Give us 5 minutes and we will show you the best book to read today. This is it, the handbook of data mining and knowledge discovery that will be your best choice for better reading book. Your five times will not spend wasted by reading this website. You can take the book as a source to make better concept. Referring the books that can be situated with your needs is sometime difficult. But here, this is so easy. You can find the best thing of book that you can read.

Handbook of Data Mining and Knowledge Discovery

The existing action recognition systems mainly focus on generalized methods to categorize human actions. However, the generalized systems cannot attain the same level of recognition performance for new users mainly due to the high variance in terms of human behavior and the way of performing actions, i.e. activity handling. The use of personalized models based on similarity was introduced to overcome the activity handling problem, but the improvement was found to be limited as the similarity was based on physiognomies rather than the behavior. Moreover, human interaction with contextual information has not been studied extensively in the domain of action recognition. Such interactions can provide an edge for both recognizing high-level activities and improving the personalization effect. In this paper, we propose the context-aware personalized human activity recognition (CAPHAR) framework which computes the class association rules between low-level actions/sensor activations and the contextual information to recognize high-level activities. The personalization in CAPHAR leverages the individual behavior process using a similarity metric to reduce the effect of the activity handling problem. The experimental results on the “daily lifelog” dataset show that CAPHAR can achieve at most 23.73% better accuracy for new users in comparison to the existing classification methods.

/pdf/caphar-context-aware-personalized-human-activity-recognition-upxtskk7uc.pdf

CAPHAR: context-aware personalized human activity recognition using associative learning in smart environments

Computational social sensing is enabled by the Internet of Things at large scale. Using sensors, e. g., implemented in mobile and wearable devices, human behavior and activities can then be investigated, e.g., using according models and patterns. However, the obtained models are often not explicative, i. e., interpretable, transparent, and explanation-aware, which makes assessment and validation difficult for humans. This paper proposes a novel explicative classification approach featuring interpretable and explainable models. For this purpose, we embed a framework for building rule-based classifiers using class association rules. For evaluation, we apply two real-world datasets: One collected in the domain of personalized health using wearable sensors (accelerometers), the second one utilizing smartphone sensors for activity recognition. Our results indicate, that the proposed approach outperforms the baselines clearly, concerning both accuracy and complexity of the resulting predictive models.

Explicative human activity recognition using adaptive association rule-based classification

Explainable machine learning and artificial intelligence models have been used to justify a model's decision-making process. This added transparency aims to help improve user performance and understanding of the underlying model. However, in practice, explainable systems face many open questions and challenges. Specifically, designers might reduce the complexity of deep learning models in order to provide interpretability. The explanations generated by these simplified models, however, might not accurately justify and be truthful to the model. This can further add confusion to the users as they might not find the explanations meaningful with respect to the model predictions. Understanding how these explanations affect user behavior is an ongoing challenge. In this paper, we explore how explanation veracity affects user performance and agreement in intelligent systems. Through a controlled user study with an explainable activity recognition system, we compare variations in explanation veracity for a video review and querying task. The results suggest that low veracity explanations significantly decrease user performance and agreement compared to both accurate explanations and a system without explanations. These findings demonstrate the importance of accurate and understandable explanations and caution that poor explanations can sometimes be worse than no explanations with respect to their effect on user performance and reliance on an AI system.

Don't Explain without Verifying Veracity: An Evaluation of Explainable AI with Video Activity Recognition

Electronic communication is crucial for monitoring the rescue-relief operations and providing assistance to the affected people during and after disasters. Given the ubiquity of smartphones, we envision that smartphones with lost connection (due to damage) to the communications infrastructure are nevertheless integrated seamlessly into the network as far as possible. To achieve this, we propose to build ad hoc subnetworks of disconnected smartphones using the WiFi tethering technology and ultimately connect them to either the emergency communication equipment deployed in the disaster area or to other smartphones that have still the network connectivity. The proposed architecture for such integration and a defined software-based control through the emergency control center (ECC) enables battery aware collection of critical data through smartphone sensors. The developed solution supports mobility of all smartphones, including those that have lost direct cellular connectivity as well as those that have not and are willing to act as gateways. We demonstrate how the proposed scheme can be tied to the standardized wireless emergency alert service and how it can effectively handle mobility tolerant device discovery and data transfer.

https://dl.acm.org/doi/pdf/10.1145/3372145

A Smartphone-based Network Architecture for Post-disaster Operations Using WiFi Tethering

The analysis of human activity data is an important research area in the context of ubiquitous and social environments. Using sensor data obtained by mobile devices, e. g., utilizing accelerometer sensors contained in mobile phones, behavioral patterns and models can then be obtained. However, the utilized models are often not simple to interpret by humans in order to facilitate assessment, evaluation and validation, e. g., in computational social science or in medical contexts. In this paper, we propose a novel approach for generating interpretable rule sets for classification: We present an adaptive framework for mining class association rules using subgroup discovery, and analyze different techniques for obtaining the final classifier. The approach is investigated in the context of human activity recognition. For our evaluation, we apply real-world activity data collected using mobile phone sensors.

/pdf/adaptive-class-association-rule-mining-for-human-activity-4ocdnpaf9s.pdf

Adaptive class association rule mining for human activity recognition

By understanding a person's context, smart assistant systems aim to simplify and automate tasks. One type of useful context information is the mode of transportation. Commonly, the mode of transportation is recognized by analyzing raw sensor data of mobile devices, such as a smartphone. However, fine-grained sampling and collecting sensor data at high frequency to analyze raw sensor data is also conducted by activity recognition systems. These systems have been shown to accurately recognize activities such as sitting, standing, or walking. This means several systems analyze raw data for their needs. In our opinion, this doubled use of resources should be avoided. In this paper, we propose an approach, which avoids doubled raw sensor data analysis by taking advantage of the already available information of a person's activity. As a hypothesis, the approach assumes that observed activity sequences can lead to the mode of transportation. Thus, we aim to map activity sequences to modes of transportation. Applying the proposed approach, we show that the three different modes of transportation car, tram, and bus are recognized with an accuracy of up to 97 %.

An activity history based approach for recognizing the mode of transportation

Mobile devices are increasingly used for context recognition Recognition accuracies partly depend on the time synchronicity between the mobile devices used for data recording and labeling Mobile device synchronization can be done via the Internet or GPS, but both are not available in all areas This paper presents our novel approach "Event Driven Time Synchronization of Mobile Devices" that works anytime, anywhere The idea is to trigger sensor events on each device as much as possible at the same time The time difference of the sensor event occurrences is interpreted as the time difference between the devices, called time offset between the devices Our prototype utilizes proximity events to enable this Our evaluation shows that 99% of the time offsets vary not more than 60 ms Compared to this, only 17% are within this variance when using Network Time Protocol via a mobile High Speed Downlink Packet Access Internet connection

Event driven time synchronization of mobile devices

Smartphone sensors deliver useful information for applications such as indoor and outdoor navigation. An integral part of such applications is the detection of the orientation and movement direction of a smartphone user. Until now, movement direction detection using smartphones typically relies on GPS, which is often not available indoors. Alternatively, other approaches use sensors such as accelerometer and compass instead. These approaches rely on carrying the smartphone in a predefined orientation, or knowing the orientation of the smartphone in relation to the orientation of the user. In this paper, we present an approach to detecting the orientation and movement direction of users carrying smartphones inside the trouser pocket. This approach first determines the orientation of the smartphone's top using compass and orientation sensor. Second, this approach determines the orientation of the smartphone's screen, and the user's movement direction by observing compass and accelerometer during at least two steps the user takes. After these two steps, the approach is capable of continuously aligning smartphone orientation and user orientation. With our approach, the user is free to change direction, movement speed, or to stop moving at all. The smartphone can be placed in the trouser pocket arbitrarily. And the smartphone is free to wobble in the trouser pocket. How well our approach works, is investigated based on experimental measurements.

Dennis Kroll

Papers

Explicative human activity recognition using adaptive association rule-based classification

Adaptive class association rule mining for human activity recognition

An activity history based approach for recognizing the mode of transportation

Event driven time synchronization of mobile devices

Direction Detection of Users Independent of Smartphone Orientations