Hariton Costin

• Professor, PhD
• Medical electronics and informatics at Grigore T. Popa University of Medicine and Pharmacy

We analyzed the possibility of detecting and predicting ventricular fibrillation (VF), a medical emergency that may put people’s lives at risk, as the medical prognosis depends on the time in which medical personnel intervene. Therefore, besides immediate detection of VF, the possibility of predicting VF 40 or even 50 min in advance was analyzed. F...

In this paper an evaluation method for neuromotor rehabilitation level is proposed. The method is completely non-invasive, based on the analysis of video sequences in which the patient performs certain relevant activities. In the first step, the position of the patient who is walking in the frontal plane is estimated in all frames of the video sequ...

Abstract— In this paper, a user authentication method based on biometric movement patterns is proposed. As input, the data acquired from the accelerometer of a wearable device is used. Using machine learning methods, i.e. k-Nearest Neighbors, Random Forests classifiers and a 1D Convolutional Neural Network, the person which performs a known activit...

This paper presents an intelligent decision system based on statistical learning that regards the tactics of an investor in predicting the next intraday stock price. Significant percentages can be won or lost depending on the tactics applied for buying/selling shares. This paper includes a case study regarding the efficiency of a group of machine l...

Classification performances for some classes of electrocardiographic (ECG) and electroencephalographic (EEG) signals processed to dimensionality reduction with different degrees are investigated. Results got with various classification methods are given and discussed. So far we investigated three techniques for reducing dimensionality: Laplacian ei...

In the context of the Covid-19 pandemic the pressure that is put on the medical systems is increasing exponentially. Healthcare systems resources are in general scarce, and hence they require policies that ensure the optimal usage of beds and utilization costs. The aim of this study is to explore how an artificial immune system approach for a multi...

The paper describes the evolution in design and implementation of a new complex electro-informatics assistive medical system used for the communication with neuromotor disabled patients. These patients are severe handicapped persons who cannot interfere with real world by normal ways like speech, writing or language signs. Fortunately, these person...

This book illustrates the rapid pace of development in intelligent assistive technology in recent years, and highlights some salient examples of using modern IT&C technologies to provide devices, systems and application software for persons with certain motor or cognitive disabilities. The book proposes both theoretical and practical approaches to...

A data clustering procedure based on the usage of nature inspired (NI) algorithms combined with chaotic sequences is proposed. Four NI algorithms: Particle Swarm Optimization (PSO), Multi Swarm Optimization (MSO), Cuckoo Search Algorithm (CSA) and Black Hole Algorithm (BHA) where combined with nine chaotic maps. The procedure was validated using a...

Gaze interaction is a computer access method that allows disabled people to control a computer with their eyes. Gaze interaction only requires the movement of the eye itself— the movement of other muscles is not required, making it a perfect solution for those with rehabilitative disabilities (paralysis, spinal cord injury, repetitive strain injury...

Heart rate variability has become an important marker for prognosis not only in cardiovascular, diabetic or renal patients, but also in oncological patients. Heart rate variability as an indicator of autonomic nervous system dysfunction is associated with cancer progression, cancer-relatedpain intensity, cancer-related fatigue and even quality of l...

The paper proposes a hand gesture recognition system based on support vector machine classification. The analysis was performed on two publicly available databases and one acquired in our laboratory. Methods based on computer vision provide improved results for the analysis of the databases in the literature. The analysis of the database acquired i...

This paper explores the behavior of the Flower Pollination Algorithm (FPA) and Particle Swarm Optimization (PSO) metaheuristic algorithm in resolving Resource Constrained Project Scheduling Problems (RCPSP) that can model certain practical issues in distributed applications. A RCPSP type problem has at the input a set of activities between which th...

Computational Intelligence Re-meets Medical Image Processing Analysis of Machine Learning Algorithms for Diagnosis of Diffuse Lung Diseases Background In the last decades, new optimization methods based on the nature's intelligence were developed. These metaheuristics can find a nearly optimal solution faster than other traditional algorithms even...

In the Image Processing (IP) domain, optimization algorithms have to be applied in many cases. Nature-inspired heuristics allow obtaining near optimal solutions using lower computing resources. In this paper the Fireworks Algorithm (FWA) behavior is studied for Image Registration (IR) problems. The IR results accuracy is analyzed for different type...

The nature inspired (NI) algorithms have demonstrated their capabilities in solving optimization problems in many domains with the advantage that the solution is obtained faster than using the classical methods. Almost every time a new NI algorithm is proposed the author claims that it is more efficient than other algorithms at least in solving a p...

In the last years the demographic changes and ageing of population increase health care demand. The growing number of chronic patients and elders requires close attention to their health conditions. In this paper we present the realization of a wireless remote monitoring system, based on body area network of medical sensors, capable to measure proc...

Cardiovascular diseases are one of the major problems of humanity and therefore one of their component, arrhythmia detection and classification drawn an increased attention worldwide. The presence of randomness in discrete time series, like those arising in electrophysiology, is firmly connected with computational complexity measure. This connectio...

This paper presents a comparison of different threshold-based selection methods, implemented and adapted for eye image segmentation. We used three subclasses of segmentation methods: fixed threshold segmentation (fixed threshold, quantitative threshold and cumulative distribution function method), global threshold segmentation (minimum error Kittle...

Aim: Fetal acidosis is a consequence of anaerobic metabo-lism due to lack of or a limited amount of oxygen delivered through the umbilical cord to the fetus. Direct determination of fetal blood pH remains the current method used in practice and needs fetal blood extraction. This is an elaborate procedure and cannot be performed or re-peated anytime...

The implementation of a hand gesture detection using a stereo camera system is used to determine the hand position in a space described by two intersecting planes and the finger position by determining the finger tips, which leads to the classification of the hand image viewed from above into six different types. The hand movement is simulated usin...

Monitoring of the evolution of the pregnancy from early stages presents high interest due to the possibility of identifying high risk situations that can be further managed by health care professionals. One of the more recent and promising methods of monitoring fetal and maternal physiological wellbeing is the electrohysterogram (EHG) which is a no...

In this paper, we propose to present real solutions for close self-monitoring of older adults, given the permanent assistance and rapid intervention needed in emergency medical situations. The recent medical devices integrate existing or in development technologies that are easy to use, affordable, accessible and sustainable solutions that addres...

Traditional methods of fetal monitoring are used mainly during labor, leaving the only course of action  the caesarean intervention  in cases with high risk of fetal distress. We used another approach and set up a database that consists of cardiotocographic (CTG) recordings acquired ante partum during the 25th-28th week of pregnancy, by means of...

Eye-tracking devices are currently used for improving communication and psychosocial status among patients with neuro-motor disabilities. This paper presents the experimental implementation of a control system for a robotic platform using eye tracking technology. The main system is based on an eye tracking subsystem that uses the circular Hough tra...

In this paper we propose to investigate the possibility to use the randomness from different types of arrhythmias for detection and classification of them from ECG signals. Randomness present in discrete time series is strongly connected with complexity of information present in substrings associated with time series and an appropriate coding of th...

Optimization procedures are often encountered in computer applications. These procedures can be more or less complex depending on the complexity and number of functions to optimize and also on the size of the problem domain and required precision. To obtain faster a near optimal solution the nature inspired algorithms were defined and used in the l...

Image registration (IR) is the process of geometric overlaying or alignment f two or more 2D/3D images of the same scene (unimodal registration), taken r not at different time slots, from different angles, and/or by different image acquisition ystems (multimodal registration). Technically, image registration implies complex optimization of differen...

Besides medical and pharmacy specialists, the engineering branch has a main role in modern health care, characterized by high medical technology, powerful software programs for data analysis, and top management tools to increase efficiency of the health care system. Among many engineering specialties, bioengineers and biomedical engineers, even if...

Image processing problems often require optimization algorithms to be applied. In this paper some aspects concerning the behavior of Bat and Cuckoo Search optimization algorithms are presented. The obtained accuracy and the processing time depend on the input images characteristics, chosen optimization criteria, dimension of the search space and, l...

The experiment proposes to identify the minimum required time of exposure to generate decoding and meaning at visual lexical items and identify the relation between type of stimulus, reaction times and stimulus exhibition duration. A group of 50 persons was tested at a lexical decision task using lists of intermixed word, pseudoword, non-words and...

The experiments used a patented psycho-verbal stimulation interface to study the origin of cognitive visual N400 evoked potential onset in reading process. The acquisition was performed in Oz, Pz, Cz, Fz leads, on a group of 50 normal persons, in two experiments. First experiment aims to probe the automatic origin of N400 by delivered each 500 word...

This paper presents the implementation of a research project focused on the use of robotics as an effective tool in teaching technical disciplines to dyslexic children. Dyslexia is the most common learning disability and affects between 5 and 12 percent of all students. The goal of this project is to develop educational programs which will boost sc...

The experiments used a patented psycho-verbal stimulation interface to study the origin of cognitive visual N400 evoked potential onset in reading process. The acquisition was performed in Oz, Pz, Cz, Fz leads, on a group of 50 normal persons, in two experiments. First experiment aims to probe the automatic origin of N400 by delivered each 500 word...

In the last three decades many research teams have been doing advanced researches to develop accurate positioning and telemonitoring technologies. We developed an experimental model, a very light and ergonomic mobile platform, to identify cases with high human risk factor inside buildings. For positioning we designed an advanced INS/ GPS integrated...

In this review article, we present some challenges and opportunities in Ambient Assisted Living (AAL) for disabled and elderly people addressing various state of the art and recent approaches particularly in artificial intelligence, biomedical engineering, and body sensor networking.

Parkinson’s disease (PD) is a neurodegenerative disorder that occurs due to a progressive degeneration of dopaminergic (DA) neurons. Brain area affected by progressive destruction of neurons controls movements, and patients with PD reveal rigid and uncontrollable gestures, postural instability, small handwriting and tremor. There are some risk fact...

Fetal acidosis is reflected by the values of umbilical cord pH and base deficit (BDecf): normal recordings (pH over 7.2 and BDecf under 8 mmol/l) and abnormal recordings (pH under 7.2 and BDecf over 8 mmol/l). The purpose of this paper is to present the implementation of an automated system for detecting fetal acidosis in cardiotocographic recordin...

IEEE Xplore indexed.

IEEE Xplore indexed.

The paper is dedicated to the 50 years passed since the theory of fuzzy sets and fuzzy logic was established. This opportunity is used to analyze some research directions in the last decades and to suggest what directions may be fruitful to develop. The paper undertakes the task of reviewing some of our laboratory applications in 1D/2D signal proce...

The purpose of this paper was to design and develop a reliable remote monitoring system that allows health care professionals to monitor the daily calories expenditure of obese subjects. The system was implemented by using the Z430-Chronos wireless development kit and BM-CS5 wireless chest strap. These devices were used to acquire and wirelessly tr...

This paper describes the research for the design and realization of a flexible, scalable and cost-effective medical wireless measurement system for remote monitoring of changes in patient's electrical bioimedance, based on wireless sensor networks. The bioimpedance is continuously measured using a custom developed wireless sensor node and then is w...

In this paper a strategy to enhance performances in Bacterial Foraging Optimization Algorithm (BFOA) based Image Registration (IR) is proposed. The goal of the IR optimization problem is to determine a geometric transform which maximizes the similarity to a model image when is applied to a source image. In each step of standard BFOA, the bacteria m...

This paper presents an overview of our project for measuring the ROM (range of motion) for upper limb in case of post stroke rehabilitation, that uses a simple and accessible method for any rehabilitation laboratory. The system is comprised of a wheelchair with an artificial upper limb that has a laser light source that is projected on a plexiglass...

The aim of this study is the identification of the dynamic relationship between intrapartum fetal heart rate (FHR) variability and uterine pressure (UP) for normal and hypoxic fetuses. A new method for automatic analysis and identification of uterine contractions is developed and tested on 552 recordings. Using contractions, the fetal heart rate va...

The ubiquitous aspiration to health and life propels healthcare industry as the world’s biggest industrial sector. Biomedical engineering (BME) occupies a central place in healthcare industry and it is one of the few areas of engineering that, as a whole, is expected to continue to grow for many years. In Republic of Moldova considering the need to...

Image Registration (IR) is an optimization problem computing optimal parameters of a geometric transform used to overlay one or more source images to a given model by maximizing a similarity measure. In this paper the use of bio-inspired optimization algorithms in image registration is analyzed. Results obtained by means of three di®erent algorithm...

Sleep represents a dynamic physiological process having an important role in the restoration of the central nervous system. Nowadays, because a significant part of the population suffers of sleep disorders, the dynamic long time continuous monitoring of human respiration has an important role in diagnosis and treatment. This paper proposes a flexib...

The physiological response during fetal distress caused by labor varies from case to case and it is reflected both in the umbilical cord pH value and the fetal cord arterial base deficit (BDecf). The purpose of this study is to reveals the changes in fetal heart rate variability in abnormal cases (pH < 7.2 and BDecf > 8 mmol/L). Fetal heart rate va...

Neurological diseases like Alzheimer, epilepsy, Parkinson’s disease, multiple sclerosis and other dementias influence the lives of patients, their families and society. Parkinson's disease (PD) is a neurodegenerative disease that occurs due to loss of dopamine, a neurotransmitter and slow destruction of neurons. Brain area affected by progressive d...

In this paper it is proposed a parallel approach for the pixel intensity based image registration (IR) problem on multi-core processors. While IR is an optimization problem which computes the optimal parameters for a geometric transform, two classes of bio-inspired algorithms are studied: Bacterial Foraging Optimization Algorithm (BFOA) and Genetic...

The fetal heart rate (FHR) is a fundamental tool for clinical monitoring, when investigating the wellbeing of the fetus. The detection of the QRS complex of the fetal electrocardiogram using the abdominal signal enables the non-invasive evaluation of the FHR. There are many clinical causes for FHR variability, but a slight variance indicates a good...

The experiment used a patented psycho-verbal stimulation interface to study the utility of cognitive visual N400 evoked potential in detecting the reading process. The acquisition was performed in Oz, Pz, Cz, Fz leads, on a group of 50 normal persons, at three type of list contained each 500 paragraphic modified words: unreadable non-words, readabl...

Medical signals are increasingly being used within healthcare for diagnosis, planning treatment, guiding treatment and monitoring disease evolution. Medical imaging mainly treats and processes missing, ambiguous, complementary, redundant, contradictory, distorted data, and information has a strong structural character. This paper reports two "immun...

Schizophrenia as severe mental disorder is characterized by a disintegration of the process of thinking and of emotional responsiveness whereas the underlying mechanisms of schizophrenia are complex and still discussed. The objective of this study is to find out if patients with schizophrenia and their healthy first-degree relatives have abnormal a...

The experiment purposes to assess which type of mental strategy in training lexical abilities has the best reaction time improvement. Three groups of 16 persons each (equal men-women), equalized distributed as lexical performance after a pre-evaluated test were trained three days each using one of three type of methods - icon-nonlexical, graphemic-...

In medicine, there is a growing interest in gaining new insights into the main physiological control mechanisms functioning and interactions, both in health and in disease. Recently, we developed a new method, the Normalized Short Time Partial Directed Coherence (NSTPDC) method, for analyzing complex dynamic systems couplings. In this study, the re...

Nowadays a significant part of the population suffers of sleep disorders, so the dynamic long term monitoring of skin temperature during sleep is very useful for analysis and understanding the circadian rhythm. In this paper we describe the realization of a patient skin temperature monitoring system, based on wireless devices, capable to measure an...

Partial Directed Coherence (PDC) method and its extensions proved to be useful tools in analysing couplings in multivariate dynamic systems. We introduced the normalised short time PDC method (NST-PDC), to investigate the dynamic behaviour of couplings. First simulated signals obtained from coupled oscillators were analysed and information about th...

Recently, methods have been developed to analyse couplings in dynamic systems. In the field of medical analysis of complex cardiovascular and cardiorespiratory systems, there is growing interest in how insights may be gained into the interaction between regulatory mechanisms in healthy and diseased persons. The couplings within and between these sy...

A complex goal in biomedical information technology today is the design and implementation of telemedicine and e-health solutions, which provide (chronic) patients and elderly people services that can enhance their quality of life. We used wireless sensor network technology, low-power integrated embedded systems and wireless communications, which h...

In the real medical world, there are many symptoms or chronic diseases that cannot be characterized in a deterministic way, and which must be examined in a random way. In the study of these stochastic processes, Markov chains are used. There is a wide variety of phenomena that suggest a behavior in a Markov process manner such as: the probability t...