Challenges In Machine Learning Research Articles

Improved Heart Disease Prediction Using Particle Swarm Optimization Based Stacked Sparse Autoencoder

Heart disease is the leading cause of death globally. The most common type of heart disease is coronary heart disease, which occurs when there is a build-up of plaque inside the arteries that supply blood to the heart, making blood circulation difficult. The prediction of heart disease is a challenge in clinical machine learning. Early detection of people at risk of the disease is vital in preventing its progression. This paper proposes a deep learning approach to achieve improved prediction of heart disease. An enhanced stacked sparse autoencoder network (SSAE) is developed to achieve efficient feature learning. The network consists of multiple sparse autoencoders and a softmax classifier. Additionally, in deep learning models, the algorithm’s parameters need to be optimized appropriately to obtain efficient performance. Hence, we propose a particle swarm optimization (PSO) based technique to tune the parameters of the stacked sparse autoencoder. The optimization by the PSO improves the feature learning and classification performance of the SSAE. Meanwhile, the multilayer architecture of autoencoders usually leads to internal covariate shift, a problem that affects the generalization ability of the network; hence, batch normalization is introduced to prevent this problem. The experimental results show that the proposed method effectively predicts heart disease by obtaining a classification accuracy of 0.973 and 0.961 on the Framingham and Cleveland heart disease datasets, respectively, thereby outperforming other machine learning methods and similar studies.

Three-Year Review of the 2018–2020 SHL Challenge on Transportation and Locomotion Mode Recognition From Mobile Sensors

The Sussex-Huawei Locomotion-Transportation (SHL) Recognition Challenges aim to advance and capture the state-of-the-art in locomotion and transportation mode recognition from smartphone motion (inertial) sensors. The goal of this series of machine learning and data science challenges was to recognize eight locomotion and transportation activities (Still, Walk, Run, Bus, Car, Train, Subway). The three challenges focused on time-independent (SHL 2018), position-independent (SHL 2019) and user-independent (SHL 2020) evaluations, respectively. Overall, we received 48 submissions (out of 93 teams who registered interest) involving 201 scientists over the three years. The survey captures the state-of-the-art through a meta-analysis of the contributions to the three challenges, including approaches, recognition performance, computational requirements, software tools and frameworks used. It was shown that state-of-the-art methods can distinguish with relative ease most modes of transportation, although the differentiating between subtly distinct activities, such as rail transport (Train and Subway) and road transport (Bus and Car) still remains challenging. We summarize insightful methods from participants that could be employed to address practical challenges of transportation mode recognition, for instance, to tackle over-fitting, to employ robust representations, to exploit data augmentation, and to exploit smart post-processing techniques to improve performance. Finally, we present baseline results to compare the three challenges with a unified recognition pipeline and decision window length.

A Convex Formulation for Learning from Crowds

Recently crowdsourcing services are often used to collect a large amount of labeled data for machine learning, since they provide us an easy way to get labels at very low cost and in a short period. The use of crowdsourcing has introduced a new challenge in machine learning, that is, coping with the variable quality of crowd-generated data. Although there have been many recent attempts to address the quality problem of multiple workers, only a few of the existing methods consider the problem of learning classifiers directly from such noisy data. All these methods modeled the true labels as latent variables, which resulted in non-convex optimization problems. In this paper, we propose a convex optimization formulation for learning from crowds without estimating the true labels by introducing personal models of the individual crowd workers. We also devise an efficient iterative method for solving the convex optimization problems by exploiting conditional independence structures in multiple classifiers. We evaluate the proposed method against three competing methods on synthetic data sets and a real crowdsourced data set and demonstrate that the proposed method outperforms the other three methods.

Exploring Opportunities and Challenges of Artificial Intelligence and Machine Learning in Higher Education Institutions

The way people travel, organise their time, and acquire information has changed due to information technologies. Artificial intelligence (AI) and machine learning (ML) are mechanisms that evolved from data management and developing processes. Incorporating these mechanisms into business is a trend many different industries, including education, have identified as game-changers. As a result, education platforms and applications are more closely aligned with learners’ needs and knowledge, making the educational process more efficient. Therefore, AI and ML have great potential in e-learning and higher education institutions (HEI). Thus, the article aims to determine its potential and use areas in higher education based on secondary research and document analysis (literature review), content analysis, and primary research (survey). As referent points for this research, multiple academic, scientific, and commercial sources were used to obtain a broader picture of the research subject. Furthermore, the survey was implemented among students in the Republic of Serbia, with 103 respondents to generate data and information on how much knowledge of AI and ML is held by the student population, mainly to understand both opportunities and challenges involved in AI and ML in HEI. The study addresses critical issues, like common knowledge and stance of research bases regarding AI and ML in HEI; best practices regarding usage of AI and ML in HEI; students’ knowledge of AI and ML; and students’ attitudes regarding AI and ML opportunities and challenges in HEI. In statistical considerations, aiming to evaluate if the indicators were considered reflexive and, in this case, belong to the same theoretical dimension, the Correlation Matrix was presented, followed by the Composite Reliability. Finally, the results were evaluated by regression analysis. The results indicated that AI and ML are essential technologies that enhance learning, primarily through students’ skills, collaborative learning in HEI, and an accessible research environment.

Automatic features generation and selection from external sources: A DBpedia use case

Feature engineering is one of the major challenges of machine learning. While multiple automation solutions have been proposed in recent years, the vast majority focuses on extracting features from the analyzed dataset itself and not from other (external) sources. In this study we present FGSES, a general framework for automatic feature engineering and its application to DBpedia. Our framework automatically matches the entities in the analyzed dataset to those of the external data source, and then proceeds to generate a large and diverse set of candidate features, both from structured and unstructured content. To efficiently process the large number of generated features, FGSES uses a meta learning-based ranking approach. Our evaluation, conducted on 18 tabular datasets with diverse characteristics, shows that FGSES achieves an average error reduction of 16.5%, significantly outperforming the evaluated baselines.

Two novelty learning models developed based on deep cascade forest to address the environmental imbalanced issues: A case study of drinking water quality prediction

Environmental quality data sets are typically imbalanced, because environmental pollution events are rarely observed in daily life. Prediction of imbalanced data sets is a major challenge in machine learning. Our recent work has shown deep cascade forest (DCF), as a base learning model, is promising to be recommended for environmental quality prediction. Although some traditional models were improved by introducing the cost matrix, little is known about whether cost matrix could enhance the prediction performance of DCF. Additionally, feature extraction is also an important way to potentially improve the model's ability to predict the imbalanced data. Here, we developed two novelty learning models based on DCF: cost-sensitive DCF (CS-DCF) and DCF that combines unsupervised learning models and greedy methods (USM-DCF-G). Subsequently, CS-DCF and USM-DCF-G were successfully verified by an imbalanced drinking water quality data set. Our data presented both CS-DCF and USM-DCF-G show better prediction performance than that of DCF alone did. In particular, USM-DCF-G shows the best performance with the highest F1-score (95.12 ± 2.56%), after feature extraction and selection by using unsupervised learning models and greedy methods. Thus, the two learning models, especially USM-DCF-G, were promising learning models to address environmental imbalanced issues and accurately predict environmental quality.

Modern Challenges in Machine Learning and Artificial Intelligence

The usage and development of Machine Learning models along with the advancement and popularization of Artificial Intelligence, naturally leads to new challenges in multiple levels in the field. In one hand the trust in the field of AI needs to be boosted in order to increase the adoption rate, on the other hand the usage of AI has been largely abused by those who decided to adopt the term in their line of work. A clear line of what is expected from AI and what AI is, must be drawn so that the trust, acceptance and adoption of AI can be increased. These, and other data related problems are the primary subject of this paper.

PD58-08 AUTOMATING SUTURING SKILLS ASSESSMENT WITH A LIMITED SURGEON DATASET: META LEARNING

You have accessJournal of UrologySurgical Technology & Simulation: Training & Skills Assessment (PD58)1 Sep 2021PD58-08 AUTOMATING SUTURING SKILLS ASSESSMENT WITH A LIMITED SURGEON DATASET: META LEARNING Andrew J. Hung, Sirisha Rambhatla, Daniel I. Sanford, Nilay Pachauri, Jessica H. Nguyen, and Yan Liu Andrew J. HungAndrew J. Hung More articles by this author , Sirisha RambhatlaSirisha Rambhatla More articles by this author , Daniel I. SanfordDaniel I. Sanford More articles by this author , Nilay PachauriNilay Pachauri More articles by this author , Jessica H. NguyenJessica H. Nguyen More articles by this author , and Yan LiuYan Liu More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000002092.08AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Automating technical skills assessment with machine learning models can revolutionize how we credential surgeons, and it can identify critical errors before they become patient complications. Common to many machine learning challenges, having limited training data can prevent our ability to accurately project skills assessment for a wide population of surgeons. Herein, we utilized meta learning, a specialized form of machine learning, to learn from a limited set of surgeons, and adapt learned representations to new additional surgeons. METHODS: Training and faculty surgeons completed a suturing simulation task on the Mimic Flex VR robotic simulator. Video and kinematic data (instrument XYZ coordinates and pose) were collected. Three human raters utilized the video and a suturing assessment tool to provide ground truth labels for skill domains. Kinematic data was utilized by two baseline models and the proposed Meta learning model to project skills assessment. For each skill domain, surgeons with minimum two ideal and non-ideal performance examples were included. Data from five surgeons were randomly selected for the test set, remainder was utilized for training. Three two-layer LSTM-based models projected skills assessment: No-customization, Fine-tune (customized the base model for new surgeons), and Meta learning (not only customized predictions, but also updated the base model thereby maximizing learning). Best area under the curve (AUC) metric across epochs was used to assess performance. RESULTS: In total, 21 surgeons contributed performance data for analysis. 16 surgeons contributed examples to Needle positioning scoring, 19 to Needle entry angle, 20 to Needle driving, and 20 to Needle withdraw. For all skill domains, Meta learning achieved the highest performance in projecting the ground truth labels (AUC = 0.72-0.88) (Table). In all skill domains, Meta learning outperformed both the Fine-tune and No customization models. Fine-tune outperformed No customization in all domains, except for Needle withdrawal. CONCLUSIONS: Our initial experiments with Meta learning demonstrate that it can augment model performance in automated suturing skill assessment with a limited surgeon dataset by applying learned patterns to new additional surgeons. Overall, Meta learning projection results are very robust. Source of Funding: Research reported in this publication was supported in part by the National Institute Of Biomedical Imaging And Bioengineering of the National Institutes of Health under Award Number K23EB026493. © 2021 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 206Issue Supplement 3September 2021Page: e1019-e1020 Advertisement Copyright & Permissions© 2021 by American Urological Association Education and Research, Inc.MetricsAuthor Information Andrew J. Hung More articles by this author Sirisha Rambhatla More articles by this author Daniel I. Sanford More articles by this author Nilay Pachauri More articles by this author Jessica H. Nguyen More articles by this author Yan Liu More articles by this author Expand All Advertisement Loading ...

BARRIERS to Early Detection of Deterioration in Hospitalized Infants Using Predictive Analytics.

BARRIERS to Early Detection of Deterioration in Hospitalized Infants Using Predictive Analytics.

Optimizing the Weights and Thresholds in Dendritic Neuron Model Using the Whale Optimization Algorithm

In recent years, with the great success of dendritic neuron model (DNM) in various fields, the application of intelligent optimization algorithms in dendritic neuron model has attracted increasing attention of researchers. The training process of neural network is regarded as one of the great challenges of machine learning because of its non-linear nature and unknown optimal parameters. The traditional training algorithm of DNM is prone to fall into local optimum and speed of convergence slowly and so on, resulting in the problem of accuracy and low efficiency. In this paper, for solving the classification problem of dendritic neural model, an innovative intelligent optimization algorithm which named whale optimization algorithm (WOA), is applied to the training of DNM for the first time. Compared with six traditional and classic intelligent optimization algorithms in four classic datasets, the results indicate that WOA-DNM has good performance in various aspects, and its advantage is remarkable.

A comprehensive study on artificial intelligence in oil and gas sector.

The authors investigate how artificial intelligence modifies a huge piece of the energy area, the oil and gas industry. This paper attempts to evaluate technical and non-technical factors affecting the adoption of machine learning technologies. The study includes machine learning development platforms, network architecture, and opportunities and challenges of adopting machine learning technologies in the oil and gas industry. The authors elaborate on the three different sectors in this industry namely upstream, midstream, and downstream. Herein, a review is presented to evaluate the applications and scope of machine learning in the oil and gas industry to optimize the upstream operations (including exploration, drilling, reservoir, and production), midstream operations (including transportation using pipelines, ships, and road vehicles), and downstream operations (including production of refinery products like fuels, lubricants, and plastics). Enhanced processing of seismic data is illustrated which provides the industry with a better understanding of machine learning applications. Basing on the investigation of AI implementation prospects and the survey of subsisting implementations, they diagram the latest patterns in creating AI-based instruments and distinguish their impacts on speeding up and de-gambling measures in the business. They examine AI proposition and calculations, just as the job and accessibility of information in the portion. Furthermore, they examine the principal non-specialized difficulties that forestall the concentrated use of man-made brainpower in the oil and gas industry (OGI), identified with information, individuals, and new types of joint effort. They additionally diagram potential situations of how man-made reasoning will create in the OGI and how it might transform it later on (in 5, 10, and 20 years).

Application of Machine Learning in Google Services- A Case Study

Purpose: Google Search is currently the most preferred search engine worldwide, making it one of the websites with the highest traffic. It assists people in discovering the content they are searching for, from the large repository of the World Wide Web. Google has grown to be the best in the search engine market that it is the single most important variable to be considered when optimizing a website for search. There are many ranking algorithms used by Google to make the searching process more precise. Google has the vision “to provide access to the world's information in one click”. Machine learning is the most popular methodology applied in predicting future outcomes or organizing information to assist people in making required decisions.ML algorithms are trained over instances or examples through which they analyze the historical data available and learn from past experiences. By repeatedly training over the samples, the patterns in the data can be identified in order to make predictions about the future. Google, as an organization, can be a pioneer in ML, and as a technology product, can be a use case for machine learning. Here, a case analysis has been prepared on few applications of machine learning in the products and services of Google. Within this paper, we highlight their technological history, services with machine learning applications, financial plans, and challenges. The paper also tries to examine the various products of Google which apply ML, such as Google Maps, Gmail, Google Photos, Google Assistant, and review the algorithms used in each service. Approach: The detailed survey method on secondary data is used for analysing the data. Findings: Based on the developed case study, it is clearly evident that Google is using machine learning algorithms with few artificial intelligence features to enhance the quality of the services they provide. Originality: A new way of analysis was performed to identify the methods used in the organization’s services. Paper Type: Descriptive Case Study Research

Machine learning and algorithmic fairness in public and population health

Until now, much of the work on machine learning and health has focused on processes inside the hospital or clinic. However, this represents only a narrow set of tasks and challenges related to health; there is greater potential for impact by leveraging machine learning in health tasks more broadly. In this Perspective we aim to highlight potential opportunities and challenges for machine learning within a holistic view of health and its influences. To do so, we build on research in population and public health that focuses on the mechanisms between different cultural, social and environmental factors and their effect on the health of individuals and communities. We present a brief introduction to research in these fields, data sources and types of tasks, and use these to identify settings where machine learning is relevant and can contribute to new knowledge. Given the key foci of health equity and disparities within public and population health, we juxtapose these topics with the machine learning subfield of algorithmic fairness to highlight specific opportunities where machine learning, public and population health may synergize to achieve health equity. Algorithmic solutions to improve treatment are starting to transform health care. Mhasawade and colleagues discuss in this Perspective how machine learning applications in population and public health can extend beyond clinical practice. While working with general health data comes with its own challenges, most notably ensuring algorithmic fairness in the face of existing health disparities, the area provides new kinds of data and questions for the machine learning community.

Follow the perturbed approximate leader for solving semi-bandit combinatorial optimization

Combinatorial optimization in the face of uncertainty is a challenge in both operational research and machine learning. In this paper, we consider a special and important class called the adversarial online combinatorial optimization with semi-bandit feedback, in which a player makes combinatorial decisions and gets the corresponding feedback repeatedly. While existing algorithms focus on the regret guarantee or assume there exists an efficient offline oracle, it is still a challenge to solve this problem efficiently if the offline counterpart is NP-hard. In this paper, we propose a variant of the Follow-the-Perturbed-Leader (FPL) algorithm to solve this problem. Unlike the existing FPL approach, our method employs an approximation algorithm as an offline oracle and perturbs the collected data by adding nonnegative random variables. Our approach is simple and computationally efficient. Moreover, it can guarantee a sublinear (1+e)-scaled regret of order O(T^{2/3}) for any small e > 0 for an important class of combinatorial optimization problems that admit an FPTAS (fully polynomial time approximation scheme), in which T is the number of rounds of the learning process. In addition to the theoretical analysis, we also conduct a series of experiments to demonstrate the performance of our algorithm.

A holistic approach to interpretability in financial lending: Models, visualizations, and summary-explanations

Lending decisions are usually made with proprietary models that provide minimally acceptable explanations to users. In a future world without such secrecy, what decision support tools would one want to use for justified lending decisions? This question is timely, since the economy has dramatically shifted due to a pandemic, and a massive number of new loans will be necessary in the short term. We propose a framework for such decisions, including a globally interpretable machine learning model, an interactive visualization of it, and several types of summaries and explanations for any given decision. The machine learning model is a two-layer additive risk model, which resembles a two-layer neural network, but is decomposable into subscales. In this model, each node in the first (hidden) layer represents a meaningful subscale model, and all of the nonlinearities are transparent. Our online visualization tool allows exploration of this model, showing precisely how it came to its conclusion. We provide three types of explanations that are simpler than, but consistent with, the global model: case-based reasoning explanations that use neighboring past cases, a set of features that were the most important for the model's prediction, and summary-explanations that provide a customized sparse explanation for any particular lending decision made by the model. Our framework earned the FICO recognition award for the Explainable Machine Learning Challenge, which was the first public challenge in the domain of explainable machine learning.11Authors are listed alphabetically.

Dynamically adaptive and diverse dual ensemble learning approach for handling concept drift in data streams

AbstractConcept drift refers to the change in data distributions and evolving relationships between input and output variables with the passage of time. To analyze such variations in learning environments and generate models which can accommodate changing performance of predictive systems is one of the challenging machine learning applications. In general, the majority of the existing schemes consider one of the specific drift types: gradual, abrupt, recurring, or mixed, with traditional voting setup. In this work, we propose a novel data stream framework, dynamically adaptive and diverse dual ensemble (DA‐DDE) which responds to multiple drift types in the incoming data streams by combining online and block‐based ensemble techniques. In the proposed scheme, a dual diversified ensemble‐based system is constructed with the combination of active and passive ensembles, updated over a diverse set of resampled input space. The adaptive weight setting method is proposed in this work which utilizes the overall performance of learners on historic as well as recent concepts of distributions. Further a dual voting system has been used for hypothesis generation by considering dynamic adaptive credibility of ensembles in real time. Comparative analysis with 14 state‐of‐the‐art algorithms on 24 artificial and 11 real datasets shows that DA‐DDE is highly effective in handling various drift types.

Learning Then, Learning Now, and Every Second in Between: Lifelong Learning With a Simulated Humanoid Robot.

Long-term human-robot interaction requires the continuous acquisition of knowledge. This ability is referred to as lifelong learning (LL). LL is a long-standing challenge in machine learning due to catastrophic forgetting, which states that continuously learning from novel experiences leads to a decrease in the performance of previously acquired knowledge. Two recently published LL approaches are the Growing Dual-Memory (GDM) and the Self-organizing Incremental Neural Network+ (SOINN+). Both are growing neural networks that create new neurons in response to novel sensory experiences. The latter approach shows state-of-the-art clustering performance on sequentially available data with low memory requirements regarding the number of nodes. However, classification capabilities are not investigated. Two novel contributions are made in our research paper: (I) An extended SOINN+ approach, called associative SOINN+ (A-SOINN+), is proposed. It adopts two main properties of the GDM model to facilitate classification. (II) A new LL object recognition dataset (v-NICO-World-LL) is presented. It is recorded in a nearly photorealistic virtual environment, where a virtual humanoid robot manipulates 100 different objects belonging to 10 classes. Real-world and artificially created background images, grouped into four different complexity levels, are utilized. The A-SOINN+ reaches similar state-of-the-art classification accuracy results as the best GDM architecture of this work and consists of 30 to 350 times fewer neurons, evaluated on two LL object recognition datasets, the novel v-NICO-World-LL and the well-known CORe50. Furthermore, we observe an approximately 268 times lower training time. These reduced numbers result in lower memory and computational requirements, indicating higher suitability for autonomous social robots with low computational resources to facilitate a more efficient LL during long-term human-robot interactions.

A Critical Overview of Privacy in Machine Learning

This article reviews privacy challenges in machine learning and provides a critical overview of the relevant research literature. The possible adversarial models are discussed, a wide range of attacks related to sensitive information leakage is covered, and several open problems are highlighted.

Machine Learning Challenges for IoT Device Fingerprints Identification

The dramatic growth of Internet of Things (IoT) devices in recent years increases the IoT networks’ vulnerabilities and introduces new challenges among machine learning (ML) algorithms to detect the networked devices. The creation of a Device Fingerprint (DFP) may depend on extracting the network traffic features related to the device except for the identities assigned to it. In this paper, Device Fingerprints for 20 IoT devices are created by extracting 30 features during startup operation. Wireshark Network Protocol Analyzer is used to collect network traffic of 8 home IoT devices, meanwhile the traffics of the remaining devices are taken from the captures_IoT-Sentinel publicly available dataset. Four supervised machine learning algorithms were applied and tested to detect authorized devices and isolate unknown devices, namely: Support Vector Machine (SVM), Decision Tree (DT), Ensemble Random Forest (RF), and Gradient Boosting Classifier (GBC). Random Forest model and Gradient Boosting Classifier both showed better results of about 98.8% as an average of overall accuracy with less difference comparing with the accuracy of Decision Tree. Voting classifier was applied using the three estimators that resulted in high accuracy (DT, RF, and GBC) and achieving 99.5% as an average of overall accuracy.

Meta‐learning and the new challenges of machine learning

In the last years, organizations and companies in general have found the true potential value of collecting and using data for supporting decision-making. As a consequence, data are being collected at an unprecedented rate. This poses several challenges, including, for example, regarding the storage and processing of these data. Machine Learning (ML) is also not an exception, in the sense that algorithms must now deal with novel challenges, such as learn from streaming data or deal with concept drift. ML engineers also have a harder task when it comes to selecting the most appropriate model, given the wealth of algorithms and possible configurations that exist nowadays. At the same time, training time is a stronger restriction as the computational complexity of the training model increases. In this paper we propose a framework for dealing with these challenges, based on meta-learning. Specifically, we tackle two well-defined problems: automatic algorithm selection and continuous algorithm updates that do not require the retraining of the whole algorithm to adapt to new data. Results show that the proposed framework can contribute to ameliorate the identified issues.