Summary of the Cooking Activity Recognition Challenge

Alia, Sayeda Shamma; Lago, Paula; Takeda, Shingo; Adachi, Keiichiro; Benaissa, Brahim; Ahad, Md. Atiqur Rahman; Inoue, Sozo

doi:10.1007/978-981-15-8269-1_1

Cited by 15 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cooking activity data set [ 6 , 16 ] provides accelerometer signals from four subjects during the preparation of three meals (sandwich, salad, and cereals). Four smart devices collected signals at four body locations (smartphone at the right arm and the left hip, smartwatches at the wrists).…”

Section: Resultsmentioning

confidence: 99%

“…Alia et al [ 16 ] summarized the “Cooking Activity Recognition Challenge”. The task was to classify micro- and macro-activities in three cooking recipes based on predefined windows of accelerometer and motion capture data.…”

Section: Related Workmentioning

confidence: 99%

“…For better readability, we assign the following numeric codes to the cooking activities. 0: cut, 1: mix, 2: open, 3: peel, 4: pour, 5: put, 6: take, 7: wash. With the help of [ 16 ], we have identified the following cooking activity sequences per recipe. Sandwich: 60567056705, 67056056705, 67056705605; cereal: 630565624, 656246305, 656305624; fruitsalad: 63056305630561.…”

Section: Appendix A1 Cooking Activity Data Setmentioning

confidence: 99%

“…The distinction between human micro- and macro-activities, however, is a more general problem that is not particularly restricted to the sports domain. In 2020, a macro-activity recognition competition [ 16 ] challenged participants to accurately detect macro-activities and their micro-activities in cooking scenarios. For example, the macro-activity preparing salad consists of various micro-activities, such as taking some vegetables, washing them, slicing them, and putting them in a bowl [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Detection and Validation of Macro-Activities in Human Inertial Signals Using Graph Link Prediction

Wieland,

Pankratius

2024

Sensors

View full text Add to dashboard Cite

With the continuous development of new wearable devices, sensor-based human activity recognition is enjoying enormous popularity in research and industry. The signals from inertial sensors allow for the detection, classification, and analysis of human activities such as jogging, cycling, or swimming. However, human activity recognition is often limited to basic activities that occur in short, predetermined periods of time (sliding windows). Complex macro-activities, such as multi-step sports exercises or multi-step cooking recipes, are still only considered to a limited extent, while some works have investigated the classification of macro-activities, the automated understanding of how the underlying micro-activities interact remains an open challenge. This study addresses this gap through the application of graph link prediction, a well-known concept in graph theory and graph neural networks (GNNs). To this end, the presented approach transforms micro-activity sequences into micro-activity graphs that are then processed with a GNN. The evaluation on two derived real-world data sets shows that graph link prediction enables the accurate identification of interactions between micro-activities and the precise validation of composite macro-activities based on learned graph embeddings. Furthermore, this work shows that GNNs can benefit from positional encodings in sequence recognition tasks.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Appendix A1 Cooking Activity Data Setmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection and Validation of Macro-Activities in Human Inertial Signals Using Graph Link Prediction

Wieland,

Pankratius

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…However, until recently, very little attention was given to the recognition of activities in professional contexts. Special interest seems to be rising for tracking the activities of medical practitioners, such as doctors and nurses [26] and, in a smaller scale, activities such as cooking [27].…”

Section: Activity Recognition In Professional Contextsmentioning

confidence: 99%

Introducing VTT-ConIot: A Realistic Dataset for Activity Recognition of Construction Workers Using IMU Devices

et al. 2021

View full text Add to dashboard Cite

Sustainable work aims at improving working conditions to allow workers to effectively extend their working life. In this context, occupational safety and well-being are major concerns, especially in labor-intensive fields, such as construction-related work. Internet of Things and wearable sensors provide for unobtrusive technology that could enhance safety using human activity recognition techniques, and has the potential of improving work conditions and health. However, the research community lacks commonly used standard datasets that provide for realistic and variating activities from multiple users. In this article, our contributions are threefold. First, we present VTT-ConIoT, a new publicly available dataset for the evaluation of HAR from inertial sensors in professional construction settings. The dataset, which contains data from 13 users and 16 different activities, is collected from three different wearable sensor locations.Second, we provide a benchmark baseline for human activity recognition that shows a classification accuracy of up to 89% for a six class setup and up to 78% for a sixteen class more granular one. Finally, we show an analysis of the representativity and usefulness of the dataset by comparing it with data collected in a pilot study made in a real construction environment with real workers.

show abstract