{"title":"Biomarker discovery and validation for Parkinson's Disease: A machine learning approach","authors":"Dana Bazazeh, R. Shubair, Wasim Q. Malik","doi":"10.1109/BIOSMART.2016.7835465","DOIUrl":"https://doi.org/10.1109/BIOSMART.2016.7835465","url":null,"abstract":"Parkinson's disease is recognized as the second most common neurodegenerative disorder, after Alzheimer's, however, diagnosis remains a challenging task with no gold standard clinical test available. The use of machine learning (ML) techniques has been seen across a wide array of applications in bioinformatics, including biomarker discovery and validation. Biomarkers are defined as an objective measure of biological parameters that can diagnose a disease, monitor its progression, or predict therapeutic pathologies. Biomarkers range from genetic and biochemical, to neuroimaging and clinical. Biomarker identification is a sequential and repetitive process that consists of many critical steps, including data-preprocessing, feature extraction, model selection and biomarker validation. This paper provides an overview of the symptoms of Parkison's disease, both motor and non-motor, as well as a description of the state-of-the-art biomarkers currently in use. Additionally, the paper provides a synopsis showcasing the several subdivisions of the discovery and validation process.","PeriodicalId":158108,"journal":{"name":"2016 International Conference on Bio-engineering for Smart Technologies (BioSMART)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126783153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Face aging predictive model due to methamphetamine addiction","authors":"E. Farazdaghi, A. Nait-Ali","doi":"10.1109/BIOSMART.2016.7835607","DOIUrl":"https://doi.org/10.1109/BIOSMART.2016.7835607","url":null,"abstract":"Facial aging is a biological phenomenon that can be affected by various factors. Although it is inexorable, a strong correlation is found between face age and lifestyle. Drug addiction can significantly change the manner of the face ageing, therefore the awareness of its negative effects and risks may help avoid addiction and reduce the number of the addicts. Unlike numerous studies dealing with the natural and ordinary ageing process, in this work, we propose a model aiming at presenting the horrifying effects of drugs specially methamphetamine addiction on an individual's appearance age. First a primal predictive ageing model has been made based on the expected aging process by constructing face templates corresponding to the different age decades. Meanwhile, by using the statistical survey on the methamphetamine addicts' face database, one coefficient is obtained which shows the difference in the appearance age between normal people and methamphetamine addicts. The final model will be built on the basis of these two, to illustrate that drug addicts look Delta years older than their natural age. Some minor geometrical changes that can appear by drug addiction are applied.","PeriodicalId":158108,"journal":{"name":"2016 International Conference on Bio-engineering for Smart Technologies (BioSMART)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123991881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Deformation of red blood cells under Dielectrophoresis","authors":"N. Hallfors, F. Alhammadi, A. Alazzam","doi":"10.1109/BIOSMART.2016.7835594","DOIUrl":"https://doi.org/10.1109/BIOSMART.2016.7835594","url":null,"abstract":"In this work we describe the effect of Dielectrophoresis (DEP) on the deformation of red blood cells by measuring the change in aspect ratio. The force induced through DEP will act against the elastic force of the cell, lengthening and slimming the cell. The change in dimensions due to deformation under DEP is measured under a microscope, and when compared to DEP force applied, can provide useful information about the mechanical properties of cell. Deformation characteristics can be used to classify cells, as well as provide information on effects of DEP on cells.","PeriodicalId":158108,"journal":{"name":"2016 International Conference on Bio-engineering for Smart Technologies (BioSMART)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132473336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Chkeir, F. Mourad-Chehade, D. Hewson, J. Duchêne, Francis Lévi, J. Beau, Monique Maurice, Sandra Komarzynski
{"title":"A pilot study to detect human circadian rhythms using a novel thoracic temperature sensor","authors":"A. Chkeir, F. Mourad-Chehade, D. Hewson, J. Duchêne, Francis Lévi, J. Beau, Monique Maurice, Sandra Komarzynski","doi":"10.1109/BIOSMART.2016.7835464","DOIUrl":"https://doi.org/10.1109/BIOSMART.2016.7835464","url":null,"abstract":"Perturbations of circadian rhythms have been related to cancer progression and worsening of metabolic diseases. This paper aims at optimizing the analytical methods suited for the detection of such perturbations using skin temperature signals as a circadian biomarker. Five control subjects were evaluated in this pilot study. Skin temperature was recorded every five minutes for four days. Using a novel thoracic infrared sensor. Four different interpolation methods were compared in order to replace missing values and help subsequently prolong sensor battery life. A Cosinor model was used to characterize circadian rhythms, and compute relevant parameters, with their confidence limits. A divergence study is then proposed to detect changes in these parameters. The results support the enlargement of the sample size and warrant further assessment in cancer patients.","PeriodicalId":158108,"journal":{"name":"2016 International Conference on Bio-engineering for Smart Technologies (BioSMART)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133059645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Residual stress of graphene-based MEMS ICP piezoresistive pressure sensors","authors":"Siti Hajar Abd Rahman, N. Soin, F. Ibrahim","doi":"10.1109/BIOSMART.2016.7835469","DOIUrl":"https://doi.org/10.1109/BIOSMART.2016.7835469","url":null,"abstract":"Thin diaphragm play an important role in highly sensitive MEMS piezoresistive pressure sensor for intracranial pressure measurement. The thinness of graphene was utilized in this pressure sensor to maximize the sensitivity of the ICP pressure sensor. However a very thin diaphragm can cause a pressure nonlinearity performance problem due to the residual stresses. This present paper study the effect of residual stress due to different number of graphene layers on MEMS intracranial (ICP) piezoresistive pressure sensor. COMSOL simulation was used to determine the pre-stressed deformed square diaphragm hence the value for residual stress of single layer and multilayer graphene can be calculated. It was found that the application of multilayer graphene can reduce the effect of residual stress on graphene based MEMS ICP piezoresistive pressure sensor. Residual stress of 1.94 × 107 Mpa was reduced to 9.72 × 103 Mpa by utilizing 20 layers of graphene. This study has suggested a simplified method to produced highly sensitive pressure sensor with reduced pressure non linearity problem by using multilayered graphene diaphragm instead of complicated single layer application method.","PeriodicalId":158108,"journal":{"name":"2016 International Conference on Bio-engineering for Smart Technologies (BioSMART)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131588418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Uterine Contraction characterisation during labour with smart wireless ECG detection","authors":"W. Zgallai","doi":"10.1109/BIOSMART.2016.7835470","DOIUrl":"https://doi.org/10.1109/BIOSMART.2016.7835470","url":null,"abstract":"The aim of this paper is to separate the Uterine Contractions Interference Signal (UCIS) from the combined fetal and mother transabdominal ECG signals. The UCIS is measured during peak contractions at the full-term, 40 weeks of gestation, with a separation of 10 minutes between contractions and 90 seconds in duration. The UCIS signal is then characterized and its eigenvectors are separated into orthogonal subspace to that of the eigenvectors of the fetal and mother components. This improves the detection of fetal and mother spectral peaks uniquely identified from the transabdominally-measured signal by employing adaptive LMS- and LMF-based Volterra filters, higher order statistics, and spectral super-resolution techniques, such as Multiple Signal Classification.","PeriodicalId":158108,"journal":{"name":"2016 International Conference on Bio-engineering for Smart Technologies (BioSMART)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129774260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Cherifi, Fateh Cherfaoui, Si Nabil Yacini, A. Nait-Ali
{"title":"Fusion of face recognition methods at score level","authors":"D. Cherifi, Fateh Cherfaoui, Si Nabil Yacini, A. Nait-Ali","doi":"10.1109/BIOSMART.2016.7835458","DOIUrl":"https://doi.org/10.1109/BIOSMART.2016.7835458","url":null,"abstract":"The face recognition problem has been extensively studied by many researchers but accuracy is not satisfactory. This work presents analysis and performance evaluation of global methods (PCA, FLD, DCT, DWT), local methods (SIFT, LBP) and all possible fusions of two methods among them. The fusion is done by consolidating the output of multiple feature extraction algorithms at score levels using four fusion rules which are Mean, Maximum, Minimum, and product [1]. The hybrid methods are tested in terms of recognition rate under different working environment and conditions such as pose variation, illumination and facial expression change, adding effects as blur, motion, noise or combination of those effects. Finally, their robustness is tested by adding some objects as wearing a scarf, putting on a hat, background change, wearing glasses and beard.","PeriodicalId":158108,"journal":{"name":"2016 International Conference on Bio-engineering for Smart Technologies (BioSMART)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130996165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fawad Ahmad, Tanveerulhaq, Irfan Ishaq, Danish Ali, M. F. Riaz
{"title":"Bionic Kinect device to assist visually impaired people by haptic and voice feedback","authors":"Fawad Ahmad, Tanveerulhaq, Irfan Ishaq, Danish Ali, M. F. Riaz","doi":"10.1109/BIOSMART.2016.7835472","DOIUrl":"https://doi.org/10.1109/BIOSMART.2016.7835472","url":null,"abstract":"This paper presents a wearable bionic Kinect device for blinds that helps visually challenging persons to move freely without any external assistance. This wearable consists of Kinect sensor, NUC (Next Unit of Computing) board and haptic feedback. Kinect sensor is used to get color data by RGB (Red Green Blue) camera and depth data by infrared projector which emits coded pattern received by receiver sensor that captures deformed pattern due to reflection by obstacles; algorithm decodes these variations into depth matrix. Image processing algorithms are applied on depth matrix to remove noise. Two dimensional Image processing algorithms of edge, contour detection and segmentation techniques are applied on multidimensional matrix at each level to extract important information about obstacle, humans and their characteristics. Extracted information of obstacles and humans are converted to haptic sequence and voice commands. Haptic feedback device receives the sequence, decodes sequence by using onboard microcontroller algorithm and creates vibration of different intensity at different regions. Text is recognized by optical character recognition system and faces by machine learning algorithms of device uses Kinect color data. All these tasks are performed by two processing units, a microcontroller and NUC which is excellent combination of wearable ubiquitous computing. Whole system is light weight, battery powered with intelligent power management circulatory to make it portable and easy to use.","PeriodicalId":158108,"journal":{"name":"2016 International Conference on Bio-engineering for Smart Technologies (BioSMART)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130195007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Preliminary tests of new composite material based on shape memory alloys for artificial aortic valve leaflets","authors":"A. Mezyk, W. Klein, M. Pawlak, O. Dudek","doi":"10.1109/BIOSMART.2016.7835468","DOIUrl":"https://doi.org/10.1109/BIOSMART.2016.7835468","url":null,"abstract":"Nowadays bioengineers actively search for new materials for different kind of implants. The natural tissues used for these purposes have many defects, of which the most important is the possibility of transplant rejection. However, properties of artificial biomaterials have also many deficiencies among which there are insufficient mechanical and fatigue properties. The example of this can be the aortic valve leaflets, which anatomy is complicated both in terms of geometrical shape and internal structure. This causes significant difficulties with finding suitable material for this type of implants. The most frequently used methods of obtaining material for that purpose are based on the processing of biopolymers (e.g. electrospinning) and also on extraction of porcine pericardial tissue. This paper presents a new concept of composite biomaterial based on shape memory alloys (SMA) with biopolymer matrix. The SMA thin fibers imitate collagen fibers in aortic valve leaflets which stabilize the aortic valve motion and reduce stresses. The numerical simulation of blood flow was done to verify assumptions and investigate the extent of deformation of the new composite structure.","PeriodicalId":158108,"journal":{"name":"2016 International Conference on Bio-engineering for Smart Technologies (BioSMART)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127839623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A novel approach of black skin lesion images segmentation based on MLP Neural Network","authors":"Géraud M. Azehoun-Pazou, K. Assogba, H. Adegbidi","doi":"10.1109/BIOSMART.2016.7835598","DOIUrl":"https://doi.org/10.1109/BIOSMART.2016.7835598","url":null,"abstract":"Black skin lesion images generally show low contrast between lesion parts and safe ones. Segmentation of such images is a challenging task. In this paper, we propose a novel method that first select safe likely skin region using a Multi-Layer Perceptron (MLP) Neural Network. Then, color of these selected regions is transformed, in order to increase the contrast with lesion regions. The obtained image is therefore segmented using clustering algorithms. The proposed method has been applied to many black skin lesion images and produced good results.","PeriodicalId":158108,"journal":{"name":"2016 International Conference on Bio-engineering for Smart Technologies (BioSMART)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126988126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}