Machine Learning Algorithms for Heterogeneous Data: A Comparative Study

Nataraja, Poornima; Ramesh, Bharathi

doi:10.34218/ijcet.10.3.2019.002

Cited by 2 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concerning SVM, it gives poor performance with large dataset (Nataraja and Ramesh, 2019). Finally, VB and GLM are often inaccurate when the data are heterogeneous and when the responses are non-linear (Nataraja and Ramesh, 2019). Other studies from agriculture-related sectors also reported similar trend in the performance of machine learning algorithms.…”

Section: Discussionmentioning

confidence: 82%

“…Moreover, the numerical features in our dataset are in very different scales, it is necessary to normalize them for ANNs and KNN to reduce effects of disparate ranges (Sarle et al, 1991;Han et al, 2011;Ali et al, 2019). Concerning SVM, it gives poor performance with large dataset (Nataraja and Ramesh, 2019). Finally, VB and GLM are often inaccurate when the data are heterogeneous and when the responses are non-linear (Nataraja and Ramesh, 2019).…”

Section: Discussionmentioning

confidence: 99%

“…RF, GBM, SVM are able to handle such heterogeneous features, while ANNs, KNN, XGBOOST work usually better with numerical and homogeneous inputs (Ali et al, 2019;Zhou, 2021). Converting categorical features to numerical will also increase the number of feature inputs, it will dramatically increase the computational time for, e.g., ANNs (Nataraja and Ramesh, 2019). Moreover, the numerical features in our dataset are in very different scales, it is necessary to normalize them for ANNs and KNN to reduce effects of disparate ranges (Sarle et al, 1991;Han et al, 2011;Ali et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Performances of Machine Learning Algorithms in Predicting the Productivity of Conservation Agriculture at a Global Scale

Zhang

Gabrielle

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Assessing the productive performance of conservation agriculture (CA) has become a major issue due to growing concerns about global food security and sustainability. Numerous experiments have been conducted to assess the performance of CA under various local conditions, and meta-analysis has become a standard approach in agricultural sector for analysing and summarizing the experimental data. Meta-analysis provides valuable synthetic information based on mean effect size estimation. However, summarizing large amounts of information by way of a single mean effect value is not always satisfactory, especially when considering agricultural practices. Indeed, their impacts on crop yields are often non-linear, and vary widely depending on a number of factors, including soil properties and local climate conditions. To address this issue, here we present a machine learning approach to produce data-driven global maps describing the spatial distribution of the productivity of CA versus conventional tillage (CT). Our objective is to evaluate and compare several machine-learning models for their ability in estimating the productivity of CA systems, and to analyse uncertainty in the model outputs. We consider different usages, including classification, point regression and quantile regression. Our approach covers the comparison of 12 different machine learning algorithms, model training, tuning with cross-validation, testing, and global projection of results. The performances of these algorithms are compared based on a recent global dataset including more than 4,000 pairs of crop yield data for CA vs. CT. We show that random forest has the best performance in classification and regression, while quantile regression forest performs better than quantile neural networks in quantile regression. The best algorithms are used to map crop productivity of CA vs. CT at the global scale, and results reveal that the performance of CA vs. CT is characterized by a strong spatial variability, and that the probability of yield gain with CA is highly dependent on geographical locations. This result demonstrates that our approach is much more informative than simply presenting average effect sizes produced by standard meta-analyses, and paves the way for such probabilistic, spatially-explicit approaches in many other fields of research.

show abstract

Section: Discussionmentioning

confidence: 82%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Performances of Machine Learning Algorithms in Predicting the Productivity of Conservation Agriculture at a Global Scale

Zhang

Gabrielle

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…On the other hand, integrating different methods by compounding their strength definitely would be more beneficial for overcoming this challenge related to heterogeneous data analysis. [ 150 ] For example, a novel CNN‐based algorithm based on both structured and unstructured data from hospitals has been proposed to predict chronic disease outbreaks in disease‐prone areas. The data heterogeneity problem was resolved in this study, and the disease prediction accuracy was 94.8%.…”

Section: Challenging Issues Faced With Ai and Microfluidics For Biote...mentioning

confidence: 99%

Recent Advances of Utilizing Artificial Intelligence in Lab on a Chip for Diagnosis and Treatment

Harofte

Soltani

Siavashy

et al. 2022

Small

View full text Add to dashboard Cite

utilization of biological systems to develop new products at one end of the spectrum to the application of technology for solving the problems in biology at the other end. [1] According to the new experimental technologies like DNA nucleotide sequencing and RNA sequencing genomics, [2] Mass Spectrometry [3] as well as X-ray crystallography and Nuclear Magnetic Resonance spectroscopy [4] in proteomics, large datasets are generated and sorted in the field of biotechnology that make new opportunities for researchers along with companies that present services and products in this area. Nowadays, performing stateof-the-art research in biotechnology is roughly impossible without exploiting database and artificial intelligence (AI) technologies. [5] The integration of AI and biotechno logy is now prevalent. AI elucidates computational systems which extract signals and learn from the input. [1] Historically, AI has a close relationship with biology. Precisely, this relation is between statistics and genetics. Compared to text or image datasets, biological data is more multidimensional, complicated, and noisy. Hence, AI models are more pertinent than simple statistical models for biological datasets. [6] Nowadays, artificial intelligence (AI) creates numerous promising opportunities in the life sciences. AI methods can be significantly advantageous for analyzing the massive datasets provided by biotechnology systems for biological and biomedical applications. Microfluidics, with the developments in controlled reaction chambers, high-throughput arrays, and positioning systems, generate big data that is not necessarily analyzed successfully. Integrating AI and microfluidics can pave the way for both experimental and analytical throughputs in biotechnology research. Microfluidics enhances the experimental methods and reduces the cost and scale, while AI methods significantly improve the analysis of huge datasets obtained from high-throughput and multiplexed microfluidics. This review briefly presents a survey of the role of AI and microfluidics in biotechnology. Also, the incorporation of AI with microfluidics is comprehensively investigated. Specifically, recent studies that perform flow cytometry cell classification, cell isolation, and a combination of them by gaining from both AI methods and microfluidic techniques are covered. Despite all current challenges, various fields of biotechnology can be remarkably affected by the combination of AI and microfluidic technologies. Some of these fields include point-of-care systems, precision, personalized medicine, regenerative medicine, prognostics, diagnostics, and treatment of oncology and non-oncology-related diseases.

show abstract

Machine Learning Algorithms for Heterogeneous Data: A Comparative Study

Cited by 2 publications

References 20 publications

Performances of Machine Learning Algorithms in Predicting the Productivity of Conservation Agriculture at a Global Scale

Performances of Machine Learning Algorithms in Predicting the Productivity of Conservation Agriculture at a Global Scale

Recent Advances of Utilizing Artificial Intelligence in Lab on a Chip for Diagnosis and Treatment

Contact Info

Product

Resources

About