SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.09396 · 2021

Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2104.09396.json · badge: /api/ran/2104.09396.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
srvCodes/continual-learning-benchmark canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
calculate_forgetting Ran
ran, honoured the contract we drafted
srvCodes/continual-learning-benchmark/train/result_analyser.py
code served (permissive licence) · get_code("1fb9333deb663b63")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned DataFrame. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
import pandas as pd
from statistics import stdev, mean

# Analyze the function to understand what data structures are needed:
# - sequence_to_previous_task_scores: dict of seq_id -> dict of task_id -> dict of prev_task_id -> scores
# - sequence_to_max_task_scores: dict of seq_id -> dict of prev_task_id -> max_score

# Build test data
sequence_to_previous_task_scores = {
    0: {
        0: {0: 0.8, 1: 0.7},
        1: {0: 0.75, 1: 0.85},
    },
    1: {
        0: {0: 0.9, 1: 0.6},
        1: {0: 0.7, 1: 0.8},
    }
}

sequence_to_max_task_scores = {
    0: {0: 1.0, 1: 1.0},
    1: {0: 1.0, 1: 1.0}
}

ARGS = {
    "sequence_to_previous_task_scores": sequence_to_previous_task_scores,
    "sequence_to_max_task_scores": sequence_to_max_task_scores
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
pickle_reader Ran
ran, honoured the contract we drafted
srvCodes/continual-learning-benchmark/train/result_analyser.py
code served (permissive licence) · get_code("61898baa0540b707")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import pickle
import tempfile
import os

# Create a temporary pickle file with sample accuracy data
temp_dir = tempfile.gettempdir()
temp_filename = os.path.join(temp_dir, "test_accuracies.pkl")

# Create sample accuracies data
sample_accuracies = [0.85, 0.87, 0.89, 0.91, 0.92]

# Write to pickle file
with open(temp_filename, 'wb') as f:
    pickle.dump(sample_accuracies, f)

ARGS = {
    'filename': temp_filename
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
calculate_forgetting 1 other paper
1 dated earlier
2007.03032 (2020-07)
Continual Learning in Human Activity Recognition: an Empirical Analysis of Regularization
pickle_reader 1 other paper
1 dated earlier
2007.03032 (2020-07)
Continual Learning in Human Activity Recognition: an Empirical Analysis of Regularization

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Sensor-based human activity recognition (HAR), i.e., the ability to discover human daily activity patterns from wearable or embedded sensors, is a key enabler for many real-world applications in smart homes, personal healthcare, and urban planning. However, with an increasing number of applications being deployed, an important question arises: how can a HAR system autonomously learn new activities over a long period of time without being re-engineered from scratch? This problem is known as continual learning and has been particularly popular in the domain of computer vision, where several techniques to attack it have been developed. This paper aims to assess to what extent such continual learning techniques can be applied to the HAR domain. To this end, we propose a general framework to evaluate the performance of such techniques on various types of commonly used HAR datasets. We then present a comprehensive empirical analysis of their computational cost and effectiveness of tackling HAR-specific challenges (i.e., sensor noise and labels' scarcity). The presented results uncover useful insights on their applicability and suggest future research directions for HAR systems. Our code, models and data are available at https://github.com/srvCodes/continual-learning-benchmark.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.09396")
get_code_for_paper("2104.09396")
have("2104.09396")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.09396.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.09396.svg)](https://syntology.ai/paper/2104.09396)

Connect an agent — have() is free.