Laura Sbernini

Resistive flex sensors: a survey

Resistive flex sensors can be used to measure bending or flexing with relatively little effort and a relativelylow budget. Their lightness, compactness, robustness, measurement effectiveness and low power consumption make these sensors useful for manifold applications in diverse fields. Here, we provide a comprehensive survey of resistive flex sensors, taking into account their working principles, manufacturing aspects, electrical characteristics and equivalent models, useful front-end conditioning circuitry, and physic-bio-chemical aspects. Particular effort is devoted to reporting on and analyzing several applications of resistive flex sensors, related to the measurement of body position and motion, and to the implementation of artificial devices. In relation to the human body, we consider the utilization of resistive flex sensors for the measurement of physical activity and for the development of interaction/interface devices driven by human gestures. Concerning artificial devices, we deal with applications related to the automotive field, robots, orthosis and prosthesis, musical instruments and measuring tools. The presented literature is collected from different sources, including bibliographic databases, company press releases, patents, master’s theses and PhD theses.

Support vector machines to detect physiological patterns for EEG and EMG-based human-computer interaction: a review

Support vector machines (SVMs) are widely used classifiers for detecting physiological patterns in human-computer interaction (HCI). Their success is due to their versatility, robustness and large availability of free dedicated toolboxes. Frequently in the literature, insufficient details about the SVM implementation and/or parameters selection are reported, making it impossible to reproduce study analysis and results. In order to perform an optimized classification and report a proper description of the results, it is necessary to have a comprehensive critical overview of the applications of SVM. The aim of this paper is to provide a review of the usage of SVM in the determination of brain and muscle patterns for HCI, by focusing on electroencephalography (EEG) and electromyography (EMG) techniques. In particular, an overview of the basic principles of SVM theory is outlined, together with a description of several relevant literature implementations. Furthermore, details concerning reviewed papers are listed in tables and statistics of SVM use in the literature are presented. Suitability of SVM for HCI is discussed and critical comparisons with other classifiers are reported.

Evaluating the influence of subject-related variables on EMG-based hand gesture classification

In this study we evaluated the effect of subject-related variables, i.e. hand dominance, gender and experience in using, on the performances of an EMG-based system for virtual upper limb and prosthesis control. The proposed system consists in a low density EMG sensors arrangement, a purpose-built signal-conditioning electronic circuitry and a software able to classify the gestures and to replicate them via avatars. The classification algorithm was optimized in terms of feature extraction and dimensionality reduction. In its optimal configuration, the system allows to accurately discriminate five different hand gestures (accuracy = 88.85 ± 7.19%). Statistical analysis demonstrated no significant difference in classification accuracy related to hand-dominance (handedness) and to gender. In addition, maximum accuracy in dominant hand is achieved since first use of the system, whilst accuracy in classifying gestures of the non-dominant hand significantly increases with experience. These results indicate that this system can be potentially used by every trans-radial upper-limb amputee for virtual/real limb control.

Surgical Skill Evaluation by Means of a Sensory Glove and a Neural Network

In this work we used the HiTEg data glove to measure the skill of a physician or physician student in the execution of a typical surgical task: the suture. The aim of this project is to develop a system that, analyzing the movements of the hand, could tell if they are correct. To collect a set of measurements, we asked 18 subjects to performing the same task wearing the sensory glove. Nine subjects were skilled surgeons and nine subjects were non-surgeons, every subject performed ten repetitions of the same task, for two sessions, yielding to a dataset of 36 instances. Acquired data has been processed and classified with a neural network. A feature selection has been done considering only the features that have less variance among the expert subjects. The cross-validation of the classifier shows an error of 5.6%.

Advanced algorithms for surgical gesture classification

A novel gesture binary classification procedure is presented to determine surgical ability. To this aim a sensory glove was employed to track surgical hand movements and sensors data were recorded to be processed by a specific algorithm. The classification task was able to discriminate a gesture made by an expert surgeon with respect to a novice one, thanks to a two steps classification strategy. The first one produced a binary tree of parameters associated to a sensor time function; they were elaborated in the second step by a neural network providing a real output whose magnitude was associated to the surgeon ability. Experimental tests correctly classify all operators in a group.

In-vitro Force Assessments of an Autoclavable Instrumented Sternal Retractor

It is well known that median sternotomy might lead to rib and/or sternum micro/macro-fractures and/or brachial plexus injuries, eventually resulting in chronic pain with significant impact on patient’s quality life.Postoperative chronic pain is recognized as a multifactorial complex issue, it has been assessed that excessive sternum retraction forces can be considered one of these factors. On this basis, the Authors developed a reliable and sterilizable system potentially able to real-time monitor and control the retraction forces along the hemisternums. A Finochietto sternal retractor was instrumented by means of ultra-thin force sensors interfaced with ad hoc electronic circuitry. Two different sets of sensors were adopted, one of which able to support autoclave operating conditions. In vitro tests were performed by means of a made on purpose dummy. The instrumented retractor allows monitoring of the force exerted on both the arms during the opening procedure. Force versus time patterns were real-time acquired and stored, distribution of forces was determined along with the values of mean, maximum and plateau force. Results demonstrate the reliability of the instrumented retractor in measuring forces, up to 400N. Cost-effectiveness and feasibility can be considered further additional values of the proposed instrumented retractor.

Evaluation of a Stretch Sensor for its inedited application in tracking hand finger movements

Flex sensors are frequently used as wearable tools for unobtrusively tracking human joint movements. Among all the flex sensor types, the resistive ones are the mostly adopted thanks to their electrical and mechanical properties capable to furnish electrical resistance values related to the amount of mechanical flexion. In particular, resistive flex sensors have been finding many applications when embedded into gloves, in order to evaluate fine flexion/extension movements of the finger joints. Within this frame, here we investigate the possible utilization of a different type of flex sensors embedded into gloves, i.e., the stretch ones, since the stretch sensors change in resistance proportionally to their stretch that can be just obtained when laid on-top of a finger joint. In such a view, here we compare the characteristics of commercial flex and stretch sensors obtained by means of an ad-hoc setup and protocol. Results demonstrate the different peculiarities of the two different types of sensors, so to determine when it is convenient to adopt one type instead of the other.

Assessment of Hand Rehabilitation after Hand Surgery by Means of a Sensory Glove

The assessment of hand functions after hand surgery treatment is essential to address the optimal rehabilitation procedures for any patient. To this aim, the current procedures anachronistically rely mainly on manual goniometers (highly prone to human errors) and know-how of experienced medical staffs (potentially prone to biased judgment), so that there is room for improvements in objective measurements of hand capabilities and new technological systems are very welcome. In particular, systems based on sensory glove are gaining more and more relevance in acquiring hand movement capabilities. Within this frame, in this research the Range of Motion (ROM) for all fingers and the ability of participants (health vs. patient subjects) to repeat two ADL (Activities of Daily Living)-based tasks were investigated. As a result, the glove-based system was evaluated in its feasibility for the assessment of hand function in clinical practice and rehabilitation settings.

Towards an Objective Tool for Evaluating the Surgical Skill

In this paper we present a system for the evaluation of the skill of a physician or physician student by means of the analysis of the movements of the hand. By comparing these movements to the ones of a set of subjects known to be skilled, we could tell if they are correct. We consider the execution of a typical surgical task: the suture. For the data acquisition we used the HiTEg sensory glove, then, we extract a set of features from data analysis and classify it by means of different kind of classifiers. We compared results from an RBF neural network and a Bayesian classifier. The system has been tested on a set of 18 subjects. We found that accuracy depends on the feature set that is used, and it can reach 94 % when we consider a set of 20 features: 9 of them are taken from data of bending sensor, 10 from accelerometers and gyroscopes, and one feature is the length of the gesture.

A new glove for gesture recognition and classification for surgical skill assesment

Cutaneous abdominal metastasis from a primary lung tumour conveys a poor prognosis. Abdominal wall reconstruction following tumour resection usually involves construction of a myocutaneous flap, creating significant risk of hernia formation and increasing morbidity in the palliative patient. In the presented patient, loss of cutaneous continuity due to metastatic tumour and subsequent radiotherapy resulted in a contaminated operating field. As an alternative to a myocutaneous flap, a biological mesh was laparoscopically placed deep to the abdominal wall resection defect, providing reinforcement and reducing the risk of prosthesis infection. Split skin grafting from a right thigh donor site was then performed. To our knowledge, this is the first reported laparoscopic mesh placement for the prevention of ventral hernia formation following abdominal wall lung cancer metastasis resection. It provides a quick, low morbidity alternative to more extensive abdominal wall reconstruction enabling faster discharge from hospital. P002 – Abdominal Cavity and Abdominal WallAim: Laparoscopic splenectomy presents a challenge in patients with splenomegaly despite being the preferred procedure for most elective splenectomies. Our experience with laparoscopic splenectomy in the setting of splenomegaly is presented. Methods: The data were collected prospectively from May 2003. to October 2011. in 39 patients that underwent LS in Clinical Hospital “Dubrava” Zagreb, Croatia. The nature of disease, spleen size (measured on CT or ultrasound), gender, age, op time, conversion, hospital stay, need for accessory incision, type of splenic artery ligation preoperative and postoperative platelet values were recorded. The impact of diagnosis (benign/malignant) and the spleen size onto the outcome following LS in seven years period were evaluated. Results: Majority of patients submitted to LS had benign hematologic disease (30 of 39) and more than half of them had splenomegaly (23/39). Majority of patients with splenic malignancy have splenomegaly (8 of 9). The mean spleen size in splenomegaly patients was 23, 88 cm (range 15-31 cm). Splenomegaly was associated with higher conversion rate (3 vs 2) due to bleeding and longer mean operative time (128, 54 vs 104, 75 min). Furthermore, in splenomegaly more patients required accessory incision and additional port (7 vs 1) and blood transfusion (8 vs 1). But length of stay and postoperative morbidity was not associated with enlarged spleen in our series. Conclusion: According to our results, the same as to some previously presented studies LS has become a treatment of choice for majority of patients including those with splenomegaly. In spite of longer operative time and more blood loss laparoscopic splenectomy in the setting of splenomegaly is safe in appropriately experienced hands with full awareness of increased complexity of technical performance and caution requirement.