random variables with values in a Hilbert space.

Pairwise learning usually refers to a learning task which involves a loss function depending on pairs of examples, among which most notable ones include ranking, metric learning and AUC maximization. In this paper, we study an online algorithm for pairwise learning with a least-square loss function in an unconstrained setting of a reproducing kernel Hilbert space (RKHS), which we refer to as the Online Pairwise lEaRning Algorithm (OPERA). In contrast to existing works \cite{Kar,Wang} which require that the iterates are restricted to a bounded domain or the loss function is strongly-convex, OPERA is associated with a non-strongly convex objective function and learns the target function in an unconstrained RKHS. Specifically, we establish a general theorem which guarantees the almost surely convergence for the last iterate of OPERA without any assumptions on the underlying distribution. Explicit convergence rates are derived under the condition of polynomially decaying step sizes. We also establish an interesting property for a family of widely-used kernels in the setting of pairwise learning and illustrate the above convergence results using such kernels. Our methodology mainly depends on the characterization of RKHSs using its associated integral operators and probability inequalities for random variables with values in a Hilbert space.

It is well known in the literature that the problem of learning the structure of Bayesian networks is very hard to tackle: its computational complexity is super-exponential in the number of nodes in the worst case and polynomial in most real-world scenarios. Efficient implementations of score-based structure learning benefit from past and current research in optimisation theory, which can be adapted to the task by using the network score as the objective function to maximise. This is not true for approaches based on conditional independence tests, called constraint-based learning algorithms. The only optimisation in widespread use, backtracking, leverages the symmetries implied by the definitions of neighbourhood and Markov blanket. In this paper we illustrate how backtracking is implemented in recent versions of the bnlearn R package, and how it degrades the stability of Bayesian network structure learning for little gain in terms of speed. As an alternative, we describe a software architecture and framework that can be used to parallelise constraint-based structure learning algorithms (also implemented in bnlearn) and we demonstrate its performance using four reference networks and two real-world data sets from genetics and systems biology. We show that on modern multi-core or multiprocessor hardware parallel implementations are preferable over backtracking, which was developed when single-processor machines were the norm.

With the advancement in the artificial intelligence technologies and development of fifth generation networks, a network may face many hazards and challenges as the number of users are accessing the network simultaneously which makes the user to think of losing the confidentiality of the data and hence the network to be considered for security. Threats on the network can be classified in many ways and to detect such threats an Intrusion detection system (IDS) is the one which is mainly used. A network can be attacked in two ways as minor attack and major attack. Denial-of-Service (DoS) and Prob attacks belong to major kind and User-to-Root (U2R) and Remote-to-Login (R2L) goes to minor attack categories. The minor attacks are also called as rare attacks which are very injurious for a host and it is very difficult to recognize these attacks. This paper consists of a survey made on IDS and different algorithms used to implement these IDSs using machine learning. 

Understanding Machine Learning From Theory To Algorithms By Shai Shalev Shwartz And Shai Ben David

Includes bibliographical references (p. 11)

SMS spam detection is a crucial task in text classification, as unsolicited messages continue to pose security risks and inconvenience to users. This study explores the effectiveness of machine learning-based algorithms, particularly the Naive Bayes classifier, in accurately identifying and filtering spam messages. The primary objective is to classify SMS messages into spam or ham categories by analysing the occurrence of words and patterns within the text. The proposed approach involves a comprehensive pre-processing stage, including tokenization, stop-word removal, stemming, and feature extraction using techniques such as Term Frequency-Inverse Document Frequency (TF-IDF). The Naive Bayes algorithm is then trained on a labelled dataset to learn probabilistic distributions of words in spam and ham messages. Additionally, we compare the performance of Naive Bayes with other machine learning models like Support Vector Machines (SVM), Decision Trees, and Random Forest to assess their efficiency in spam detection. The experimental analysis demonstrates that the Naive Bayes classifier, due to its probabilistic nature, achieves high accuracy with minimal computational complexity. The study also evaluates precision, recall, F1-score, and overall classification accuracy to determine the best-performing algorithm. The results suggest that machine learning-based approaches significantly enhance SMS spam detection, reducing false positives and improving message filtering. Future work aims to integrate deep learning techniques and real-time detection mechanisms to further enhance accuracy and adaptability in dynamic environments.

This work aims at improving the energy consumption forecast of electric vehicles by enhancing the prediction with a notion of uncertainty. The algorithm itself learns from driver and traffic data in a training set to generate accurate, driver-individual energy consumption forecasts.

This article is from Frontiers in Public Health , volume 2 . Abstract Background: Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data.Methods: We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time.Results: The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%.Conclusion: Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel.

A systematic review and meta-analysis of the diagnostic test accuracy of deep learning in diagnosing or grading pterygium.

Talk by Marc Wanner - Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms @QTMLConference

ABSTRACT: In the field of computer science known as "machine learning," a computer makes predictions about the tasks it will perform next by examining the data that has been given to it. The computer can access data via interacting with the environment or by using digitalized training sets. In contrast to static programming algorithms, which require explicit human guidance, machine learning algorithms may learn from data and generate predictions on their own. Various supervised and unsupervised strategies, including rule-based techniques, logic-based techniques, instance-based techniques, and stochastic techniques, have been presented in order to solve problems. Our paper's main goal is to present a comprehensive comparison of various cutting-edge supervised machine learning techniques. 

ABSTRACT: In the field of computer science known as "machine learning," a computer makes predictions about the tasks it will perform next by examining the data that has been given to it. The computer can access data via interacting with the environment or by using digitalized training sets. In contrast to static programming algorithms, which require explicit human guidance, machine learning algorithms may learn from data and generate predictions on their own. Various supervised and unsupervised strategies, including rule-based techniques, logic-based techniques, instance-based techniques, and stochastic techniques, have been presented in order to solve problems. Our paper's main goal is to present a comprehensive comparison of various cutting-edge supervised machine learning techniques. 

Preeclampsia and eclampsia are the most common obstetric disorders associated with poor maternal and neonatal outcome. The study’s primary objective is to assess the accuracy of novel high-risk factors core using machine learning algorithms in predicting preeclampsia. The study included 400 pregnant women and used 27 novel high-risk factors to predict preeclampsia. The target variables for predicting preeclampsia are systolic and diastolic blood pressures. Various algorithms, including decision tree (DT), random forest (RF), gradient boosting, support vector machine (SVM), K-neighbors, light gradient boosting machine (LGBM), multi-layer perceptron (MLP), Adaboost classifier, and extra trees classifier are used in the analysis. The accuracy and precision of the LGBM classifier (0.85 and 0.9583 with F1 0.7188), support vector classifier (0.8417 and 0.92 with F1 0.7077), DT (0.825 and 0.913 with F1 0.6667), and extra trees (0.8167 and 0.9091 with F1 0.6452) are found to be better algorithms for prediction of preeclampsia. According to the novel high-risk factors score, 17.5% of pregnant women were identified as being at high risk for preeclampsia during the first trimester, which increased to 18.7% in 3rd trimester; in addition, 16% of pregnant women had a blood pressure of 140/90 mmHg and the above. Novel, high-risk scores and machine learning algorithms can effectively predict preeclampsia at an early period.

Welcome to Imarticus Learning! In this video, we explain the main differences between parametric and non-parametric algorithms in machine learning. If you're just starting out or planning to become a data scientist, this topic is very important. It helps you choose the right type of model depending on your data and goals. We’ll talk about what parametric algorithms are, how they work, and why they are useful. We’ll also cover their limitations. Then, we’ll explain non-parametric algorithms, how they offer more flexibility, and when to use them. You’ll also learn about the pros and cons of both types and see real examples of how these algorithms are used in fields like finance, healthcare, and marketing. If you're looking for the best machine learning course , Imarticus Learning can guide you with expert-led training, hands-on projects, and industry-relevant content. Watch the full video to understand these key concepts in a simple and practical way.

Email phishing is a manipulative technique aimed at compromising information security and user privacy. To overcome the limitations of traditional detection methods, such as blacklists, this research proposes a phishing detection model that leverages natural language processing (NLP) and deep learning technologies to analyze Indonesian email headers. The primary objective is to more efficiently detect zero-day phishing attacks by focusing on the unique linguistic and cultural context of the Indonesian language. This enables the development of models capable of recognizing phishing attack patterns that differ from those in other language contexts. Four models are tested, combining Indonesian bidirectional encoder representation of transformers (IndoBERT) and FastText feature extraction techniques with convolutional neural network (CNN) and long short-term memory (LSTM) deep learning algorithms. The results indicate that the combination of FastText and CNN achieved the highest performance in accuracy, precision, and F1-score metrics, each at 98.4375%. Meanwhile, the FastText model with LSTM showed the best performance in recall, with a score of 98.9583%. The research suggests exploring deeper into email content or integrating analysis between headers and email content in future studies to further improve accuracy and effectiveness in phishing email detection.

Handwritten digit recognition is a technique or technology for automatically recognizing and detecting handwritten digital data through different Machine Learning models. In this paper we use various Machine Learning algorithms to enhance the productiveness of technique and reduce the complexity using various models. Machine Learning is an application of Artificial Intelligence that learns from previous experience and improves automatically through experience. We illustrate various Machine learning algorithms such as Support Vector Machine, Convolutional Neural Network, Quantum Computing, K-Nearest Neighbor Algorithm, Deep Learning used in Recognition technique.

In this Learning Data Structures and Algorithms video training course, Rod Stephens will teach you how to analyze and implement common algorithms used in data processing. This course is designed for the absolute beginner, meaning no previous programming experience is required. You will start by learning about the complexity theory, then jump into learning about numerical algorithms, including randomizing arrays, prime factorization, and numerical integration. From there, Rod will teach you about linked lists, such as singly linked lists, sorted, and doubly linked lists. This video tutorial also covers arrays, stacks and queues, and sorting. You will also learn about searching, hash tables, recursion, and backtracking algorithms. Finally, you will cover trees, balanced trees, decision trees, and network algorithms. Once you have completed this video training course, you will be fully capable of analyzing and implementing algorithms, as well as be able to select the best algorithm for various situations. Working files are included, allowing you to follow along with the author throughout the lessons.