Search results for: skin or non-skin classification

Authors: Ali J. Ghandour, Houssam A. Krayem, Abedelkarim A. Jezzini

Abstract:

High-resolution satellite images and remote sensing can provide global information in a fast way compared to traditional methods of data collection. Under such high resolution, a road is not a thin line anymore. Objects such as cars and trees are easily identifiable. Automatic vehicles enumeration can be considered one of the most important applications in traffic management. In this paper, autonomous vehicle detection and classification approach in highway environment is proposed. This approach consists mainly of three stages: (i) first, a set of preprocessing operations are applied including soil, vegetation, water suppression. (ii) Then, road networks detection and delineation is implemented using built-up area index, followed by several morphological operations. This step plays an important role in increasing the overall detection accuracy since vehicles candidates are objects contained within the road networks only. (iii) Multi-level Otsu segmentation is implemented in the last stage, resulting in vehicle detection and classification, where detected vehicles are classified into cars and trucks. Accuracy assessment analysis is conducted over different study areas to show the great efficiency of the proposed method, especially in highway environment.

Keywords: remote sensing, object identification, vehicle and road extraction, vehicle and road features-based classification

Procedia PDF Downloads 226

Authors: Laura Pytel, Georg Baumann, Gregor Gstrein, Corina Klug

Abstract:

Premium cars often coat the instrument panels with a bilaminate consisting of a soft foam and a plastic skin. The coating is torn open during the passenger airbag deployment under high strain rates. Characterizing and simulating the top coat layer is crucial for predicting the attenuation that delays the airbag deployment, effecting the design of the restrain system and to reduce the demand of simulation adjustments through expensive physical component testing.Up to now, bilaminates used within cars either have been modelled by using a two-dimensional shell formulation for the whole coating system as one which misses out the interaction of the two layers or by combining a three-dimensional formulation foam layer with a two-dimensional skin layer but omitting the foam in the significant parts like the expected tear line area and the hinge where high compression is expected. In both cases, the properties of the coating causing the attenuation are not considered. Further, at present, the availability of material information, as there are failure dependencies of the two layers, as well as the strain rate of up to 200 1/s, are insufficient. The velocity of the passenger airbag flap during an airbag shot has been measured with about 11.5 m/s during first ripping; the digital image correlation evaluation showed resulting strain rates of above 1500 1/s. This paper provides a high strain rate material characterization of a bilaminate consisting of a thin polypropylene foam and a thermoplasctic olefins (TPO) skin and the creation of validated material models. With the help of a Split Hopkinson tension bar, strain rates of 1500 1/s were within reach. The experimental data was used to calibrate and validate a more physical modelling approach of the forced ripping of the bilaminate. In the presented model, the three-dimensional foam layer is continuously tied to the two-dimensional skin layer, allowing failure in both layers at any possible position. The simulation results show a higher agreement in terms of the trajectory of the flaps and its velocity during ripping. The resulting attenuation of the airbag deployment measured by the contact force between airbag and flaps increases and serves usable data for dimensioning modules of an airbag system.

Keywords: bilaminate ripping behavior, High strain rate material characterization and modelling, induced material failure, TPO and foam

Procedia PDF Downloads 64

Authors: Majid Habib Khan, Jinwei Zhao, Xinhong Hei, Liu Jiedong, Rana Shahzad Noor, Muhammad Imran

Abstract:

Deep learning is increasingly employed in image classification, yet the scarcity and high cost of labeled data for training remain a challenge. Limited samples often lead to overfitting due to biased sample distribution. This paper introduces a dynamic distribution calibration method for few-shot learning. Initially, base and new class samples undergo normalization to mitigate disparate feature magnitudes. A pre-trained model then extracts feature vectors from both classes. The method dynamically selects distribution characteristics from base classes (both adjacent and remote) in the embedding space, using a threshold value approach for new class samples. Given the propensity of similar classes to share feature distributions like mean and variance, this research assumes a Gaussian distribution for feature vectors. Subsequently, distributional features of new class samples are calibrated using a corrected hyperparameter, derived from the distribution features of both adjacent and distant base classes. This calibration augments the new class sample set. The technique demonstrates significant improvements, with up to 4% accuracy gains in few-shot classification challenges, as evidenced by tests on miniImagenet and CUB datasets.

Keywords: deep learning, computer vision, image classification, few-shot learning, threshold

Procedia PDF Downloads 56

Authors: Rawia M. Khalil, Ahmed A. Abd El Rahman, Mahfouz A. Kassem, Mohamed S. El Ridi, Mona M. Abou Samra, Ghada E. A. Awad, Soheir S. Mansy

Abstract:

Solid lipid nanoparticles (SLNs) have gained great attention for the topical treatment of skin associated fungal infection as they facilitate the skin penetration of loaded drugs. Our work deals with the preparation of nystatin loaded solid lipid nanoparticles (NystSLNs) using the hot homogenization and ultrasonication method. The prepared NystSLNs were characterized in terms of entrapment efficiency, particle size, zeta potential, transmission electron microscopy, differential scanning calorimetry, rheological behavior and in vitro drug release. A stability study for 6 months was performed. A microbiological study was conducted in male rats infected with Candida albicans, by counting the colonies and examining the histopathological changes induced on the skin of infected rats. The results showed that SLNs dispersions are spherical in shape with particle size ranging from 83.26±11.33 to 955.04±1.09 nm. The entrapment efficiencies are ranging from 19.73±1.21 to 72.46±0.66% with zeta potential ranging from -18.9 to -38.8 mV and shear-thinning rheological Behavior. The stability studies done for 6 months showed that nystatin (Nyst) is a good candidate for topical SLN formulations. A least number of colony forming unit/ ml (cfu/ml) was recorded for the selected NystSLN compared to the drug solution and the commercial Nystatin® cream present in the market. It can be fulfilled from this work that SLNs provide a good skin targeting effect and may represent promising carrier for topical delivery of Nyst offering the sustained release and maintaining the localized effect, resulting in an effective treatment of cutaneous fungal infection.

Keywords: candida infections, hot homogenization, nystatin, solid lipid nanoparticles, stability, topical delivery

Procedia PDF Downloads 384

Authors: Mekamı Hayet, Bounoua Nacer, Benabderrahmane Sidahmed, Taleb Ahmed

Abstract:

Pose estimation is an important task in computer vision. Though the majority of the existing solutions provide good accuracy results, they are often overly complex and computationally expensive. In this perspective, we propose the use of dimensionality reduction techniques to address the problem of facial pose estimation. Firstly, a face image is converted into one-dimensional time series using Hilbert space filling curve, then the approach converts these time series data to a symbolic representation. Furthermore, a distance matrix is calculated between symbolic series of an input learning dataset of images, to generate classifiers of frontal vs. profile face pose. The proposed method is evaluated with three public datasets. Experimental results have shown that our approach is able to achieve a correct classification rate exceeding 97% with K-NN algorithm.

Keywords: machine learning, pattern recognition, facial pose classification, time series

Procedia PDF Downloads 346

Authors: Kenan Morani, Esra Kaya Ayana

Abstract:

This study aimed to develop a novel pipeline for COVID-19 detection using a large and rigorously annotated database of computed tomography (CT) images. The pipeline consists of UNet-based segmentation, lung extraction, and a classification part, with the addition of optional slice removal techniques following the segmentation part. In this work, a batch normalization was added to the original UNet model to produce lighter and better localization, which is then utilized to build a full pipeline for COVID-19 diagnosis. To evaluate the effectiveness of the proposed pipeline, various segmentation methods were compared in terms of their performance and complexity. The proposed segmentation method with batch normalization outperformed traditional methods and other alternatives, resulting in a higher dice score on a publicly available dataset. Moreover, at the slice level, the proposed pipeline demonstrated high validation accuracy, indicating the efficiency of predicting 2D slices. At the patient level, the full approach exhibited higher validation accuracy and macro F1 score compared to other alternatives, surpassing the baseline. The classification component of the proposed pipeline utilizes a convolutional neural network (CNN) to make final diagnosis decisions. The COV19-CT-DB dataset, which contains a large number of CT scans with various types of slices and rigorously annotated for COVID-19 detection, was utilized for classification. The proposed pipeline outperformed many other alternatives on the dataset.

Keywords: classification, computed tomography, lung extraction, macro F1 score, UNet segmentation

Procedia PDF Downloads 125

Authors: Guoliang Lu, Changhou Lu, Xueyong Li

Abstract:

In action recognition, previous studies have demonstrated the effectiveness of using multiple features to improve the recognition performance. We focus on two practical issues: i) most studies use a direct way of concatenating/accumulating multi features to evaluate the similarity between two actions. This way could be too strong since each kind of feature can include different dimensions, quantities, etc; ii) in many studies, the employed classification methods lack of a flexible and effective mechanism to add new feature(s) into classification. In this paper, we explore an unified scheme based on recently-proposed multi-dimensional dynamic time warping (MD-DTW). Experiments demonstrated the scheme's effectiveness of combining multi-feature and the flexibility of adding new feature(s) to increase the recognition performance. In addition, the explored scheme also provides us an open architecture for using new advanced classification methods in the future to enhance action recognition.

Keywords: action recognition, multi features, dynamic time warping, feature combination

Procedia PDF Downloads 434

Authors: Farhana Karim, Abdullah N. S. Khan, Mohiuddin A. K. Chowdhury, Nabila Zaka, Alexander Manu, Shams El Arifeen, Sk Masum Billah

Abstract:

Breastfeeding, an integral part of newborn care, can reduce 55-87% of all-cause neonatal mortality and morbidity. Early initiation of breastfeeding within 1 hour of birth can avert 22% of newborn mortality. Only 45% of world’s newborns and 42% of newborns in South-Asia are put to the breast within one hour of birth. In Bangladesh, only a half of the mothers practice early initiation of breastfeeding which is less likely to be practiced if the baby is born in a health facility. This study aims to generate strong evidence for early initiation of breastfeeding practices in the government health facilities and to explore the associated factors influencing the practice. The study was conducted in selected health facilities in three neighbouring districts of Northern Bangladesh. Total 249 normal vaginal delivery cases were observed for 24 hours since the time of birth. The outcome variable was initiation of breastfeeding within 1 hour while the explanatory variables included type of health facility, privacy, presence of support person, stage of labour at admission, need for augmentation of labour, complications during delivery, need for episiotomy, spontaneous cry of the newborn, skin-to-skin contact with mother, post-natal contact with the service provider, receiving a post-natal examination and counselling on breastfeeding during postnatal contact. The simple descriptive statistics were employed to see the distribution of samples according to socio-demographic characteristics. Kruskal-Wallis test was carried out for testing the equality of medians among two or more categories of each variable and P-value is reported. A series of simple logistic regressions were conducted with all the potential explanatory variables to identify the determining factors for breastfeeding within 1 hour in a health facility. Finally, multiple logistic regression was conducted including the variables found significant at bi-variate analyses. Almost 90% participants initiated breastfeeding at the health facility and median time to initiate breastfeeding was 38 minutes. However, delivering in a sub-district hospital significantly delayed the breastfeeding initiation in comparison to delivering in a district hospital. Maintenance of adequate privacy and presence of separate staff for taking care of newborn significantly reduced the time in early breastfeeding initiation. Initiation time was found longer if the mother had an augmented labour, obstetric complications, and the newborn needed resuscitation. However, the initiation time was significantly early if the baby was put skin-to-skin on mother’s abdomen and received a postnatal examination by a provider. After controlling for the potential confounders, the odds of initiating breastfeeding within one hour of birth is higher if mother gives birth in a district hospital (AOR 3.0: 95% CI 1.5, 6.2), privacy is well-maintained (AOR 2.3: 95% CI 1.1, 4.5), babies cry spontaneously (AOR 7.7: 95% CI 3.3, 17.8), babies are put to skin-to-skin contact with mother (AOR 4.6: 95% CI 1.9, 11.2) and if the baby is examined by a provider in the facility (AOR 4.4: 95% CI 1.4, 14.2). The evidence generated by this study will hopefully direct the policymakers to identify and prioritize the scopes for creating and supporting early initiation of breastfeeding in the health facilities.

Keywords: Bangladesh, early initiation of breastfeeding, health facility, normal vaginal delivery, skin to skin contact

Procedia PDF Downloads 147

Authors: N. Garrós, P. Bustos, N. Beirampour, R. Mohammadi, M. Mallandrich, A.C. Calpena, H. Colom

Abstract:

Atopic dermatitis (AD) is a persistent skin condition characterized by chronic inflammation caused by an autoimmune response. It is a prevalent clinical issue that requires continual treatment to enhance the patient's quality of life. Systemic therapy often involves the use of glucocorticoids or immunosuppressants to manage symptoms. Our objective was to create and assess topical liposomal formulations containing Baricitinib (BNB), a reversible inhibitor of Janus-associated kinase (JAK), which is involved in various immune responses. These formulations were intended to address flare-ups and improve treatment outcomes for AD. We created three distinct liposomal formulations by combining different amounts of 1-palmitoyl-2-oleoyl-glycero-3-phosphocholine (POPC), cholesterol (CHOL), and ceramide (CER): (i) pure POPC, (ii) POPC mixed with CHOL (at a ratio of 8:2, mol/mol), and (iii) POPC mixed with CHOL and CER (at a ratio of 3.6:2.4:4.0 mol/mol/mol). We conducted various tests to determine the formulations' skin tolerance, irritancy capacity, and their ability to cause erythema and edema on altered skin. We also assessed the transepidermal water loss (TEWL) and skin hydration of rabbits to evaluate the efficacy of the formulations. Histological analysis, the HET-CAM test, and the modified Draize test were all used in the evaluation process. The histological analysis revealed that liposome POPC and POPC:CHOL avoided any damage to the tissues structures. The HET-CAM test showed no irritation effect caused by any of the three liposomes, and the modified Draize test showed a good Draize score for erythema and edema. Liposome POPC effectively counteracted the impact of xylol on the skin, and no erythema or edema was observed during the study. TEWL values were constant for all the liposomes with similar values to the negative control (within the range 8 - 15 g/h·m2, which means a healthy value for rabbits), whereas the positive control showed a significant increase. The skin hydration values were constant and followed the trend of the negative control, while the positive control showed a steady increase during the tolerance study. In conclusion, the developed formulations containing BNB exhibited no harmful or irritating effects, they did not demonstrate any irritant potential in the HET-CAM test and liposomes POPC and POPC:CHOL did not cause any structural alteration according to the histological analysis. These positive findings suggest that additional research is necessary to evaluate the efficacy of these liposomal formulations in animal models of the disease, including mutant animals. Furthermore, before proceeding to clinical trials, biochemical investigations should be conducted to better understand the mechanisms of action involved in these formulations.

Keywords: baricitinib, HET-CAM test, histological study, JAK inhibitor, liposomes, modified draize test

Procedia PDF Downloads 89

Authors: Anukriti Kumar, Tanmay Singh, Dinesh Kumar Vishwakarma

Abstract:

Traffic control has been one of the most common and irritating problems since the time automobiles have hit the roads. Problems like traffic congestion have led to a significant time burden around the world and one significant solution to these problems can be the proper implementation of the Intelligent Transport System (ITS). It involves the integration of various tools like smart sensors, artificial intelligence, position technologies and mobile data services to manage traffic flow, reduce congestion and enhance driver's ability to avoid accidents during adverse weather. Road and traffic signs’ recognition is an emerging field of research in ITS. Classification problem of traffic signs needs to be solved as it is a major step in our journey towards building semi-autonomous/autonomous driving systems. The purpose of this work focuses on implementing an approach to solve the problem of traffic sign classification by developing a Convolutional Neural Network (CNN) classifier using the GTSRB (German Traffic Sign Recognition Benchmark) dataset. Rather than using hand-crafted features, our model addresses the concern of exploding huge parameters and data method augmentations. Our model achieved an accuracy of around 97.6% which is comparable to various state-of-the-art architectures.

Keywords: multiclass classification, convolution neural network, OpenCV

Procedia PDF Downloads 166

Authors: Mohd Noah A. Rahman, Afzaal H. Seyal, Norhafilah Bara

Abstract:

Developing a software application using an interface with computers and peripheral devices using gestures of human body such as hand movements keeps growing in interest. A review on this hand gesture detection and recognition based on computer vision technique remains a very challenging task. This is to provide more natural, innovative and sophisticated way of non-verbal communication, such as sign language, in human computer interaction. Nevertheless, this paper explores hand detection and hand gesture recognition applying a vision based approach. The hand detection and recognition used skin color spaces such as HSV and YCrCb are applied. However, there are limitations that are needed to be considered. Almost all of skin color space models are sensitive to quickly changing or mixed lighting circumstances. There are certain restrictions in order for the hand recognition to give better results such as the distance of user’s hand to the webcam and the posture and size of the hand.

Keywords: hand detection, hand gesture, hand recognition, sign language

Procedia PDF Downloads 301

Authors: Ebtehal Aljedaani, Maha Aljohani

Abstract:

Privacy and security patterns are both important for developing software that protects users' data and privacy. Privacy patterns are designed to address common privacy problems, such as unauthorized data collection and disclosure. Security patterns are designed to protect software from attack and ensure reliability and trustworthiness. Using privacy and security patterns, software engineers can implement security and privacy by design principles, which means that security and privacy are considered throughout the software development process. These patterns are available to translate "security & privacy-by-design" into practical advice for software engineering. Previous research on privacy and security patterns has typically focused on one category of patterns at a time. This paper aims to bridge this gap by merging the two categories and identifying their similarities and differences. To do this, the authors conducted a systematic literature review of 25 research papers on privacy and security patterns. The papers were analysed based on the category of the pattern, the classification of the pattern, and the security requirements that the pattern addresses. This paper presents the results of a comprehensive review of privacy and security design patterns. The review is intended to help future IT designers understand the relationship between the two types of patterns and how to use them to design secure and privacy-preserving software. The paper provides a clear classification of privacy and security design patterns, along with examples of each type. The authors found that there is only one widely accepted classification of privacy design patterns, while there are several competing classifications of security design patterns. Three types of security design patterns were found to be the most commonly used.

Keywords: design patterns, security, privacy, classification of patterns, security patterns, privacy patterns

Procedia PDF Downloads 123

Authors: R. R. Ramsheeja, R. Sreeraj

Abstract:

For view the internal structures of the human body such as liver, brain, kidney etc have a wide range of different modalities for medical images are provided nowadays. Computer Tomography is one of the most significant medical image modalities. In this paper use CT liver images for study the use of automatic computer aided techniques to calculate the volume of the liver tumor. Segmentation method is used for the detection of tumor from the CT scan is proposed. Gaussian filter is used for denoising the liver image and Adaptive Thresholding algorithm is used for segmentation. Multiple Region Of Interest(ROI) based method that may help to characteristic the feature different. It provides a significant impact on classification performance. Due to the characteristic of liver tumor lesion, inherent difficulties appear selective. For a better performance, a novel proposed system is introduced. Multiple ROI based feature selection and classification are performed. In order to obtain of relevant features for Support Vector Machine(SVM) classifier is important for better generalization performance. The proposed system helps to improve the better classification performance, reason in which we can see a significant reduction of features is used. The diagnosis of liver cancer from the computer tomography images is very difficult in nature. Early detection of liver tumor is very helpful to save the human life.

Keywords: computed tomography (CT), multiple region of interest(ROI), feature values, segmentation, SVM classification

Procedia PDF Downloads 504

Authors: Mayank Gupta, Siba Prasad Samal, Vasu Kakkirala

Abstract:

The internet world and its priorities have changed considerably in the last decade. Browsing on smart phones has increased manifold and is set to explode much more. Users spent considerable time browsing different websites, that gives a great deal of insight into user’s preferences. Instead of plain information classifying different aspects of browsing like Bookmarks, History, and Download Manager into useful categories would improve and enhance the user’s experience. Most of the classification solutions are server side that involves maintaining server and other heavy resources. It has security constraints and maybe misses on contextual data during classification. On device, classification solves many such problems, but the challenge is to achieve accuracy on classification with resource constraints. This on device classification can be much more useful in personalization, reducing dependency on cloud connectivity and better privacy/security. This approach provides more relevant results as compared to current standalone solutions because it uses content rendered by browser which is customized by the content provider based on user’s profile. This paper proposes a Naive Bayes based lightweight classification engine targeted for a resource constraint devices. Our solution integrates with Web Browser that in turn triggers classification algorithm. Whenever a user browses a webpage, this solution extracts DOM Tree data from the browser’s rendering engine. This DOM data is a dynamic, contextual and secure data that can’t be replicated. This proposal extracts different features of the webpage that runs on an algorithm to classify into multiple categories. Naive Bayes based engine is chosen in this solution for its inherent advantages in using limited resources compared to other classification algorithms like Support Vector Machine, Neural Networks, etc. Naive Bayes classification requires small memory footprint and less computation suitable for smartphone environment. This solution has a feature to partition the model into multiple chunks that in turn will facilitate less usage of memory instead of loading a complete model. Classification of the webpages done through integrated engine is faster, more relevant and energy efficient than other standalone on device solution. This classification engine has been tested on Samsung Z3 Tizen hardware. The Engine is integrated into Tizen Browser that uses Chromium Rendering Engine. For this solution, extensive dataset is sourced from dmoztools.net and cleaned. This cleaned dataset has 227.5K webpages which are divided into 8 generic categories ('education', 'games', 'health', 'entertainment', 'news', 'shopping', 'sports', 'travel'). Our browser integrated solution has resulted in 15% less memory usage (due to partition method) and 24% less power consumption in comparison with standalone solution. This solution considered 70% of the dataset for training the data model and the rest 30% dataset for testing. An average accuracy of ~96.3% is achieved across the above mentioned 8 categories. This engine can be further extended for suggesting Dynamic tags and using the classification for differential uses cases to enhance browsing experience.

Keywords: chromium, lightweight engine, mobile computing, Naive Bayes, Tizen, web browser, webpage classification

Procedia PDF Downloads 160

Authors: Ben Abderrahmane Ayoub El Fateh, Bnina Rachid

Abstract:

A comprehensive comparison of antioxidant defenses in the dermis and epidermis and their response to exposure to ultraviolet (UV) irradiation has not previously been attempted. In this study, enzymic and non-enzymic antioxidants in epidermis and dermis of hairless mice were compared. Enzyme activities are presented both as units/gram of skin and units/milligram of protein; arguments are presented for the superiority of skin wet weight as a reference base. Catalase, glutathione peroxidase, and glutathione reductase (units/gram of skin) were higher in the epidermis than dermis by 49%, 86%, and 74%, respectively. Superoxide dismutase did not follow this pattern. Lipophilic antioxidants ( -tocopherol, ubiquinol 9, and ubiquinone 9) and hydrophilic antioxidants (ascorbic acid, dehydroascorbic acid, and glutathione) were 24–95% higher in the epidermis than in dermis. In contrast, oxidized glutathione was 60% lower in the epidermis than in dermis. Mice were irradiated with solar light to examine the response of these cutaneous layers to UV irradiation. After irradiation with 25 J/cm2 (UVA + UVB, from a solar simulator), 10 times the minimum erythemal dose, epidermal and dermal catalase and superoxide dismutase activities were greatly decreased. Tocopherol, ubiquinol 9, ubiquinone 9, ascorbic acid, dehydroascorbic acid, and reduced glutathione decreased in both epidermis and dermis by 26-93%. Oxidizedgiutathione showed a slight, non-significant increase. Because the reduction in total ascorbate and catalase was much more severe in the epidermis than dermis, it can be concluded that UV light is more damaging to the antioxidant defenses in the epidermis than in the dermis.

Keywords: antioxidant defenses, enzymic, epidermis, oxidizedgiutathione

Procedia PDF Downloads 434

Authors: Doyin Afolabi, Phillip Adewole, Oladipupo Sennaike

Abstract:

Most well-known classifiers, including the decision tree algorithm, can make predictions on balanced datasets efficiently. However, the decision tree algorithm tends to be biased towards imbalanced datasets because of the skewness of the distribution of such datasets. To overcome this problem, this study proposes a weighted decision tree algorithm that aims to remove the bias toward the majority class and prevents the reduction of majority observations in imbalance datasets classification. The proposed weighted decision tree algorithm was tested on three imbalanced datasets- cancer dataset, german credit dataset, and banknote dataset. The specificity, sensitivity, and accuracy metrics were used to evaluate the performance of the proposed decision tree algorithm on the datasets. The evaluation results show that for some of the weights of our proposed decision tree, the specificity, sensitivity, and accuracy metrics gave better results compared to that of the ID3 decision tree and decision tree induced with minority entropy for all three datasets.

Keywords: data mining, decision tree, classification, imbalance dataset

Procedia PDF Downloads 118

Authors: Eiman Kattan

Abstract:

This study aims to evaluate the impact of classifying labelled remote sensing images conventional neural network (CNN) architecture, i.e., AlexNet on different land cover scenarios based on two remotely sensed datasets from different point of views such as the computational time and performance. Thus, a set of experiments were conducted to specify the effectiveness of the selected convolutional neural network using two implementing approaches, named fully trained and fine-tuned. For validation purposes, two remote sensing datasets, AID, and RSSCN7 which are publicly available and have different land covers features were used in the experiments. These datasets have a wide diversity of input data, number of classes, amount of labelled data, and texture patterns. A specifically designed interactive deep learning GPU training platform for image classification (Nvidia Digit) was employed in the experiments. It has shown efficiency in training, validation, and testing. As a result, the fully trained approach has achieved a trivial result for both of the two data sets, AID and RSSCN7 by 73.346% and 71.857% within 24 min, 1 sec and 8 min, 3 sec respectively. However, dramatic improvement of the classification performance using the fine-tuning approach has been recorded by 92.5% and 91% respectively within 24min, 44 secs and 8 min 41 sec respectively. The represented conclusion opens the opportunities for a better classification performance in various applications such as agriculture and crops remote sensing.

Keywords: conventional neural network, remote sensing, land cover, land use

Procedia PDF Downloads 360

Authors: Arian Hosseini, Mahmudul Hasan

Abstract:

To address the increasing need for efficient and accurate content moderation, we propose an efficient and lightweight deep classification ensemble structure. Our approach is based on a combination of simple visual features, designed for high-accuracy classification of violent content with low false positives. Our ensemble architecture utilizes a set of lightweight models with narrowed-down color features, and we apply it to both images and videos. We evaluated our approach using a large dataset of explosion and blast contents and compared its performance to popular deep learning models such as ResNet-50. Our evaluation results demonstrate significant improvements in prediction accuracy, while benefiting from 7.64x faster inference and lower computation cost. While our approach is tailored to explosion detection, it can be applied to other similar content moderation and violence detection use cases as well. Based on our experiments, we propose a "think small, think many" philosophy in classification scenarios. We argue that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, and lightweight models with narrowed-down visual features can possibly lead to predictions with higher accuracy.

Keywords: deep classification, content moderation, ensemble learning, explosion detection, video processing

Procedia PDF Downloads 41

Authors: Mohammad Tarek Al Muallim, Ozhan Duzenli, Ceyhun Ilguy

Abstract:

Harbor protection systems are so important. The need for automatic protection systems has increased over the last years. Diver detection active sonar has great significance. It used to detect underwater threats such as divers and autonomous underwater vehicle. To automatically detect such threats the sonar image is processed by algorithms. These algorithms used to detect, track and classify of underwater objects. In this work, divers tracking and classification algorithm is improved be proposing a robust wake detection method. To detect objects the sonar images is normalized then segmented based on fixed threshold. Next, the centroids of the segments are found and clustered based on distance metric. Then to track the objects linear Kalman filter is applied. To reduce effect of noise and creation of false tracks, the Kalman tracker is fine tuned. The tuning is done based on our active sonar specifications. After the tracks are initialed and updated they are subjected to a filtering stage to eliminate the noisy and unstable tracks. Also to eliminate object with a speed out of the diver speed range such as buoys and fast boats. Afterwards the result tracks are subjected to a classification stage to deiced the type of the object been tracked. Here the classification stage is to deice wither if the tracked object is an open circuit diver or a close circuit diver. At the classification stage, a small area around the object is extracted and a novel wake detection method is applied. The morphological features of the object with his wake is extracted. We used support vector machine to find the best classifier. The sonar training images and the test images are collected by ARMELSAN Defense Technologies Company using the portable diver detection sonar ARAS-2023. After applying the algorithm to the test sonar data, we get fine and stable tracks of the divers. The total classification accuracy achieved with the diver type is 97%.

Keywords: harbor protection, diver detection, active sonar, wake detection, diver classification

Procedia PDF Downloads 234

Authors: Salima Smiti, Ines Gasmi, Makram Soui

Abstract:

Credit risk is the most important issue for financial institutions. Its assessment becomes an important task used to predict defaulter customers and classify customers as good or bad payers. To this objective, numerous techniques have been applied for credit risk assessment. However, to our knowledge, several evaluation techniques are black-box models such as neural networks, SVM, etc. They generate applicants’ classes without any explanation. In this paper, we propose to assess credit risk using rules classification method. Our output is a set of rules which describe and explain the decision. To this end, we will compare seven classification algorithms (JRip, Decision Table, OneR, ZeroR, Fuzzy Rule, PART and Genetic programming (GP)) where the goal is to find the best rules satisfying many criteria: accuracy, sensitivity, and specificity. The obtained results confirm the efficiency of the GP algorithm for German and Australian datasets compared to other rule-based techniques to predict the credit risk.

Keywords: credit risk assessment, classification algorithms, data mining, rule extraction

Procedia PDF Downloads 171

Authors: Yulong Wang, Yuan Yan Tang, Cuiming Zou, Lina Yang

Abstract:

This paper presents a novel sparse representation method for robust pattern classification. Generalized orthogonal matching pursuit (GOMP) is a recently proposed efficient sparse representation technique. However, GOMP adopts the mean square error (MSE) criterion and assign the same weights to all measurements, including both severely and slightly corrupted ones. To reduce the limitation, we propose an information-theoretic GOMP (ITGOMP) method by exploiting the correntropy induced metric. The results show that ITGOMP can adaptively assign small weights on severely contaminated measurements and large weights on clean ones, respectively. An ITGOMP based classifier is further developed for robust pattern classification. The experiments on public real datasets demonstrate the efficacy of the proposed approach.

Keywords: correntropy induced metric, matching pursuit, pattern classification, sparse representation

Procedia PDF Downloads 352

Authors: Vinay Kant Shankhdhar

Abstract:

Purpose: Maxillary defects are three dimensional and require complex bone and soft tissue reconstruction. Maxillary reconstruction using fibula osteocutaneous flaps in situation requiring orbital floor, orbital wall, palatal defects, and external skin, all at the same time require special planning and multiple osteotomies. We tried to improvise our reconstruction using multiple osteotomies and skin paddle designs for fibula and Flexor Hallucis Longus Muscle. This study aims at discussing the planning and outcome in complex maxillary reconstructions using fibula flaps and soft tissue flaps with or without bone grafts. Material and Methods: From 2011 to 2017 a total of 129 Free fibula flaps were done, 67 required two or more struts, 164 Anterolateral Thigh Flaps, 11 Deep Inferior Epigastric Artery perforator flaps and 3 vertical rectus abdominis muscle flaps with iliac crest bone graft. The age range was 2 to 70 years. The reconstruction was evaluated based on the post-operative rehabilitation including orbital support (prevention of diplopia), oral diet, speech and cosmetic appearance. Results: The follow- up is from 5 years to 1 year. In this series, we observed that the common complications were the de-vascularisation of most distal segment of osteotomised fibula and native skin necrosis. Commonest area of breakdown is the medial canthal region. Plate exposure occurs most commonly at the pyriform sinus. There was extrusion of one non-vascularized bone graft. All these complications were noticed post-radiotherapy. Conclusions: The use of free fibula osteocutaneous flap gives very good results when only alveolar reconstruction is required. The reconstruction of orbital floor with extensive skin loss with post operative radiotherapy has maximum complication rate in long term follow up. A soft tissue flap with non vascularized bone graft may be the best option in such cases.

Keywords: maxilla reconstruction, fibula maxilla, post cancer maxillary reconstruction

Procedia PDF Downloads 127

Authors: Qi Xiu, Hiromu Hota, Yohsuke Ishii, Takuya Oda

Abstract:

Recently, collectable manufacturing data are rapidly increasing. On the other hand, mega recall is getting serious as a social problem. Under such circumstances, there are increasing needs for preventing mega recalls by defect analysis such as root cause analysis and abnormal detection utilizing manufacturing data. However, the time to classify strings in manufacturing data by traditional method is too long to meet requirement of quick defect analysis. Therefore, we present String Length Distribution Classification method (SLDC) to correctly classify strings in a short time. This method learns character features, especially string length distribution from Product ID, Machine ID in BOM and asset list. By applying the proposal to strings in actual manufacturing data, we verified that the classification time of strings can be reduced by 80%. As a result, it can be estimated that the requirement of quick defect analysis can be fulfilled.

Keywords: string classification, data quality, feature selection, probability distribution, string length

Procedia PDF Downloads 312

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on HSI dataset Indian Pines. The results confirm the capability of the proposed method.

Keywords: continual learning, data reconstruction, remote sensing, hyperspectral image segmentation

Procedia PDF Downloads 251

Authors: Abir O. El Sadik

Abstract:

Introduction: Wound healing involves the interaction of multiple biological processes among different types of cells, intercellular matrix and specific signaling factors producing enhancement of cell proliferation of the epidermis over dermal granulation tissue. Several studies investigated multiple strategies to promote wound healing and to minimize infection and fluid losses. However, burn crisis, and its related morbidity and mortality are still elevated. The aim of the present study was to examine the effects of mesenchymal stem cells (MSCs) in accelerating wound healing and to compare the most efficient route of administration of MSCs, either intradermal or systemic injection, with focusing on the mechanisms producing epidermal and dermal cell regeneration. Material and methods: Forty-two adult male Sprague Dawley albino rats were divided into three equal groups (fourteen rats in each group): control group (group I); full thickness surgical skin wound model, Group II: Wound treated with systemic injection of MSCs and Group III: Wound treated with intradermal injection of MSCs. The healing ulcer was examined on day 2, 6, 10 and 15 for gross morphological evaluation and on day 10 and 15 for fluorescent, histological and immunohistochemical studies. Results: The wounds of the control group did not reach complete closure up to the end of the experiment. In MSCs treated groups, better and faster healing of wounds were detected more than the control group. Moreover, the intradermal route of administration of stem cells increased the rate of healing of the wounds more than the systemic injection. In addition, the wounds were found completely healed by the end of the fifteenth day of the experiment in all rats of the group injected intradermally. Microscopically, the wound areas of group III were hardly distinguished from the adjacent normal skin with complete regeneration of all skin layers; epidermis, dermis, hypodermis and underlying muscle layer. Fully regenerated hair follicles and sebaceous glands in the dermis of the healed areas surrounded by different arrangement of collagen fibers with a significant increase in their area percent were recorded in this group more than in other groups. Conclusion: MSCs accelerate the healing process of wound closure. The route of administration of MSCs has a great influence on wound healing as intradermal injection of MSCs was more effective in enhancement of wound healing than systemic injection.

Keywords: intradermal, mesenchymal stem cells, morphology, skin wound, systemic injection

Procedia PDF Downloads 196

Authors: Sunil Kumar, Rajesh Sharma

Abstract:

Toxic epidermal necrolysis, pruritis, rashes, lichen planus like eruption, hyper pigmentation of skin are rare toxic effects of choloroquine used over a long time. Skin and mucus membrane hyper pigmentation is generally of a bluish black or grayish color and irreversible after discontinuation of the drug. According to Ayurveda, Dushivisha is the name given to any poisonous substance which is not fully endowed with the qualities of poison by nature (i.e. it acts as an impoverished or weak poison) and because of its mild potency, it remains in the body for many years causing various symptoms, one among them being discoloration of skin.The objective of this case report is to investigate the effect of Ayurvedic management of chloroquine induced hyper-pigmentation on the line of treatment of Dushivisha. Case Report: A 26-year-old female was suffering from hyper-pigmentation of the skin over the neck, forehead, temporo-mandibular joints, upper back and posterior aspect of both the arms since 8 years had history of taking Chloroquine came to Out Patient Department of National Institute of Ayurveda, Jaipur, India in Jan. 2015. The routine investigations (CBC, ESR, Eosinophil count) were within normal limits. Punch biopsy skin studied for histopathology under hematoxylin and eosin staining showed epidermis with hyper-pigmentation of the basal layer. In the papillary dermis as well as deep dermis there were scattered melanophages along with infiltration by mononuclear cells. There was no deposition of amyloid-like substances. These histopathological findings were suggestive of Chloroquine induced hyper-pigmentation. The case was treated on the line of treatment of Dushivisha and was given Vamana and Virechana (therapeutic emesis and purgation) every six months followed by Snehana karma (oleation therapy) with Panchatikta Ghrit and Swedana (sudation). Arogyavardhini Vati -1 g, Dushivishari Vati 500 mg, Mahamanjisthadi Quath 20 ml were given twelve hourly and Aragwadhadi Quath 25 ml at bed time orally. The patient started showing lightening of the pigments after six months and almost complete remission after 12 months of the treatment. Conclusion: This patient presented with the Dushivisha effect of Chloroquineandwas administered two relevant procedures from Panchakarma viz. Vamana and Virechana. Both Vamana and Virechanakarma here referred to Shodhana karma (purification procedures) eliminates accumulated toxins from the body. In this process, oleation dislodge the toxins from the tissues and sudation helps to bring them to the alimentary tract. The line of treatment did not target direct hypo pigmentary effects; rather aimed to eliminate the Dushivisha. This gave promising results in this condition.

Keywords: Ayurveda, chloroquine, Dushivisha, hyper-pigmentation

Procedia PDF Downloads 230

Authors: Jularat Chumnaul

Abstract:

In forensic science, corpses from various homicides are different; there are both complete and incomplete, depending on causes of death or forms of homicide. For example, some corpses are cut into pieces, some are camouflaged by dumping into the river, some are buried, some are burned to destroy the evidence, and others. If the corpses are incomplete, it can lead to the difficulty of personally identifying because some tissues and bones are destroyed. To specify gender of the corpses from skeletal remains, the most precise method is DNA identification. However, this method is costly and takes longer so that other identification techniques are used instead. The first technique that is widely used is considering the features of bones. In general, an evidence from the corpses such as some pieces of bones, especially the skull and pelvis can be used to identify their gender. To use this technique, forensic scientists are required observation skills in order to classify the difference between male and female bones. Although this technique is uncomplicated, saving time and cost, and the forensic scientists can fairly accurately determine gender by using this technique (apparently an accuracy rate of 90% or more), the crucial disadvantage is there are only some positions of skeleton that can be used to specify gender such as supraorbital ridge, nuchal crest, temporal lobe, mandible, and chin. Therefore, the skeletal remains that will be used have to be complete. The other technique that is widely used for gender specifying in forensic science and archeology is skeletal measurements. The advantage of this method is it can be used in several positions in one piece of bones, and it can be used even if the bones are not complete. In this study, the classification and cluster analysis are applied to this technique, including the Kth Nearest Neighbor Classification, Classification Tree, Ward Linkage Cluster, K-mean Cluster, and Two Step Cluster. The data contains 507 particular individuals and 9 skeletal measurements (diameter measurements), and the performance of five methods are investigated by considering the apparent error rate (APER). The results from this study indicate that the Two Step Cluster and Kth Nearest Neighbor method seem to be suitable to specify gender from human skeletal remains because both yield small apparent error rate of 0.20% and 4.14%, respectively. On the other hand, the Classification Tree, Ward Linkage Cluster, and K-mean Cluster method are not appropriate since they yield large apparent error rate of 10.65%, 10.65%, and 16.37%, respectively. However, there are other ways to evaluate the performance of classification such as an estimate of the error rate using the holdout procedure or misclassification costs, and the difference methods can make the different conclusions.

Keywords: skeletal measurements, classification, cluster, apparent error rate

Procedia PDF Downloads 245

Authors: Evan Lowhorn, Rocio Alba-Flores

Abstract:

The purpose of this work is to develop a method for classifying hand signals and using the output in a drone control algorithm. To achieve this, methods based on Convolutional Neural Networks (CNN) were applied. CNN's are a subset of deep learning, which allows grid-like inputs to be processed and passed through a neural network to be trained for classification. This type of neural network allows for classification via imaging, which is less intrusive than previous methods using biosensors, such as EMG sensors. Classification CNN's operate purely from the pixel values in an image; therefore they can be used without additional exteroceptive sensors. A development bench was constructed using a desktop computer connected to a high-definition webcam mounted on a scissor arm. This allowed the camera to be pointed downwards at the desk to provide a constant solid background for the dataset and a clear detection area for the user. A MATLAB script was created to automate dataset image capture at the development bench and save the images to the desktop. This allowed the user to create their own dataset of 12,000 images within three hours. These images were evenly distributed among seven classes. The defined classes include forward, backward, left, right, idle, and land. The drone has a popular flip function which was also included as an additional class. To simplify control, the corresponding hand signals chosen were the numerical hand signs for one through five for movements, a fist for land, and the universal “ok” sign for the flip command. Transfer learning with PyTorch (Python) was performed using a pre-trained 18-layer residual learning network (ResNet-18) to retrain the network for custom classification. An algorithm was created to interpret the classification and send encoded messages to a Ryze Tello drone over its 2.4 GHz Wi-Fi connection. The drone’s movements were performed in half-meter distance increments at a constant speed. When combined with the drone control algorithm, the classification performed as desired with negligible latency when compared to the delay in the drone’s movement commands.

Keywords: classification, computer vision, convolutional neural networks, drone control

Procedia PDF Downloads 203

Authors: Andreas Aceranti, Simonetta Vernocchi, Marco Colorato, Ludwig Conistabile, Martina Falappi

Abstract:

This study was born out of the necessity to delve into and understand the intricate world of tattoos, a millenary art that lays its foundation, although sometimes complex, for effective non-verbal communication. What is most astonishing about a phenomenon such as irreversibly branding the skin, which at first glance may appear superficial, especially in the eyes of those who do not fully understand its meaning, is the fact that it is actually one of the most enduring forms of communication: body modification through tattoos or ornamental dyes indicated the wearer's membership in a particular ethnic group, social class or religious community. Even within crime-based aggregations, tattoos had (and still have) the purpose of conveying one's affiliation to a particular group, thus making one's criminal identity known. The profession of a language and cultural mediator teaches that it is essential to be able to read between the lines to grasp all those aspects that words alone do not convey. Tattooing, therefore, becomes a tool of analysis and a language that is not secondary to be taken into account for an in-depth reading of the reality that surrounds us and of cultures different from our own.

Keywords: tattoo, cultural tattoos, tattooing, non verbal communication

Procedia PDF Downloads 197

Authors: Ilma Robo, Saimir Heta, Rialda Xhizdari, Kers Kapaj

Abstract:

Background: The ideal disinfectant for surfaces, instruments, air, skin, both in dentistry and in the fields of medicine, does not exist.This is for the sole reason that all the characteristics of the ideal disinfectant cannot be contained in one; these are the characteristics that if one of them is emphasized, it will conflict with the other. A disinfectant must be stable, not be affected by changes in the environmental conditions where it stands, which means that it should not be affected by an increase in temperature or an increase in the humidity of the environment. Both of these elements contradict the other element of the idea of an ideal disinfectant, as they disrupt the solubility ratios of the base substance of the disinfectant versus the diluent. Material and methods: The study aims to extract the constant of each disinfectant/antiseptic used during dental disinfection protocols, accompanied by the side effects of the surface of the skin or mucosa where it is applied in the role of antiseptic. In the end, attempts were made to draw conclusions about the best possible combination for disinfectants after a dental procedure, based on the data extracted from the basic literature required during the development of the pharmacology module, as a module in the formation of a dentist, against data published in the literature. Results: The sensitivity of the disinfectant to changes in the atmospheric conditions of the environment where it is kept is a known fact. The care against this element is always accompanied by the advice on the application of the specific disinfectant, in order to have the desired clinical result. The constants of disinfectants according to the classification based on the data collected and presented are for alcohols 70-120, glycols 0.2, aldehydes 30-200, phenols 15-60, acids 100, povidone iodine halogens 5-75, hypochlorous acid halogens 150, sodium hypochlorite halogens 30-35, oxidants 18-60, metals 0.2-10. The part of halogens should be singled out, where specific results were obtained according to the representatives of this class, since it is these representatives that find scope for clinical application in dentistry. Conclusions: The search for the "ideal", in the conditions where its defining criteria are also established, not only for disinfectants but also for any medication or pharmaceutical product, is an ongoing search, without any definitive results. In this mine of data in the published literature if there is something fixed, calculable, such as the specific constant for disinfectants, the search for the ideal is more concrete. During the disinfection protocols, different disinfectants are applied since the field of action is different, including water, air, aspiration devices, tools, disinfectants used in full accordance with the production indications.

Keywords: disinfectant, constant, ideal, side effects

Procedia PDF Downloads 63