Ensembles of Deep LSTM Learners for Activity Recognition using Wearables
Open accessThe DOI matches its Crossref record; 53 of the 65 references it cites were found in a registry or an index, and 10 are not checked yet; none of the 62 sources its claims cite is checked for support yet.
Abstract
Recently, deep learning (DL) methods have been introduced very successfully into human activity recognition (HAR) scenarios in ubiquitous and wearable computing. Especially the prospect of overcoming the need for manual feature design combined with superior classification capabilities render deep neural networks very attractive for real-life HAR applications. Even though DL-based approaches now outperform the state-of-the-art in a number of recognition tasks, still substantial challenges remain. Most prominently, issues with real-life datasets, typically including imbalanced datasets and problematic data quality, still limit the effectiveness of activity recognition using wearables. In this paper we tackle such challenges through Ensembles of deep Long Short Term Memory (LSTM) networks. LSTM networks currently represent the state-of-the-art with superior classification performance on relevant HAR benchmark datasets. We have developed modified training procedures for LSTM networks and combine sets of diverse LSTM learners into classifier collectives. We demonstrate that Ensembles of deep LSTM learners outperform individual LSTM networks and thus push the state-of-the-art in human activity recognition using wearables. Through an extensive experimental evaluation on three standard benchmarks (Opportunity, PAMAP2, Skoda) we demonstrate the excellent recognition capabilities of our approach and its potential for real-life applications of human activity recognition.
Checked 2026-10-05 · 10 references not checked yet
Overview
CoChat Summary
TL;DR
The paper introduces ensembles of deep LSTM learners for wearable activity recognition, using an epoch-wise bagging-style training procedure and score-level fusion of multiple LSTM models. Across Opportunity, PAMAP2, and Skoda, the ensembles outperform individual LSTMs and state-of-the-art baselines, with the largest gains on the challenging, imbalanced Opportunity dataset.
Key findings
- Ensembles of LSTM learners improve over single LSTMs on all three benchmarks. For Opportunity, single CE LSTM F1 = 0.674 ± 0.021 vs. Ensemble M=10 CE = 0.716 ± 0.011 and M=20 CE = 0.720 ± 0.011; the best combined CE+F1 ensemble reaches 0.726 ± 0.008. For PAMAP2, single CE = 0.802 ± 0.045 vs. Ensemble M=10 CE = 0.848 ± 0.021 and M=20 CE = 0.852 ± 0.026; combined CE+F1 = 0.854 ± 0.026. For Skoda, single CE = 0.918 ± 0.007 vs. Ensemble M=10 CE = 0.925 ± 0.002 and M=20 CE = 0.926 ± 0.001; combined CE+F1 = 0.924 ± 0.002.
- The LSTM ensemble outperforms reported state-of-the-art baselines: LSTM baseline 0.659/0.756/0.904, DeepConvLSTM 0.672/0.748/0.912, and LSTM-S 0.684/0.838/0.921 for Opportunity/PAMAP2/Skoda, respectively, versus the ensemble’s 0.726/0.854/0.924.
- Performance generally plateaus at M=10 base learners; increasing to M=20 gives no statistically significant improvement except for Opportunity with F1 loss, where the improvement is “just significant.” Combining CE and F1 loss functions further improves Opportunity but not PAMAP2, and Skoda shows no substantial boost.
- The training procedure intentionally omits data: on average about 35%–38% of training data is not used per epoch when using a uniformly distributed random number generator for training frames.
Methods
- The authors use two-layer LSTM networks with 256 LSTM units per layer, dropout 0.5 at both hidden layers, ADAM with learning rate 0.001, implemented in Lasagne/Theano and trained on an NVIDIA Tesla K40. Training uses randomly drawn mini-batch sizes from U(128, 256) and frame lengths from U(16, 32); test-time inference is sample-wise with mini-batch size and frame length set to 1.
- The core method is epoch-wise bagging: for each epoch, random mini-batch size, random starting positions, and random frame lengths are drawn; one LSTM learner is produced per epoch (MaxEpoch = 100). The M best models on a validation set are retained and fused by arithmetic mean of their softmax class-probability vectors. Both cross-entropy and F1 loss are explored.
- Evaluation uses three standard benchmarks: Opportunity, PAMAP2, and Skoda, with hold-out validation/test protocols replicating prior work. Results are mean F1 scores over 30 repetitions, with two-tailed independent t-tests for significance.
Limitations
- The paper states that implementation issues for field deployments or products are not yet addressed; ensembles inflate the parameter space, though the authors argue pruning remains accessible because the base LSTM models are unchanged.
- The paper notes that F1 loss is a global measure and cannot directly measure individual sample losses; because LSTMs are trained on mini-batches, it may not precisely approximate the true gradient toward optimal F1 over the whole training set.
- The paper states that Skoda shows no substantial performance boost, attributed to only one worker being considered and the task lacking challenging test data from different environments; the baseline models already achieve high specialisation (F1 > 0.9). Evident from the text: evaluation is limited to three benchmark datasets and does not include an in-the-wild deployment, and frame-based results from prior work were converted to sample-wise predictions for comparability.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 11 Not valid · 48 Not checked · 80 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Through an extensive experimental evaluation on three standard benchmarks (Opportunity, PAMAP2, Skoda) we demonstrate the excellent recognition capabilities of our approach and its potential for real-life applications of human activity recognition.”
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By outperforming the state-of-the-art our results indicate increased robustness of our Ensembles of deep LSTM learners with regards to typical challenges of human activity recognition in ubiquitous and wearable computing scenarios.”
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We demonstrate that Ensembles of deep LSTM learners outperform individual LSTM networks and thus push the state-of-the-art in human activity recognition using wearables.”
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“strong learners -LSTM models in our case- can indeed be integrated into very effective ensembles that outperform single, that is, individual models. Recognition results are consistent across all three tasks”
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“PAMAP2 does not benefit from diversity in loss function”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
55 more claims
Create a free account to see all 139 claims and to verify the 62 references still open.
- It may state two separate claims as one. 32
- The quote only partly states this claim. 2
- Probably not a substantial claim. 59
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Many wearables datasets exhibit substantial class imbalance [68].”
From Past, Present, and Future of Sensor-based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task (2025) · cites this paper as [68]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3.2 Modified Training for LSTM Models · p. 12
“Overall, only a total of ˆ B ⌊ T/ ˆ B ⌋ samples are used in each epoch.”
§ ALGORITHM 1: Epoch-wise bagging for LSTM learners. · p. 13
“while L seq ≤ ⌊ T/ ˆ B j ⌋ do draw random integer ˆ L i (i.e., frame length) from discrete uniform distribution U ( L low , L high ) ;”
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325
Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations
Rumelhart, D. E., McClelland, J. L., & AU (1986) · doi:10.7551/mitpress/5236.001.0001 · Cited by 15,686
The Computer for the 21st Century
Weiser, M. (1991) · Scientific American · doi:10.1038/scientificamerican0991-94 · Cited by 10,017
Large-Scale Machine Learning with Stochastic Gradient Descent
Bottou, L. (2010) · Proceedings of COMPSTAT'2010 · doi:10.1007/978-3-7908-2604-3_16 · Cited by 5,795
Kittler, J., Hatef, M., Duin, R. P. W., & Matas, J. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.667881 · Cited by 5,290 · cited 5×
“Independent of the cause for diversity in base classifiers (in our case LSTMs) the meta-optimisation objective for classifier Ensembles is to generate classifiers that are diverse and minimally correlated [Kittler et al. 1998].”
BackgroundMethodInfluentialThe Strength of Weak Learnability
Schapire, R. E. (1990) · Machine Learning · doi:10.1007/bf00116037 · Cited by 4,600
Combining Pattern Classifiers: Methods and Algorithms
Bagui, S. C. (2005) · Technometrics · doi:10.1198/tech.2005.s320 · Cited by 3,202 · cited 2×
“It has been shown that classifier Ensembles have great potential to outperform traditional single classifier systems especially on challenging recognition tasks [Kuncheva 2004].”
BackgroundMethodCombining Pattern Classifiers: Methods and Algorithms
Kuncheva, L. I. (2004) · Wiley eBooks · doi:10.1002/0471660264 · Cited by 3,005 · cited 2×
“It has been shown that classifier Ensembles have great potential to outperform traditional single classifier systems especially on challenging recognition tasks [Kuncheva 2004].”
BackgroundMethodDeep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761
Parallel & distributed processing
Slusallek, P., Shirley, P., Mark, W., Stoll, G., & Wald, I. (2005) · ACM SIGGRAPH 2005 Courses on - SIGGRAPH '05 · doi:10.1145/1198555.1198750 · Cited by 2,568
Ensembling neural networks: Many could be better than all
Zhou, Z.-H., Wu, J., & Tang, W. (2002) · Artificial Intelligence · doi:10.1016/s0004-3702(02)00190-x · Cited by 1,964 · cited 1×
“The most popular strong base learners include decision trees [Breiman 2001], neural networks [Zhou et al. 2002], or kernel methods [Valentini and Dietterich 2004], and the corresponding variances are significantly reduced through bagging, yielding improved generalisation capabilities.”
BackgroundA tutorial on human activity recognition using body-worn inertial sensors
Bulling, A., Blanke, U., & Schiele, B. (2014) · ACM Computing Surveys · doi:10.1145/2499621 · Cited by 1,668 · cited 7×
“The majority of related work in HAR utilises (variants of) the well established sliding-window, frame-based analysis approach [Bulling et al. 2014].”
BackgroundMethodInfluentialStatic Analysis of Shape in TensorFlow Programs
The Theano Development Team, Al‐Rfou, R., Alain, G., Almahairi, A., Angermueller, C., Bahdanau, D., Ballas, N., Bastien, F., Bayer, J., Belikov, A., et al. (2016) · arXiv (Cornell University) · doi:10.4230/lipics.ecoop.2020.15 · Cited by 1,589
Introducing a New Benchmarked Dataset for Activity Monitoring
Reiss, A., & Stricker, D. (2012) · 2012 16th International Symposium on Wearable Computers · doi:10.1109/iswc.2012.13 · Cited by 1,456 · cited 2×
“We evaluate our method on three standard benchmark datasets, namely the Opportunity challenge [Chavarriaga et al. 2013], PAMAP2 [Reiss and Stricker 2012], and the Skoda dataset [Stiefmeier et al. 2008].”
BackgroundMethodThere is more to context than location
Schmidt, A., Beigl, M., & Gellersen, H.-W. (1999) · Computers & Graphics · doi:10.1016/s0097-8493(99)00120-x · Cited by 1,083 · cited 1×
“HAR has become one of the pillars of the third generation of computing [Schmidt et al. 1999] and it is more than likely that future developments will depend on robust and reliable activity recognition from sensor data as well [Abowd 2016].”
BackgroundSensor-Based Activity Recognition
Chen, L., Hoey, J., Nugent, C. D., Cook, D. J., & Yu, Z. (2012) · IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) · doi:10.1109/tsmcc.2012.2198883 · Cited by 1,074 · cited 1×
“We argue that HAR can now safely be considered common knowledge and thus refer to seminal papers and tutorials such as [Bulling et al. 2014; Chen et al. 2012; Avci et al. 2010].”
Background(2015) · Cited by 989
Convolutional Neural Networks for Human Activity Recognition using Mobile Sensors
Zeng, M., Nguyen, L. T., Yu, B., Mengshoel, O. J., Zhu, J., Wu, P., & Zhang, J. (2014) · Proceedings of the 6th International Conference on Mobile Computing, Applications and Services · doi:10.4108/icst.mobicase.2014.257786 · Cited by 876 · cited 3×
“A multitude of applications are based on CNNs, including but not limited to [Zeng et al. 2014; Ronaoo and Cho 2015; Yang et al. 2015; Rad et al. 2015].”
BackgroundMethodThe Opportunity challenge: A benchmark database for on-body sensor-based activity recognition
Chavarriaga, R., Sagha, H., Calatroni, A., Digumarti, S. T., Tröster, G., Millán, J. D. R., & Roggen, D. (2013) · Pattern Recognition Letters · doi:10.1016/j.patrec.2012.12.014 · Cited by 742
Wearable Assistant for Parkinson’s Disease Patients With the Freezing of Gait Symptom
Bachlin, M., Plotnik, M., Roggen, D., Maidan, I., Hausdorff, J. M., Giladi, N., & Troster, G. (2010) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2009.2036165 · Cited by 693 · cited 1×
“For example, freeze of gait in Parkinson’s is a common problem amongst patients but throughout the day such freezing episodes are rare – though very critical w.r.t. health and wellbeing of the patient and thus require reliable recognition (e.g., [Bachlin et al. 2010]).”
BackgroundThe Elements of Statistical Learning
Sapatinas, T. (2004) · Journal of the Royal Statistical Society Series A: Statistics in Society · doi:10.1111/j.1467-985x.2004.298_11.x · Cited by 635
Deep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables
Hammerla, N. Y., Halloran, S., & Ploetz, T. (2016) · arXiv · doi:10.48550/arxiv.1604.08880 · Cited by 606 · cited 22×
“Note that we report sample-wise prediction results, which is according to our overall motivation and in line with previous work [Hammerla et al. 2016] but di↵erent to frame-wise results as, for example, reported in [Ordóñez and Roggen 2016].”
BackgroundMethodResultInfluentialAvci, A., Bosch, S., Marin-Perianu, M., Marin-Perianu, R., & Havinga, P. (2010) · University of Twente Research Information · Cited by 563
Constructing support vector machine ensemble
Kim, H.-C., Pang, S., Je, H.-M., Kim, D., & Yang Bang, S. (2003) · Pattern Recognition · doi:10.1016/s0031-3203(03)00175-4 · Cited by 478 · cited 1×
“However, in recent years it has been shown that Ensemble classification is even more e↵ective when strong base classifiers are integrated (e.g., [Kim et al. 2003]).”
BackgroundLarge-Scale Machine Learning with Stochastic Gradient Descent
Bottou, L. (2011) · Chapman & Hall/CRC Computer Science & Data Analysis · doi:10.1201/b11429-4 · Cited by 460
Digits: freehand 3D interactions anywhere using a wrist-worn gloveless sensor
Kim, D., Hilliges, O., Izadi, S., Butler, A. D., Chen, J., Oikonomidis, I., & Olivier, P. (2012) · Proceedings of the 25th annual ACM symposium on User interface software and technology · doi:10.1145/2380116.2380139 · Cited by 428 · cited 2×
“…innovative sensing and analysis approaches that target a plethora of application areas, including but not limited to novel interaction techniques [Kim et al. 2012], situated support in smart environments [Hoey et al. 2011], automated health [Plötz et al. 2012] and wellbeing assessments [Kranz…”
BackgroundBagging, Boosting and Ensemble Methods
Bühlmann, P. (2012) · Handbook of Computational Statistics · doi:10.1007/978-3-642-21551-3_33 · Cited by 375
Wearable Activity Tracking in Car Manufacturing
Stiefmeier, T., Roggen, D., Ogris, G., Lukowicz, P., & Tr, G. (2008) · IEEE Pervasive Computing · doi:10.1109/mprv.2008.40 · Cited by 367 · cited 4×
“We evaluate our method on three standard benchmark datasets, namely the Opportunity challenge [Chavarriaga et al. 2013], PAMAP2 [Reiss and Stricker 2012], and the Skoda dataset [Stiefmeier et al. 2008].”
BackgroundMethodInfluentialFeature Learning for Activity Recognition in Ubiquitous Computing
Plötz, T., Hammerla, N., & Olivier, P. (2011) · Newcastle University · doi:10.25405/ncl.34175319 · Cited by 337
Self-citationDeepEar: robust smartphone audio sensing in unconstrained acoustic environments using deep learning
Lane, N. D., Georgiev, P., & Qendro, L. (2015) · Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2750858.2804262 · Cited by 310
Dieleman, S., Schlüter, J., Raffel, C., Olson, E. M., Sønderby, S. K., Nouri, D., Maturana, D., Thoma, M., Battenberg, E., Kelly, J., et al. (2015) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.27878 · Cited by 279
The strength of weak learnability
Schapire, R. E. (1989) · 30th Annual Symposium on Foundations of Computer Science · doi:10.1109/sfcs.1989.63451 · Cited by 257
Bias-Variance Analysis of Support Vector Machines for the Development of SVM-Based Ensemble Methods
Valentini, G., & Dietterich, T. G. (2004) · doi:10.5555/1005332.1016783 · Cited by 250
Ensemble deep learning for speech recognition
Deng, L., & Platt, J. C. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-433 · Cited by 248 · cited 1×
“…for Ensemble learning of sets of deep neural networks have been applied successfully to speech recognition applications where class posterior probabilities as computed by convolutional, recurrent, and fully-connected deep neural networks are integrated into an Ensemble [Deng and Platt 2014].”
MethodBhattacharya, S., & Lane, N. D. (2016) · Proceedings of the 14th ACM Conference on Embedded Networked Sensor Systems CD-ROM · doi:10.1145/2994551.2994564 · Cited by 236
Deep Activity Recognition Models with Triaxial Accelerometers
Alsheikh, M. A., Selim, A., Niyato, D. T., Doyle, L., Lin, S., & Tan, H.-P. (2015) · DR-NTU (Nanyang Technological University) · Cited by 204
The mobile fitness coach: Towards individualized skill assessment using personalized mobile devices
Kranz, M., Möller, A., Hammerla, N., Diewald, S., Plötz, T., Olivier, P., & Roalter, L. (2013) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2012.06.002 · Cited by 199
Self-citationPD Disease State Assessment in Naturalistic Environments Using Deep Learning
Hammerla, N., Fisher, J., Andras, P., Rochester, L., Walker, R., & Ploetz, T. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9484 · Cited by 179 · cited 4×
“Based on this, subsequent works explored the e↵ectiveness of pre-trained, fully-connected RBM networks, for example, for automated assessments of disease states in Parkinson’s patients [Hammerla et al. 2015], in combination with more traditional sequence models (HMMs) [Zhang et al.”
BackgroundMethodInfluentialSelf-citationThe Cauchy-Schwarz Master Class: An Introduction to the Art of Mathematical Inequalities
Garling, D. J. H., & Steele, J. M. (2005) · American Mathematical Monthly · doi:10.2307/30037539 · Cited by 139
Hammerla, N. Y., Kirkham, R., Andras, P., & Ploetz, T. (2013) · Proceedings of the 2013 International Symposium on Wearable Computers · doi:10.1145/2493988.2494353 · Cited by 138 · cited 2×
“2014] or on more sophisticated transformations [Hammerla et al. 2013], which is in line with the majority of recent, Deep Learning based analysis methods in the field of human activity recognition using wearable sensing platforms.”
MethodResultSelf-citationMorales, F. J. O., & Roggen, D. (2016) · Proceedings of the 2016 ACM International Symposium on Wearable Computers · doi:10.1145/2971763.2971764 · Cited by 136 · cited 4×
“(c) Combinations of CNN and LSTM (c/o [Morales and Roggen 2016]).”
BackgroundMethodInfluentialDeep Activity Recognition Models with Triaxial Accelerometers
Alsheikh, M. A., Selim, A., Niyato, D., Doyle, L., Lin, S., & Tan, H.-P. (2015) · arXiv · doi:10.48550/arxiv.1511.04664 · Cited by 126 · cited 2×
“2015], in combination with more traditional sequence models (HMMs) [Zhang et al. 2015; Alsheikh et al. 2016], and very successfully for auditory scene analysis in Ubicomp applications [Lane et al.”
BackgroundMethodAutomatic assessment of problem behavior in individuals with developmental disabilities
Plötz, T., Hammerla, N., Rozga, A., Reavis, A. R., Call, N. A., & Abowd, G. D. (2012) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2370216.2370276 · Cited by 125
Self-citationClimbAX: skill assessment for climbing enthusiasts
Ladha, C., Hammerla, N., Olivier, P. L., & Plötz, T. (2013) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2493432.2493492 · Cited by 122 · cited 2×
“…interaction techniques [Kim et al. 2012], situated support in smart environments [Hoey et al. 2011], automated health [Plötz et al. 2012] and wellbeing assessments [Kranz et al. 2012], health care automation [Avci et al. 2010], sports tracking and coaching [Ladha et al. 2013] to name but a few.”
BackgroundSelf-citationRapid specification and automated generation of prompting systems to assist people with dementia
Hoey, J., Plötz, T., Jackson, D., Monk, A. F., Pham, C., & Olivier, P. L. (2010) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2010.11.007 · Cited by 116 · cited 2×
“…plethora of application areas, including but not limited to novel interaction techniques [Kim et al. 2012], situated support in smart environments [Hoey et al. 2011], automated health [Plötz et al. 2012] and wellbeing assessments [Kranz et al. 2012], health care automation [Avci et al. 2010],…”
BackgroundSelf-citationLet's (not) stick together: pairwise similarity biases cross-validation in activity recognition
Hammerla, N. Y., & Plötz, T. (2015) · Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2750858.2807551 · Cited by 91
Self-citationMaximum expected F-measure training of logistic regression models
Jansche, M. (2005) · doi:10.3115/1220575.1220662 · Cited by 88
Dembczyński, K., Jachnik, A., Kotłowski, W., Waegeman, W., & Hüllermeier, E. (2013) · Open access LMU (Ludwid Maxmilian's Universitat Munchen) · Cited by 79
When Ensemble Learning Meets Deep Learning: a New Deep Support Vector Machine for Classification
Qi, Z., Wang, B., Tian, Y., & Zhang, P. (2016) · Knowledge-Based Systems · doi:10.1016/j.knosys.2016.05.055 · Cited by 76 · cited 1×
“Examples of deep learning Ensembles include the combination of Support Vector Machines (SVM) into classifier Ensembles [Qi et al. 2016].”
BackgroundBeyond Weiser: From Ubiquitous to Collective Computing
Abowd, G. D. (2016) · Computer · doi:10.1109/mc.2016.22 · Cited by 75
Beyond activity recognition: skill assessment from accelerometer data
Khan, A., Mellor, S., Berlin, E., Thompson, R. J., McNaney, R., Olivier, P. L., & Plötz, T. (2015) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2750858.2807534 · Cited by 72 · cited 2×
“Most prominently, issues with real-life datasets, typically including imbalanced datasets and problematic data quality, still limit the e↵ectiveness of activity recognition using wearables.”
BackgroundSelf-citationHuman activity recognition with HMM-DNN model
Zhang, L., Wu, X. H., & Luo, D. (2015) · IEEE International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) · doi:10.1109/icci-cc.2015.7259385 · Cited by 52 · cited 2×
“2015], in combination with more traditional sequence models (HMMs) [Zhang et al. 2015; Alsheikh et al. 2016], and very successfully for auditory scene analysis in Ubicomp applications [Lane et al.”
BackgroundMethodActivity Recognition and Healthier Food Preparation
Plötz, T., Moynihan, P. J., Pham, C., & Olivier, P. L. (2011) · Atlantis ambient and pervasive intelligence · doi:10.2991/978-94-91216-05-3_14 · Cited by 45 · cited 1×
“Apart from potential subsampling and modality fusion, sensor data are used ”as is” that is without employing feature extraction methods be it based on heuristics [Ploetz et al. 2010; Bulling et al. 2014] or on more sophisticated transformations [Hammerla et al.”
MethodSelf-citationRonao, C. A., & Cho, S. (2015) · 한국정보과학회 학술발표논문집 · Cited by 41
Ensemble of deep long short term memory networks for labelling origin of replication sequences
Singh, U., Chauhan, S., Krishnamachari, A., & Vig, L. (2015) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2015.7344871 · Cited by 26 · cited 1×
“For example, [Singh et al. 2015] employed three variants of LSTM networks (vanilla deep LSTM, and two variants of bi-directional LSTMs) in parallel for biological sequence analysis and then applied majority voting for final classification.”
MethodConvolutional Neural Network for Stereotypical Motor Movement Detection in AutismPreprint
Rad, N. M., Bizzego, A., Kia, S. M., Jurman, G., Venuti, P., & Furlanello, C. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.01865 · Cited by 26 · cited 1×
“A multitude of applications are based on CNNs, including but not limited to [Zeng et al. 2014; Ronaoo and Cho 2015; Yang et al. 2015; Rad et al. 2015].”
BackgroundDiversity encouraged learning of unsupervised LSTM ensemble for neural activity video predictionPreprint
Song, Y., Viventi, J., & Wang, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.04899 · Cited by 2 · cited 1×
“Most related to our work, [Song et al. 2016] have described a system that utilises Ensembles of LSTM learners for predicting actions from video data.”
Research works printed but not linked: 2
- James L McClelland and David E Rumelhart . 1986. Parallel distributed processing . MIT Press . James L McClelland and David E Rumelhart. 1986. Parallel distributed processing. MIT Press.
- Theano Development Team . 2016 . Theano: A Python framework for fast computation of mathematical expressions. arXiv e-prints abs/1605.02688 (May 2016). http://arxiv.org/abs/1605.02688 Theano Development Team. 2016. Theano: A Python framework for fast computation of mathematical expressions. arXiv e-prints abs/1605.02688 (May 2016). http://arxiv.org/abs/1605.02688 · arXiv
Cited by
Deep learning for sensor-based activity recognition: A survey
Wang, J., Chen, Y., Hao, S., Peng, X., & Hu, L. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.02.010 · Cited by 2,014
“(Guan and Ploetz, 2017) Body-worn, object, ambient RNN ADL, smart home D01, D02, D04”
BackgroundMethodNweke, H. F., Teh, Y. W., Al-garadi, M. A., & Alo, U. R. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.03.056 · Cited by 930
Deep Learning for Sensor-based Human Activity Recognition
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2022) · ACM Computing Surveys · doi:10.1145/3447744 · Cited by 690
“st a certain percentage of data in the training set. Another direction of solving the imbalance concern is to modify the model-building strategy instead of directly balancing the training dataset. In [49], Guan and Plötz utilized the F1-score rather than the conventional cross-entropy as the loss function to address t…”
BackgroundMethodQiu, S., Zhao, H., Jiang, N., Wang, Z., Liu, L., An, Y., Zhao, H., Miao, X., Liu, R., & Fortino, G. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.11.006 · Cited by 671
Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi
Zheng, Y., Zhang, Y., Qian, K., Zhang, G., Liu, Y., Wu, C., & Yang, Z. (2019) · Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3307334.3326081 · Cited by 557
“Traditional approaches use cameras [16, 24, 42], wearable devices and phones [8, 17, 36] or sonar [22, 29, 48] as the sensing module.”
Method
Metadata
- Authors
- Guan, Y., & Plötz, T.
- Affiliations
- Newcastle University (GB)
- Georgia Institute of Technology (US)
- ORCID
- Guan, Yu
- Venue
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Published
- 2017-06-30
- Volume
- 1
- Issue
- 2
- Pages
- 1-28
- ISSN
- 2474-9567 (ISSN-L)
- OpenAlex
- W2604630936
- Cited by
- 511
- References
- 65
- Citations by year
- 2026: 33 · 2025: 35 · 2024: 59 · 2023: 60 · 2022: 70 · 2021: 82 · 2020: 87 · 2019: 46 · 2018: 33 · 2017: 6
- FWCI
- 19.53
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Engineering and Physical Sciences Research Council (EP/M020576/1)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Gait Recognition and Analysis
- Keywords
- human activity recognition, wearable sensors, deep learning, ensemble classifiers, class imbalance, data quality, training protocols, PAMAP2, Opportunity dataset
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.