Demo System Research Articles

IoT Based Fire Extinguisher Rover

The objective of the paper is to study, analyze and design a fire detection and extinguisher system. This topic was acceptable because it covered a basic and important aspect in our modern life. The author has gained the valuable experience in the field of fire detection and alarm system from studying and conducting the project. The objectives of the project were to provide information on fire alarm system and the extinguishing techniques used in India and around the globe, to show the differences and similarity between the systems and the lack in existing systems used for fire detection. Secondly, in the practical part, the objective was to build a demo system to demonstrate how a basic fire alarm system works and the improvements can be added to it to make better systems to detect and extinguish fire in order to reduce the casualties and loss of capital. To achieve the purpose of this thesis, the author studied the main standards on fire detection and alarm systems in India and around the world. For the practical part, NodeMCU-ESP32 and Blynk Application are used as the control unit with other necessary components. Keywords Node MCU-ESP32, Blynk Application, Fire Detection, Fire Alarm System

Using a 3D heat map to explore the diverse correlations among elements and mineral species

This paper presents an enhanced 3D heat map for exploratory data analysis (EDA) of open mineral data, addressing the challenges caused by rapidly evolving datasets and ensuring scientifically meaningful data exploration. The Mindat website, a crowd-sourced database of mineral species, provides a constantly updated open data source via its newly established application programming interface (API). To illustrate the potential usage of the API, we constructed an automatic workflow to retrieve and cleanse mineral data from it, thus feeding the 3D heat map with up-to-date records of mineral species. In the 3D heat map, we developed scientifically sound operations for data selection and visualization by incorporating knowledge from existing mineral classification systems and recent studies in mineralogy. The resulting 3D heat map has been shared as an online demo system, with the source code made open on GitHub. We hope this updated 3D heat map system will serve as a valuable resource for researchers, educators, and students in geosciences, demonstrating the potential for data-intensive research in mineralogy and broader geoscience disciplines.

CareerMiner: Automatic extraction of professional network from large Chinese resume data

The professional contacts of a person, including their past colleagues and supervisors, can play an important role in job recommendation and intelligent human resources management. However, collecting such information on a large scale can be challenging and costly. In this paper, we propose CareerMiner, a system to automatically construct a dynamic professional network to capture people’s colleague and supervisor relationships based on inter-related work experiences in a large collection of Chinese resumes. Specifically, we extract fine-grained work affiliation and job title information from resume text using a customized Name Entity Recognition model and introduce a trie-like data structure to efficiently index the hierarchical affinities of the implicit organizational structure in work experiences. Then, the topology of leaf nodes is used to identify professional relationships. Experimental results on real-world resume data are presented to demonstrate the effectiveness of the proposed system. Additionally, we develop an open-source demo system that includes the main features of the system. We also conduct a case study to illustrate how CareerMiner can be utilized for the social science research and data mining applications of professional networks.

Clinker based on calcium looped meals from the Cleanker Project.

The Cleanker (CLEAN clinKER production by Calcium Looping process) project, financed in the framework of Horizon 2020 EU funding program, has demonstrated the feasibility of the integrated CaL concept at industrial scale in a new demo system realised in the Buzzi Unicem cement plant in Vernasca (IT). The Calcium Looping (CaL) CO2 capture process exploits the reversible reaction of limestone calcination/carbonation (CaCO3 ↔ CaO + CO2). The Cleanker pilot plant consists of the coupling of a carbonator and an oxyfuel calciner. When the flue gases from kiln (containing CO2) flow through the carbonator together with calcined meal, which acts as a CO2 sorbent, carbonation takes place and CO2 is fixed in calcium carbonate. CaO is then regenerated in the calciner, where the opposite reaction takes place, and the captured CO2 is released. When the lime/limestone looping is carried out through a carbonator and a calciner operated in oxyfuel, a concentrated CO2 stream is obtained that can be efficiently addressed towards CCS or CCUS processes. In the Cleanker Project, the possibility to use raw meal for clinker production has been exploited and the meals sampled at the outlet of the oxyfuel calciner have been characterised and used for producing clinker at a lab scale. Calcium looped (CaL) meals collected at different sampling point during the operation of the CaL plant were characterised by means of X-ray fluorescence spectroscopy, X-ray diffraction and particle size distribution. Electron scanning microscopy revealed significant differences in the surface of particles of the looped meals with respect to the original one, resulting from the loading and unloading of CO2 during the looping cycles. The meals were burnt in a laboratory furnace and the obtained clinkers have been characterised on a chemical, mineralogical and microscopical point of view, revealing the good burnability of all the meals and attesting the possibility to reintegrate the materials in the clinker production process. A lower alite/belite ratio in the clinker produced from the looped meals was observed: actually, the depletion of calcium during the recirculation of the meal in the calciner/carbonator system led to a reduction of the lime saturation factor influencing the mineralogical composition of the product.

Multimode OAM Convergent Transmission With Co-Divergent Angle Tailored by Airy Wavefront

Wireless backhaul offers a more cost-effective, time-efficient, and reconfigurable solution than wired backhaul to connect the edge-computing cells to the core network. As the amount of transmitted data increases, the low-rank characteristic of Line-of-Sight (LoS) channel severely limits the growth of channel capacity in the point-to-point backhaul transmission scenario. Orbital Angular Momentum (OAM), also known as vortex beam, is considered a potentially effective solution for high-capacity LoS wireless transmission. However, due to the shortcomings of its energy divergence and the specificity of multi-mode divergence angles, OAM beams have been difficult to apply in practical communication systems for a long time. In this work, a novel multi-mode convergent transmission with co-scale reception scheme is proposed. OAM beams of different modes can be transmitted with the same beam divergent angle, while the wavefronts are tailored by the ring-shaped Airy compensation lens during propagation, so that the energy will converge to the same spatial area for receiving. Based on this scheme, not only is the Signal-to-Noise Ratio (SNR) greatly improved, but it is also possible to simultaneously receive and demodulate OAM channels multiplexed with different modes in a limited space area. Through prototype experiments, we demonstrated that 3 kinds of OAM modes are tunable, and different channels can be separated simultaneously with receiving power increasing. The measurement isolations between channels are over 11 dB, which ensures a reliable 16-QAM multiplexing wireless transmission demo system. This work may explore the potential applications of OAM-based multi-mode convergent transmission in LoS wireless communications.

Metasurface-Based Modulation With Enhanced Interference Resilience

Reconfigurable Intelligent Surfaces (RISs) have great potential for Internet of Things (IoT) applications due to their cost-effectiveness and energy-efficiency. However, under the application of RIS, current RIS systems cannot actively predict and avoid interference, as evolving interference signals can dynamically change their frequency bands. To address this issue, we develop a learning-based dynamic RIS spectrum access scheme to avoid interference and enhance wireless transmission reliability. An intelligent metasurface-based modulation (MM) is designed for generating and reflecting anti-interference radio-frequency signals. Specifically, a Dyna-Q algorithm is employed at the RIS controller to learn the frequency of interference signals, which is used to determine the frequency of the carrier signals. Experiments are conducted on the proposed RIS demo system to evaluate its anti-interference capability, and the results show that our scheme leads to an increase of at least 50% in the system throughput. These numerical results demonstrate the effectiveness of proposed scheme.

Structural optimisation of the DEMO alternative divertor configurations based on FE and RBF mesh morphing

The DEMO tokamak exhibits extraordinary complexity due to the constraints and requirements pertaining to different fields of physics and engineering. The multidisciplinary nature of the DEMO system makes its design phase extremely challenging since different and often opposite requirements need to be accounted for. Toroidal field (TF) coils generate the toroidal magnetic field required to magnetically confine the plasma particles and support at the same time the poloidal field coils. They must bear tremendous loads deriving from electromagnetic interactions between the coil currents and the generated magnetic field. An efficient tokamak design aims at minimizing the energy stored in its magnetic field and hence at reducing the toroidal volume within the TF coils whose shape would hence ideally mimic co-centrically the shape of the plasma. In order to bear the enormous forces a D-shape is most suitable for the TF coils as it allows them to resist the very large compression on the inner side and to carry the electro-magnetic (EM) pressure mainly by membrane stresses preventing large bending to occur on the outer side. At the same time the divertor structures must fit within the TF coils and this requires adaptations of the TF coil shape in the case of so-called advanced divertor configurations (ADCs), which require larger divertor structures. This article shows the TF coils adapted to ADCs using a structural optimisation procedure applied to the reference shape. The introduced strategy takes as structural optimum the iso-stress profile associated to each coil. A continuous transformation, based on radial basis functions mesh morphing, turns the baseline finite element (FE) model into its iso-stress counterpart, with a series of intermediate configurations available for electromagnetic and structural investigations as output. The adopted strategy allowed to determine, for each of the ADC cases, a candidate shape. Static membrane stress levels during magnetization could be reduced significantly from more than 700 MPa to below 450 MPa.

Illumination-Insensitive Binary Descriptor for Visual Measurement Based on Local Inter-Patch Invariance

Binary feature descriptors have been widely used in various visual measurement tasks, particularly those with limited computing resources and storage capacities. Existing binary descriptors may not perform well for long-term visual measurement tasks due to their sensitivity to illumination variations. It can be observed that when image illumination changes dramatically, the relative relationship among local patches mostly remains intact. Based on the observation, consequently, this study presents an illumination-insensitive binary (IIB) descriptor by leveraging the local inter-patch invariance exhibited in multiple spatial granularities to deal with unfavorable illumination variations. By taking advantage of integral images for local patch feature computation, a highly efficient IIB descriptor is achieved. It can encode scalable features in multiple spatial granularities, thus facilitating a computationally efficient hierarchical matching from coarse to fine. Moreover, the IIB descriptor can also apply to other types of image data, such as depth maps and semantic segmentation results, when available in some applications. Numerical experiments on both natural and synthetic datasets reveal that the proposed IIB descriptor outperforms state-of-the-art binary descriptors and some testing float descriptors. The proposed IIB descriptor has also been successfully employed in a demo system for long-term visual localization. The code <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> of the IIB descriptor will be publicly available.

X-ray radioluminescent battery with near milliwatt output power using CsI:Tl single crystal scintillator

Low output power has long been the bottleneck of micro-radioisotope batteries as power supplies for the wireless sensor network, implantable medical equipment, and outer space exploration. Recently, x-ray radioluminescent batteries demonstrated the great potential to break the deadlock. In this work, we fabricated an x-ray radioluminescent battery with near milliwatt output power and demonstrated various potential applications. A 100% improvement on the conversion efficiency of 2.46% and the highest output power of 136.1 μW/cm2 were achieved when adopting a thallium doped cesium iodide (CsI:Tl) single-crystal scintillator in the battery. Subsequently, a 2 × 2 battery array was fabricated with a maximum output power of 466.9 μW and was used to power devices including micro-LEDs and a wireless sensor system with temperature monitoring. This demo system shows the feasibility of x-ray radioluminescent batteries as a long-lifetime micropower. The tremendous progress will draw broad attention on micro-nuclear batteries and inspire further exploration on the applications in the field of medical devices, space explorations, and Internet of Things.

A study on solid oxide electrolyzer stack and system performance based on alternative mapping models

In this study, a solid oxide electrolyzer cell (SOEC) stack model is developed based on an alternative mapping concept. The SOEC stack performance in a commercial hot box is systematically studied under different operating currents, flow rates, and flow directions. The results revealed that the SOEC stack operated in a hot box has thoroughly different temperature distributions, resulting in additional efficiency losses and an increase in thermal neutral voltage. The SOEC stack model computation results are summarized into stack performance diagrams and used in the system design. A 6-Nm 3 /h SOEC system with preheaters and recycling cathode materials is designed, and its performance is studied. The system efficiency is greatly influenced by the steam generator, and an external steam source can help increase the total efficiency of the system to more than 83%. Even the current increase may deteriorate the stack performance. It can increase the SOEC system efficiency by saving energy in the steam generator and preheaters. An increase in the flow rate around anode and cathode can improve the system capacity and efficiency. The system's maximum capacity is limited by the preheater heat balance and the stack output temperature. The feasible maximum system capacity is 33.4 kW electrolysis electric power input and 9.93 Nm 3 /h hydrogen production rate. At a constant system capacity, decreasing the air flow rate can minimize the heat losses in anode off-gas and achieve more than 87% nonsteam system efficiency. • A new SOEC stack modeling method based on the alternative mapping concept. • The differences of the stack performances in lab scale test and commercial installation circumstances are fully discussed. • A 6 m 3 /h SOEC demo system is designed and analyzed to get the best capacity and efficiency.

A Quasi-Steady State Model of a Solar Parabolic Dish Micro Gas Turbine Demonstration Plant

In the framework of the European Optimised Microturbine Solar Power system (OMSoP) project, a novel energy system for solar electricity production was developed, based on the integration of the solar dish technology with Micro Gas Turbines (MGT). A pilot plant with a capacity of 5–7 kWe was realized and installed at the ENEA Casaccia site (Rome) and went under testing to validate the feasibility of the technology and improve the current design. The present work deals with the development of a quasi-state system model, built in the Engineering Equation Solver environment, composed of different modules that correspond to the main system components. The system model was used to define the optimal system parameters, to help the elaboration on an operational strategy to maximize the overall plant efficiency, and to guide the improvement of the single components in view of their optimised design. From the analysis it emerged that the system in design conditions is able to generate, in nominal conditions, 4.5 kWe instead of the expected 5 kWe due to the limitation of the stator current to 13 A, while maximum levels of 5.6 kW could be achieved by “overcharging” the high-speed generator up to 15 A and operating the MGT at the very high speed of 150 krpm. From the transient simulation of the demo system on an annual basis, the maximum average output power is 3.58 kWe. Regarding the cycle efficiency, the annual averaged value is about 17%, whereas the target value is 21%. The improvement of the generator only does not seem to significantly increase the power output on the annual basis (3.75 kWe vs. 3.58 kWe). Differently, the improvement of the solar dish, with the upgrade of the other system components, would significantly increase the system power output to around ~10 kWe.

A Prototypical Network-Based Approach for Low-Resource Font Typeface Feature Extraction and Utilization

This paper introduces a framework for retrieving low-resource font typeface databases by handwritten input. A new deep learning model structure based on metric learning is proposed to extract the features of a character typeface and predict the category of handwrittten input queries. Rather than using sufficient training data, we aim to utilize ancient character font typefaces with only one sample per category. Our research aims to achieve decent retrieval performances over more than 600 categories of handwritten characters automatically. We consider utilizing generic handcrafted features to train a model to help the voting classifier make the final prediction. The proposed method is implemented on the ‘Shirakawa font oracle bone script’ dataset as an isolated ancient-character-recognition system based on free ordering and connective strokes. We evaluate the proposed model on several standard character and symbol datasets. The experimental results showed that the proposed method provides good performance in extracting the features of symbols or characters’ font images necessary to perform further retrieval tasks. The demo system has been released, and it requires only one sample for each character to predict the user input. The extracted features have a better effect in finding the highest-ranked relevant item in retrieval tasks and can also be utilized in various technical frameworks for ancient character recognition and can be applied to educational application development.

PupilEXT: Flexible Open-Source Platform for High-Resolution Pupillometry in Vision Research.

The human pupil behavior has gained increased attention due to the discovery of the intrinsically photosensitive retinal ganglion cells and the afferent pupil control path’s role as a biomarker for cognitive processes. Diameter changes in the range of 10–2 mm are of interest, requiring reliable and characterized measurement equipment to accurately detect neurocognitive effects on the pupil. Mostly commercial solutions are used as measurement devices in pupillometry which is associated with high investments. Moreover, commercial systems rely on closed software, restricting conclusions about the used pupil-tracking algorithms. Here, we developed an open-source pupillometry platform consisting of hardware and software competitive with high-end commercial stereo eye-tracking systems. Our goal was to make a professional remote pupil measurement pipeline for laboratory conditions accessible for everyone. This work’s core outcome is an integrated cross-platform (macOS, Windows and Linux) pupillometry software called PupilEXT, featuring a user-friendly graphical interface covering the relevant requirements of professional pupil response research. We offer a selection of six state-of-the-art open-source pupil detection algorithms (Starburst, Swirski, ExCuSe, ElSe, PuRe and PuReST) to perform the pupil measurement. A developed 120-fps pupillometry demo system was able to achieve a calibration accuracy of 0.003 mm and an averaged temporal pupil measurement detection accuracy of 0.0059 mm in stereo mode. The PupilEXT software has extended features in pupil detection, measurement validation, image acquisition, data acquisition, offline pupil measurement, camera calibration, stereo vision, data visualization and system independence, all combined in a single open-source interface, available at https://github.com/openPupil/Open-PupilEXT.

Protein deep profile and model predictions for identifying the causal genes of male infertility based on deep learning

A principal task in dissecting the genetics of complex traits is to identify causal genes for disease phenotypes. Millions of genes have been sequenced in data-driven genomics era, but their causal relationships with disease phenotypes remain limited, due to the difficulty of elucidating underlying causal genes by laboratory-based strategies. Here, we proposed an innovative deep learning computational modeling alternative (DPPCG framework) for identifying causal (coding) genes for a specific disease phenotype. In terms of male infertility, we introduced proteins as intermediate cell variables, leveraging integrated deep knowledge representations (Word2vec, ProtVec, Node2vec, and Space2vec) quantitatively represented as ‘protein deep profiles’. We adopted deep convolutional neural network (CNN) classifier to model protein deep profiles relationships with male infertility, creatively training deep CNN models of single-label binary classification and multi-label eight classification. We demonstrate the capabilities of DPPCG framework by integrating and fully harnessing the utility of heterogeneous biomedical big data, including literature, protein sequences, protein–protein interactions, gene expressions, and gene–phenotype relationships, and effective indirect prediction of 794 causal genes of male infertility and associated pathological processes. We present this research in an interactive ‘Smart Protein’ intelligent (demo) system (http://www.smartprotein.cloud/public/home). Researchers can benefit from our intelligent system by (i) accessing a shallow gene/protein-radar service involving research status and a knowledge graph-based vertical search; (ii) querying and downloading protein deep profile matrices; (iii) accessing intelligent recommendations for causal genes of male infertility and associated pathological processes, and references for model architectures, parameter settings, and training outputs; and (iv) carrying out personalized analysis such as online K-Means clustering.

Comparing Alternative Route Planning Techniques: A Comparative User Study on Melbourne, Dhaka and Copenhagen Road Networks

Many modern navigation systems and map-based services do not only provide the fastest route from a source location s to a target location t but also provide a few alternative routes to the users as more options to choose from. Consequently, computing alternative paths has received significant research attention. However, it is unclear which of the existing approaches generates alternative routes of better quality because the quality of these alternatives is mostly subjective. Motivated by this, in this paper, we present a user study conducted on the road networks of Melbourne, Dhaka and Copenhagen that compares the quality (as perceived by the users) of the alternative routes generated by four of the most popular existing approaches including the routes provided by Google Maps. We also present a web-based demo system that can be accessed using any internet-enabled device and allows users to see the alternative routes generated by the four approaches for any pair of selected source and target. We report the average ratings received by the four approaches and our statistical analysis shows that there is no credible evidence that the four approaches receive different ratings on average. We also discuss the limitations of this user study and recommend the readers to interpret these results with caution because certain factors may have affected the participants' ratings.

Toward Plant Energy Harvesting for 5G Signal Amplification

In this work, we design an electricity generation demo from plant microbial fuel cells (PMFCs) promoted by graphene quantum dots (GQDs) in the plant. The GQD material could promote the demo system ...

Mineral sequestration of CO2 from Vernasca Ca-looping demo system: scale up to a pilot

In recent years, carbon sequestration into thermodynamically stable carbonates has been developed as a promising carbon capture, utilization and storage (CCUS) method, especially, when alkaline industrial wastes are used as sorbents. The use of industrial wastes to sequester CO2 plays a dual role in environment protection, creating opportunities not only for capture and disposal of CO2 but also for recycling of wastes and promoting the transition to circular economy. The CLEANKER project (Horizon 2020 Project Clean clinker production by Calcium looping process) aims to build a CO2 mineralization pilot incorporated into Ca-looping demo system in Vernasca cement plant and use the re-carbonated wastes in concrete applications. Different types of wastes such as burnt oil shale (BOS) from Eesti, Balti and Auvere power plants as well as from Enefit280 oil producing unit in Estonia, concrete demolition wastes (CDW), cement by-pass dust (CBD) from Robilante, Italy, blast furnace slag (NSF) from Bremen, Germany were tested first in laboratory scale via dry and wet direct carbonation routes under the conditions of CO2-rich model gas flow of 70 – 100% CO2, simulating the Ca-looping system. The results show that selected types of BOS and cement wastes could be used as efficient binders in both dry and wet CO2 mineralization systems with binding capacities up to 0.18 kg of CO2 per kg of BOS and up to 0.24 kg of CO2 per kg of CBD. The activating effect of hydration as a pre-treatment method showed that at lower operating temperatures, the same level of CO2 capture can be achieved, thereby rendering the carbonization processes of similar industrial wastes more energy efficient. Moreover, the CO2 mineralization tests with BOS in a 46 L concrete mixer confirmed the applicability of wet carbonization process also in larger scale. Based on the results, the most promising materials, BOS and CBD, were selected for in the proposed CO2-mineralization process in wet conditions at ambient temperature. The pilot (200 L) was designed based on a commercially available concrete mixer integrated into CLEANKER Ca-looping demo system and equipped with CO2 inlets and outlets, as well as CO2, temperature and moisture sensors to detect the reaction progress. The re-carbonated wastes will be tested via concrete casting in order to demonstrate the quality of the commercial product in the following stages of the project.

A W-Band Single-Antenna FMCW Radar Transceiver With Adaptive Leakage Cancellation

This article presents a leakage cancellation architecture for single-antenna frequency-modulated continuous-wave (FMCW) radars at W-band. A shared antenna for transmitter (TX) and receiver (RX) can substantially reduce the form factor, cost, and complexity of radar modules. Due to the simultaneous operation of the TX and RX in FMCW radars, employing a shared antenna will, however, significantly increase TX-to-RX leakage, resulting in RX saturation and desensitization. Our proposed cancellation scheme employs analog feedback to confine the TX leakage right at the RX input port, and thus, relieves the ongoing RX chain from saturation. The proposed single-antenna transceiver (TRX) prototype was fabricated in 65-nm CMOS technology with a die area of 1 mm2. The output power of 2 dBm was achieved for the TX in a frequency range of 80–84 GHz. In addition, a conversion gain and noise figure of 45 and 15 dB was measured for the RX in the presence of the TX signal via a shared antenna port. TX-to-RX isolation of more than 45 dB was achieved in the operating W-band. The chip consumes 108 mW (80.5 mW for the TX and 27.5 mW for the RX) from a 1.2-V supply voltage. Moreover, the functionality of the single-antenna radar operation was verified by connecting the chip to an on -printed circuit board (PCB) $4 \times 8$ patch antenna array with a simulated gain of 15 dBi, implemented on RO3003 Rogers material. Using the single-antenna radar module as a demo system, a $40\times 50$ cm2 rectangular metallic plate was detected at a distance up to 19 m.

Design of an Online Brain-Computer Interface System Based on Field Programmable Gate Array

In the article, an online brain-computer interface (BCI) demo system based on Field Programmable Gate Array (FPGA) was designed. A colour visual stimulator based on a Video Graphics Array (VGA) monitor controlled by FPGA is designed to produce transient visual stimulations. An electroencephalography (EEG) acquisition module including active electrodes and driven-right-leg circuit is used to acquire the visual evoked potential (VEP) signal; Finite impulse response (FIR) filtering combined with an averaging method allows for extraction of the weak VEP signals. The template matching method is used in target identification. The FPGA is successfully used in the BCI system to complete multiple tasks such as the VGA controller, analog to digital (AD) converter controller, VEP signal processor and electronic device controller. Experiments show that the subjects’ transient VEP can successfully activate the electronic devices by the online BCI system which has relatively high identification accuracy. All these results show that the real time BCI demo system based on FPGA is feasible and effective.

Self-Synchronized, Continuous Body Weight Monitoring Using Flexible Force Sensors and Ground Reaction Force Signal Processing

Change patterns in body weight are significant indicators of a variety of medical conditions and in some instances, such as congestive heart failure, strong predictors of critical care interventions. The continuous monitoring of body weight can therefore help care givers and patients reduce the risks that are inherent in ignoring body weight changes or in measuring them infrequently. One possible approach to continuous body weight monitoring is to use shoe-integrated sensors. Such approach is however hampered by the lack of patient’s adherence to medical protocols and by the detrimental impact of motion artifacts on weight measurements during body movement. The objective of this paper is to show that both problems can be readily addressed by pushing body weight measurement into the background of the patient’s daily routine and by adapting piezoresistive flexible force sensors to the specific requirements of accurate body weight measurement during motion. The proposed solution is enabled by two major innovations. The first is a sensor array architecture that helps in collecting the total vertical GRF on each foot during the walk cycle. The second is based on extracting unique features from the waveforms of ground reaction forces (GRFs) as measured by the flexible force sensor array. This paper is dedicated to a full and detailed description of this second innovation that includes the extraction of GRF waveform features using real-time signal processing and the elimination of motion artifacts using accurate estimates of the vertical acceleration of the body’s center of mass. A prototype demo system of the proposed solution is described along with testing results using a human subject in various walk conditions. The prototype is comprised of three subsystems: the shoe-integrated flexible sensor array, a sentinel subsystem implemented as a wearable smart watch, and a communication subsystem between sensors and sentinel. The prototype is distinguished with several unique features that ensures its wearability and low cost, including its self synchronizing data collection and the absence of any inertial motion units.