Mindful Active Learning
Authors: Zhila Esna Ashari, Hassan Ghasemzadeh
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the effectiveness of our approach on three publicly available datasets and by simulating oracles with various memory strengths. We show that the activity recognition accuracy ranges from 21% to 97% depending on memory strength, query budget, and difficulty of the machine learning task. Our results also indicate that EMMA achieves an accuracy level that is, on average, 13.5% higher than the case when only informativeness of the sensor data is considered for active learning. |
| Researcher Affiliation | Academia | Zhila Esna Ashari and Hassan Ghasemzadeh School of Electrical Engineering & Computer Science, Washington State University, Pullman, WA {z.esnaashariesfahan, hassan.ghasemzadeh}@wsu.edu |
| Pseudocode | Yes | Algorithm 1 Greedy algorithm for EMMA |
| Open Source Code | Yes | Software for EMMA (Entropy-Memory Maximization) is available at https://github.com/zhesna/EMMA. |
| Open Datasets | Yes | To assess the performance of EMMA, we used three realworld, publicly-available, sensor-based datasets including HART [Anguita et al., 2013], DAS [Altun et al., 2010; Barshan and Y uksek, 2014; Altun and Barshan, 2010], and ARe M [Palumboa et al., 2016]. |
| Dataset Splits | No | The paper describes training and testing but does not explicitly specify a separate 'validation' dataset split or validation strategy (e.g., cross-validation folds, percentage of data for validation). |
| Hardware Specification | No | The paper does not mention any specific hardware components (e.g., GPU models, CPU types, or cloud instance specifications) used for running the experiments. |
| Software Dependencies | No | The paper mentions using SVM as the classifier and experimenting with linear/RBF kernels, logistic regression, and decision trees, but it does not provide specific version numbers for any of the software libraries or frameworks used. |
| Experiment Setup | Yes | To simulate the oracle s remembering of the event associated with a queried sensor observation Xi based on a given memory strength value s, we first computed memory retention Ri for Xi using (7). We then assigned the correct label with the probability R and incorrect label with the probability (1 R). To alleviate the effect of randomness in our simulation, we repeated each experiment 30 times and report the average results. In our experiments, Z initially had two randomly selected labeled samples. we conducted multiple experiments by changing algorithm parameters including query budget, B, and memory strength, s. |