For the Instituto Mexicano del Seguro Social (IMSS), population aging represents a major challenge as a social security institution. This is why the Epidemiological Research and Health Care Services Unit/Aging Area has developed multi-disciplinary research concerning the older adult population, in order to contribute with programs of prevention, detection and attention of that age group and develop policies with plural perspective in which the voices of the older adults can be heard.

Aging and health

In the era of the Internet of Things (IoT) and Industry 4.0, the indoor usage of smart devices is expected to increase, thereby making their location information more important. Based on various practical issues related to large delays, high design cost, and limited performance, conventional localization techniques are not practical for indoor IoT applications. In recent years, many researchers have proposed a wide range of machine learning (ML)-based indoor localization approaches using Wi-Fi received signal strength indicator (RSSI) fingerprints. This survey attempts to provide a summarized investigation of ML-based Wi-Fi RSSI fingerprinting schemes, including data preprocessing, data augmentation, ML prediction models for indoor localization, and postprocessing in ML, and compare their performance. Any ML-based study is heavily reliant on datasets. Therefore, we dedicate a significant portion of this survey to the discussion of dataset collection and open-source datasets. To provide good direction for future research, we discuss the current challenges and potential solutions related to ML-based indoor localization systems.

/pdf/machine-learning-based-indoor-localization-using-wi-fi-rssi-1bn2qkrcux.pdf

Machine Learning Based Indoor Localization Using Wi-Fi RSSI Fingerprints: An Overview

We propose a comprehensive sensing platform called SenStick, which is composed of hardware (ultra tiny all-in-one sensor board), software (iOS, Android, and PC), and 3D case data. The platform aims to allow all the researchers to start IoT research, such as activity recognition and context estimation, easily and efficiently. The most important contribution is the hardware that we have designed. Various sensors often used for research are embedded in an ultra tiny board with the size of 50 mm ( ) × 10 mm ( ) × 5 mm ( ) and weight around 3 g including a battery. Concretely, the following sensors are embedded on this board: acceleration, gyro, magnetic, light, UV, temperature, humidity, and pressure. In addition, this board has BLE (Bluetooth low energy) connectivity and capability of a rechargeable battery. By using 110 mAh battery, it can run more than 15 hours. The most different point from other similar boards is that our board has a large flash memory for logging all the data without a smartphone. By using SenStick, all the users can collect various data easily and focus on IoT data analytics. In this paper, we introduce SenStick platform and some case studies. Through the user study, we confirmed the usefulness of our proposed platform.

/pdf/senstick-comprehensive-sensing-platform-with-an-ultra-tiny-s0izl5ojlr.pdf

SenStick: Comprehensive Sensing Platform with an Ultra Tiny All-In-One Sensor Board for IoT Research

Nowadays, smart mobile devices include more and more sensors on board, such as motion sensors (accelerometer, gyroscope, magnetometer), wireless signal strength indicators (WiFi, Bluetooth, Zigbee), and visual sensors (LiDAR, camera). People have developed various indoor positioning techniques based on these sensors. In this paper, the probabilistic fusion of multiple sensors is investigated in a hidden Markov model (HMM) framework for mobile-device user-positioning. We propose a graph structure to store the model constructed by multiple sensors during the offline training phase, and a multimodal particle filter to seamlessly fuse the information during the online tracking phase. Based on our algorithm, we develop an indoor positioning system on the iOS platform. The experiments carried out in a typical indoor environment have shown promising results for our proposed algorithm and system design.

/pdf/probabilistic-multi-sensor-fusion-based-indoor-positioning-1fd69ike7h.pdf

Probabilistic Multi-Sensor Fusion Based Indoor Positioning System on a Mobile Device

The LifeChair is a smart cushion that provides vibrotactile feedback by actively sensing and classifying sitting postures to encourage upright posture and reduce slouching. The key component of the LifeChair is our novel conductive fabric pressure sensing array. Fabric sensors have been explored in the past, but a full sensing solution for embedded real world use has not been proposed. We have designed our system with commercial use in mind, and as a result, it has a high focus on manufacturability, cost-effectiveness and adaptiveness. We demonstrate the performance of our fabric sensing system by installing it into the LifeChair and comparing its posture detection accuracy with our previous study that implemented a conventional flexible printed PCB-sensing system. In this study, it is shown that the LifeChair can detect all 11 postures across 20 participants with an improved average accuracy of 98.1%, and it demonstrates significantly lower variance when interfacing with different users. We also conduct a performance study with 10 participants to evaluate the effectiveness of the LifeChair device in improving upright posture and reducing slouching. Our performance study demonstrates that the LifeChair is effective in encouraging users to sit upright with an increase of 68.1% in time spent seated upright when vibrotactile feedback is activated.

/pdf/lifechair-a-conductive-fabric-sensor-based-smart-cushion-for-1dk8hrme76.pdf

LifeChair: A Conductive Fabric Sensor-Based Smart Cushion for Actively Shaping Sitting Posture.

Rec-CNN: In-vehicle networks intrusion detection using convolutional neural networks trained on recurrence plots

In recent years, some bus companies have raised revenue by reviewing the route plan using the number of passengers. The company has a system that can automatically counts the number of passengers on an ongoing basis. But they are costly because they use cameras and sensors those are dedicated for counting. It is too expensive for bus companies that really need to reconsider their route planning to introduce the system. In order to solve this problem and realize efficient operation, we propose a method to count passengers by using a drive recorder and sensors those are already equipped with buses. Drive recorders and various sensors will be obliged by the government to be set up by bus operators in the future. We constructed a model using Random Forest Regression with the position of the bus from the GPS module in the buses, the position of the bus stop used for operation management, and the number of passengers estimated from the image processing method combining YOLOv3 and Deep SORT. As a result, the average correct answer rate when the passengers get on and off are 96.2% and 70.1% respectively. Our method which utilized non-dedicated camera achieved higher correct answer rate than the conventional method which utilizes dedicated camera for counting passenger.

Passenger Counter Based on Random Forest Regressor Using Drive Recorder and Sensors in Buses

The number of computer controlled vehicles throughout the world is rising at a staggering speed. Even though this enhances the driving experience, it opens a new security hole in the automotive industry. To alleviate this issue, we are proposing an intrusion detection system (IDS) to the controller area network (CAN), which is the de facto communication standard of present-day vehicles. We implemented an IDS based on the analysis of ID sequences. The IDS uses a trained Long-Short Term Memory (LSTM) to predict an arbitration ID that will appear in the future by looking back to the last 20 packet arbitration IDs. The output from the LSTM network is a softmax probability of all the 42 arbitration IDs in our test car. The softmax probability is used in two approaches for IDS. In the first approach, a single arbitration ID is predicted by taking the class which has the highest softmax probability. This method only gave us an accuracy of 0.6. Applying this result in a real vehicle would give us a lot of false negatives, hence we devised a second approach that uses log loss as an anomaly signal. The evaluated log loss is compared with a predefined threshold to see if the result is in the anomaly boundary. Furthermore, We have tested our approach using insertion, drop and illegal ID attacks which greatly outperform the conventional method with practical F1 scores of 0.9, 0.84, and 1.0 respectively.

ID Sequence Analysis for Intrusion Detection in the CAN bus using Long Short Term Memory Networks

Controller Area Network (CAN) is a de facto standard of in-vehicle networks. Since CAN employs broadcast communication and a slower network than other general networks (e.g. Ethernet, IEEE802.11), it is inherently vulnerable to Denial-of-Service (DoS) attacks. As a countermeasure against DoS attacks on CAN, a method for detecting a DoS attack using the entropy in a sliding window has been proposed. This method has a good advantage in terms of effectiveness and the small computational overhead. However, this method may only be effective against DoS attacks under naive conditions such as some higher priority messages. In addition, if an adversary can adjust the entropy of the DoS attack to its normal value, the conventional method cannot detect a DoS attack in which the adversary manipulates the entropy. We found this type of DoS attack, which is called an entropy-manipulated attack. In this paper, we propose a method that can detect an entropy-manipulated attack by using the similarity of two sliding windows. We confirmed that the proposed method detected the DoS attack in 100% of the cases in our experiment, and we showed that the detection time is up to 93% (14 μs) shorter than the conventional method.

/pdf/normal-and-malicious-sliding-windows-similarity-analysis-3d7sj6fvne.pdf

Normal and Malicious Sliding Windows Similarity Analysis Method for Fast and Accurate IDS Against DoS Attacks on In-Vehicle Networks

Indoor localization has been a hot area of research over the past two decades. Since its advent, it has been steadily utilizing the emerging technologies to improve accuracy, and machine learning has been at the heart of that. Machine learning has been increasingly used in fingerprint-based indoor localization to replace or emulate the radio map that is used to predict locations given a location signature. The prediction quality of a machine learning model primarily depends on how well the model was trained, which relies on the amount and quality of data used to train it. Data augmentation has been used to improve quality of the trained models by synthetically producing more training data, and several approaches were used in the literature that tackles the problem of lack of training data from different angles. In this paper, we propose DataLoc+, a data augmentation technique for room-level indoor localization that combines different approaches in a simple algorithm. We evaluate the technique by comparing it to the typical direct snapshot approach using data collected from a field experiment conducted in a hospital. Our evaluation shows that the model trained using the proposed technique achieves higher accuracy. We also show that the technique adapts to larger problems using a limited dataset while maintaining high accuracy.

Ismail Arai

Papers

Rec-CNN: In-vehicle networks intrusion detection using convolutional neural networks trained on recurrence plots

Passenger Counter Based on Random Forest Regressor Using Drive Recorder and Sensors in Buses

ID Sequence Analysis for Intrusion Detection in the CAN bus using Long Short Term Memory Networks

Normal and Malicious Sliding Windows Similarity Analysis Method for Fast and Accurate IDS Against DoS Attacks on In-Vehicle Networks

DataLoc+: A Data Augmentation Technique for Machine Learning in Room-Level Indoor Localization