Search results for: audio classification

Authors: Ting Lu, Ya-Ru Diao, Fei Fan, Ye Xue, Lei Shi, Xian-e Tang, Meng-jun Zhan, Zhen-hua Deng

Abstract:

Accurate adult age estimation (AAE) is a significant and challenging task in forensic and archeology fields. Attempts have been made to explore optimal adult age metrics, and the rib is considered a potential age marker. The traditional way is to extract age-related features designed by experts from macroscopic or radiological images followed by classification or regression analysis. Those results still have not met the high-level requirements for practice, and the limitation of using feature design and manual extraction methods is loss of information since the features are likely not designed explicitly for extracting information relevant to age. Deep learning (DL) has recently garnered much interest in imaging learning and computer vision. It enables learning features that are important without a prior bias or hypothesis and could be supportive of AAE. This study aimed to develop DL models for AAE based on CT images and compare their performance to the manual visual scoring method. Chest CT data were reconstructed using volume rendering (VR). Retrospective data of 2500 patients aged 20.00-69.99 years were obtained between December 2019 and September 2021. Five-fold cross-validation was performed, and datasets were randomly split into training and validation sets in a 4:1 ratio for each fold. Before feeding the inputs into networks, all images were augmented with random rotation and vertical flip, normalized, and resized to 224×224 pixels. ResNeXt was chosen as the DL baseline due to its advantages of higher efficiency and accuracy in image classification. Mean absolute error (MAE) was the primary parameter. Independent data from 100 patients acquired between March and April 2022 were used as a test set. The manual method completely followed the prior study, which reported the lowest MAEs (5.31 in males and 6.72 in females) among similar studies. CT data and VR images were used. The radiation density of the first costal cartilage was recorded using CT data on the workstation. The osseous and calcified projections of the 1 to 7 costal cartilages were scored based on VR images using an eight-stage staging technique. According to the results of the prior study, the optimal models were the decision tree regression model in males and the stepwise multiple linear regression equation in females. Predicted ages of the test set were calculated separately using different models by sex. A total of 2600 patients (training and validation sets, mean age=45.19 years±14.20 [SD]; test set, mean age=46.57±9.66) were evaluated in this study. Of ResNeXt model training, MAEs were obtained with 3.95 in males and 3.65 in females. Based on the test set, DL achieved MAEs of 4.05 in males and 4.54 in females, which were far better than the MAEs of 8.90 and 6.42 respectively, for the manual method. Those results showed that the DL of the ResNeXt model outperformed the manual method in AAE based on CT reconstruction of the costal cartilage and the developed system may be a supportive tool for AAE.

Keywords: forensic anthropology, age determination by the skeleton, costal cartilage, CT, deep learning

Procedia PDF Downloads 68

Authors: Matthieu-P. Schapranow

Abstract:

Recruitment of participants for clinical trials requires the screening of a big number of potential candidates, i.e. the testing for trial-specific inclusion and exclusion criteria, which is a time-consuming and complex task. Today, a significant amount of time is spent on identification of adequate trial participants as their selection may affect the overall study results. We introduce a unique patient eligibility metric, which allows systematic ranking and classification of candidates based on trial-specific filter criteria. Our web application enables real-time analysis of patient data and assessment of candidates using freely definable inclusion and exclusion criteria. As a result, the overall time required for identifying eligible candidates is tremendously reduced whilst additional degrees of freedom for evaluating the relevance of individual candidates are introduced by our contribution.

Keywords: in-memory technology, clinical trials, screening, eligibility metric, data analysis, clustering

Procedia PDF Downloads 490

Authors: Birmohan Singh, V.K.Jain

Abstract:

Computer aided diagnosis systems provide vital opinion to radiologists in the detection of early signs of breast cancer from mammogram images. Masses and microcalcifications, architectural distortions are the major abnormalities. In this paper, a computer aided diagnosis system has been proposed for distinguishing abnormal mammograms with architectural distortion from normal mammogram. Four types of texture features GLCM texture, GLRLM texture, fractal texture and spectral texture features for the regions of suspicion are extracted. Support Vector Machine has been used as classifier in this study. The proposed system yielded an overall sensitivity of 96.47% and accuracy of 96% for the detection of abnormalities with mammogram images collected from Digital Database for Screening Mammography (DDSM) database.

Keywords: architecture distortion, mammograms, GLCM texture features, GLRLM texture features, support vector machine classifier

Procedia PDF Downloads 485

Authors: Omojokun Gabriel Aju

Abstract:

Communication network is a process of exchanging data between two or more devices via some forms of transmission medium using communication protocols. The data could be in form of text, images, audio, video or numbers which can be grouped into FTP, Email, HTTP, VOIP or Video applications. The effectiveness of such data exchange will be proved if they are accurately delivered within specified time. While some senders will not really mind when the data is actually received by the receiving device, inasmuch as it is acknowledged to have been received by the receiver. The time a data takes to get to a receiver could be very important to another sender, as any delay could cause serious problem or even in some cases rendered the data useless. The validity or invalidity of a data after delay will therefore definitely depend on the type of data (information). It is therefore imperative for the network device (such as router) to be able to differentiate among the packets which are time sensitive and those that are not, when they are passing through the same network. So, here is where the queuing disciplines comes to play, to handle network resources when such network is designed to service widely varying types of traffics and manage the available resources according to the configured policies. Therefore, as part of the resources allocation mechanisms, a router within the network must implement some queuing discipline that governs how packets (data) are buffered while waiting to be transmitted. The implementation of the queuing discipline will regulate how the packets are buffered while waiting to be transmitted. In achieving this, various queuing disciplines are being used to control the transmission of these packets, by determining which of the packets get the highest priority, less priority and which packets are dropped. The queuing discipline will therefore control the packets latency by determining how long a packet can wait to be transmitted or dropped. The common queuing disciplines are first-in-first-out queuing, Priority queuing and Weighted-fair queuing (FIFO, PQ and WFQ). This paper critically evaluates and analyse through the use of Optimized Network Evaluation Tool (OPNET) Modeller, Version 14.5 the effects of three queuing disciplines (FIFO, PQ and WFQ) on the performance of 5 different applications (FTP, HTTP, E-Mail, Voice and Video) within specified parameters using packets sent, packets received and transmission delay as performance metrics. The paper finally suggests some ways in which networks can be designed to provide better transmission performance while using these queuing disciplines.

Keywords: applications, first-in-first-out queuing (FIFO), optimised network evaluation tool (OPNET), packets, priority queuing (PQ), queuing discipline, weighted-fair queuing (WFQ)

Procedia PDF Downloads 356

Authors: S. Athiralakshmi, B.E. Bhojaraja, U. Pruthviraj

Abstract:

In agriculture, remote sensing is applied for monitoring of plant development, evaluating of physiological processes and growth conditions. Especially valuable are the spatio-temporal aspects of the remotely sensed data in detecting crop state differences and stress situations. In this study, hyperion imagery is used for classifying arecanut crops based on their age so that these maps can be used in yield estimation of crops, irrigation purposes, applying fertilizers etc. Traditional hard classifiers assigns the mixed pixels to the dominant classes. The proposed method uses a sub pixel level classifier called linear spectral unmixing available in ENVI software. It provides the relative abundance of surface materials and the context within a pixel that may be a potential solution to effectively identifying the land-cover distribution. Validation is done referring to field spectra collected using spectroradiometer and the ground control points obtained from GPS.

Keywords: FLAASH, Hyperspectral remote sensing, Linear Spectral Unmixing, Spectral Angle Mapper Classifier.

Procedia PDF Downloads 518

Authors: Antoine F. Dedewanou, Eric N. Ekpinda

Abstract:

We investigate whether and how deposit insurance program affects savings decisions in the Economic Community of Central African States (ECCAS). Specifically, using the World Bank’s 2014 and 2011 Global Financial Inclusion (Global Findex) databases, we apply special regressor approach. We find that the deposit insurance program increases significantly, everything else equal, the probability that people save their money at a financial institution by 11 percentage points in Gabon, by 22.2 percentage points in DR Congo and by 15.1 percentage points in Chad. These effects are matched with positive effects of age and education level. But in Cameroon, the effect of deposit insurance is not significant. The policies aimed at fostering financial inclusion will be more effective if there is a deposit insurance scheme in place, along with awareness among young people, and education programs. JEL Classification: G21, O12, O16

Keywords: deposit insurance, savings, special regressor, ECCAS countries

Procedia PDF Downloads 185

Authors: Sisira Edirippulige

Abstract:

Background: Digital health education and training (DHET) is imperative for preparing current and future clinicians to work competently in digitally enabled environments. Despite rapid integration of digital health in modern health services, systematic education and training opportunities for health workers is still lacking. Objectives: This study aimed to investigate healthcare professionals’ perspectives and expectations regarding the knowledge, skills and competency needs in digital health for current and future healthcare workforce. Methods: A qualitative study design with semi-structured individual interviews was employed. A purposive sample method was adopted to collect relevant information from the health workers. Inductive thematic analysis was used to analyse data. Interviews were audio-recorded and transcribed verbatim. Consolidated Criteria for Reporting Qualitative Research (COREQ) was followed when we reported this study. Results: Two themes emerged while analysing the data: (1) what to teach in DHET and (2) how to teach DHET. Overall, healthcare professionals agreed that DHET is important for preparing current and future clinicians for working competently in digitally enabled environments. Knowledge relating to what is digital health, types of digital health, use of technology and human factors in digital health were considered as important to be taught in DHET. Skills relating to digital health consultations, clinical information system management and remote monitoring were considered important to be taught. Blended learning which combined e-learning and classroom-based teaching, simulation sessions and clinical rotations were suggested by healthcare professionals as optimal approaches to deliver the above-mentioned content. Conclusions: This study is the first of its kind to investigate health professionals’ perspectives and expectations relating to the knowledge, skills and competency needs in digital health for current and future healthcare workforce. Healthcare workers are keen to acquire relevant knowledge, skills and competencies related to digital health. Different modes of education delivery is of interest to fit in with busy schedule of health workers.

Keywords: digital health, telehealth, telemedicine, education, curriculum

Procedia PDF Downloads 142

Authors: Maamar Ali Saud Al Tobi, Geraint Bevan, K. P. Ramachandran, Peter Wallace, David Harrison

Abstract:

Centrifugal pumps are complex machines which can experience different types of fault. Condition monitoring can be used in centrifugal pump fault detection through vibration analysis for mechanical and hydraulic forces. Vibration analysis methods have the potential to be combined with artificial intelligence systems where an automatic diagnostic method can be approached. An automatic fault diagnosis approach could be a good option to minimize human error and to provide a precise machine fault classification. This work aims to introduce an approach to centrifugal pump fault diagnosis based on artificial intelligence and genetic algorithm systems. An overview of the future works, research methodology and proposed experimental setup is presented and discussed. The expected results and outcomes based on the experimental work are illustrated.

Keywords: centrifugal pump setup, vibration analysis, artificial intelligence, genetic algorithm

Procedia PDF Downloads 405

Authors: Covadonga Rodrigo, Felipe Alvarez Arrieta, Ana Garcia Serrano

Abstract:

Mobile augmented reality technologies have become very popular in the last years in the educational field. Researchers have studied how these technologies improve the engagement of the student and better understanding of the process of learning. But few studies have been made regarding the accessibility of these new technologies applied to digital humanities. The goal of our research is to develop an accessible mobile application with embedded augmented reality main characters of the art work and gamification events accompanied by multi-sensorial activities. The mobile app conducts a learning itinerary around the artistic work, driving the user experience in and out the museum. The learning design follows the inquiry-based methodology and social learning conducted through interaction with social networks. As for the software application, it’s being user-centered designed, following the universal design for learning (UDL) principles to assure the best level of accessibility for all. The mobile augmented reality application starts recognizing a marker from a masterpiece of a museum using the camera of the mobile device. The augmented reality information (history, author, 3D images, audio, quizzes) is shown through virtual main characters that come out from the art work. To comply with the UDL principles, we use a version of the technology acceptance model (TAM) to study the easiness of use and perception of usefulness, extended by the authors with specific indicators for measuring accessibility issues. Following a rapid prototype method for development, the first app has been recently produced, fulfilling the EN 301549 standard and W3C accessibility guidelines for mobile development. A TAM-based web questionnaire with 214 participants with different kinds of disabilities was previously conducted to gather information and feedback on user preferences from the artistic work on the Museo del Prado, the level of acceptance of technology innovations and the easiness of use of mobile elements. Preliminary results show that people with disabilities felt very comfortable while using mobile apps and internet connection. The augmented reality elements seem to offer an added value highly engaging and motivating for the students.

Keywords: H.5.1 (multimedia information systems), artificial, augmented and virtual realities, evaluation/methodology

Procedia PDF Downloads 132

Authors: Eugene Stepanov, Arcady Ponosov

Abstract:

To model gene regulatory networks one uses ordinary differential equations with switching nonlinearities, where the initial value problem is known to be well-posed if the trajectories cross the discontinuities transversally. Otherwise, the initial value problem is usually ill-posed, which lead to theoretical and numerical complications. In the presentation, it is proposed to apply the theory of hybrid dynamical systems, rather than switched ones, to regularize the problem. 'Hybridization' of the switched system means that one attaches a dynamic discrete component ('automaton'), which follows the trajectories of the original system and governs its dynamics at the points of ill-posedness of the initial value problem making it well-posed. The construction of the automaton is based on the classification of the attractors of the specially designed adjoint dynamical system. Several examples are provided in the presentation, which support the suggested analysis. The method can also be of interest in other applied fields, where differential equations contain switchings, e.g. in neural field models.

Keywords: hybrid dynamical systems, ill-posed problems, singular perturbation analysis, switching nonlinearities

Procedia PDF Downloads 179

Authors: Samaneh Nadali, Masrah Azrifah Azmi Murad

Abstract:

As a result of the growth of the web, people are able to express their views and opinions. They can now post reviews of products at merchant sites and express their views on almost anything in internet forums, discussion groups, and blogs. Therefore, the number of product reviews has grown rapidly. The large numbers of reviews make it difficult for manufacturers or businesses to automatically classify them into different semantic orientations (positive, negative, and neutral). For sentiment classification, most existing methods utilize a list of opinion words whereas this paper proposes a fuzzy approach for evaluating sentiments expressed in customer product reviews, to predict the strength levels (e.g. very weak, weak, moderate, strong and very strong) of customer product reviews by combinations of adjective, adverb and verb. The proposed fuzzy approach has been tested on eight benchmark datasets and obtained 74% accuracy, which leads to help the organization with a more clear understanding of customer's behavior in support of business planning process.

Keywords: fuzzy logic, customer product review, sentiment analysis

Procedia PDF Downloads 362

Authors: Elena Puica

Abstract:

This paper aims to investigate the impact of Supply Chain Management (SCM) on the environment by applying a Machine Learning model while pointing out the efficiency of the technology used. The Machine Learning model was used to derive the efficiency and optimization of technology used in SCM and the environmental impact of SCM processes. The model applied is a predictive classification model and was trained firstly to determine which stage of the SCM has more outputs and secondly to demonstrate the efficiency of using advanced technology in SCM instead of recuring to traditional SCM. The outputs are the emissions generated in the environment, the consumption from different steps in the life cycle, the resulting pollutants/wastes emitted, and all the releases to air, land, and water. This manuscript presents an innovative approach to applying advanced technology in SCM and simultaneously studies the efficiency of technology and the SCM's impact on the environment. Identifying the conceptual relationships between SCM practices and their impact on the environment is a new contribution to the research. The authors can take a forward step in developing recent studies in SCM and its effects on the environment by applying technology.

Keywords: machine-learning model in SCM, SCM processes, SCM and the environmental impact, technology in SCM

Procedia PDF Downloads 113

Authors: Cristina Vatamanu, Doina Cosovan, Dragos Gavrilut, Henri Luchian

Abstract:

In the past few years, the amount of malicious software increased exponentially and, therefore, machine learning algorithms became instrumental in identifying clean and malware files through semi-automated classification. When working with very large datasets, the major challenge is to reach both a very high malware detection rate and a very low false positive rate. Another challenge is to minimize the time needed for the machine learning algorithm to do so. This paper presents a comparative study between different machine learning techniques such as linear classifiers, ensembles, decision trees or various hybrids thereof. The training dataset consists of approximately 2 million clean files and 200.000 infected files, which is a realistic quantitative mixture. The paper investigates the above mentioned methods with respect to both their performance (detection rate and false positive rate) and their practicability.

Keywords: ensembles, false positives, feature selection, one side class algorithm

Procedia PDF Downloads 287

Authors: Asimina Paparrigopoulou, John Pavlopoulos, Maria Konstantinidou

Abstract:

Dating papyri accurately is crucial not only to editing their texts but also for our understanding of palaeography and the history of writing, ancient scholarship, material culture, networks in antiquity, etc. Most ancient manuscripts offer little evidence regarding the time of their production, forcing papyrologists to date them on palaeographical grounds, a method often criticized for its subjectivity. By experimenting with data obtained from the Collaborative Database of Dateable Greek Bookhands and the PapPal online collections of objectively dated Greek papyri, this study shows that deep learning dating models, pre-trained on generic images, can achieve accurate chronological estimates for a test subset (67,97% accuracy for book hands and 55,25% for documents). To compare the estimates of these models with those of humans, experts were asked to complete a questionnaire with samples of literary and documentary hands that had to be sorted chronologically by century. The same samples were dated by the models in question. The results are presented and analysed.

Keywords: image classification, papyri images, dating

Procedia PDF Downloads 77

Authors: Ramon Hernán, Maria Teresa Corzo

Abstract:

This study examines the impact and contribution of the main journals in the discipline of behavioral finance to determine the state of the art of the discipline and the growth lines and concepts studied to date. This is a unique and novel study given that a review of the discipline has not been carried out through the keywords of the articles that allows visualizing through this component of the research, which are the main topics of discussion and the relationships that arise between the concepts discussed. To carry out this study, 3,876 articles have been taken as a reference, which includes 15,859 keywords from the main journals responsible for the growth of the discipline.; Journal of Behavioral Finance, Review of Behavioral Finance, Journal of Behavioral and Experimental Economics, Journal of Behavioral and Experimental Economics and Review of Behavioral Finance. The results indicate which are the topics most covered in the discipline throughout the period from 2000 to 2020, how these concepts have been dealt with on a recurring basis along with others throughout the aforementioned period and how the different concepts have been grouped based on the keywords established by the authors for the classification of their articles with a network diagram to complete the analysis.

Keywords: behavioral finance, keywords, co-words, top journals, data visualization

Procedia PDF Downloads 186

Authors: Haslinda Nahazanan, Afshin Asadi, Zainuddin Md. Yusoff, Nik Nor Syahariati Nik Daud

Abstract:

Mudrocks is considered as a problematic material due to their unexpected behaviour specifically when they are contacting with water or being exposed to the atmosphere. Many instability problems of cutting slopes were found lying on high slaking mudrocks. It has become one of the major concerns to geotechnical engineer as mudrocks cover up to 50% of sedimentary rocks in the geologic records. Mudrocks display properties between soils and rocks which can be very hard to understand. Therefore, this paper aims to review the definition, mineralogy, geo-chemistry, classification and engineering properties of mudrocks. As water has become one of the major factors that will rapidly change the behaviour of mudrocks, a review on the shear strength of mudrocks in Derbyshire has been made using a fully automated hydraulic stress path testing system under three states: dry, short-term inundated and long-term inundated. It can be seen that the strength of mudrocks has deteriorated as it condition changed from dry to short-term inundated and finally to long-term inundated.

Keywords: mudrocks, sedimentary rocks, inundation, shear strength

Procedia PDF Downloads 232

Authors: Divya Pande

Abstract:

The dynamics of culture expresses itself in language. Even after India got independence in 1947 English subtly crept in the language of the masses with a silent and powerful flow towards the vernacular. The culture contact resulted in learning and emergence of a new language across the Hindi speaking belt of Northern and Central India. The hybrid words thus formed displaced the original word and got contextualized and absorbed in the language of the common masses. The research paper explores the interesting new vocabulary used extensively in the urban and rural districts of the state of Uttar- Pradesh which is the most populous state of India. The paper adopts a two way classification- formal and contextual for the analysis of the hybrid vocabulary of the linguistic items where one element is necessarily from the English language and the other from the Hindi. The new vocabulary represents languages of the wider world cutting across the geographical and the cultural barriers. The paper also broadly points out to the Hinglish commonly used in the state.

Keywords: assimilation, culture contact, Hinglish, hybrid words

Procedia PDF Downloads 397

Authors: Juliza Hidayati, Sawarni Hasibuan

Abstract:

PT. XYZ is a manufacturing company that produces Crude Palm Oil (CPO). The fierce competition in the global markets not only between companies but also a competition between supply chains. This research aims to analyze the supply chain and value chain of Crude Palm Oil (CPO) in the company. Data analysis method used is qualitative analysis and quantitative analysis. The qualitative analysis describes supply chain and value chain, while the quantitative analysis is used to find out value added and the establishment of the value chain. Based on the analysis, the value chain of crude palm oil (CPO) in the company consists of four main actors that are suppliers of raw materials, processing, distributor, and customer. The value chain analysis consists of two actors; those are palm oil plantation and palm oil processing plant. The palm oil plantation activities include nurseries, planting, plant maintenance, harvesting, and shipping. The palm oil processing plant activities include reception, sterilizing, thressing, pressing, and oil classification. The value added of palm oil plantations was 72.42% and the palm oil processing plant was 10.13%.

Keywords: palm oil, value chain, value added, supply chain

Procedia PDF Downloads 364

Authors: Liang Zhou, Xiaojing Zhu, Yin Lu

Abstract:

Danshen can induce the angiogenesis in advanced ischemic heart disease while inhibiting the angiogenesis in cancer. Additionally, Danshen mainly contains two groups of ingredients: the hydrophilic phenolic acids (danshensu, caffeic acid and salvianolic acid B), and the lipophilic tanshinones (dihydrotanshinone I, tanshinone II A, and cryptotanshinone). The lipophilic tanshinones reduced the VEGF- and bFGF-induced proliferation of HUVECs in dose-dependent manner, but cannot perform in others. Conversely, caffeic acid and salvianolic acid B had the opposite effect. Danshensu inhibited the VEGF- and bFGF-induced migration of HUVECs, and others were not. Most of them interrupted the forming capillary-like structures of HUVECs, except the danshensu and caffeic acid. Oppositely, caffeic acid enhanced the ability of forming capillary-like structures of HUVECs. Ultimately, the lipophilic tanshinones, danshensu and salvianolic acid B inhibited the angiogenesis, whereas the caffeic acid induced the angiogenesis. These data provide useful information for the classification of ingredients of Danshen for angiogenesis.

Keywords: angiogenesis, Danshen, HUVECs, ingredients

Procedia PDF Downloads 387

Authors: Nishtha Madaan, Prateek Chaudhury, Nishant Kumar, Srikanta Bedathur

Abstract:

In modern NLP applications, word embeddings are a crucial backbone that can be readily shared across a number of tasks. However, as the text distributions change and word semantics evolve over time, the downstream applications using the embeddings can suffer if the word representations do not conform to the data drift. Thus, maintaining word embeddings to be consistent with the underlying data distribution is a key problem. In this work, we tackle this problem and propose TransDrift, a transformer-based prediction model for word embeddings. Leveraging the flexibility of the transformer, our model accurately learns the dynamics of the embedding drift and predicts future embedding. In experiments, we compare with existing methods and show that our model makes significantly more accurate predictions of the word embedding than the baselines. Crucially, by applying the predicted embeddings as a backbone for downstream classification tasks, we show that our embeddings lead to superior performance compared to the previous methods.

Keywords: NLP applications, transformers, Word2vec, drift, word embeddings

Procedia PDF Downloads 84

Authors: Alberto Alcalá-Alvarez, Pablo Padilla-Longoria

Abstract:

The present paper describes a framework for constructing mathematical networks encoding relevant musical information from a music score for structural analysis. These graphs englobe statistical information about music elements such as notes, chords, rhythms, intervals, etc., and the relations among them, and so become helpful in visualizing and understanding important stylistic features of a music fragment. In order to build such networks, musical data is parsed out of a digital symbolic music file. This data undergoes different analytical procedures from Graph Theory, such as measuring the centrality of nodes, community detection, and entropy calculation. The resulting networks reflect important structural characteristics of the fragment in question: predominant elements, connectivity between them, and complexity of the information contained in it. Music pieces in different styles are analyzed, and the results are contrasted with the traditional analysis outcome in order to show the consistency and potential utility of this method for music analysis.

Keywords: computational musicology, mathematical music modelling, music analysis, style classification

Procedia PDF Downloads 98

Authors: B. Arzhanov, A. Correia, P. Delgado, J. Meireles

Abstract:

Quad Flat No-Lead (QFN) packages have become very popular for turners, converters and audio amplifiers, among others applications, needing efficient power dissipation in small footprints. Since semiconductor junction temperature (TJ) is a critical parameter in the product quality. And to ensure that die temperature does not exceed the maximum allowable TJ, a thermal analysis conducted in an earlier development phase is essential to avoid repeated re-designs process with huge losses in cost and time. A simulation tool capable to estimate die temperature of components with QFN package was developed. Allow establish a non-empirical way to define an acceptance criterion for amount of voids in solder interface between its exposed pad and Printed Circuit Board (PCB) to be applied during industrialization process, and evaluate the impact of PCB designs parameters. Targeting PCB layout designer as an end user for the application, a user-friendly interface (GUI) was implemented allowing user to introduce design parameters in a convenient and secure way and hiding all the complexity of finite element simulation process. This cost effective tool turns transparent a simulating process and provides useful outputs after acceptable time, which can be adopted by PCB designers, preventing potential risks during the design stage and make product economically efficient by not oversizing it. This article gathers relevant information related to the design and implementation of the developed tool, presenting a parametric study conducted with it. The simulation tool was experimentally validated using a Thermal-Test-Chip (TTC) in a QFN open-cavity, in order to measure junction temperature (TJ) directly on the die under controlled and knowing conditions. Providing a short overview about standard thermal solutions and impacts in exposed pad packages (i.e. QFN), accurately describe the methods and techniques that the system designer should use to achieve optimum thermal performance, and demonstrate the effect of system-level constraints on the thermal performance of the design.

Keywords: QFN packages, exposed pads, junction temperature, thermal management and measurements

Procedia PDF Downloads 251

Authors: A. Biran, P. Sobhe Bidari, A. Almazroe, V. Lakshminarayanan, K. Raahemifar

Abstract:

Diabetic Retinopathy (DR) is a severe retinal disease which is caused by diabetes mellitus. It leads to blindness when it progress to proliferative level. Early indications of DR are the appearance of microaneurysms, hemorrhages and hard exudates. In this paper, an automatic algorithm for detection of DR has been proposed. The algorithm is based on combination of several image processing techniques including Circular Hough Transform (CHT), Contrast Limited Adaptive Histogram Equalization (CLAHE), Gabor filter and thresholding. Also, Support Vector Machine (SVM) Classifier is used to classify retinal images to normal or abnormal cases including non-proliferative or proliferative DR. The proposed method has been tested on images selected from Structured Analysis of the Retinal (STARE) database using MATLAB code. The method is perfectly able to detect DR. The sensitivity specificity and accuracy of this approach are 90%, 87.5%, and 91.4% respectively.

Keywords: diabetic retinopathy, fundus images, STARE, Gabor filter, support vector machine

Procedia PDF Downloads 292

Authors: Deniz Peksen

Abstract:

This thesis aims to predict trend movement of closing price of stock and to maximize portfolio by utilizing the predictions. In this context, the study aims to define a stock portfolio strategy from models created by using Logistic Regression, Gradient Boosting and Random Forest. Recently, predicting the trend of stock price has gained a significance role in making buy and sell decisions and generating returns with investment strategies formed by machine learning basis decisions. There are plenty of studies in the literature on the prediction of stock prices in capital markets using machine learning methods but most of them focus on closing prices instead of the direction of price trend. Our study differs from literature in terms of target definition. Ours is a classification problem which is focusing on the market trend in next 20 trading days. To predict trend direction, fourteen years of data were used for training. Following three years were used for validation. Finally, last three years were used for testing. Training data are between 2002-06-18 and 2016-12-30 Validation data are between 2017-01-02 and 2019-12-31 Testing data are between 2020-01-02 and 2022-03-17 We determine Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate as benchmarks which we should outperform. We compared our machine learning basis portfolio return on test data with return of Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate. We assessed our model performance with the help of roc-auc score and lift charts. We use logistic regression, Gradient Boosting and Random Forest with grid search approach to fine-tune hyper-parameters. As a result of the empirical study, the existence of uptrend and downtrend of five stocks could not be predicted by the models. When we use these predictions to define buy and sell decisions in order to generate model-based-portfolio, model-based-portfolio fails in test dataset. It was found that Model-based buy and sell decisions generated a stock portfolio strategy whose returns can not outperform non-model portfolio strategies on test dataset. We found that any effort for predicting the trend which is formulated on stock price is a challenge. We found same results as Random Walk Theory claims which says that stock price or price changes are unpredictable. Our model iterations failed on test dataset. Although, we built up several good models on validation dataset, we failed on test dataset. We implemented Random Forest, Gradient Boosting and Logistic Regression. We discovered that complex models did not provide advantage or additional performance while comparing them with Logistic Regression. More complexity did not lead us to reach better performance. Using a complex model is not an answer to figure out the stock-related prediction problem. Our approach was to predict the trend instead of the price. This approach converted our problem into classification. However, this label approach does not lead us to solve the stock prediction problem and deny or refute the accuracy of the Random Walk Theory for the stock price.

Keywords: stock prediction, portfolio optimization, data science, machine learning

Procedia PDF Downloads 77

Authors: Mustafa M. Bob, Norhan Rahman, Abdalla Elamin, Saud Taher

Abstract:

The objective of this study was to assess the suitability of Madinah city groundwater for irrigation purposes. Of the twenty three wells that were drilled in different locations in the city for the purposes of this study, twenty wells were sampled for water quality analyses. The United States Department of Agriculture (USDA) classification of irrigation water that is based on Sodium hazard (SAR) and salinity hazard was used for suitability assessment. In addition, the residual sodium carbonate (RSC) was calculated for all samples and also used for irrigation suitability assessment. Results showed that all groundwater samples are in the acceptable quality range for irrigation based on RSC values. When SAR and salinity hazard were assessed, results showed that while all groundwater samples (except one) fell in the acceptable range of SAR, they were either in the high or very high salinity zone which indicates that care should be taken regarding the type of soil and crops in the study area.

Keywords: irrigation suitability, TDS, salinity, SAR

Procedia PDF Downloads 369

Authors: Alexander Rych

Abstract:

Piql Preservation Services (“Piql”) is a turnkey solution designed for secure, migration-free long- term preservation of digital data. Piql sets an open standard for long- term preservation for the future. It consists of equipment and processes needed for writing and retrieving digital data. Exponentially growing amounts of data demand for logistically effective and cost effective processes. Digital storage media (hard disks, magnetic tape) exhibit limited lifetime. Repetitive data migration to overcome rapid obsolescence of hardware and software bears accelerated risk of data loss, data corruption or even manipulation and adds significant repetitive costs for hardware and software investments. Piql stores any kind of data in its digital as well as analog form securely for 500 years. The medium that provides this is a film reel. Using photosensitive film polyester base, a very stable material that is known for its immutability over hundreds of years, secure and cost-effective long- term preservation can be provided. The film reel itself is stored in a packaging capable of protecting the optical storage medium. These components have undergone extensive testing to ensure longevity of up to 500 years. In addition to its durability, film is a true WORM (write once- read many) medium. It therefore is resistant to editing or manipulation. Being able to store any form of data onto the film makes Piql a superior solution for long-term preservation. Paper documents, images, video or audio sequences – all of those file formats and documents can be preserved in its native file structure. In order to restore the encoded digital data, only a film scanner, a digital camera or any appropriate optical reading device will be needed in the future. Every film reel includes an index section describing the data saved on the film. It also contains a content section carrying meta-data, enabling users in the future to rebuild software in order to read and decode the digital information.

Keywords: digital data, long-term preservation, migration-free, photosensitive film

Procedia PDF Downloads 388

Authors: Monika Chuchro

Abstract:

This paper presents a preliminary attempt to apply classification of time series using meta-clusters in order to improve the quality of regression models. In this case, clustering was performed as a method to obtain a subgroups of time series data with normal distribution from inflow into waste water treatment plant data which Composed of several groups differing by mean value. Two simple algorithms: K-mean and EM were chosen as a clustering method. The rand index was used to measure the similarity. After simple meta-clustering, regression model was performed for each subgroups. The final model was a sum of subgroups models. The quality of obtained model was compared with the regression model made using the same explanatory variables but with no clustering of data. Results were compared by determination coefficient (R2), measure of prediction accuracy mean absolute percentage error (MAPE) and comparison on linear chart. Preliminary results allows to foresee the potential of the presented technique.

Keywords: clustering, data analysis, data mining, predictive models

Procedia PDF Downloads 462

Authors: Maha Wiss, Wael Khreich

Abstract:

Animals, objects, foods, plants, and other non-human terms are commonly used as a source of metaphors to describe females in formal and slang language. Comparing women to non-human items not only reflects cultural views that might conceptualize women as subordinates or in a lower position than humans, yet it conveys this degradation to the listeners. Moreover, the dehumanizing representation of females in the language normalizes the derogation and even encourages sexism and aggressiveness against women. Although dehumanization has been a popular research topic for decades, according to our knowledge, no studies have linked women's dehumanizing language to the machine learning field. Therefore, we introduce our research work as one of the first attempts to create a tool for the automated detection of the dehumanizing depiction of females in English texts. We also present the first labeled dataset on the charted topic, which is used for training supervised machine learning algorithms to build an accurate classification model. The importance of this work is that it accomplishes the first step toward mitigating dehumanizing language against females.

Keywords: gender bias, machine learning, NLP, women dehumanization

Procedia PDF Downloads 76

Authors: Ines Gasmi, Salima Smiti, Makram Soui, Khaled Ghedira

Abstract:

Credit risk is considered as one of the important issues for financial institutions. It provokes great losses for banks. To this objective, numerous methods for credit risk evaluation have been proposed. Many evaluation methods are black box models that cannot adequately reveal information hidden in the data. However, several works have focused on building transparent rules-based models. For credit risk assessment, generated rules must be not only highly accurate, but also highly interpretable. In this paper, we aim to build both, an accurate and transparent credit risk evaluation model which proposes a set of classification rules. In fact, we consider the credit risk evaluation as an optimization problem which uses a genetic programming (GP) algorithm, where the goal is to maximize the accuracy of generated rules. We evaluate our proposed approach on the base of German and Australian credit datasets. We compared our finding with some existing works; the result shows that the proposed GP outperforms the other models.

Keywords: credit risk assessment, rule generation, genetic programming, feature selection

Procedia PDF Downloads 349

Authors: Chuluundorj Begz

Abstract:

This paper presents the dynamic, psycho-cognitive approach to study of human verbal thinking on the basis of typologically different languages /as a Mongolian, English and Russian/. Topological equivalence in verbal communication serves as a basis of Universality of mental structures and therefore deep structures. Mechanism of verbal thinking consisted at the deep level of basic concepts, rules for integration and classification, neural networks of vocabulary. In neuro cognitive study of language, neural architecture and neuro psychological mechanism of verbal cognition are basis of a vector-based modeling. Verbal perception and interpretation of the infinite set of meanings and propositions in mental continuum can be modeled by applying tensor methods. Euclidean and non-Euclidean spaces are applied for a description of human semantic vocabulary and high order structures.

Keywords: Euclidean spaces, isomorphism and homomorphism, mental lexicon, mental mapping, semantic memory, verbal cognition, vector space

Procedia PDF Downloads 518