Falling is among the most damaging event elderly people may experience. With the ever-growing aging population, there is an urgent need for the development of fall detection systems. Thanks to the rapid development of sensor networks and the Internet of Things (IoT), human-computer interaction using sensor fusion has been regarded as an effective method to address the problem of fall detection. In this paper, we provide a literature survey of work conducted on elderly fall detection using sensor networks and IoT. Although there are various existing studies which focus on the fall detection with individual sensors, such as wearable ones and depth cameras, the performance of these systems are still not satisfying as they suffer mostly from high false alarms. Literature shows that fusing the signals of different sensors could result in higher accuracy and lower false alarms, while improving the robustness of such systems. We approach this survey from different perspectives, including data collection, data transmission, sensor fusion, data analysis, security, and privacy. We also review the benchmark data sets available that have been used to quantify the performance of the proposed methods. The survey is meant to provide researchers in the field of elderly fall detection using sensor networks with a summary of progress achieved up to date and to identify areas where further effort would be beneficial.

/pdf/elderly-fall-detection-systems-a-literature-survey-9nx87469di.pdf

Elderly Fall Detection Systems: A Literature Survey

A review on speaker recognition: Technology and challenges

Significance: Beer–Lambert law (BLL) is a widely used tool for contact and remote determination of absorber concentration in various media, including living tissues. Originally proposed in the 18th century as a simple exponential expression, it has survived numerous modifications and updates. The basic assumptions of this law may not be fulfilled in real measurement conditions. This can lead to mistaken or misinterpreted results. In particular, the effects to be additionally taken into account in the tissue measurements include anisotropy, scattering, fluorescence, chemical equilibria, interference, dichroism, spectral bandwidth disagreements, stray radiation, and instrumental effects.
Aim: We review the current state of the art and the main limitations of remote tissue diagnostics using the BLL. Historical development of updating this law by taking into account specific additional factors such as light scattering and photon pathlengths in diffuse reflectance is described, along with highlighting the main risks to be considered by interpreting the measured data.
Approach: Literature data related to extension and modification of the BLL related to tissue assessment and concentration estimation of specific tissue molecules are collected and analyzed. The main emphasis here is put on the optical measurements of living tissue chromophore concentrations and estimation of physiological parameters, e.g., blood oxygen saturation.
Results: Modified expressions of the BLL suitable for several specific cases of living tissue characterization are presented and discussed.
Conclusions: Applications of updated/modified Beer–Lambert law (MBLL) with respect to particular measurement conditions are helpful for obtaining more reliable data on the target tissue physiological state and biochemical content. MBLL accounting for the role of scattering in several ways appears to be a successful approach. Extended MBLL and BLL in the time domain form could provide more accurate results, but this requires more time resources to be spent.

/pdf/beer-lambert-law-for-optical-tissue-diagnostics-current-2fu247r9x1.pdf

Beer-Lambert law for optical tissue diagnostics: current state of the art and the main limitations.

Smart driver assistance system using raspberry pi and sensor networks

The autonomous vehicle steering system, a multi-input multi-output (MIMO) system, is challenging to design using traditional controllers due to the interaction between inputs and outputs. If PID controllers are used the control loops are executed independently of each other as there is no interaction between the loops. Designing a larger system increases the controller parameters requiring tuning. Model Predictive Control (MPC) overcomes this problem, as it is a multi-variable control method taking into account the interactions of the variables in the target system. Achieving a high safety level is also critical for autonomous vehicle systems. This can be provided by an MPC controller, which can handle constraints such as maintaining a safe distance from other cars. Wider applicability of the Model Predictive Controller calls for more efficient hardware architectures for implementation. The aim of this paper is to achieve optimal implementation of the MPC controller by increasing the computational speed in order to reduce execution time for optimization. An MPC controller is used to control the steering system of an autonomous vehicle to keep it on the desired path. A traditional MPC controller is used to control the system where the plant dynamics do not change, whereas an Adaptive MPC controller is used when the system is nonlinear or its characteristics vary with time (the longitudinal velocity changes as the vehicle moves). Results are discussed in terms of performance, resource utilization, cost, and energy-effective implementations taking into consideration a reasonable size number of constraints handled by the controller.

/pdf/model-predictive-control-for-automated-vehicle-steering-c7gvumhifv.pdf

Model Predictive Control for Automated Vehicle Steering

This paper reviews the state-of-the-art an automatic speech recognition (ASR) based approach for speech therapy of aphasic patients. Aphasia is a condition in which the affected person suffers from speech and language disorder resulting from a stroke or brain injury. Since there is a growing body of evidence indicating the possibility of improving the symptoms at an early stage, ASR based solutions are increasingly being researched for speech and language therapy. ASR is a technology that transfers human speech into transcript text by matching with the system’s library. This is particularly useful in speech rehabilitation therapies as they provide accurate, real-time evaluation for speech input from an individual with speech disorder. ASR based approaches for speech therapy recognize the speech input from the aphasic patient and provide real-time feedback response to their mistakes. However, the accuracy of ASR is dependent on many factors such as, phoneme recognition, speech continuity, speaker and environmental differences as well as our depth of knowledge on human language understanding. Hence, the review examines recent development of ASR technologies and its performance for individuals with speech and language disorders.

/pdf/automatic-speech-recognition-asr-based-approach-for-speech-319epgn7zg.pdf

Automatic speech recognition (ASR) based approach for speech therapy of aphasic patients: A review

We propose an analog-digital hybrid circuit model of one-dimensional cardiac tissue with hardware implementation that allows us to perform real-time simulations of spatially conducting cardiac action potentials. Each active nodal compartment of the tissue model is designed using analog circuits and a dsPIC microcontroller, by which the time-dependent and time-independent nonlinear current-voltage relationships of six types of ion channel currents employed in the Luo-Rudy phase I (LR-I) model for a single mammalian cardiac ventricular cell can be reproduced quantitatively. Here, we perform real-time simulations of reentrant excitation conduction in a ring-shaped tissue model that includes eighty nodal compartments. In particular, we show that the hybrid tissue model can exhibit real-time dynamics for initiation of reentries induced by uni-directional block, as well as those for phase resetting that leads to annihilation of the reentry in response to impulsive current stimulations at appropriate nodes and timings. The dynamics of the hybrid model are comparable to those of a spatially distributed tissue model with LR-I compartments. Thus, it is conceivable that the hybrid model might be a useful tool for large scale simulations of cardiac tissue dynamics, as an alternative to numerical simulations, leading toward further understanding of the reentrant mechanisms.

Reentrant excitation in an analog-digital hybrid circuit model of cardiac tissue

Driver’s drowsiness is one of the leading contributing factors to the increasing accidents statistics in Malaysia. Therefore, the design and development of driver drowsiness detection based on image processing using Raspberry Pi camera module sensor interfacing with Raspberry Pi 3 board are proposed in this paper. To achieve the aim of the research, the Haar Cascade Classifier algorithm is implemented for eyes and face detection whereas for eyes blink (open and close) detection, the Eye Aspect Ratio (EAR) algorithm is employed. From several experiments conducted on six recruited subjects, the findings revealed that the accuracy of Haar Cascade classifier to detect the eyes and faces was subjected to correct sitting position (head must facing to the camera) as well as the eyes must not be covered with glasses or shades. Meanwhile, the range of average EAR value detected by the system was between 0.141 (eyes closed) and 0.339 (eyes opened). In conclusion, the image processing-based Haar Cascade and EAR algorithms utilized on Raspberry Pi platform have been successfully executed. For future improvement, the current board can be replaced with Raspberry Pi Touch Screen to minimize the hardware setup and the physiological based analysis using alcohol and heart rate sensors can be added.

/pdf/implementation-of-haar-cascade-classifier-and-eye-aspect-525085gay9.pdf

Farhanahani Mahmud

Papers

Automatic speech recognition (ASR) based approach for speech therapy of aphasic patients: A review

Reentrant excitation in an analog-digital hybrid circuit model of cardiac tissue

Implementation of Haar Cascade Classifier and Eye Aspect Ratio for Driver Drowsiness Detection Using Raspberry Pi

An Analog-Digital Hybrid Model of Electrical Excitation in a Cardiac Ventricular Cell

Investigation on the Growth Process of Gold Nanoplates Formed by Seed Mediated Growth Method