**6. Human AML for autism students**

One goal of recent researches is to incorporate ML models with behavioral models to teach students and to investigate whether they can benefit from ML techniques to learn better.

Radwan et al. [21] were the first to attempt to use AML for teaching students with autism spectrum disorders (ASD). Students with ASD cannot learn in the same way as most people, and they need special treatment to learn a concept or an object. One of the difficulties faced by people with ASD is the recognition of categories. Radwan et al. [21] proposed a novel batchmode pool-based AML framework for teaching students with ASD and compare the effectiveness of PL vs. AML on teaching object recognition for those students. AML approach presented to the student the most informative teaching set of objects based on the uncertainty sampling strategy. In this framework, a student plays the role of the classifier and does not have a probabilistic model. So, the uncertainty is computed in the context of the child's responses to measure informativeness for all objects. If an object's uncertainty is high, it implies that the student does not have sufficient knowledge to classify the object, and then adding this object into the training set can improve the child's recognition ability.

For this purpose, a web- and touch-based application was developed and presented on a tablet PC. Objects from everyday lives of children were grouped based on their categories and four difficulty levels L1–L4; see **Figure 5**. Picture stimuli of target objects were colored images, and they were collected using image search engines, in particular Google and Bing. The teaching procedure was based on applied behavioral analysis (ABA) principles. Five students with mild to moderate levels of ASD participated in the experiment. An alternating treatment design of single subject research methods was used to compare the effects of AML and PL.

The results indicate that AML was more effective than PL for four out of the five students. Consequently, students can learn faster and are able to reach a learning criterion with fewer teaching trials [21]. AML approach was generally more effective in terms of accuracy. The statistical results demonstrated that there was a statistically significant difference in accuracy level between the means of PL and AML. The AML approach and procedures provide two

**References**

Inc; 2009

[thesis]. 2016

pp. 241-248

2009;**3**(1):1-130

Learning. 2007;**68**(3):235-265

sertations thesis]. 2015

Wisconsin; 2010. p. 11

DOI:10.1080/21693277.2016.1192517

[1] Sinha P, Sinha P. Comparative Study of Chronic Kidney Disease Prediction using KNN and SVM [Online]. Available from: paper/Comparative-Study-of-Chronic-Kidney-

Human Active Learning

27

http://dx.doi.org/10.5772/intechopen.81371

[2] O'Neill J. An evaluation of selection strategies for active learning with regression [dis-

[3] Bird S, Klein E, Loper E. Natural Language Processing with Python. 1st ed. O'Reilly Media,

[4] Nore PW. Pollution detection in a low-cost electronic nose, a machine learning approach

[5] Settles B. Active Learning Literature Survey. Vol. 52, No. 55-66. Madison: University of

[6] Kremer J, Pedersen KS, Igel C. Active learning with support vector machines. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. 2014;**4**(4):313-326 [7] Wuest T, Weimer D, Irgens C, Thoben KD. Machine learning in manufacturing: Advantages, challenges, and applications. Production & Manufacturing Research. **4**(1): 23-45.

[9] Chen Y, Mani S, Xu H. Applying active learning to assertion classification of concepts in

[10] Grabinger S, Dunlap JC, Duffield JA. Rich environments for active learning in action:

[11] Deng C, Liu X, Li C, Tao D. Active multi-kernel domain adaptation for hyperspectral

[12] Castro RM, Kalish C, Nowak R, Qian R, Rogers T, Zhu X. Human active learning. In: Advances in Neural Information Processing Systems (NIPS), Vancouver, Canada. 2008.

[13] Davy M. A review of active learning and co-training in text classification. In: Computer Science Technical Report TCD-CS-2005-64. Dublin: Trinity College; 2005. pp. 170-179 [14] Zhu X, Goldberg AB. Introduction to Semi-Supervised Learning, Synthesis Lectures on Artificial Intelligence and Machine Learning. San Refael: Morgan & Claypool Publishers;

[15] Schein AI, Ungar LH. Active learning for logistic regression: an evaluation. Machine

[16] Tong S, Koller D. Support vector machine active learning with applications to text clas-

[17] Chapelle O, Scholkopf B, Zien EA. Semi-supervised learning (Chapelle O. et al., eds. 2006) [Book reviews]. IEEE Transactions on Neural Networks. 2009;**20**(3):542-542

[8] Tong S. Active Learning: Theory and Applications. Stanford University; 2001

clinical text. Journal of Biomedical Informatics. 2012;**45**(2):265-272

Problem-based learning. Alternatives Journal. 1997;**5**(2):5-17

image classification. Pattern Recognition. 2018;**77**(C):306-315

sification. Journal of Machine Learning Research. 2002;**2**:45-66

Disease-using-Sinha-Sinha/3ec05afd1eb4bb4d5ec17a9e0b3d09f5cbc30304

**Figure 5.** A sample of images from the dataset used for teaching and test. Columns L1–L4 show different difficulty levels.

features that helped to reduce repetition in learning environment: (1) minimizing the number of teaching trials required for training and (2) determining mastery criterion for levels. When a participant reached mastery criterion, the application no longer assesses this level in the following phases.
