Figure 1.
Sequence of activated sensors by daily activity, cooking breakfast.
Citation: Mario P. Carante, Francesca Ballarini. Modelling cell death for cancer hadrontherapy[J]. AIMS Biophysics, 2017, 4(3): 465-490. doi: 10.3934/biophy.2017.3.465
| [1] | Yunqian Yu, Zhenliang Hao, Guojie Li, Yaqing Liu, Run Yang, Honghe Liu . Optimal search mapping among sensors in heterogeneous smart homes. Mathematical Biosciences and Engineering, 2023, 20(2): 1960-1980. doi: 10.3934/mbe.2023090 |
| [2] | Ray-Ming Chen . Extracted features of national and continental daily biweekly growth rates of confirmed COVID-19 cases and deaths via Fourier analysis. Mathematical Biosciences and Engineering, 2021, 18(5): 6216-6238. doi: 10.3934/mbe.2021311 |
| [3] | Sakorn Mekruksavanich, Anuchit Jitpattanakul . RNN-based deep learning for physical activity recognition using smartwatch sensors: A case study of simple and complex activity recognition. Mathematical Biosciences and Engineering, 2022, 19(6): 5671-5698. doi: 10.3934/mbe.2022265 |
| [4] | Keruo Jiang, Zhen Huang, Xinyan Zhou, Chudong Tong, Minjie Zhu, Heshan Wang . Deep belief improved bidirectional LSTM for multivariate time series forecasting. Mathematical Biosciences and Engineering, 2023, 20(9): 16596-16627. doi: 10.3934/mbe.2023739 |
| [5] | Xiaoguang Liu, Meng Chen, Tie Liang, Cunguang Lou, Hongrui Wang, Xiuling Liu . A lightweight double-channel depthwise separable convolutional neural network for multimodal fusion gait recognition. Mathematical Biosciences and Engineering, 2022, 19(2): 1195-1212. doi: 10.3934/mbe.2022055 |
| [6] | Wajid Aziz, Lal Hussain, Ishtiaq Rasool Khan, Jalal S. Alowibdi, Monagi H. Alkinani . Machine learning based classification of normal, slow and fast walking by extracting multimodal features from stride interval time series. Mathematical Biosciences and Engineering, 2021, 18(1): 495-517. doi: 10.3934/mbe.2021027 |
| [7] | Tianjun Lu, Xian Zhong, Luo Zhong, RuiqiLuo . A location-aware feature extraction algorithm for image recognition in mobile edge computing. Mathematical Biosciences and Engineering, 2019, 16(6): 6672-6682. doi: 10.3934/mbe.2019332 |
| [8] | Shangbin Li, Yu Liu . Human motion recognition based on Nano-CMOS Image sensor. Mathematical Biosciences and Engineering, 2023, 20(6): 10135-10152. doi: 10.3934/mbe.2023444 |
| [9] | Xihe Qiu, Xiaoyu Tan, Chenghao Wang, Shaotao Chen, Bin Du, Jingjing Huang . A long short-temory relation network for real-time prediction of patient-specific ventilator parameters. Mathematical Biosciences and Engineering, 2023, 20(8): 14756-14776. doi: 10.3934/mbe.2023660 |
| [10] | Xiaoguang Liu, Yubo Wu, Meng Chen, Tie Liang, Fei Han, Xiuling Liu . A double-channel multiscale depthwise separable convolutional neural network for abnormal gait recognition. Mathematical Biosciences and Engineering, 2023, 20(5): 8049-8067. doi: 10.3934/mbe.2023349 |
Smart homes aim to provide a comfortable, convenient, and efficient living environment and effectively alleviate the impact of the functional decline [1,2]. Besides, smart home is also designed to improve energy management [3,4,5]. The premise of achieving the goal is to accurately recognize daily activities, which take place in smart homes. To achieve good activity recognition performance, several approaches have been proposed. Existing approaches focus on different stages of the process of activity recognition [6]. Some approaches focus on stages such as, segmenting sensor event streams [7,8,9,10], extracting and selecting daily activity features [11,12,13,14,15], and developing recognition models [16,17,18,19]. In this paper, the proposed approach focuses on extracting and selecting daily activity features.
The primary task of extracting and selecting daily activity features is to establish a feature space and generate a sample space. Daily activity features are divided into temporal and sensor features. Temporal features include the start time, end time, and duration of the daily activity. For the sensor features, while some approaches take all smart home sensors as the feature space, others take the sets or sequences of frequency sensors as the feature space. For a given sensor feature and daily activity, most of the approaches take the frequency activated in the daily activity as the value of the sensor feature. The existing common practice for extracting daily activity features is discretizing sensor event streams. This widespread practice leads to the character loss of the time series of sensor event streams and limits the improvement of activity recognition performance.
To utilize the character of the time series of sensor event streams to improve activity recognition performance, this paper proposes a novel approach for extracting daily activity features. As compared with existing approaches, the proposed approach achieves better activity recognition performance. The main contributions of this paper are as follows.
(1) An algorithm that serves to extract time series data from sensor event streams is proposed.
(2) Several common statistic formulas are proposed to establish an initial feature space.
(3) A feature selection algorithm is employed to generate final daily activity features.
(4) The proposed approach is evaluated on two common datasets. The experiment results show that the proposed approach achieves better performance than previous approaches for solving daily activity features.
The rest of this paper is arranged as follows: First, related work is introduced; the proposed approach is then introduced; the proposed approach is validated and results discussed. Finally, we summarize our findings.
Approaches for activity recognition in smart homes can be divided into knowledge-driven and data-driven approaches. For knowledge-driven approaches, an activity model is developed as a reusable context model, which associates objects, space, and time with activities. The knowledge driven model is semantically clear and follows an agreed indication. Logic language and ontology are the two most common models representing domain knowledge [20,21,22,23,24,25,26]. After the knowledge model is established, logical reasoning is employed to perform activity recognition. Knowledge-driven approaches are robust but face limitations in the case of uncertain data.
Data-driven approaches adopt data mining and machine learning techniques to develop the activity recognition model. Conventional classification algorithms e. g. Naive Bayesian (NB) [27,28,29,30], Hidden Markov Model (HMM) [31,32], Dynamic Bayesian Network (DBN) [33], Support Vector Machine (SVM) [34], Conditional Random Field (CRF) [35], and Recursive Neural Network (RNN) [36] have been widely used in activity recognition tasks. Besides conventional classification algorithms, some specialized algorithms were invented. Wan et al. proposed a novel activity recognition model called COBRA. COBRA mixed the combined sliding window with a logistic regression model for near-real-time activity recognition [37]. To deal with the problem of class imbalance and improve the performance of the model, Medina-Quero et al. developed an integrated classifier based on long short-term memory (LSTM) to recognize daily activities [38].
Besides classification algorithms, the fine features of daily activities are equally vital to activity recognition performance. Daily activity features can be divided into temporal and sensor features. The temporal features space usually includes the time when a daily activity starts, its duration, and when it ends. The sensor features space is generated directly or indirectly from the set of initial sensors. Liu et al. take the set of initial sensors as the sensor features space and a sensor as a daily activity feature [39]. Because the relationship between sensors is lost when a sensor is taken as a daily activity feature, daily activities which activate similar sensors are hard to differentiate. To improve activity recognition performance, the frequent items mining method [40], frequent periodic pattern mining method [41], and activity modelling based on a low-dimensional feature space [42] were proposed. In addition, Wen et al. and Nasreen et al. used the association rules mining method to mine frequent sensor combinations, to conduct activity modelling for the low-dimensional feature space [43,44]. Twomey proposed an unsupervised method to learn the topology structure of sensors in a smart home and mined effective combinations of sensor events as daily behaviour characteristics, according to the topology structure [45]. Yatbaz et al. [46] used a Scanpath Trend Analysis (STA) method to set a priority for sensors to obtain sensor combinations that represent daily activity features, to improve the evaluation standard of the model. Compared to the approach where a sensor is taken as a daily activity feature, these approaches consume more computing resources, even if activity recognition performance is slightly improved.
For sensor features, truth value, frequency, and density of the activated sensors are the most common eigenvalues [47]. In addition, the term frequency-inverse document frequency (TF-IDF) formula [8], mutual information formula [48], deep learning technology [49], and differential representation between different activities were employed to compute these eigenvalues [50]. However, these above mentioned strategies for estimating the eigenvalues generate only shallow features, which are far from adequate when describing the nature of the time series of sensor event streams. This paper performs an in-depth feature mining on the time series data, which can preserve the essential information of the time itself. Consequently, the proposed approach can be extended to promote the user activity recognition model.
In a smart home, different types of non-invasive sensors e.g. infrared motion sensors, and temperature sensors, are deployed in different parts of the house. When residents carry on daily activities e.g. sleeping, and bathing, corresponding sensor readings are generated accordingly. Figure 1 shows a sequence of sensors triggered by cooking breakfast as a daily activity. Each line denotes a sensor event. Each activated sensor is recorded as a sensor event se, denoted as a four tuple; se = (D, T, I, R). D and T are the date and the time when the se is generated, respectively; I is the identification of the activated sensor, and R is the sensor reading. For example, the sensor event shown in line 1 is generated at 07:58:39.655022 on 2011-06-15. The activated sensor is M007 with a reading ON.
Based on the nature time series of sensor events, 6 categories of common daily activity features are proposed in form of statistic formulas. Each statistic formula corresponds to a given time series. Throughout this section, T = < t1, t2, …, tn > denotes a time series, where tiis the ith time value of a given time series.
(1) Mean: µ(T) returns the mean of T. µ(T) is defined in formula (1).
| μ(T)=∑tin | (1) |
(2) Standard Deviation: σ(T) returns the standard deviation of T. σ(T) is defined in formula (2).
| σ(T)=√∑(ti−μ)2n−1 | (2) |
(3) Skewness: Skew(T) returns the skewness of T. Skew(T) is defined in formula (3).
| Skew(T)=μ3σ3 | (3) |
(4) Slope: Slope(T) returns the slope of the linear least-squares regression for the values of T. Slope(T) is defined in formula (4).
| Slope(T)=slope(llsr(T)) | (4) |
Where llsr returns the linear least-squares regression for the values of T.
(5) Wave: Wave(T) returns the number of troughs and peaks and of T. Wave(T) is defined in formula (5).
| Wave(T)=peaks(T)+troughs(T) | (5) |
Where peaks returns the number of peaks of T. troughs returns the number of troughs of T.
(6) Wavelet Transform Coefficients: For two specified parameters w and t∈T, CWTC(t, w) returns continuous wavelet transform coefficients. CWTC(t, w) is defined in formula (6). cwt(t, w) returns a continuous wavelet transform for the ricker wavelet of the wavelet function.
| CWTC(t,w)=wavelettransformcoefficients(t,w,cwt(t,w)) | (4.1) |
| cwt(t,w)=2√3⋅w⋅π14(1−t2w2)exp(−t22⋅w2) | (6.2) |
Where w is the width parameter in the wavelet transform function, which is 2 in the experiment.
For a sequence of sensor events activated by a daily activity, time series data which is input to each feature category. Feature space is generated by Algorithm 1. Algorithm 1 can be divided into two stages. In the first stage (lines 4-12), the identification and times of each activated sensor are extracted. Activated times form time series data. In the second stage (lines 13-22), features are extracted using feature formulas with extracted time series data.
One drawback to the features of daily activity is the high dimension of feature set. To obtain the strong ability features and eliminate the weak ability ones, we need to use feature selection technique to optimize feature subset. In this paper, the SDSFS algorithm [51] is used to evaluate the activity recognition capability of these features.
In the initial phase, each agent is assigned to combine the features subset in their respective search spaces (all possible combinations of the features). Each agent will use an independent random split to divide the dataset into training and testing subsets according to a ratio of 4:1. The hypothesis is a binary string that represents the feature subset within the subset size. In the string, if the bit is 1, it contains its corresponding feature, if 0, it is not.
In the test phase, these activities of the agent are determined according to the average F-score of multiple classifiers in their fitness function, where the agent selects another random agent and compares them. If the F-score of the selected agent is more than that of the random agent, then the selected agent is set to active, otherwise it is set to inactive. The agents will repeat this process to determine their respective states. After that, the diffusion phase would ideally begin.
In the diffusion phase, both inactive and active agents choose other agents. If the randomly selected agent is active, it will offset the hypothesis (the feature subset), which will be shared with an inactive agent. Instead, the selected agents choose the new random hypothesis (the feature subset) from its search space (all feature combinations in the subset size). For offsetting, one of the features is randomly removed (by changing 1 to 0) with another randomly added one (by changing 0 to 1). This keeps the size of the subset. Besides, when the active agent picks another active agent that maintains a similar hypothesis, the selected agent will be set to inactive and assigned to a random hypothesis. This frees up all agents and increases diversity. Algorithm 2 is repeatedly executed until the maximum number of iterations (numIterations) is reached.
| Algorithm 1. featureExtraction |
| Input: S, deployed sensor identifications in smart house Φ, set of the proposed feature categories E, a sequence of sensor events activated by a daily activity a Output: F 1. F←Ø; 2. TS←Ø; 3. IS←Ø; // set of sensor identifications activated by a 4. while(true) 5. e←getNextSensorEvent(E); //Get next sensor event e in E. 6. (t, s)←extractTime & Sensor(e)//Extract T and I of e. 7. TS←TS∪{(T, I)}; 8. IS←IS∪{I}; 9. if(e is last traversed sensor event in E) then 10. break; 11. end if 12. end for 13. for each I in S 14. for each φ in Φ 15. if I∈IS then 16. TI 17. F←F∪{(I, j(TI))}; 18. else 19. F←F∪{(I, 0)}; 20. end if 21. end for 22. end for 23. return F |
| Algorithm 2. Description of SDSFS algorithm |
| Input: numIterations, the number of iterations numAgents, the number of agents Output: Optimal feature subset 1. //Initialisation phase 2. Assign numAgents agents to random hypotheses with inactive states, each agent represents a set of features. 3. while less than numIterations do 4. //Evaluation phase 5. for each agent in agents 6. Evaluate the fitness value; 7. Find the maximum fitness value; 8. end for 9. //Test phase 10. for each agent in agents 11. if Agent’s fitness > random agent’s fitness then 12. Set agent as active; 13. end if 14. end for 15. //Diffusion phase 16. for each agent in agents 17. if agent is inactive then 18. Select a random agent; 19. if selected agent is active then 20. Copy its hypothesis & offset it; 21. Evaluate the fitness value; 22. else 23. Pick a random hypothesis; 24. Evaluate the fitness value; 25. end if 26. end if 27. end for 28. end for 29. return Optimal feature subset |
Activity recognition performance depends on the daily activity feature. We use two common datasets “Cairo” and “Tulum2009” to evaluate the approaches for solving activity recognition performance of daily activity features. “Cairo” and “Tulum2009” are provided by the Washington State University [52]. The involved sensors and daily activities are listed in Table 1.
| Dataset | Residents and pets | Sensor Categories | Number of sensors | Activity Categories | Number of Activity instances | Measurement Time |
| “Cairo” | 2 residents and 1 pet | “Motion sensors” (M001-M027) | 27 | “Night_wandering” | 67 | 57 days |
| “Bed_to_toilet” | 30 | |||||
| “R1_wake” | 53 | |||||
| “R2_wake” | 52 | |||||
| “R2_take_medicine” | 44 | |||||
| “Breakfast” | 48 | |||||
| “Temperature sensors ”(T001-T005) | 5 | “Leave_home” | 69 | |||
| “Lunch” | 37 | |||||
| “Dinner” | 42 | |||||
| “R2_sleep” | 52 | |||||
| “R1_sleep” | 50 | |||||
| “R1_work_in_office” | 46 | |||||
| “Laundry” | 10 | |||||
| “tulum2009” | 2 residents | “Motion sensors” (M001-M018) | 18 | “Cook_Breakfast” | 80 | 84 days |
| “R1_Eat_Breakfast” | 66 | |||||
| “Cook_Lunch” | 71 | |||||
| “Leave_Home” | 75 | |||||
| “Watch_TV” | 528 | |||||
| “Temperature sensors ”(T001-T002) | 2 | “R1_Snack” | 491 | |||
| “Enter_Home” | 73 | |||||
| “Group_Meeting” | 11 | |||||
| “R2_Eat_Breakfast” | 47 | |||||
| “Wash_Dishes” | 71 |
DownLoad:
CSV
For daily activity feature solving approaches, we use Jupyter Notebook to carry out experimental comparison of four methods. First, the proposed method is called "SR", and the second is called "FR". FR is an extraction approach of daily activity feature. For FR method, frequency of activated sensor is extracted as daily activity feature. “FR” and its variants have been be used most extensively as daily activity feature. Feature spaces of the approach are composed of “st”, “et”, “du” and sensor features [53]. The other two are the combination of SR and FR with SDSFS algorithm respectively, called "SR+FS" and "FR+FS". FR+FS (FR+FS) means that SDSFS is employed to select features of daily activity after features are extracted.
For a given daily activity, the values of st, et, and du refer to the start time, end time, and duration of the daily activity, respectively. Sensor features, each of which corresponds to a sensor are mapped to all deployed sensors in the smart home. For FR, the value of a sensor feature is the frequency that activates the corresponding sensor in the given daily activity. For the SDSFS algorithm, the parameters involved are listed in Table 2.
| Configuration Name | Parameter Interpretation |
| the number of iterations | numIterations←150 |
| the number of agents | numAgents←30 |
| the minimum number of features included in an agent | lowerLim←5 |
| the maximum number of features included in an agent | upperLim←30 |
DownLoad:
CSV
For data-driven approaches, activity recognition is usually treated as a classification problem. Without loss of generality, Logistic Regression (LR), Naive Bayesian (NB), Decision Tree (DT) and LSTM are used to evaluate the proposed approach. The parameters involved are listed in Table 3. The rest of the parameters are default. A leave-one-day-out cross validation is taken to evaluate the proposed approach. The performance indicators used are the Recall, Precision, and F-score, which are defined in formula (7), (8) and (9), respectively, where Q is the number of activity labels; TPi is the number of true positives; FPi is the number of false positives; FNi is the number of false negatives; TNi is the number of true negatives.
| Recall=Q∑i=1TPiTPi+FNiQ | (7) |
| Precision=Q∑i=1TPiTPi+FPiQ | (8) |
| F−score=2∗Precision∗RecallPrecision+Recall | (9) |
| Classifiers Name | Parameter Name | Parameter Settings |
| LR | regularization intensity, random number seed | C←1.0, random_state←2018 |
| DT | random number seed | random_state←2018 |
| NB | / | / |
| LSTM | The number of units | 16 |
| Gradient descent algorithm | AdamOptimizar | |
| Learning rate | 1e-3 | |
| Batch size | 100 | |
| Epoch number | 100 |
DownLoad:
CSV
Recall, Precision, and F-measure are listed in Tables 4-9 and Figures 3, 5.
| Approaches | LR | NB | DT | LSTM |
| FR | 79.263% | 72.207% | 84.346% | 81.021% |
| SR | 70.900% | 70.775% | 79.358% | 88.152% |
| FR + FS | 83.112% | 81.334% | 87.379% | / |
| SR + FS | 87.006% | 83.958% | 89.511% | / |
DownLoad:
CSV
| Approaches | LR | NB | DT | LSTM |
| FR | 74.776% | 70.225% | 85.018% | 75.2693% |
| SR | 66.043% | 68.411% | 78.236% | 88.268% |
| FR + FS | 81.310% | 79.023% | 86.295% | / |
| SR + FS | 82.918% | 80.634% | 87.114% | / |
DownLoad:
CSV
| Approaches | LR | NB | DT | LSTM |
| FR | 75.603% | 69.265% | 84.280% | 76.321% |
| SR | 66.254% | 67.167% | 78.074% | 87.748% |
| FR + FS | 81.021% | 78.589% | 86.189% | / |
| SR + FS | 84.133% | 80.214% | 87.529% | / |
DownLoad:
CSV
| Approaches | LR | NB | DT | LSTM |
| FR | 72.627% | 58.688% | 84.993% | 85.907% |
| SR | 77.075% | 73.139% | 80.689% | 88.8% |
| FR + FS | 81.864% | 65.650% | 86.122% | / |
| SR + FS | 90.844% | 81.221% | 85.329% | / |
DownLoad:
CSV
| Approaches | LR | NB | DT | LSTM |
| FR | 64.540% | 72.008% | 79.591% | 76.256% |
| SR | 74.478% | 75.513% | 78.609% | 86.716% |
| FR + FS | 65.519% | 75.564% | 81.985% | / |
| SR + FS | 86.101% | 87.574% | 84.771% | / |
DownLoad:
CSV
| Approaches | LR | NB | DT | LSTM |
| FR | 65.912% | 58.368% | 81.628% | 80% |
| SR | 75.543% | 71.112% | 79.265% | 86.909% |
| FR + FS | 68.535% | 66.448% | 83.669% | / |
| SR + FS | 88.205% | 83.562% | 84.727% | / |
DownLoad:
CSV
(1) Results on Dataset “Cairo”
After feature selection, the scores of each agent are shown in Figure 2. FR+FS and SR+FS have the highest average F-score in the 14th and 3rd agents respectively. Based on the above results, we conduct the following experiments using the features in the best agents respectively.
The Precision obtained using SR+FS is higher than that obtained using the other three methods for all classifiers. The Recall and F-score obtained using SR+FS are higher than those obtained using FR, SR and FR+FS for LR and NB. The highest Precision (89.511%), Recall (87.114%) and F-score (87.529%) are obtained using SR+FS for DT. Besides, the first three classifiers, their average Precision value obtained using SR+FS improves by at least 2.883% compared with the performance of other tests. And the average Recall value of the SR+FS is 83.555%. There is 1.346% improvement over the best outcomes of the first three methods. Similarly, the average F-score of the SR+FS achieves at least 7.574%, 13.459% and 2.024% improvements over other benchmark methods. Finally, SR also beats FR in every metric of the LSTM.
(2) Results on Dataset “Tulum2009”
After feature selection, the scores of each agent are shown in Figure 4. FR+FS and SR+FS have the highest average F-score in the 5th and 22nd agents respectively. Based on the above results, we conduct the following experiments using the features in the best agents respectively.
The dataset also gets the same result pattern. The Precision obtained using SR+FS is also higher than that obtained using the other three methods for all classifiers. The Recall and F-score obtained using SR+FS are higher than those obtained using FR, SR and FR+FS for LR and NB. Although SR+FS lags behind FR + FS in the Precision of DT. Besides, the first three classifiers, their average Precision value obtained using SR+FS improves by at least 7.919% compared with the performance of other tests. Besides, the average Recall value of the SR+FS is 86.148%. There is 9.948% improvement over the best outcomes of the first three methods. Similarly, the average F-score of the SR+FS achieves at least 16.862%, 10.192% and 12.614% improvements over other benchmark methods. Finally, SR also beats FR in every metric of the LSTM.
We discuss few crucial observations from our experiments. As shown in Figures 3, 5, SR+FS performs better than the other three groups. First, this gain may be due to feature selection. There are inevitably redundant features in the original data. These features are not sensitive to the classification label, but they can disturb the classifier's correct judgment of the sample. Therefore, the performance of SR is low in some classifiers.
In addition, it may be that the traditional method only counts the frequency of the sensor and loses the time information of the sensor. In contrast, our method extracts the trigger time of the sensor in the activity in turn, and then carries out feature calculation. Such different feature computing methods increase the diversity of features. In this way, the frequency information and the time information of the time series data are retained.
We note that there are imbalances of categories in daily activities, but this paper does not do the corresponding processing when modeling. Excessive differences between categories may make the model biased towards more categories, which may affect the performance evaluation of the model to some extent. Consequentially, it may be worthwhile to perform further studies to determine how such problems impact performance, especially in smart home environment.
Daily activity features have a significant influence on activity recognition performance. To improve activity recognition performance, we proposed a statistic representation of daily activity features based on the time series nature of sensor event streams. We utilized four classifiers to compare the proposed approach with approaches based on the frequency and truth of sensor events on two common datasets. The results showed that the proposed approach can significantly improve activity recognition performance.
This work was supported by the National Natural Science Foundation of China (No. 61976124); the Open Project Program of Artificial Intelligence Key Laboratory of Sichuan Province (Nos. 2018RYJ09, 2019RZJ01); the Opening Project of Key Laboratory of Higher Education of Sichuan Province for Enterprise Informationalization and Internet of Things(No. 2019WZY03); the Major Frontier Project of Science and Technology Plan of Sichuan Province (No. 2018JY0512).
The authors declare no conflicts of interest.
| [1] |
Durante M, Loeffler JS (2010) Charged particles in radiation oncology. Nat Rev Clin Oncol 7: 37–43. doi: 10.1038/nrclinonc.2009.183
|
| [2] | Particle Therapy Co-Operative Group (PTCOG). Available from: http://www.ptcog.ch. |
| [3] |
Tommasino F, Scifoni E, Durante M (2015) New ions for therapy. Int J Particle Ther 2: 428–438. doi: 10.14338/IJPT-15-00027.1
|
| [4] | Weyrather WK (2004) Medical Applications of Accelerated Ions, In: Al-Khalili J, Roeckl E, The Euroschool Lectures on Physics with Exotic Beams, Berlin, Heidelberg: Springer Berlin Heidelberg, 469–490. |
| [5] | Molière G (1948) Theorie der streuung schneller geladener teilchen ii mehrfach-und vielfachstreuung. Z Naturforschung A 3: 78–97. |
| [6] |
Amaldi U, Kraft G (2005) Radiotherapy with beams of carbon ions. Rep Prog Phys 68: 1861–1882. doi: 10.1088/0034-4885/68/8/R04
|
| [7] | Linz U (2012) Physical and biological rationale for using ions in therapy, In: Ion Beam Therapy, Berlin, Heidelberg: Springer Berlin Heidelberg, 45–59. |
| [8] | Battistoni G, Bauer J, Boehlen TT, et al. (2016) The FLUKA code: An accurate simulation tool for particle therapy. Front Oncol 6: 116. |
| [9] |
Sato T, Niita K, Matsuda N, et al. (2014) Overview of the PHITS code and its application to medical physics. Prog Nucl Sci Technol 4: 879–882. doi: 10.15669/pnst.4.879
|
| [10] |
Allison J, Amaco K, Apostolakis J, et al. (2016) Recent developments in Geant4. Nucl Instrum Meth A 835: 186–225. doi: 10.1016/j.nima.2016.06.125
|
| [11] |
Scholz M, Kraft G (1994) Calculation of heavy ion inactivation probabilities based on track structure, X ray sensitivity and target size. Radiat Prot Dosim 52: 29–33. doi: 10.1093/oxfordjournals.rpd.a082156
|
| [12] |
Kase Y, Kanai T, Matsumoto Y, et al. (2006) Microdosimetric measurements and estimation of human cell survival for heavy-ion beams. Radiat Res 166: 629–638. doi: 10.1667/RR0536.1
|
| [13] |
Wouters BG, Lam GK, Oelfke U, et al. (1996) Measurements of relative biological effectiveness of the 70 MeV proton beam at TRIUMF using V79 cells and the high precision cell sorter assay. Radiat Res 146: 159–170. doi: 10.2307/3579588
|
| [14] |
Gerweck LE, Kozin SV (1999) Relative biological effectiveness of proton beams in clinical therapy. Radiother Oncol 50: 135–142. doi: 10.1016/S0167-8140(98)00092-9
|
| [15] |
Paganetti H (2002) Relative Biological Effectiveness (RBE) values for proton beam therapy. J Radiat Oncol Biol Phys 53: 407–421. doi: 10.1016/S0360-3016(02)02754-2
|
| [16] |
Paganetti H, van Luijk P (2013) Biological considerations when comparing proton therapy and photon therapy. Semin Radiat Oncol 23: 77–87. doi: 10.1016/j.semradonc.2012.11.002
|
| [17] |
Chaudary P, Marshall TI, Perozziello FM, et al. (2014) Relative biological effectiveness variation along monoenergetic and modulated bragg peaks of a 62-MeV therapeutic proton beam: a preclinical assessment. Int J Radiat Oncol Biol Phys 90: 27–35. doi: 10.1016/j.ijrobp.2014.05.010
|
| [18] |
Michaelidesová A, Vachelová J, Puchalska M, et al. (2017) Relative biological effectiveness in a proton spread-out Bragg peak formed by pencil beam scanning mode. Australas Phys Eng Sci Med 40: 359–368. doi: 10.1007/s13246-017-0540-8
|
| [19] |
Grün R, Friedrich T, Krämer M, et al. (2017) Systematics of relative biological effectiveness measurements for proton radiation along the spread out Bragg peak: experimental validation of the local effect model. Phys Med Biol 62: 890–908. doi: 10.1088/1361-6560/62/3/890
|
| [20] | Scholz M, Kraft G (1996) Track structure and the calculation of biological effects of heavy charged particles. Adv Space Res 18: 5–14. |
| [21] | Hubert F, Fleury A, Bimbot R, et al. (1980) Range and stopping power tables for 2.5–100 MeV/nucleon heavy ions in solids. Ann Phys 5: 214–218. |
| [22] | Nortllcliff LC, Shilling RF (1970) Range and stopping power tables for heavy ions. Atom Data Nucl Data 7: 233–437. |
| [23] |
Elsässer T, Krämer M, Scholz M (2008) Accuracy of the local effect model for the prediction of biologic effects of carbon ion beams in vitro and in vivo. Int J Radiat Oncol Biol Phys 71: 866–872. doi: 10.1016/j.ijrobp.2008.02.037
|
| [24] |
Kiefer J, Straaten H (1986) A model of ion track structure based on classical collision dynamics. Phys Med Biol 31: 1201–1209. doi: 10.1088/0031-9155/31/11/002
|
| [25] |
Scholz M, Kellerer AM, Kraft-Weyrather W, et al. (1997) Computation of cell survival in heavy ion beams for therapy. The model and its approximation. Radiat Environ Bioph 36: 59–66. doi: 10.1007/s004110050055
|
| [26] |
Elsässer T, Scholz M (2007) Cluster effects within the local effect model. Radiat Res 167: 319–329. doi: 10.1667/RR0467.1
|
| [27] |
Elsässer T, Weyrather WK, Friedrich T, et al. (2010) Quantification of the relative biological effectiveness for ion beam radiotherapy: direct experimental comparison of proton and carbon ion beams and a novel approach for treatment planning. Int J Radiat Oncol Biol Phys 78: 1177–1183. doi: 10.1016/j.ijrobp.2010.05.014
|
| [28] |
Grün R, Friedrich T, Elsässer T, et al. (2012) Impact of enhancements in the Local Effect Model (LEM) on the predicted RBE-weighted target dose distribution in carbon ion therapy. Phys Med Biol 57: 7261–7274. doi: 10.1088/0031-9155/57/22/7261
|
| [29] |
Kanai T, Furusawa Y, Fukutsu K, et al. (1997) Irradiation of mixed beam and design of spread-out Bragg peak for heavy-ion radiotherapy. Radiat Res 147: 78–85. doi: 10.2307/3579446
|
| [30] |
Kanai T, Endo M, Minohara S, et al (1999) Biophysical characteristics of HIMAC clinical irradiation system for heavy-ion radiation therapy. Int J Radiat Oncol Biol Phys 44: 201–210. doi: 10.1016/S0360-3016(98)00544-6
|
| [31] | Kraft G (2002) Radiobiological effecs of highly-charged ions, In: Currel FJ, The physics of highly and multiply charged ions, Kluwer Academic Publisher. |
| [32] |
Mizoe J, Tsujii H, Kamada T, et al. (2004) Dose escalation study of carbon ion radiotherapy for locally advanced head-and-neck cancer. Int J Radiat Oncol Biol Phys 60: 358–364. doi: 10.1016/j.ijrobp.2004.02.067
|
| [33] |
Kanai T, Matsufuji N, Miyamoto T, et al. (2006) Examination of GyE system for HIMAC carbon therapy. Int J Radiat Oncol Biol Phys 64: 650–656. doi: 10.1016/j.ijrobp.2005.09.043
|
| [34] |
Hawkins RB (1994) A statistical theory of cell killing by radiation of varying linear energy transfer. Radiat Res 140: 366–374. doi: 10.2307/3579114
|
| [35] |
Hawkins RB (2003) A microdosimetric-kinetic model for the effect of non-Poisson distribution of lethal lesions on the variation of RBE with LET. Radiat Res 160: 61–69. doi: 10.1667/RR3010
|
| [36] |
Kellerer M, Rossi HH (1978) A generalized formulation of dual radiation action. Radiat Res 75: 471–488. doi: 10.2307/3574835
|
| [37] |
Kase Y, Kanai T, Matsufuji N, et al. (2008) Biophysical calculation of cell survival probabilities using amorphous track structure models for heavy-ion irradiation. Phys Med Biol 53: 37–59. doi: 10.1088/0031-9155/53/1/003
|
| [38] |
Inaniwa T, Furukawa T, Kase Y, et al. (2010) Treatment planning for a scanned carbon beam with a modified microdosimetric kinetic model. Phys Med Biol 55: 6721–6737. doi: 10.1088/0031-9155/55/22/008
|
| [39] |
Furusawa Y, Fukutsu K, Aoki M, et al. (2000) Inactivation of aerobic and hypoxic cells from three different cell lines by accelerated He-, C- and Ne-ion beams. Radiat Res 154: 485–496. doi: 10.1667/0033-7587(2000)154[0485:IOAAHC]2.0.CO;2
|
| [40] |
Inaniwa T, Furukawa T, Sato S, et al. (2008) Development of treatment planning for scanning irradiation at HIMAC. Nucl Instr Meth Phys Res B 266: 2194–2198. doi: 10.1016/j.nimb.2008.02.070
|
| [41] |
Sato T, Kase Y, Watanabe R, et al. (2009) Biological dose estimation for charged particle therapy using an improved PHITS code coupled with a MK model. Radiat Res 171: 107–117. doi: 10.1667/RR1510.1
|
| [42] |
Sato T, Furusawa Y (2012) Cell survival fraction estimation based on the probability densities of domain and cell nucleus specific energies using improved Microdosimetric Kinetic Models. Radiat Res 178: 341–356. doi: 10.1667/RR2842.1
|
| [43] |
Sato T, Hamada N (2014) Model assembly for estimating cell surviving fraction for both targeted and nontargeted effects based on microdosimetric probability densities. P loS One 9: e114056. doi: 10.1371/journal.pone.0114056
|
| [44] |
Kramer M, Wang JF, Weyrather W (2003) Biological dosimetry of complex ion radiation fields. Phys Med Biol 48: 2063–2070. doi: 10.1088/0031-9155/48/14/302
|
| [45] |
Magro G, Dahle TJ, Molinelli S, et al. (2017) The FLUKA Monte Carlo code coupled with the NIRS approach for clinical dose calculations in carbon ion therapy. Phys Med Biol 62: 3814–3827. doi: 10.1088/1361-6560/aa642b
|
| [46] |
Frese MC, Yu VK, Stewart RD, et al. (2012) A mechanism-based approach to predict the relative biological effectiveness of protons and carbon ions in radiation therapy. Int J Radiat Oncol Biol Phys 83: 442–450. doi: 10.1016/j.ijrobp.2011.06.1983
|
| [47] |
Tilly N, Johansson J, Isacsson U, et al. (2005) The influence of RBE variations in clinical proton treatment plan for a hypopharynx cancer. Phys Med Biol 50: 2765–2777. doi: 10.1088/0031-9155/50/12/003
|
| [48] |
Belli M, Cera F, Cherubini R, et al. (1993) Inactivation and mutation induction in V79 cells by low energy protons: re-evaluation of the results at the LNL facility. Int J Radiat Biol 63: 331–337. doi: 10.1080/09553009314550441
|
| [49] |
Belli M, Cera F, Cherubini R, et al. (1998) RBE-LET relationships for cell inactivation and mutation induced by low energy protons in V79 cells: further results at the LNL facility. Int J Radiat Biol 74: 501–509. doi: 10.1080/095530098141375
|
| [50] |
Belli M, Bettega D, Calzolari P, et al. (2000) Inactivation of human normal and tumour cells irradiated with low energy protons. Int J Radiat Biol 76: 831–839. doi: 10.1080/09553000050028995
|
| [51] |
Folkard M, Prise KM, Vojnovic B, et al. (1996) Inactivation of V79 cells by low-energy protons, deuterons and helium-3 ions. Int J Radiat Biol 69: 729–738. doi: 10.1080/095530096145472
|
| [52] |
Bettega D, Calzolari P, Marchesini R, et al. (1998) Inactivation of C3H10T1/2 cells by low energy protons and deuterons. Int J Radiat Biol 73: 303–309. doi: 10.1080/095530098142400
|
| [53] | Frese MC, Wilkens JJ, Huber PE, et al. (2011) Application of constant vs. variable relative biological effectiveness in treatment planning of intensity-modulated proton therapy. Int J Radiat Oncol Biol Phys 79: 80–88. |
| [54] |
Wilkens JJ, Oelfke U (2004) A phenomenological model for the relative biological effectiveness in therapeutic proton beams. Phys Med Biol 49: 2811–2825. doi: 10.1088/0031-9155/49/13/004
|
| [55] | ICRU (1993) Stopping powers and ranges for protons and alpha particles, report 49, International Commission on Radiation Units and Measurements, Bethesda, MD, USA. |
| [56] |
Carabe-Fernandez A, Moteabbed M, Depauw N, et al. (2012) Range uncertainty in proton therapy due to variable biological effectiveness. Phys Med Biol 57: 1159–1172. doi: 10.1088/0031-9155/57/5/1159
|
| [57] |
Belli M, Cherubini R, Finotto S, et al. (1989) RBE-LET relationship for the survival of V79 cells irradiated with low energy protons. Int J Radiat Biol 55: 93–104. doi: 10.1080/09553008914550101
|
| [58] | Perris A, Pialoglou P, Katsanos AA, et al. (1986) Biological effectiveness of low energy protons. I. Survival of chinese hamster cells. Int J Radiat Biol 50: 1093–1101. |
| [59] |
Coutrakon G, Cortese J, Ghebremedhin A, et al. (1997) Microdosimetry spectra of the Loma Linda proton beam and relative biological effectiveness comparisons. Med Phys 24: 1499–1506. doi: 10.1118/1.598038
|
| [60] |
Wedenberg M, Lind BK, Hardemark B (2013) A model for the relative biological effectiveness of protons: the tissue specific parameter a/b of photons is a predictor for the sensitivity to LET changes. Acta Oncol 52: 580–588. doi: 10.3109/0284186X.2012.705892
|
| [61] | Paganetti H (2014) Relative biological effectiveness (RBE) values for proton beam therapy. Variations as a function of biological endpoint, dose, and linear energy transfer. Phys Med Biol 59: R419–R472. |
| [62] |
McNamara AL, Schuemann J, Paganetti H (2015) A phenomenological relative biological effectiveness (RBE) model for proton therapy based on all published in vitro cell survival data. Phys Med Biol 60: 8399–8416. doi: 10.1088/0031-9155/60/21/8399
|
| [63] |
Wedenberg M, Toma-Dasu I (2014) Disregarding RBE variation in treatment plan comparison may lead to bias in favor of proton plans. Med Phys 41: 091706. doi: 10.1118/1.4892930
|
| [64] |
Giovannini G, Böhlen T, Cabal G, et al. (2016) Variable RBE in proton therapy: comparison of different model predictions and their influence on clinical-like scenarios. Radiat Oncol 11: 68. doi: 10.1186/s13014-016-0642-6
|
| [65] |
Ottolenghi A, Ballarini F, Biaggi M (2001) Modelling chromosomal aberration induction by ionising radiation: the influence of interphase chromosome architecture. Adv Space Res 27: 369–382. doi: 10.1016/S0273-1177(01)00004-7
|
| [66] |
Ballarini F, Ottolenghi A (2004) A model of chromosome aberration induction and CML incidence at low doses. Radiat Environ Bioph 43: 165–171. doi: 10.1007/s00411-004-0246-7
|
| [67] | Ballarini F (2010) From DNA radiation damage to cell death: Theoretical approaches. J Nucleic Acids. |
| [68] |
Ballarini F, Altieri S, Bortolussi S, et al. (2013) A model of radiation-induced cell killing: insights into mechanisms and applications for hadrontherapy. Radiat Res 180: 307–315. doi: 10.1667/RR3285.1
|
| [69] |
Ballarini F, Altieri S, Bortolussi S, et al. (2014) The BIANCA model/code of radiation-induced cell death: application to human cells exposed to different radiation types. Radiat Environ Bioph 53: 525–533. doi: 10.1007/s00411-014-0537-6
|
| [70] |
Carante MP, Altieri S, Bortolussi S, at al. (2015) Modelling radiation-induced cell death: role of different levels of DNA damage clustering. Radiat Environ Bioph 54: 305–316. doi: 10.1007/s00411-015-0601-x
|
| [71] | Carante MP, Ballarini F (2016) Calculating variations in biological effectiveness for a 62 MeV proton beam. Front Oncol 6: 76. |
| [72] | Ballarini F, Carante MP (2016) Chromosome aberrations and cell death by ionizing radiation: evolution of a biophysical model. Radiat Phys Chem 128C: 18–25. |
| [73] |
Aiginger HV, Andersen F, Ballarini, et al. (2005) The FLUKA code: new developments and application to 1 GeV/n Iron beams. Adv Space Res 35: 214–222. doi: 10.1016/j.asr.2005.01.090
|
| [74] |
Ballarini F, Ottolenghi A (2005) A model of chromosome aberration induction: applications to space research. Radiat Res 164: 567–570. doi: 10.1667/RR3365.1
|
| [75] | Ballarini F, Alloni D, Facoetti A, et al. (2007) Radiation risk estimation: modelling approaches for "targeted" and "non-targeted" effects. Adv Space Res 40: 1392–1400. |
| [76] |
Campa AD, Alloni F, Antonelli, et al. (2009) DNA fragmentation induced in human fibroblasts by 56Fe ions: experimental data and MC simulations. Radiat Res 171: 438–445. doi: 10.1667/RR1442.1
|
| [77] |
Wu H, George K, Yang TC (1999) Estimate of the frequency of true incomplete exchanges in human lymphocytes exposed to 1 GeV/u Fe ions in vitro. Int J Radiat Biol 75: 593–599. doi: 10.1080/095530099140230
|
| [78] |
Cornforth MN, Bedford JS (1985) On the nature of a defect in cells from individuals with Ataxia-Telangiectasia. Science 227: 1589–1591. doi: 10.1126/science.3975628
|
| [79] |
Boei JJ, Vermeulen S, Mullenders LH, et al. (2001) Impact of radiation quality on the spectrum of induced chromosome exchange aberrations. Int J Radiat Biol 77: 847–857. doi: 10.1080/09553000110054610
|
| [80] |
Chen AM, Lucas JN, Simpson PJS, et al. (1997) Computer simulation of data on chromosome aberrations produced by X rays or alpha particles and detected by fluorescence in situ hybridization. Radiat Res 148: S93–S101. doi: 10.2307/3579722
|
| [81] |
Cornforth M, Bedford J (1987) A quantitative comparison of potentially lethal damage repair and the rejoining of interphase chromosome breaks in low passage normal human fibroblasts. Radiat Res 111: 385–405. doi: 10.2307/3576926
|
| [82] | Carrano AV (1973) Chromosome aberrations and radiation-induced cell death. I. Transmission and survival parameters of aberrations. Mutat Res 17: 341–353. |
| [83] |
Cuttone G, Cirrone GAP, Di FG, et al. (2011) CATANA protontherapy facility: The state of art of clinical and dosimetric experience. Eur Phys J Plus 126: 65. doi: 10.1140/epjp/i2011-11065-1
|
| [84] |
Rabbits T (1994) Chromosomal translocations in human cancer. Nature 372: 143–149. doi: 10.1038/372143a0
|
| [85] |
Tommasino F, Durante M (2015) Proton radiobiology. Cancers 7: 353–381. doi: 10.3390/cancers7010353
|
| 1. | Sakorn Mekruksavanich, Anuchit Jitpattanakul, RNN-based deep learning for physical activity recognition using smartwatch sensors: A case study of simple and complex activity recognition, 2022, 19, 1551-0018, 5671, 10.3934/mbe.2022265 | |
| 2. | Keruo Jiang, Zhen Huang, Xinyan Zhou, Chudong Tong, Minjie Zhu, Heshan Wang, Deep belief improved bidirectional LSTM for multivariate time series forecasting, 2023, 20, 1551-0018, 16596, 10.3934/mbe.2023739 |
Figures(3) / Tables(4)
Mario P. Carante, Francesca Ballarini. Modelling cell death for cancer hadrontherapy[J]. AIMS Biophysics, 2017, 4(3): 465-490. doi: 10.3934/biophy.2017.3.465
| Dataset | Residents and pets | Sensor Categories | Number of sensors | Activity Categories | Number of Activity instances | Measurement Time |
| “Cairo” | 2 residents and 1 pet | “Motion sensors” (M001-M027) | 27 | “Night_wandering” | 67 | 57 days |
| “Bed_to_toilet” | 30 | |||||
| “R1_wake” | 53 | |||||
| “R2_wake” | 52 | |||||
| “R2_take_medicine” | 44 | |||||
| “Breakfast” | 48 | |||||
| “Temperature sensors ”(T001-T005) | 5 | “Leave_home” | 69 | |||
| “Lunch” | 37 | |||||
| “Dinner” | 42 | |||||
| “R2_sleep” | 52 | |||||
| “R1_sleep” | 50 | |||||
| “R1_work_in_office” | 46 | |||||
| “Laundry” | 10 | |||||
| “tulum2009” | 2 residents | “Motion sensors” (M001-M018) | 18 | “Cook_Breakfast” | 80 | 84 days |
| “R1_Eat_Breakfast” | 66 | |||||
| “Cook_Lunch” | 71 | |||||
| “Leave_Home” | 75 | |||||
| “Watch_TV” | 528 | |||||
| “Temperature sensors ”(T001-T002) | 2 | “R1_Snack” | 491 | |||
| “Enter_Home” | 73 | |||||
| “Group_Meeting” | 11 | |||||
| “R2_Eat_Breakfast” | 47 | |||||
| “Wash_Dishes” | 71 |
DownLoad:
CSV
| Configuration Name | Parameter Interpretation |
| the number of iterations | numIterations←150 |
| the number of agents | numAgents←30 |
| the minimum number of features included in an agent | lowerLim←5 |
| the maximum number of features included in an agent | upperLim←30 |
DownLoad:
CSV
| Classifiers Name | Parameter Name | Parameter Settings |
| LR | regularization intensity, random number seed | C←1.0, random_state←2018 |
| DT | random number seed | random_state←2018 |
| NB | / | / |
| LSTM | The number of units | 16 |
| Gradient descent algorithm | AdamOptimizar | |
| Learning rate | 1e-3 | |
| Batch size | 100 | |
| Epoch number | 100 |
DownLoad:
CSV
| Approaches | LR | NB | DT | LSTM |
| FR | 79.263% | 72.207% | 84.346% | 81.021% |
| SR | 70.900% | 70.775% | 79.358% | 88.152% |
| FR + FS | 83.112% | 81.334% | 87.379% | / |
| SR + FS | 87.006% | 83.958% | 89.511% | / |
DownLoad:
CSV
| Approaches | LR | NB | DT | LSTM |
| FR | 74.776% | 70.225% | 85.018% | 75.2693% |
| SR | 66.043% | 68.411% | 78.236% | 88.268% |
| FR + FS | 81.310% | 79.023% | 86.295% | / |
| SR + FS | 82.918% | 80.634% | 87.114% | / |
DownLoad:
CSV
| Approaches | LR | NB | DT | LSTM |
| FR | 75.603% | 69.265% | 84.280% | 76.321% |
| SR | 66.254% | 67.167% | 78.074% | 87.748% |
| FR + FS | 81.021% | 78.589% | 86.189% | / |
| SR + FS | 84.133% | 80.214% | 87.529% | / |
DownLoad:
CSV
| Approaches | LR | NB | DT | LSTM |
| FR | 72.627% | 58.688% | 84.993% | 85.907% |
| SR | 77.075% | 73.139% | 80.689% | 88.8% |
| FR + FS | 81.864% | 65.650% | 86.122% | / |
| SR + FS | 90.844% | 81.221% | 85.329% | / |
DownLoad:
CSV
| Approaches | LR | NB | DT | LSTM |
| FR | 64.540% | 72.008% | 79.591% | 76.256% |
| SR | 74.478% | 75.513% | 78.609% | 86.716% |
| FR + FS | 65.519% | 75.564% | 81.985% | / |
| SR + FS | 86.101% | 87.574% | 84.771% | / |
DownLoad:
CSV
| Approaches | LR | NB | DT | LSTM |
| FR | 65.912% | 58.368% | 81.628% | 80% |
| SR | 75.543% | 71.112% | 79.265% | 86.909% |
| FR + FS | 68.535% | 66.448% | 83.669% | / |
| SR + FS | 88.205% | 83.562% | 84.727% | / |
DownLoad:
CSV
| Dataset | Residents and pets | Sensor Categories | Number of sensors | Activity Categories | Number of Activity instances | Measurement Time |
| “Cairo” | 2 residents and 1 pet | “Motion sensors” (M001-M027) | 27 | “Night_wandering” | 67 | 57 days |
| “Bed_to_toilet” | 30 | |||||
| “R1_wake” | 53 | |||||
| “R2_wake” | 52 | |||||
| “R2_take_medicine” | 44 | |||||
| “Breakfast” | 48 | |||||
| “Temperature sensors ”(T001-T005) | 5 | “Leave_home” | 69 | |||
| “Lunch” | 37 | |||||
| “Dinner” | 42 | |||||
| “R2_sleep” | 52 | |||||
| “R1_sleep” | 50 | |||||
| “R1_work_in_office” | 46 | |||||
| “Laundry” | 10 | |||||
| “tulum2009” | 2 residents | “Motion sensors” (M001-M018) | 18 | “Cook_Breakfast” | 80 | 84 days |
| “R1_Eat_Breakfast” | 66 | |||||
| “Cook_Lunch” | 71 | |||||
| “Leave_Home” | 75 | |||||
| “Watch_TV” | 528 | |||||
| “Temperature sensors ”(T001-T002) | 2 | “R1_Snack” | 491 | |||
| “Enter_Home” | 73 | |||||
| “Group_Meeting” | 11 | |||||
| “R2_Eat_Breakfast” | 47 | |||||
| “Wash_Dishes” | 71 |
| Configuration Name | Parameter Interpretation |
| the number of iterations | numIterations←150 |
| the number of agents | numAgents←30 |
| the minimum number of features included in an agent | lowerLim←5 |
| the maximum number of features included in an agent | upperLim←30 |
| Classifiers Name | Parameter Name | Parameter Settings |
| LR | regularization intensity, random number seed | C←1.0, random_state←2018 |
| DT | random number seed | random_state←2018 |
| NB | / | / |
| LSTM | The number of units | 16 |
| Gradient descent algorithm | AdamOptimizar | |
| Learning rate | 1e-3 | |
| Batch size | 100 | |
| Epoch number | 100 |
| Approaches | LR | NB | DT | LSTM |
| FR | 79.263% | 72.207% | 84.346% | 81.021% |
| SR | 70.900% | 70.775% | 79.358% | 88.152% |
| FR + FS | 83.112% | 81.334% | 87.379% | / |
| SR + FS | 87.006% | 83.958% | 89.511% | / |
| Approaches | LR | NB | DT | LSTM |
| FR | 74.776% | 70.225% | 85.018% | 75.2693% |
| SR | 66.043% | 68.411% | 78.236% | 88.268% |
| FR + FS | 81.310% | 79.023% | 86.295% | / |
| SR + FS | 82.918% | 80.634% | 87.114% | / |
| Approaches | LR | NB | DT | LSTM |
| FR | 75.603% | 69.265% | 84.280% | 76.321% |
| SR | 66.254% | 67.167% | 78.074% | 87.748% |
| FR + FS | 81.021% | 78.589% | 86.189% | / |
| SR + FS | 84.133% | 80.214% | 87.529% | / |
| Approaches | LR | NB | DT | LSTM |
| FR | 72.627% | 58.688% | 84.993% | 85.907% |
| SR | 77.075% | 73.139% | 80.689% | 88.8% |
| FR + FS | 81.864% | 65.650% | 86.122% | / |
| SR + FS | 90.844% | 81.221% | 85.329% | / |
| Approaches | LR | NB | DT | LSTM |
| FR | 64.540% | 72.008% | 79.591% | 76.256% |
| SR | 74.478% | 75.513% | 78.609% | 86.716% |
| FR + FS | 65.519% | 75.564% | 81.985% | / |
| SR + FS | 86.101% | 87.574% | 84.771% | / |
| Approaches | LR | NB | DT | LSTM |
| FR | 65.912% | 58.368% | 81.628% | 80% |
| SR | 75.543% | 71.112% | 79.265% | 86.909% |
| FR + FS | 68.535% | 66.448% | 83.669% | / |
| SR + FS | 88.205% | 83.562% | 84.727% | / |
