k-Nearest neighbor is a popular classifier and has been applied in many fields. One problem with this classifier is the choice of k value. Different k values can have a large impact on the predictive accuracy of the algorithm, and picking a good value is generally unintuitive by looking at the data set. Because of the difficulty in selecting the k value, it is suggested to using variable k values instead of just one static k value. The numbers of nearest neighbors (k value) selected for different categories are adaptive to their sample size in the training set. There are many ways of choosing the k value, but a simple one is to run the algorithm many times with different k values and choose the one with the best performance. However, this method will take long time if we want to do experiment with a lot of k values. In relation to this problem, this paper will present the result of our experiment on what data properties affect the choice of k value. There are two interesting results from this experiment. The first is the experiment result showing the relationship between big data sets with more than 8000 instances (Mush, MGT, SS, Adu, and BM) and small best k values in 2-class data sets. And the second is where there is a relationship between data sets having numerical attribute type and small best k values in n-class data sets.

What Affects K Value Selection In K-Nearest Neighbor

The cases of benign and malignant skin neoplasms have been rising over the last decades. They are an esthetical and health threat and require prompt attention, the current diagnostic methods are the biopsy (expensive and invasive) and the dermatoscopy (experience dependent), so new objective methods are needed. The growth of neoplasms is influenced by blood flow, influencing, thereby, skin temperature. Infrared thermal images were taken from 85 patients at the cancer hospital, being analysed and classified with different intelligent data methods. The method that outperformed the other was the k-Nearest Neighbour with 60% accuracy.

/pdf/classifying-skin-neoplasms-with-infrared-thermal-images-28xvcq0ooh.pdf

Classifying Skin Neoplasms with Infrared Thermal Images


 The wear performance of an additively manufactured part is crucial to ensure the component's functionality and reliability. Nevertheless, wear prediction is arduous due to numerous influential factors in both the manufacturing procedure and contact conditions. Machine learning offers a facile path to predict mechanical properties if sufficient datasets is available, without which it is very challenging to attain a high prediction accuracy. In this work, high-accuracy wear prediction of 316L stainless steel parts fabricated using laser powder bed fusion and in-situ surface modification is achieved based on only 54 data using a combination of an improved machine learning algorithm and data augmentation. A new modification temperature ratio was introduced for data augmentation. Four common machine learning algorithms and sparrow search algorithm optimized back propagation neural network was conducted and compared. The results indicated that the prediction accuracy of all algorithms was improved after data augmentation, while the improved machine learning algorithm achieved the highest prediction accuracy (R2=0.978). Such an approach is applicable to predict other systematically complex properties of parts fabricated using other additive manufacturing technology.

Small-dataset machine learning for wear prediction of laser powder bed fusion fabricated steel

In this paper an algorithm for the efficient computation of a rejection threshold for Bayes classification is discussed. A theoretical and a practical evaluation of the performance regarding the accuracy of the numerical computation for uni- and multimodal high-dimensional probability distributions is given. Additionally some observations regarding the dimensionality and the number of samples are shared.

Computation of a Rejection Threshold Used for the Bayes Classifier

Many new investors that want to purchase a fund might be disappointed with the return-on-investment value. This problem occurs because they do not know important factors that could affect the market value. Plus, some assets might not be suitable for the investor's investment style. To reduce the mentioned problems, many asset management companies research the systems that could find a suitable fund for the investor. These systems consider various aspects, such as the investor's background, financial status, and the investor’s behavior. These systems typically employ a specific machine learning method to learn and predict which fund the model should recommend to customers. However, we have an assumption that the performance of the prediction could be leveraged if we applied more methods to a forecasting model. Therefore, this study aims to develop a customer predictive model for investment using voting ensemble learning techniques. The model is used for recommending suitable funds and suitable risks for investing based on the investor’s profile and comparing performance between 5 algorithms and 2 preprocessing approaches. Preprocessing approaches are clustering by date range which has an average accuracy of 62.24% and k-means clustering which has an average accuracy of 69.21%. The prediction model of suitable fund risk and prediction model of fund category has an accuracy of 92.38%. We found that the neural network has the highest accuracy of 93.43%. 

/pdf/development-of-customer-predictive-model-for-investment-37p4jfmj.pdf

Development of Customer Predictive Model for Investment Using Ensemble Learning Technique

kNN is a popular lazy-learning algorithm used for a wide variety of machine learning applications. One problem with this algorithm is the choice of k value. Different k values can have a large impact on the predictive accuracy of the algorithm, and picking a good value is generally unintuitive by looking at the data set. Cross-validation over multiple folds is often used to find the best value for k in kNN based on prediction results. In this paper, we propose automatic selection of neighboring instances as defined by a dynamic local region unique to each instance, as opposed to the traditional approach of considering the manually specified k nearest neighbors. Removing the need to select an appropriate k value removes the cross-validation step, which improves the computational performance of the algorithm. Classification accuracy achieved by this approach is only slightly lower than the results of using kNN with an optimally selected k value.

Dynamic selection of k nearest neighbors in instance-based learning

Electronic medical records provide us with an enormous amount of data with vast potential. If properly analyzed, medical data can be converted to knowledge that improves treatment, uncovers unexpected associations, and supports the personal experience of doctors and nurses, allowing them to make more informed decisions. Medical data is often generated by monitoring across a period of time, whether new data arrives quickly or slowly, consistently or sporadically, but many data mining methods are not designed to consider the temporal aspect of a data set. Besides the extra dimension of time, medical processes often involve interaction between many attributes at once, complicating the discovery of relevant patterns and associations. Specialized methods to interpret medical data can improve the quality of knowledge extracted from it. Tensors are appropriate data structures to represent our data in a multi-dimensional format, taking into account the relationship between many dimensions at once. We can further segment our data into discrete temporal chunks, creating a sequence of tensors. By applying dynamic tensor analysis to our tensor sequence, we can reveal patterns and associations within our data set and capture their change over time. This information can be developed into medical knowledge that can be used to support future treatment.

Tensor-Based Temporal Behavior Analysis in Pain Medicine

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Andy Hall

Author Tools

Chat about Author

Papers

Dynamic selection of k nearest neighbors in instance-based learning

Tensor-Based Temporal Behavior Analysis in Pain Medicine