The ubiquity of mobile devices has birthed one of the most promising IoT applications called Mobile Crowd Sensing (MCS) wherein mobile devices carried around by a crowd are used to sense phenomena of interest. Subsequently, sensed data are collected, aggregated and analysed to extract useful information. Sparse Mobile Crowd Sensing (SMCS) aims at reducing the sensing overhead (e.g., battery consumption, incentive cost, etc.) by lowering the number of sensing tasks performed. Sensed data thus collected are used to infer missing values. However, it must be ensured that user’s private information (e.g., user’s home location) cannot be derived from the sensed data shared by a user. We propose a novel approach entitled ‘Privacy Aware Missing Data Inference Scheme for Sparse Mobile Crowd Sensing (PAMDI)’ which employs the concept of perceptual hash for ensuring privacy while trying to maintain performance guarantees. Simulation results with the help of two real-world data-sets point towards the feasibility of the proposed approach for provisioning user privacy. We use regression algorithms for missing data inference in PAMDI and find that linear regression algorithms work best with the proposed privacy approach as compared to non-linear regression algorithms. Moreover, we observe that inference accuracy is more or less maintained even after introducing privacy with the proposed approach. In particular, for the first data-set (Temperature data-set), the mean absolute error (MAE) and root mean squared error (RMSE) values obtained by the linear algorithms using the proposed approach are about 2.65 ∘ C and 2 . 9 ∘ C respectively. On the other hand, the corresponding MAE and RMSE values generated by the linear algorithms when no privacy is introduced are about 2.25 ∘ C and 2.85 ∘ C respectively. For non-linear algorithms, the corresponding error values are higher. We also observe the same trend in the results of the second data-set.
{"title":"PAMDI: Privacy aware missing data inference scheme for sparse mobile crowd sensing","authors":"Tejendrakumar Thakur, N. Marchang","doi":"10.3233/ais-220475","DOIUrl":"https://doi.org/10.3233/ais-220475","url":null,"abstract":"The ubiquity of mobile devices has birthed one of the most promising IoT applications called Mobile Crowd Sensing (MCS) wherein mobile devices carried around by a crowd are used to sense phenomena of interest. Subsequently, sensed data are collected, aggregated and analysed to extract useful information. Sparse Mobile Crowd Sensing (SMCS) aims at reducing the sensing overhead (e.g., battery consumption, incentive cost, etc.) by lowering the number of sensing tasks performed. Sensed data thus collected are used to infer missing values. However, it must be ensured that user’s private information (e.g., user’s home location) cannot be derived from the sensed data shared by a user. We propose a novel approach entitled ‘Privacy Aware Missing Data Inference Scheme for Sparse Mobile Crowd Sensing (PAMDI)’ which employs the concept of perceptual hash for ensuring privacy while trying to maintain performance guarantees. Simulation results with the help of two real-world data-sets point towards the feasibility of the proposed approach for provisioning user privacy. We use regression algorithms for missing data inference in PAMDI and find that linear regression algorithms work best with the proposed privacy approach as compared to non-linear regression algorithms. Moreover, we observe that inference accuracy is more or less maintained even after introducing privacy with the proposed approach. In particular, for the first data-set (Temperature data-set), the mean absolute error (MAE) and root mean squared error (RMSE) values obtained by the linear algorithms using the proposed approach are about 2.65 ∘ C and 2 . 9 ∘ C respectively. On the other hand, the corresponding MAE and RMSE values generated by the linear algorithms when no privacy is introduced are about 2.25 ∘ C and 2.85 ∘ C respectively. For non-linear algorithms, the corresponding error values are higher. We also observe the same trend in the results of the second data-set.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"62 1","pages":"19-46"},"PeriodicalIF":1.7,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74230229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Preface to JAISE 15(1)","authors":"Andrés Muñoz, J. Augusto, H. Aghajan","doi":"10.3233/ais-235000","DOIUrl":"https://doi.org/10.3233/ais-235000","url":null,"abstract":"","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"75 1","pages":"113-114"},"PeriodicalIF":1.7,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86065192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Significant population growth and ongoing socioeconomic development have increased reliance on irrigated agriculture and agricultural intensification. However, accurately predicting crop water demand is problematic since it is affected by several factors such as weather, soil, and water properties. Many studies have shown that a hybrid irrigation system based on two irrigation strategies (i.e., evapotranspiration and soil-based irrigation) can provide a credible and reliable irrigation system. The latter can also alert farmers and other experts to phenomena such as noise, erroneous sensor signals, numerous correlated input and target variables, and incomplete or missing data, especially when the two irrigation strategies produce inconsistent results. Hence, we propose Multi-Target soil moisture and evapotranspiration prediction (MTR-SMET) for estimating soil moisture and evapotranspiration. These predictions are then used to compute water needs based on Food and Agriculture Organization (FAO) and soil-based methods. Besides, we propose an explainable MTR-SMET (xMTR-SMET) that explains the ML-based irrigation to the farmers/users using several explainable AI to provide simple visual explanations for the given predictions. It is the first attempt that explains and offers meaningful insights into the output of a machine learning-based irrigation approach. The conducted experiments showed that the proposed MTR-SMET model achieves low error rates (i.e., MSE = 0.00015, RMSE = 0.0039, MAE = 0.002) and high R 2 score (i.e., 0.9676).
显著的人口增长和持续的社会经济发展增加了对灌溉农业和农业集约化的依赖。然而，准确预测作物需水量是有问题的，因为它受到天气、土壤和水性质等多种因素的影响。许多研究表明，基于两种灌溉策略(即蒸散发和土壤灌溉)的混合灌溉系统可以提供可靠的灌溉系统。后者还可以提醒农民和其他专家注意噪声、错误的传感器信号、大量相关的输入和目标变量以及不完整或缺失的数据等现象，特别是当两种灌溉策略产生不一致的结果时。因此，我们提出了多目标土壤水分和蒸散发预测(Multi-Target soil moisture and evapotranspiration prediction, MTR-SMET)来估算土壤水分和蒸散发。然后将这些预测用于根据粮农组织(FAO)和基于土壤的方法计算水需求。此外，我们提出了一个可解释的MTR-SMET (xmrr - smet)，它使用几个可解释的人工智能为给定的预测提供简单的视觉解释，向农民/用户解释基于ml的灌溉。这是第一次尝试解释并为基于机器学习的灌溉方法的输出提供有意义的见解。实验表明，提出的MTR-SMET模型错误率低(即MSE = 0.00015, RMSE = 0.0039, MAE = 0.002)， r2得分高(即0.9676)。
{"title":"Towards an explainable irrigation scheduling approach by predicting soil moisture and evapotranspiration via multi-target regression","authors":"Emna Ben Abdallah, Rima Grati, Khouloud Boukadi","doi":"10.3233/ais-220477","DOIUrl":"https://doi.org/10.3233/ais-220477","url":null,"abstract":"Significant population growth and ongoing socioeconomic development have increased reliance on irrigated agriculture and agricultural intensification. However, accurately predicting crop water demand is problematic since it is affected by several factors such as weather, soil, and water properties. Many studies have shown that a hybrid irrigation system based on two irrigation strategies (i.e., evapotranspiration and soil-based irrigation) can provide a credible and reliable irrigation system. The latter can also alert farmers and other experts to phenomena such as noise, erroneous sensor signals, numerous correlated input and target variables, and incomplete or missing data, especially when the two irrigation strategies produce inconsistent results. Hence, we propose Multi-Target soil moisture and evapotranspiration prediction (MTR-SMET) for estimating soil moisture and evapotranspiration. These predictions are then used to compute water needs based on Food and Agriculture Organization (FAO) and soil-based methods. Besides, we propose an explainable MTR-SMET (xMTR-SMET) that explains the ML-based irrigation to the farmers/users using several explainable AI to provide simple visual explanations for the given predictions. It is the first attempt that explains and offers meaningful insights into the output of a machine learning-based irrigation approach. The conducted experiments showed that the proposed MTR-SMET model achieves low error rates (i.e., MSE = 0.00015, RMSE = 0.0039, MAE = 0.002) and high R 2 score (i.e., 0.9676).","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"9 1","pages":"89-110"},"PeriodicalIF":1.7,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76744498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Research on automated domestic appliances, categorized as Smart Home Technology (SHT), has increased exponentially over the last decade and has taken various guises, from qualitative descriptive investigation to empirically based analysis. Given the unresolved uncertainties surrounding the SHT acceptance literature and concern regarding the relatively low smart home device uptake, there is a need to reappraise the existing literature to delve deeper and search for solutions. Based on the research method PRISMA, a systematic literature review on SHT acceptance was undertaken to evaluate its different models and develop a hypothetical model. Twenty-three papers were selected in the review, and the results indicate that the Technological Acceptance Model was the most applied model when investigating SHT acceptance. Moreover, the most significant variables used to measure SHT acceptance were compatibility and perceived usefulness. The systematic literature review also revealed some significant patterns including the uptake of non-Western research and the use of sales and market share as a metric of SHT acceptance. Future directions on how researchers, smart home developers and governmental agencies can utilize the findings conclude the systematic review.
{"title":"A systematic literature review of Smart Home Technology acceptance","authors":"N. Daruwala, U. Oberst","doi":"10.3233/ais-220033","DOIUrl":"https://doi.org/10.3233/ais-220033","url":null,"abstract":"Research on automated domestic appliances, categorized as Smart Home Technology (SHT), has increased exponentially over the last decade and has taken various guises, from qualitative descriptive investigation to empirically based analysis. Given the unresolved uncertainties surrounding the SHT acceptance literature and concern regarding the relatively low smart home device uptake, there is a need to reappraise the existing literature to delve deeper and search for solutions. Based on the research method PRISMA, a systematic literature review on SHT acceptance was undertaken to evaluate its different models and develop a hypothetical model. Twenty-three papers were selected in the review, and the results indicate that the Technological Acceptance Model was the most applied model when investigating SHT acceptance. Moreover, the most significant variables used to measure SHT acceptance were compatibility and perceived usefulness. The systematic literature review also revealed some significant patterns including the uptake of non-Western research and the use of sales and market share as a metric of SHT acceptance. Future directions on how researchers, smart home developers and governmental agencies can utilize the findings conclude the systematic review.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"77 1","pages":"115-142"},"PeriodicalIF":1.7,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78946012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In indoor positioning problems, GPS technology used in outdoor positioning needs to be improved due to the characteristic features of wireless signals. There currently needs to be a generally accepted standard method for indoor positioning. In this study, an ecosystem consisting of Beacon devices, Bluetooth intelligent devices, and Wi-Fi access points has been created to propose an effective indoor location determination method by using Wi-Fi and BLE technologies in a hybrid way. First, RSSI (Received Signal Strength Indicator) data were collected using the fingerprint method. Then, Kalman Filter and Savitzky Golay Filter are used in a hybrid manner to reduce the noise on the obtained signal data and make it more stable. In the first part, using the collected data from Wi-Fi and Beacon devices, the Non-linear least squares method (NLLS), including Levenberg-Marquardt (LM), is used for indoor tracking. In the second part, a fingerprinting-based approach is tested. K Nearest Neighbor (KNN) and Support Vector Machine (SVM) algorithms estimate the area where the client is located. Each algorithm’s accuracy rate are calculated on different training and test data and presented.
在室内定位问题中，由于无线信号的特点，GPS技术在室外定位中的应用还有待改进。目前需要有一个公认的室内定位标准方法。本研究通过构建Beacon设备、蓝牙智能设备和Wi-Fi接入点组成的生态系统，提出了一种混合使用Wi-Fi和BLE技术的有效室内定位方法。首先，采用指纹法采集RSSI (Received Signal Strength Indicator)数据。然后，混合使用卡尔曼滤波和萨维茨基-戈莱滤波来降低所获得的信号数据中的噪声，使其更加稳定。在第一部分中，利用从Wi-Fi和Beacon设备收集的数据，使用非线性最小二乘法(NLLS)，包括Levenberg-Marquardt (LM)，进行室内跟踪。在第二部分中，测试了基于指纹的方法。K近邻算法(KNN)和支持向量机算法(SVM)估计客户端所在的区域。在不同的训练和测试数据上计算了每种算法的准确率。
{"title":"Hybrid indoor positioning for smart homes using WiFi and Bluetooth low energy technologies","authors":"Yunus Haznedar, Gulsum Zeynep Gurkas Aydin, Zeynep Turgut","doi":"10.3233/ais-220484","DOIUrl":"https://doi.org/10.3233/ais-220484","url":null,"abstract":"In indoor positioning problems, GPS technology used in outdoor positioning needs to be improved due to the characteristic features of wireless signals. There currently needs to be a generally accepted standard method for indoor positioning. In this study, an ecosystem consisting of Beacon devices, Bluetooth intelligent devices, and Wi-Fi access points has been created to propose an effective indoor location determination method by using Wi-Fi and BLE technologies in a hybrid way. First, RSSI (Received Signal Strength Indicator) data were collected using the fingerprint method. Then, Kalman Filter and Savitzky Golay Filter are used in a hybrid manner to reduce the noise on the obtained signal data and make it more stable. In the first part, using the collected data from Wi-Fi and Beacon devices, the Non-linear least squares method (NLLS), including Levenberg-Marquardt (LM), is used for indoor tracking. In the second part, a fingerprinting-based approach is tested. K Nearest Neighbor (KNN) and Support Vector Machine (SVM) algorithms estimate the area where the client is located. Each algorithm’s accuracy rate are calculated on different training and test data and presented.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"30 1","pages":"63-87"},"PeriodicalIF":1.7,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88061722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Juan Morales-García, A. Bueno-Crespo, Raquel Martínez-España, José M. Cecilia
Nowadays, human overpopulation is stressing our ecosystems in different ways, agriculture being a critical example as different predictions point towards food shortages in the near future. Accordingly, smart farming is becoming key to the optimization of natural resources so that different crops can be grown efficiently, consuming as few resources as possible. In particular, greenhouses have proved to be an effective way of producing a high volume of vegetables/fruits in a reduced space and within a short time span. Hence, optimizing greenhouse functioning results in less water use and nutrient consumption, less energy use, faster growth, and better product quality. In this article, we carry out an in-depth analysis of different machine learning (ML) models to improve climate control in smart greenhouses. As part of the analysis of the techniques we also considered 3 ways of pre-processing the data, as well as 12-hour and 24-hour forecasting. We focus on forecasting the indoor air temperature of an operational smart greenhouse, i.e. assessing the data anomalies that are inherently present in these environments due to the instability of IoT infrastructures. Several ML models are adapted to time series forecasting to provide an overview of these techniques and to find out which one performs better in this particular scenario. Our results show that, after statistically validating the results, the Random Forest Regression technique gives the best overall result with a mean absolute error of less than 1 degree Celsius.
{"title":"Data-driven evaluation of machine learning models for climate control in operational smart greenhouses","authors":"Juan Morales-García, A. Bueno-Crespo, Raquel Martínez-España, José M. Cecilia","doi":"10.3233/ais-220441","DOIUrl":"https://doi.org/10.3233/ais-220441","url":null,"abstract":"Nowadays, human overpopulation is stressing our ecosystems in different ways, agriculture being a critical example as different predictions point towards food shortages in the near future. Accordingly, smart farming is becoming key to the optimization of natural resources so that different crops can be grown efficiently, consuming as few resources as possible. In particular, greenhouses have proved to be an effective way of producing a high volume of vegetables/fruits in a reduced space and within a short time span. Hence, optimizing greenhouse functioning results in less water use and nutrient consumption, less energy use, faster growth, and better product quality. In this article, we carry out an in-depth analysis of different machine learning (ML) models to improve climate control in smart greenhouses. As part of the analysis of the techniques we also considered 3 ways of pre-processing the data, as well as 12-hour and 24-hour forecasting. We focus on forecasting the indoor air temperature of an operational smart greenhouse, i.e. assessing the data anomalies that are inherently present in these environments due to the instability of IoT infrastructures. Several ML models are adapted to time series forecasting to provide an overview of these techniques and to find out which one performs better in this particular scenario. Our results show that, after statistically validating the results, the Random Forest Regression technique gives the best overall result with a mean absolute error of less than 1 degree Celsius.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"27 1","pages":"3-17"},"PeriodicalIF":1.7,"publicationDate":"2023-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81807241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. M. Bhavadharini, P. Mercy Rajaselvi Beaulah, C. U. Om Kumar, R. Krithiga
Mobile Ad Hoc Networks (MANETs) are self-organizing, self-configuring, and infrastructure-less networks for performing multi-hop communication. The source mobile node can transmit the information to any other destination node, but it has limitations with energy consumption and battery lifetime. Since it appeals to a huge environment, there is a probability of obstacle present. Thus, the network requires finding the obstacles to evade performance degradation and also enhance the routing efficiency. To achieve this, an obstacle-aware efficient routing using a heuristic-based deep learning model is proposed in this paper. Firstly, the nodes in the MANET are employed for initiating the transmission. Further, it is needed to be predicted whether the node is malicious or not. Consequently, the prediction for link connection between the nodes is achieved by the Optimized Bi-directional Long-Short Term Memory (OBi-LSTM), where the hyperparameters are tuned by the Adaptive Horse Herd Optimization (AHHO) algorithm. Secondly, once the links are secured from the obstacle, it is undergone for routing purpose. Routing is generally used to transmit data or packets from one place to another. To attain better routing, various objective constraints like delay, distance, path availability, transmission power, and several interferences are used for deriving a multi-objective function, in which the optimal path is obtained through the AHHO algorithm. Finally, the simulation results of the proposed model ensure to yield efficient multipath routing by accurately identifying the intruder present in the network. Thus, the proposed model aims to reduce the objectives like delay, distance, and power consumption.
{"title":"An obstacle aware efficient MANET routing with optimized Bi-LSTM and multi-objective constraints on improved heuristic algorithm","authors":"R. M. Bhavadharini, P. Mercy Rajaselvi Beaulah, C. U. Om Kumar, R. Krithiga","doi":"10.3233/ais-220369","DOIUrl":"https://doi.org/10.3233/ais-220369","url":null,"abstract":"Mobile Ad Hoc Networks (MANETs) are self-organizing, self-configuring, and infrastructure-less networks for performing multi-hop communication. The source mobile node can transmit the information to any other destination node, but it has limitations with energy consumption and battery lifetime. Since it appeals to a huge environment, there is a probability of obstacle present. Thus, the network requires finding the obstacles to evade performance degradation and also enhance the routing efficiency. To achieve this, an obstacle-aware efficient routing using a heuristic-based deep learning model is proposed in this paper. Firstly, the nodes in the MANET are employed for initiating the transmission. Further, it is needed to be predicted whether the node is malicious or not. Consequently, the prediction for link connection between the nodes is achieved by the Optimized Bi-directional Long-Short Term Memory (OBi-LSTM), where the hyperparameters are tuned by the Adaptive Horse Herd Optimization (AHHO) algorithm. Secondly, once the links are secured from the obstacle, it is undergone for routing purpose. Routing is generally used to transmit data or packets from one place to another. To attain better routing, various objective constraints like delay, distance, path availability, transmission power, and several interferences are used for deriving a multi-objective function, in which the optimal path is obtained through the AHHO algorithm. Finally, the simulation results of the proposed model ensure to yield efficient multipath routing by accurately identifying the intruder present in the network. Thus, the proposed model aims to reduce the objectives like delay, distance, and power consumption.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43068757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Silvestro V. Veneruso, Yan Bertrand, F. Leotta, Estefanía Serral, Massimo Mecella
Scientific contributions in the area of smart environments cover different tasks of ambient intelligence including action and activity recognition, anomaly detection, and automated enactment. Algorithms solving these tasks need to be validated against sensor logs of smart environments. In order to acquire these datasets, expensive facilities are needed, containing sensors, actuators and an acquisition infrastructure. Even though several freely accessible datasets are available, each of them features a very specific set of sensors, which can limit the introduction of novel approaches that could benefit of particular types of sensors and deployment layouts. Additionally, acquiring a dataset requires a considerable human effort for labeling purposes, thus further limiting the creation of new and general ones. In this paper, we propose a model-based simulator capable to generate synthetic datasets that emulate the characteristics of the vast majority of real datasets while granting trustworthy evaluation results. The datasets are generated using the eXtensible Event Stream – XES international standard commonly used for representing event logs. Finally, the datasets produced by the simulator are validated against two real scenario’s logs from the literature.
{"title":"A model-based simulator for smart homes: Enabling reproducibility and standardization","authors":"Silvestro V. Veneruso, Yan Bertrand, F. Leotta, Estefanía Serral, Massimo Mecella","doi":"10.3233/ais-220016","DOIUrl":"https://doi.org/10.3233/ais-220016","url":null,"abstract":"Scientific contributions in the area of smart environments cover different tasks of ambient intelligence including action and activity recognition, anomaly detection, and automated enactment. Algorithms solving these tasks need to be validated against sensor logs of smart environments. In order to acquire these datasets, expensive facilities are needed, containing sensors, actuators and an acquisition infrastructure. Even though several freely accessible datasets are available, each of them features a very specific set of sensors, which can limit the introduction of novel approaches that could benefit of particular types of sensors and deployment layouts. Additionally, acquiring a dataset requires a considerable human effort for labeling purposes, thus further limiting the creation of new and general ones. In this paper, we propose a model-based simulator capable to generate synthetic datasets that emulate the characteristics of the vast majority of real datasets while granting trustworthy evaluation results. The datasets are generated using the eXtensible Event Stream – XES international standard commonly used for representing event logs. Finally, the datasets produced by the simulator are validated against two real scenario’s logs from the literature.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"32 1","pages":"143-163"},"PeriodicalIF":1.7,"publicationDate":"2023-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77972858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. Dunne, Oludamilare Matthews, Julio Vega, Simon Harper, Tim Morris
This systematic literature review presents the computational methods of human behaviour prediction research from Pentland and Liu’s seminal 1999 paper on human behaviour prediction to the latest research to date. The PRISMA framework for systematic reviews was used as the review methodology to structure this information aggregation. This review provides a high-level summary of the field with key areas identified for new research. The results show that there are frequently used datasets for training predictive models: MavHome, MavLab, LIARA, CASAS, PlaceLab, and REDD. Accuracies in the range of 43.9% to 100% for predictions of varying complexity. Common data structures for modelling behavioural data: Vectors, tables, trees, Markov models, and graphs. Algorithms that fall into three distinct categories: Machine Learning (NN, RL, LSTM), Probabilistic Graphical Models (namely Bayesian and Markov variants), and Statistical and Trend Analysis (ARIMA, Prophet). Additionally, we document other notably useful algorithms that fall outside of these three main categories including Jaro-Winkler and Levenshtein distances. Opportunities identified for further research include the use of audio as the data source for behaviour prediction methods, and applying times-series prediction machine learning algorithms (RNN, LSTM) to the smart home problem space.
{"title":"Computational methods for predicting human behaviour in smart environments","authors":"R. Dunne, Oludamilare Matthews, Julio Vega, Simon Harper, Tim Morris","doi":"10.3233/ais-210384","DOIUrl":"https://doi.org/10.3233/ais-210384","url":null,"abstract":"This systematic literature review presents the computational methods of human behaviour prediction research from Pentland and Liu’s seminal 1999 paper on human behaviour prediction to the latest research to date. The PRISMA framework for systematic reviews was used as the review methodology to structure this information aggregation. This review provides a high-level summary of the field with key areas identified for new research. The results show that there are frequently used datasets for training predictive models: MavHome, MavLab, LIARA, CASAS, PlaceLab, and REDD. Accuracies in the range of 43.9% to 100% for predictions of varying complexity. Common data structures for modelling behavioural data: Vectors, tables, trees, Markov models, and graphs. Algorithms that fall into three distinct categories: Machine Learning (NN, RL, LSTM), Probabilistic Graphical Models (namely Bayesian and Markov variants), and Statistical and Trend Analysis (ARIMA, Prophet). Additionally, we document other notably useful algorithms that fall outside of these three main categories including Jaro-Winkler and Levenshtein distances. Opportunities identified for further research include the use of audio as the data source for behaviour prediction methods, and applying times-series prediction machine learning algorithms (RNN, LSTM) to the smart home problem space.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"116 1","pages":"179-205"},"PeriodicalIF":1.7,"publicationDate":"2023-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74650138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Human action recognition (HAR) plays an important role in social interaction in various fields. This study proposes a light-weight skeleton and two-layer bidirectional LSTM-based Seq2Seq model (SB2_Seq2Seq) for HAR to trade off recognition accuracy, users’ privacy and computer resource usage. An experiment was conducted to compare the proposed SB2_Seq2Seq with other skeleton-based Seq2Seq models and non-skeleton RGB video frame-based LSTM, CNN and seq2seq models. The UCF50 dataset was used for model evaluation, where 60%, 20% and 20% for model training, validation and testing, respectively. The experimental results show that the proposed model achieves 93.54% accuracy with 0.0214 Mean Square Error (MSE), suggesting that the proposed model outperforms all the other models. Besides, it also shows that the proposed model achieves state-of-the-art accuracy compared with state-of-the-arts methods in literature.
{"title":"Seq2seq model for human action recognition based on skeleton and two-layer bidirectional LSTM","authors":"Shouke Wei, Jindong Zhao, Junhuai Li, M. Yuan","doi":"10.3233/ais-220125","DOIUrl":"https://doi.org/10.3233/ais-220125","url":null,"abstract":"Human action recognition (HAR) plays an important role in social interaction in various fields. This study proposes a light-weight skeleton and two-layer bidirectional LSTM-based Seq2Seq model (SB2_Seq2Seq) for HAR to trade off recognition accuracy, users’ privacy and computer resource usage. An experiment was conducted to compare the proposed SB2_Seq2Seq with other skeleton-based Seq2Seq models and non-skeleton RGB video frame-based LSTM, CNN and seq2seq models. The UCF50 dataset was used for model evaluation, where 60%, 20% and 20% for model training, validation and testing, respectively. The experimental results show that the proposed model achieves 93.54% accuracy with 0.0214 Mean Square Error (MSE), suggesting that the proposed model outperforms all the other models. Besides, it also shows that the proposed model achieves state-of-the-art accuracy compared with state-of-the-arts methods in literature.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":" ","pages":""},"PeriodicalIF":1.7,"publicationDate":"2023-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46595170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：