FOCUS A novel hidden Markov model-based adaptive dynamic time warping (HMDTW) gait analysis for identifying physically challenged persons Sampath Dakshina Murthy Achanta 1 • T. Karthikeyan 2 • R. Vinothkanna 3 Ó Springer-Verlag GmbH Germany, part of Springer Nature 2019 Abstract Internet of things plays vital role in real-time applications, and the research thrust towards implementing IoT in gait analysis increases day by day in order to obtain efficient gait recognition mechanism. IoT in gait analysis is used to monitor and communicate the observing gait, and also to transfer data to others is the current trend which is available. This research work provides an efficient gait recognition system with IoT using dynamic time wrapping and naı ¨ve bays classifier as combination to obtain hybrid model. The objective of this research is identifying the patients or persons with walking disabilities in a crowded area and providing suitable alerts to them by monitoring the walking styles. So that the possibility of getting injured is avoided and the information related to the persons also alerted through IoT module. Also, IoT module is used to collect information from the sensors used in persons accessories and other places. Twenty-five males and 10 females are subjected to examine the proposed model in different locations and achieved the overall accuracy percentage of 92.15%. Keywords IoT  Gait  Sensors  Dynamic time warping 1 Introduction Injuries due to unbalanced walk are common for elder persons, and it is a major health issue present all over the world. In some cases, these injuries lead to sudden deaths as heart attacks and a survey reports that more than 2% of elder persons are dying due to unbalanced walking and the resulting injuries lead to death. The fear of falling while walking due to nerve issues sometimes is due to stroke, and it is called as cautious gait. These patients may loose the stride length and gait velocity and fall down easily at fraction of seconds. So, it is essential to identify the patients for predicting falls based on the gait characteristics over the stipulated time is important. The early stage identification helps the patients to prevent from injury, while they fall down. Walking-based injury in adults accounts into 23.6 million deaths by 2030 as per the US survey. It is time to develop a better automation system for identifying the patients using their gait so that the morality rate will decrease. The risk among the abnormal gait patients particularly for elder persons influenced many scientific researches. A common report says that approximately 55–65% of patients experience the instability in their walking style, motor impairment. Their daily activities affect due to this walking style and its after effects. A simple gait recogni- tion process is illustrated in Fig. 1, and the process starts from identifying the human gait. The data acquisition collects the preliminary information, and by using feature representation the gait features are summarized. Using dimensional reduction process, the variation between the normal gait and abnormal gait is observed, and then, classification is performed through the difference data. Gait analysis and gait cycle pattern play a major role in physical assessment of persons with walking disabilities, and this includes the kinematic analysis by observing the joint angles, accelerations, angular velocities. The study Communicated by Sahul Smys. & Sampath Dakshina Murthy Achanta sampathdakshinamurthy@gmail.com 1 Koneru Lakshmaiah Education Foundation, Guntur, Andhra Pradesh, India 2 Department of ECE, Koneru Lakshmaiah Education Foundation, Guntur, Andhra Pradesh, India 3 Department of ECE, Vivekanandha College of Engineering for Women, Tiruchengode, Tamil Nadu, India 123 Soft Computing https://doi.org/10.1007/s00500-019-04108-x