Electronics and biomedical engineering

Artykuł powstał na prośbę redakcji miesięcznika naukowego "Wszechświat" i opisuje kolejne etapy zbliżania sią autora do owego miesięcznika - najpierw jako ucznia szkoły średniej szukającego wiedzy przyrodniczej, potem jako początkującego badacza prezentującego wyniki swoich badań, a potem jako autora i członka redakcji czasopisma. Wspomniani są też redaktorzy naczelni czasopisma: Jerzy Vetulani, Jacek Rajchel i Maria Śmiałowska.

W artykule powstałym jako zapis tak zwanego "wykładu mistrzowskiego", który autor miał obowiązek wygłosić podczas przyznawania mu godności honorowego profesora AGH, naszkicowano przebieg pierwszych działań, które w rezultacie doprowadziły do powstania kierunku studiów Inżynieria Biomedyczna na AGH. Wspomniano o tym, jak w latach 70. XX wieku zarówno inżynierowie, jak i medycy doszli do wniosku, że rozwój diagnostyki i terapii medycznej może zostać znacząco przyspieszony, gdy obok sposobu widzenia organizmu pacjenta jako swoistego reaktora chemicznego, weźmie się pod uwagę fakt, że w organizmie tym toczą się też liczne procesy fizyczne. Owe procesy można śledzić przy użyciu specjalnej technicznej aparatury diagnostycznej, a także można wspomagać za pomocą urządzeń technicznych pełniących rolę terapeutyczną. Droga od owego uświadomienia do realnego wykorzystania była jednak trudna i skomplikowana. Drogę tę w skrócie i uproszczeniu opisano w tekście artykułu.

Health monitoring of pregnant women is essential throughout the entire course of pregnancy to ensure proper growth of fetus. In gynecology centers and hospitals some special instruments are used to monitor the health conditions of mother and foetus. In practice, hospital based monitoring system is employed where the pregnant ladies move to the concerned centre to monitor their health. It becomes complex for them to travel and wait for long hours. To overcome this issue an instrument which is used to monitor the important parameters such as ECG (Electro cardio gram), respiration rate, heart rate and rate of dehydration is designed. All the parameters can be monitored on the computer screen which is IoT(Internet of Things) enabled so that the doctor can monitor these parameters as and when the patient uses the instrument kept at her home by fixing an appointment with the doctor. This technology has a desired impact on industrial and hospital automation. The hardware of this project is built on a printed circuit board, constituting PIC micro controller 18F4550. It is a versatile micro controller with in-built features such as 10 bit multi-channel ADC, USART, synchronous serial port, programmable low Voltage detection circuit etc., which is to be interfaced to PC system through RS232C. The software can be easily modified for any alarm setting or record intervals since it is written in Visual Basic.

this paper presents a new approach based on the continuous wavelet transform CWT and JADE algorithm for the blind source separation. The JADE algorithm has been widely used to separate the fECG and mECG signals from 8 recordings or channels, while not all of this number is needed. The present work will show that it isn’t the number of channels that counts but rather the quality of the channel used in terms of the energy or the information that it carries. That’s why before introducing the 8 channels to the JADE algorithm we will make a selection by the mathematical microscope Continuous Wavelet Transform CWT and we will show that the number of channels will be reduced to 5 or 3 or even to 2 channels. This algorithm has been validated on several real data. Keywords—blind source separation BSS. continuous wavelet transform. Independent Component Analysis ICA. JADE.

Monitoring systems in intensive care units (ICU) generate a high rate of false alarms 80% . This has the effect of desensitizing the medical staff and extending the response time to these alarms. In this work we present a new method to reduce false alarms in intensive care units that is based on packet wavelet decomposition and alarms classification by SVM.

This paper relates to the separation of single channel source signals from a single mixed signal by means of independent component analysis (ICA). The proposed idea lies in a time-frequency representation of the mixed signal and the use of ICA on spectral rows corresponding to different time intervals. In our approach, in order to reconstruct true sources, we proposed a novelty idea of grouping statistically independent time-frequency domain (TFD) components of the mixed signal obtained by ICA. The TFD components are grouped by hierarchical clustering and k-mean partitional clustering. The distance between TFD components is measured with the classical Euclidean distance and the β distance of Gaussian distribution introduced by as. In addition, the TFD components are grouped by minimizing the negentropy of reconstructed constituent signals. The proposed method was used to separate source signals from single audio mixes of two- and three-component signals. The separation was performed...

In this study we propose an automatic method for solving convolutive mixtures separation. The independent components are extracted by frequency domain analysis, where the convolutive model can be solved by instantaneous mixing model approach. The signals are reconstructed back in the observation space resolving the ICA model ambiguities. Simulations are carried out to test the validity of the proposed method

Portable products have exhibited two notable and conflicting trends over the last thirty years: They have simultaneously grown smaller and more complex. Superimposed on these trends is the unchanging size of the human hand. Together, these three curves define the limitations on miniaturization of portable products, a market segment inextricably entwined with our concept of the future. This thesis: (1) identifies the "ergonomic threshold" as the transition between electronic-limited miniaturization and interface-limited miniaturization, stating it to be an important juncture, affecting portable products directly, as well as creating an ongoing dynamic between the interface and electronic industries. (2) investigates the ergonomic threshold with respect to miniaturization technologies of the present and future, and identifies a notable gap in the stream of technologic advance along the miniaturization curve in terms of price and performance. As proof of this gap, several key...

Objective: to identify theoretical and legal problems associated with the steadily increasing spread of digital and biotechnologies’ development products; to assess the risks associated with this process that can change the position of a human in the society of the future; to develop and substantiate proposals to minimize risks and eliminate the identified problems through legal regulation.

Methods: the research is based on the methods of generalization of scientific and technical information and theoretical analysis used while studying the source materials; axiological and systematic approaches; the formal legal method and, in addition, methods of legal forecasting, primarily extrapolation, which made it possible to highlight the prospects for reforming law due to technological expansion.

Results: include a description of the dynamics of digital and bio-technologies’ development; a description of the changing social landscape with the emerging new types of entities that can affect the actual status of a human; a classification of risks threatening people due to the digital and biotechnologies development; a list of tasks whose solution based on law will help to eliminate, postpone or, at least, significantly reduce the severity of problems by increasing the time limit allotted to humanity to comprehend a number of conceptual points. The author presents arguments substantiating the need to develop special legal regulation in relation to new types of entities, the appearance of which becomes an inevitable result of the mentioned technologies’ development.

Scientific novelty: consists, first, in a comprehensive study of the development of interconnected groups of digital and biotechnologies, taking into account their increasing convergence; and, second, in the formulation of legal problems that need to be resolved due to the potential emergence of new types of entities with cognitive functions and capable of having a targeted intellectual impact on the environment and legal entities.

Practical significance: it is present in the answers given to the formulated legal questions, which contain suggestions and recommendations on the necessary adjustment of legal regulation and focus the attention of legal scholars on the problems arising from the pace and vectors of scienceconsuming technologies’ development.

Annotatsiya: Ushbu maqolada energiya samarador binolar haqida ma'lumot berildi. Aqilli uy haqida va uning imkoniyatlari aytib o'tildi. Aqilli uyning ijobiy va salbiy tomonlari sanab o'tildi. Aqilli uylar nima sababdan keng tarqalayotganligi haqida qisqacha so'z yuritildi. Kalit so'zlar: energiya samarador, energiya tejamkor, passiv uylar, aktiv uylar, aqilli shahar, aqilli uy.

Due to the continuous monitoring process of critical patients, Intensive Care Units (ICU) generate large amounts of data, which are difficult for healthcare personnel to analyze manually, especially in overloaded situations such as those present during the COVID-19 pandemic. Therefore, the automatic analysis of these data has many practical applications in patient monitoring, including the optimization of alarm systems for alerting healthcare personnel. In this paper, explainable machine learning techniques are used for this purpose, with a methodology based on age-stratification, boosting classifiers, and Shapley Additive Explanations (SHAP) proposed. The methodology is evaluated using MIMIC-III, an ICU patient research database. The results show that the proposed model can predict mortality within the ICU with AUROC values of 0.961, 0.936, 0.898, and 0.883 for age groups 18–45, 45–65, 65–85 and 85+, respectively. By using SHAP, the features with the highest impact in predicting mo...

Bugungi kunda barcha sohalar axborotlashuvi yuzaga kelmoqda. Bu esa kompyuter texnologiyasini yaxshi biladigan kadrlarga bo'lgan ehtiyojning oshishiga sabab bo'lyapti. Maktablarda ham informatika va axborot texnologiyalari fanining chuqurlashtirilib o'tilishi bejizmas, albatta. Ushbu maqola maktab o'quvchilariga informatika darslarida grafik muharrirlar to'g'risida tushunchalar berishga bag'ishlangan.

It shows the construction of an electronic system and a mobile application to reduce the risk of accident due to an explosion that could occur when forgetting the express pot on the stove, through the automatic closing of the gas supply when reaching a certain pressure in this utensil Cooking

IntraCavi represents a groundbreaking innovation in the field of neural interfaces, leveraging cranial nerve pathways to unlock unprecedented sensory and cognitive capabilities. Inspired by the decentralized nervous system of the octopus, IntraCavi integrates advanced multimodal stimulation methods, including focused ultrasound, electrical, and mechanical stimuli, to expand human abilities. This paper explores the system’s design, applications in neuromodulation, and implications for human-AI symbiosis, highlighting its potential to revolutionize rehabilitation, cognitive enhancement, and communication. By redefining the boundaries of human sensory and neural integration, IntraCavi opens the door to a new era of human potential.

IV Year Student, IV Year Student, IV Year Student, Associate Professor. 1,2,3,4,Department of Computer Science and Engineering, Panimalar Institute of Technology, Chennai. ----------------------------------------------------------------------------***-------------------------------------------------------------------------ABSTRACT: Electromyography (EMG) signals are the electrical manifestations of muscle contractions. EMG signals may be weak or at a low level when there is only a small movement in the major corresponding muscle group or when there is a strong movement in the minor corresponding muscle group. Moreover, in a singlechannel EMG classification identifying the signals may be difficult. However, weak and single-channel EMG control systems offer a very convenient way of controlling human–computer interfaces (HCIs). Identifying upper-limb movements using a single-channel surface EMG also has a number of rehabilitation and HCI applications. The fractal analysis method, known...

The subjective logatom articulation index of speech signals enhanced by means of various digital signal processing methods has been measured. To improve intelligibility, the convolutive blind source separation (BSS) algorithm by PARRA and SPENCE [1] has been used in combination with classical denoising algorithms. The efficiency of these algorithms has been investigated for speech material recorded in two spatial configurations. It has been shown that the BSS algorithm can highly improve speech recognition. Moreover, a combination of the BSS with single-microphone denoising methods can additionally increase the logatom articulation index.

The subjective logatom articulation index of speech signals enhanced by means of various digital signal processing methods has been measured. To improve intelligibility, the convolutive blind source separation (BSS) algorithm by PARRA and SPENCE [1] has been used in combination with classical denoising algorithms. The efficiency of these algorithms has been investigated for speech material recorded in two spatial configurations. It has been shown that the BSS algorithm can highly improve speech recognition. Moreover, a combination of the BSS with single-microphone denoising methods can additionally increase the logatom articulation index.

The measurement of joint space width on hand X-ray images of Rheumatoid arthritis (RA) patient is a time consuming task. Manual method is observer dependent and it is less accurate. In this paper an automatic joint space width measurement is proposed using digital image processing techniques. For the removal of noise and image enhancement we used Gaussian filtering. Initial joint locations are obtained by second order derivatives filtering technique. Thresholding can be used to create binary images and morphological filter is used to remove small binary object. Joint space width is measured between two bones. The percentage of erosion is measured on the basis of bone area. The erosion of bone contour classify into classes pre-erosion, middle level erosion and severe level of erosion. The Feed forward neural network classifier is used to classify the Rheumatoid Arthritis (RA) and non-Rheumatoid Arthritis person.

The present research deals with the development of a social robot in the area of telemedicine for the remote monitoring and diagnosis of cardiovascular diseases in the elderly, through the application of innovative electronic methods focused on telemedicine, performing real analysis in individuals with problems cardiovascular, to know their vital signs and register them in a database, the same ones that help a medical specialist to diagnose correctly. The materials used in the present investigation were, a cardiac pulse sensor, body temperature sensor, Arduino programmable cards; in terms of software, the LabVIEW development platform was used. The study was carried out in the teaching hospital of Riobamba with the patients of a cardiology specialist. As for the analysis of results, the values of an electrocardiogram and the application developed in LabVIEW were compared, proving that the measurements taken by the prototype are the same as an electrocardiogram, which allowed to accel...

This paper deals with the problem of signal modeling using fractional-order linear prediction. In this research, we obtain the closed-form expression of the optimum sampling frequency of the One-Parameter Fractional-order Linear Prediction (OPFLP) and examine the performance when the fractional order (alpha) is in (0<=alpha<=2). Our investigation focuses on determining optimum alpha within the individual ranges of 0<=alpha<=1 and 1<=alpha<=2 while considering various influential parameters, such as sampling frequency and environmental interferences. We initiate our study by examining the impact of the sampling frequency, a critical parameter that demands meticulous selection, on the optimal value ‎of‎‎ alpha. Simulation Results demonstrate that if the sampling rate falls within five to six times the maximum frequency of the signal under scrutiny, the optimal range for alpha resides within 1<=alpha<=2. Conversely, when the sampling frequency exceeds six times the maximum signal frequency, the optimal alpha shifts to 0<=alpha<=1. This observation underscores the crucial relationship between sampling frequency and the appropriate selection of the fractional order alpha for effective OPFLP performance. In the next step, we assess the robustness of OPFLP in handling challenging signal processing tasks, particularly in hands-free speech acquisition applications. We evaluate the model's performance and robustness against environmental interferences in three scenarios: noisy environments, reverberant environments, and noisy-reverberant settings. Simulation outcomes highlight OPFLP's superior robustness compared to second-order LP in handling environmental interferences. Furthermore, our investigations elucidate that noise exerts a more detrimental impact on OPFLP performance than reverberation, emphasizing the nuanced effects of these interferences on the model's efficacy.

The detection of Paroxysmal Atrial Fibrillation (PAF) is a fairly complex process performed manually by cardiologists or electrophysiologists by reading an electrocardiogram (ECG). Currently, computational techniques for automatic detection based on fast Fourier transform (FFT), Bayes optimal classifier (BOC), k-nearest neighbors (K-NNs), and artificial neural network (ANN) have been proposed. In this study, six features were obtained based on the morphology of the P-Wave, the QRS complex and the heart rate variability (HRV) of the ECG. The performance of this methodology was validated using clinical ECG signals from the Physionet arrhythmia database MIT-BIH. A feedforward neural network was used to detect the presence of PAF reaching a general accuracy of 97.4%. The results obtained show that the inclusion of the information of the P-Wave, HRV and QR Electrical alternans increases the accuracy to identify the PAF event compared to other works that use the information of only one or...

In the present paper we have designed and implemented a typical and simple Home Automation System using GSM (Global System for Mobile Communication) technology that controls electrical devices at home from a remote location by a simple mobile phone. This is achieved by sending an SMS to receiver present at home which is in turn connected to a hardware kit. The SMS received by the receiver is transmitted to the microcontroller which reads the message and controls the appropriate device. This operation is performed by program written in assembly language code that is stored in the flash memory which is in-built into the microcontroller. The practical implementation of the present prototype has been successful to control some electrical devices using an embedded circuit via SMS.

One of the common way or method to authenticate identity of person is biometric recognition system.With the growing employment of the iris recognition systems and associated research to support this, the need for large databases of iris images is growing. Iris is considered to be the most unique attribute possessed by an individual and is regarded as the most reliable form of biometric authentication. Iris portion of the eye image is complex annular part it contains many distinctive features such as arching ligaments, furrows and ridges. The compression algorithms developed for iris images have to preserve the details present in the iris part of the image, which are used for subsequent biometric processes. We propose here, a compression scheme of iris images using Mallat based wavelet transform using Directional Filter Bank. Mallat algorithm is based on the multiresolution, and it represents the wavelet transform as a pyramid. Directional Filter Bank provides the flexibility to obta...

In this paper, we propose a frequency-domain method employing robust independent component analysis (RICA) to address the multichannel Blind Source Separation (BSS) problem of convolutive speech mixtures in highly reverberant environments. We impose regularization processes to tackle the ill-conditioning problem of the covariance matrix and to mitigate the performance degradation. We evaluate the impact of several parameters on the performance of separation, e.g., windowing type and overlapping ratio of the frequency domain method. We then assess and compare different techniques to solve the frequencydomain permutation ambiguity. Furthermore, we develop an algorithm to separate the source signals in adverse conditions, i.e. high reverberation conditions when short observation signals are available. Finally, through extensive simulations and real-world experiments, we evaluate and demonstrate the superiority of the presented convolutive algorithmic system in comparison to other BSS algorithms, including recursive regularized ICA (RR-ICA) and independent vector analysis (IVA).

In the realm of wearable medical device design, the paramount goal is to enhance battery life while navigating time and cost barriers to deliver an optimal user experience. Balancing the performance-power trade-off is a formidable task for developers as power consumption escalates with system performance in battery-powered devices. Wearable medical devices, enabled by portability, often enhanced utility by obviating the need for cumbersome equipment. The trend towards handheld or wearable products necessitates microcontroller units (MCUs) with low power consumption and heightened energy efficiency. The evolution of smaller yet potent wearables challenges battery suppliers to engineer compact, high-capacity batteries, thereby reducing the dependence on non-renewable energy sources for recharging. Solar-powered wearable medical devices converge healthcare technology with renewable energy, inspiring innovative solutions for health monitoring with sustained device operability. Energy optimization and prolonged battery life are paramount in designing these devices to ensure seamless functionality in monitoring vital signs and biometric data. This research endeavours to elevate energy efficiency and operational longevity in solar-powered medical wearables through strategic optimization of performance, energy efficiency, and reliability across varied indoor and outdoor scenarios while adhering to stringent design prerequisites. Leveraging generative AI techniques empowers device design with adaptability, heightened reliability, and clinician-endorsed validation [8] [9].

The Cardiovascular disease is the leading and main cause of death worldwide. Researchers are constantly seeking to develop new monitoring systems, high-level identification and diagnosis technology for the early stages of the disease. This study aimed to design and manufactured a low-cost, wireless, ECG patient monitoring system for cardiovascular disease diagnosis. This was achieved using an Arduino, AD8232 heart rate sensor, and LabVIEW for pre-processing cardiac signals, to detect any abnormalities in the heart rhythm. This detection system followed two phases. Firstly, Arduino is used to collect data and deliver the input signals to LabVIEW. This was used to process and analyse the ECG signal as part two of the proposed technology. The analysis of heartbeats from the designed circuits are studied based on algorithms coded within Arduino Integrated Development Environment (IDE). The AD8232 sensor is used to measure the electrical activities (ECG signals) of the heart. The ECG sensor (AD8232) is an integrated signal conditioning block for ECG recordings of the patient through three electrodes attached to the patient’s body and other bio-potential measurement applications. In this study, a monitoring system of patient's health is proposed, via specialized sensors, to determine the heart rate, oxygen level, and temperature. The system operated by triggering alerts if any of the measured values were abnormal and produce alert messages to the specialist physician and the patient’s next-of-kin with the patient’s location. Three heart diseases (coronary heart disease and two types of Peripheral arterial diseases) were identified in this study, by comparing the PQRS ECG signals with the standard values of the waves. The technology proposed in this study is expected to assist doctors diagnose various heart diseases by detecting disturbances in heart rate. In this study, a clinical trial data set (cardiology ECG recording) was recorded to determine the clinical utility of this technique.
Keywords: Cardiovascular disease, ECG monitoring

The separation of moving audio sources from their mixtures is practically more useful as well as challenging in the area of source separation. In this paper, a microphone pair is used to capture the signals of multiple moving audio sources. It is assumed that the sources are static ...

Segmentasi citra merupakan bagian dari ilmu pemrosesan citra. Segmentasi citra sangat penting khususnya pada citra medis. Dalam penelitian ini dibahas mengenai segmentasi citra dengan menggunakan dasar teknik Geometric Deformable Model (GDM), yaitu metode Level Set. Dalam melakukan deteksi tepi citra medis, metoda Level Set dinilai memiliki kelebihan daripada teknik curve evolution lainnya, yaitu ketahanannya terhadap noise dan kemampuan berevolusi melalui bidang concave. Percobaan dilakukan dengan pengujian terhadap beberapa citra sintetis, baik itu citra sintetis tanpa variansi noise dan dengan variansi noise. Noise diambil berupa salt and pepper dengan beberapa nilai variansi. Pengujian dilanjutkan dengan citra medis yang didapat dari alat medis MRI (Magnetic Resonance Imaging).

Monitoring blood pressure (BP) is a fundamental step in the physiological assessment of the cardiovascular system, particularly given that high BP carries a significant risk for stroke, heart failure, and other severe illnesses, while being avoidable. Certain parallels between the Aortic Pressure waveform and other health signals that may be quickly and continuously obtained, such as photoplethysmography (PPG), can be observed. A promising method called photoplethysmography (PPG) was created to enable non-invasive, routine, or even continuous detection of blood volume change. This led to the recent development of numerous techniques for predicting BP from the PPG signal. In this study, to predict diastolic and systolic blood pressure, models are created using PPG signal. To represent BP with less features than traditional models, a variety of regression and classification models (Random Forest, LSTM, and more) are constructed, and feature reduction strategies (Pearson Correlation, ANOVA, and more) are used. Models trained on PPG data are created that perform as accurately as or better than more current, cutting-edge algorithms. Furthermore, it is demonstrated that equivalent outcomes are achieved with a large reduction of features: 0.988 tested on 10 features random forest and 1.602 MAE for DBP and 2.082 MAE for SBP tested on random forest (100 trees).

The Jaipur limb has revolutionized the treatment of amputees in India costs only about $30 compared to a prosthetic foot in the U.S. costing $8,000. Jaipur limb is given away free to the many handicapped poor who have lost a limb.  The attempt was made to replicate the model on a smaller scale without any financial help from others in a small private hospital in Surat is presented. The manufacturing process of the Jaipur foot, its advantages and drawbacks, its cost, the short coming in the project and possible reasons of inability to sustain the project is presented here.

In this paper, a circularly polarized printed monopole antenna (CPPMA) is proposed for medical microwave imaging and health monitoring applications. The proposed CPPMA is optimized to operate at the Industrial, Scientific and Medical (ISM) band. A prototype of the designed antenna is fabricated and printed on the low-cost FR-4 substrate that has a compact size of 34 × 28 × 1.5 mm 3. The simulated results indicate that the designed CPPMA operates between 2.425 GHz and 2.475 GHz while the measured results range between 2.32 GHz and 2.515 GHz. The designed CPPMA also reveals a circular polarization performance at 2.45 GHz (2.4386 GHz-2.4633 GHz). The suitability of CPPMA for microwave imaging is confirmed by checking its aptitudes to detect the presence of breast tumors and brain strokes. A great detection capability is achieved for breast tumors and brain strokes of various sizes inserted at different positions with a high sensitivity to changes or anomalies in the dielectric properties of human tissues. In addition, the usefulness of the proposed CPPMA for wearable application is justified experimentally. Excellent agreement is achieved between the simulated results and the measured ones. Index Terms-Breast tumor and brain stroke detection, circularly polarized printed monopole antenna (CPPMA), industrial scientific and medical (ISM) band, medical microwave imaging and health monitoring, phantom models, wearable antenna.

This project discusses about  car-park system using peripheral interface controller (PIC) Microcontroller application.  This system includes three blocks; parking space monitoring unit, seven segment display unit and entrance and exit monitoring unit.  The parking space monitoring unit includes mechanical normally open push buttons as space sensors and green light emitting diodes, indicator module with a small scaled model, located at the entrance, interfaced with peripheral interface controller (PIC) Microcontroller. Entrance and exit monitoring unit detects the presence of car at the entrance and exit respectively and provides data to PIC Microcontroller in real time. Seven segments display, displays the number of parking space available, the number of cars that are in the car park at present and the number of cars that utilizes the car park for a day. And, the seven segment display indicates full when the car park is filled to its capacity. The PIC microcontroller processes this data in order to update the information supplied to the ports.

This paper considers the problem of two-channel speech enhancement with a single target speaker in a diffuse noise field and proposes a novel algorithm for estimating the power spectral density (PSD) of the background noise. First, a reference noise signal is computed as the output of a blocking matrix based on blind source separation (BSS). Then the ratio between the target noise PSD and the reference noise PSD is calculated by exploiting the separation matrix obtained from BSS and the spatial coherence of the noise field which is assumed to be known. The proposed algorithm can also operate during speech active periods, which is advantageous especially in fast-changing non-stationary noise fields. Experimental results show that the proposed algorithm outperforms existing methods, both in terms of noise PSD estimation and noise suppression.

Real-time continuous tracking of seizure state is necessary to develop feedback neuromodulation therapy that can prevent or terminate a seizure early. Due to its high temporal resolution, high scalp coverage, and non-invasive applicability, electroencephalography (EEG) is a good candidate for seizure tracking. In this research, we make multiple seizure state estimations using a mixed-filter and multiple channels found over the entire sensor space; then by applying a Kalman filter, we produce a single seizure state estimation made up of these individual estimations. Using a modified wrapper feature selection, we determine two optimal features of mixed data type, one continuous and one binary analyzing all available channels. These features are used in a state-space framework to model the continuous hidden seizure state. Expectation maximization is performed offline on the training and validation data sets to estimate unknown parameters. The seizure state estimation process is performed for multiple channels, and the seizure state estimation is derived using a square-root Kalman filter. A second expectation maximization step is utilized to estimate the unknown square-root Kalman filter parameters. This method is tested in a real-time applicable way for seizure state estimation. Applying this approach, we obtain a single seizure state estimation with quantitative information about the likelihood of a seizure occurring, which we call seizure probability. Our results on the experimental data (CHB-MIT EEG database) validate the proposed estimation method and we achieve an average accuracy, sensitivity, and specificity of 92.7%, 92.8%, and 93.4%, respectively. The potential applications of this seizure estimation model are for closed-loop neuromodulation and longterm quantitative analysis of seizure treatment efficacy.

Mitral valve prolapse (MVP) is one of the cardiovascular valve abnormalities that occurs due to the stretching of mitral valve leaflets, which develops in around 2 percent of the population. MVP is usually detected via auscultation and diagnosed with an echocardiogram, which is an expensive procedure. The characteristic auscultatory finding in MVP is a mid-to-late systolic click which is usually followed by a highpitched systolic murmur. These can be easily detected on a phonocardiogram which is a graphical representation of the auscultatory signal. In this paper, we have proposed a method to automatically identify patterns in the PCG that can help in diagnosing MVP as well as monitor its progression into Mitral Regurgitation. In the proposed methodology the systolic part, which is the region of interest here, is isolated by preprocessing and thresholded Teager-Kaiser energy envelope of the signal. Scalogram images of the systole part are obtained by applying continuous wavelet transform. These scalograms are used to train the convolutional neural network (CNN). A two-layer CNN could identify the event patterns with nearly 100% accuracy on the test dataset with varying sizes (20%-40% of the entire data). The proposed method shows potential in the quick screening of MVP patients.

Mitral valve prolapse (MVP) is one of the cardiovascular valve abnormalities that occurs due to the stretching of mitral valve leaflets, which develops in around 2 percent of the population. MVP is usually detected via auscultation and diagnosed with an echocardiogram, which is an expensive procedure. The characteristic auscultatory finding in MVP is a mid-to-late systolic click which is usually followed by a highpitched systolic murmur. These can be easily detected on a phonocardiogram which is a graphical representation of the auscultatory signal. In this paper, we have proposed a method to automatically identify patterns in the PCG that can help in diagnosing MVP as well as monitor its progression into Mitral Regurgitation. In the proposed methodology the systolic part, which is the region of interest here, is isolated by preprocessing and thresholded Teager-Kaiser energy envelope of the signal. Scalogram images of the systole part are obtained by applying continuous wavelet transform. These scalograms are used to train the convolutional neural network (CNN). A two-layer CNN could identify the event patterns with nearly 100% accuracy on the test dataset with varying sizes (20%-40% of the entire data). The proposed method shows potential in the quick screening of MVP patients.

This work describes a condition based reporting technique of a multi-machine System using GSM technology. In this present approach, a dedicated microcontroller based hardware unit (DHU) has been developed to continuously measure the parameters of the motors viz. voltage, current, speed etc. to monitor the running condition of each motor in a plant. In a multi-machine monitoring system each motor is connected with one such DHU, which are also connected to a Global System for Mobile Communication (GSM) modem. The preliminary level of fault or abnormality in operation of each machine is diagnosed by the respective DHU and the fault or abnormalities details are reported to the pre-assigned operator through an SMS service. In extreme case, the provision of machine shut down by a return SMS is also provided. A proto-type lab model is set up and is working satisfactorily.

A unique design and meander line implantable antenna is examined in this paper which satisfies the requirements of ultra-wide band. The designed antenna is integrated with the electromagnetic band gap (EBG) structure based ground plane to enhance the performance. Rectangular electromagnetic band gap (EBG) structures are represented here to evaluate the antenna performance. This compact and efficient MLA antenna is applied to improve the antenna performance for numerous implantable scenarios and biomedical applications. The proposed antenna with EGB ground plane is designed for both the simplified model and anatomical realistic models for the human body and executed the performance in bio-environment. To approve the results of implantable antennas more correctly, simulation is analyzed using anatomical realistic human models. The ultimate design has the whole dimension is 15.2 x 8.8 m2. The thickness of the antenna is about 0.8 mm. FR4 is chosen as the substrate material and Copper i...

Stroke is the second cause of death and the third cause of disability in the world. One of the treatments for post-stroke patients is physiotherapy. This treatment is expensive and requires mobility. Additionally, the level of adherence of post-stroke patients in carrying out physiotherapy also influences the effectiveness of healing. Therefore, this research proposes a new tool-named "the Post-Stroke Range of Motion (ROM) Measurement Tool with Black Box Boundary Value Analysis Testing-for physiotherapy telemonitoring of post stroke patients. This tool is designed on the left hand for measuring the ROM with the integration of MPU6050, MAX30102, and Flex sensors connected to ESP WROOM 32. This study uses a quantitative research type with a laboratory and field experimental method approach. The flex sensor was tested by measuring the minimum and maximum resistance values, which are converted into straight (0<11), bending (11<46), and fully bending (46<90), and the software was tested using the Black Box Boundary Value Analysis method. The outcomes unveil that the proposed system-with its various features-has the potential to be widely applied, and readily utilized by patients in physiotherapy rehabilitation exercise at home.

Due to the various dangers involved, especially tropical cyclones, they are one of the most common and deadly calamities in the world. The very important primary step in monitoring this destructive disaster is by estimating its intensity. The aim of this research is to determine intensity of cyclones. For the estimation of cyclones and determination of their intensity, various methods have been created. It is a difficult task which requires speed and efficiency. This paper shows comparison between various types of deep learning algorithms on infrared satellite imagery dataset for tropical cyclone intensity estimation. A side-by-side comparison research revealed that the detection of the tropical cyclone intensity evaluated via the models derived from different machine learning algorithms is significantly impacted by the use of various infrared (IR) channels.

Background: Semantic Classification and region growing of brain MRI using CANFIS model for Tumor Identification. Objective: Tumor identification in brain MRI by incorporating semantics in feature extraction and region growing phase. Statistical features using wavelet and semantic features using novel method are extracted from the input MRI image. These features are fed into the neuro fuzzy classifier for normal and abnormal image identification. Results: The result of implementation shows the efficiency of semantic segmentation technique in identifying the pathological tissues accurately from the MRI images. The effectiveness of the system is measured with the parameters such as accuracy, specificity and sensitivity. Conclusion: The concept of semantics and feature extraction enables extraction of region of interest based on relationship between the components of objects in the image. Semantic region growing solves the problem of over segmentation and false edge deduction.

In this paper, we present a novel technique for the estimation of the high frequency components (4-8kHz) of speech signals from narrow-band (0-4 kHz) signals using convolutive Non-Negative Matrix Factorisation (NMF). The proposed technique utilizes a brief recording of simultaneous broad band and narrow band signals from a target speaker to learn a set of broad-band non-negative bases for the speaker. The low-frequency components of these bases are used to determine how the high-frequency components must be combined in order to reconstruct the high-frequency components of new narrow-band signals from the speaker. Experiments reveal that the technique is able to reconstruct broadband sppech that is perceptually virtually indistinguishable from true broadband recordings.

In the frequency domain, convolutive mixes with blind source separation can be successfully resolved. But the permutation issue in frequency-domain blind source separation needs to be resolved. We investigated the impact of frequency space and separation performance at each frequency bin on the amplitude correlation permutation algorithm with the goal of addressing the permutation ambiguity problem in frequency-domain blind source separation of convolutive mixtures, and we proposed an enhanced permutation algorithm. The improved algorithm uses spacing influence weight and performance influence weight to control the influence of the frequency bins sorted in the neighborhood on the frequency bins unsorted. Experiments have shown that the two influence weights are effective. Finally, blind source separation experiments are performed on the speech signals under the two convolutive mixing models and the simulated room mixing model. According to experiments, the increased signal to interference plus noise ratio of separated signals demonstrates that the improved algorithm outperforms the amplitude correlation permutation algorithm in terms of separation performance and robustness.

Intelligent machines are increasingly being used to restore and augment the user’s body. The restorative or augmentative nature of implantable chips, bionic limbs, biomimetic organs, neuroprostheses, etc., has been interpreted in many ways (see, among others, de Vignemont 2024). There are two basic ways of approaching the question of technological restoration and augmentation of the human body. The first way emphasizes the aspect of replacement. Sophisticated artificial intelligence (AI) can, at least ideally, replace existing motor, sensory, and body-related subjective abilities of the human user. This approach, which I call ‘body replacement’, builds on a conventional interpretation of computing as an artificial activity that uses human-made machines to process information in digital form. The second way sees computing as an activity inherent in the natural body that can be used by humans to create nature-inspired intelligent machines. In the so-called natural computing perspective (Adamatzky 2017), AI complements the human body by enhancing human bodily capabilities (‘body supplementation’). In this article, I present and discuss the two approaches, namely body replacement and body augmentation, following a case study strategy. The so-called neuro-reality (Houser 2017), generated by an advanced brain-computer interface (nanometric brain chips receive signals with ‘single-neuron resolution’ and transmit them wirelessly to extracorporeal computers or smartphones. See Drew 2024), is analyzed as a relevant case of body replacement. On the other hand, neuroprosthetics, especially visual neuroprostheses (implantable medical devices capable of reactivating visual neurons through electrical stimulation. For details, see Borda and Ghezzi 2022), are studied as a highly informative example of the supplementation of the user’s body by intelligent machines. The analysis of the case study brings to light the philosophical underpinnings of both the replacement and augmentation approaches to restorative and augmentative technology. Body replacement is found to be informed by a radical functionalism, according to which bodily states are identified by their functional role, i.e. by 'what they do'. Otherwise, material constituents are centralized through bodily supplementation. To understand what bodily states are, you have to look at what they are made of. What kind of representation of the human being is supported by the replacement and the suppletive approach?

A baby incubator is a biomedical equipment that can provide warmth, humidity, and adjust the amount of oxygen input into a chamber for premature newborn babies for ideal conditions similar to those of the mother. Newly born babies or preterm babies are very sensitive to rough environments. Newborn mortality has been a global issue worldwide. Sleep Apnea disorder is a major concern in newborn neonates. Adding to this, newborns may have immature, underdeveloped lungs that necessitate care and additional oxygen. Existing models available in the market are expensive and at the same time very difficult to be used in remote locations like rural maternity centers, makeshift primary health centers or war-affected areas. Due to these issues, a Portable baby incubator is necessary that can provide the same environmental conditions as a mother's womb does and monitors the baby's vital conditions such as heartbeat, blood oxygenation level, skin temperature etc. The COVID-19 epidemic has made healthcare a top priority. Being physically present with the patients has become a huge problem for doctors. In such cases, implementing an application with hospital equipment such as a Smart Baby Incubator is necessary. Our goal is to make a smart baby incubator that can detect a baby's vital parameters and indicate its deviation, from its normal state. The model is integrated with the mobile app so that doctors can track the baby's condition remotely. In the presented model baby's temperature, heart rate and SpO 2 are monitored continuously. The efficiency of the model is tested on neonates and different age groups. The results obtained are found within the standard medical condition limits.