Search results for: spatiotemporal features
2965 Human Gait Recognition Using Moment with Fuzzy
Authors: Jyoti Bharti, Navneet Manjhi, M. K.Gupta, Bimi Jain
Abstract:
A reliable gait features are required to extract the gait sequences from an images. In this paper suggested a simple method for gait identification which is based on moments. Moment values are extracted on different number of frames of gray scale and silhouette images of CASIA database. These moment values are considered as feature values. Fuzzy logic and nearest neighbour classifier are used for classification. Both achieved higher recognition.Keywords: gait, fuzzy logic, nearest neighbour, recognition rate, moments
Procedia PDF Downloads 7632964 Second Language Perception of Japanese /Cju/ and /Cjo/ Sequences by Mandarin-Speaking Learners of Japanese
Authors: Yili Liu, Honghao Ren, Mariko Kondo
Abstract:
In the field of second language (L2) speech learning, it is well-known that that learner’s first language (L1) phonetic and phonological characteristics will be transferred into their L2 production and perception, which lead to foreign accent. For L1 Mandarin learners of Japanese, the confusion of /u/ and /o/ in /CjV/ sequences has been observed in their utterance frequently. L1 transfer is considered to be the cause of this issue, however, other factors which influence the identification of /Cju/ and /Cjo/ sequences still under investigation. This study investigates the perception of Japanese /Cju/ and /Cjo/ units by L1 Mandarin learners of Japanese. It further examined whether learners’ proficiency, syllable position, phonetic features of preceding consonants and background noise affect learners’ performance in perception. Fifty-two Mandarin-speaking learners of Japanese and nine native Japanese speakers were recruited to participate in an identification task. Learners were divided into beginner, intermediate and advanced level according to their Japanese proficiency. The average correct rate was used to evaluate learners’ perceptual performance. Furthermore, the comparison of the correct rate between learners’ groups and the control group was conducted as well to examine learners’ nativelikeness. Results showed that background noise tends to pose an adverse effect on distinguishing /u/ and /o/ in /CjV/ sequences. Secondly, Japanese proficiency has no influence on learners’ perceptual performance in the quiet and in background noise. Then all learners did not reach a native-like level without the distraction of noise. Beginner level learners performed less native-like, although higher level learners appeared to have achieved nativelikeness in the multi-talker babble noise. Finally, syllable position tends to affect distinguishing /Cju/ and /Cjo/ only under the noisy condition. Phonetic features of preceding consonants did not impact learners’ perception in any listening conditions. Findings in this study can give an insight into a further understanding of Japanese vowel acquisition by L1 Mandarin learners of Japanese. In addition, this study indicates that L1 transfer is not the only explanation for the confusion of /u/ and /o/ in /CjV/ sequences, factors such as listening condition and syllable position are also needed to take into consideration in future research. It also suggests the importance of perceiving speech in a noisy environment, which is close to the actual conversation required more attention to pedagogy.Keywords: background noise, Chinese learners of Japanese, /Cju/ and /Cjo/ sequences, second language perception
Procedia PDF Downloads 1622963 Exploring Pre-Trained Automatic Speech Recognition Model HuBERT for Early Alzheimer’s Disease and Mild Cognitive Impairment Detection in Speech
Authors: Monica Gonzalez Machorro
Abstract:
Dementia is hard to diagnose because of the lack of early physical symptoms. Early dementia recognition is key to improving the living condition of patients. Speech technology is considered a valuable biomarker for this challenge. Recent works have utilized conventional acoustic features and machine learning methods to detect dementia in speech. BERT-like classifiers have reported the most promising performance. One constraint, nonetheless, is that these studies are either based on human transcripts or on transcripts produced by automatic speech recognition (ASR) systems. This research contribution is to explore a method that does not require transcriptions to detect early Alzheimer’s disease (AD) and mild cognitive impairment (MCI). This is achieved by fine-tuning a pre-trained ASR model for the downstream early AD and MCI tasks. To do so, a subset of the thoroughly studied Pitt Corpus is customized. The subset is balanced for class, age, and gender. Data processing also involves cropping the samples into 10-second segments. For comparison purposes, a baseline model is defined by training and testing a Random Forest with 20 extracted acoustic features using the librosa library implemented in Python. These are: zero-crossing rate, MFCCs, spectral bandwidth, spectral centroid, root mean square, and short-time Fourier transform. The baseline model achieved a 58% accuracy. To fine-tune HuBERT as a classifier, an average pooling strategy is employed to merge the 3D representations from audio into 2D representations, and a linear layer is added. The pre-trained model used is ‘hubert-large-ls960-ft’. Empirically, the number of epochs selected is 5, and the batch size defined is 1. Experiments show that our proposed method reaches a 69% balanced accuracy. This suggests that the linguistic and speech information encoded in the self-supervised ASR-based model is able to learn acoustic cues of AD and MCI.Keywords: automatic speech recognition, early Alzheimer’s recognition, mild cognitive impairment, speech impairment
Procedia PDF Downloads 1282962 Nonlinear Power Measurement Algorithm of the Input Mix Components of the Noise Signal and Pulse Interference
Authors: Alexey V. Klyuev, Valery P. Samarin, Viktor F. Klyuev, Andrey V. Klyuev
Abstract:
A power measurement algorithm of the input mix components of the noise signal and pulse interference is considered. The algorithm efficiency analysis has been carried out for different interference to signal ratio. Algorithm performance features have been explored by numerical experiment results.Keywords: noise signal, pulse interference, signal power, spectrum width, detection
Procedia PDF Downloads 3402961 Insights into the Annotated Genome Sequence of Defluviitoga tunisiensis L3 Isolated from a Thermophilic Rural Biogas Producing Plant
Authors: Irena Maus, Katharina Gabriella Cibis, Andreas Bremges, Yvonne Stolze, Geizecler Tomazetto, Daniel Wibberg, Helmut König, Alfred Pühler, Andreas Schlüter
Abstract:
Within the agricultural sector, the production of biogas from organic substrates represents an economically attractive technology to generate bioenergy. Complex consortia of microorganisms are responsible for biomass decomposition and biogas production. Recently, species belonging to the phylum Thermotogae were detected in thermophilic biogas-production plants utilizing renewable primary products for biomethanation. To analyze adaptive genome features of representative Thermotogae strains, Defluviitoga tunisiensis L3 was isolated from a rural thermophilic biogas plant (54°C) and completely sequenced on an Illumina MiSeq system. Sequencing and assembly of the D. tunisiensis L3 genome yielded a circular chromosome with a size of 2,053,097 bp and a mean GC content of 31.38%. Functional annotation of the complete genome sequence revealed that the thermophilic strain L3 encodes several genes predicted to facilitate growth of this microorganism on arabinose, galactose, maltose, mannose, fructose, raffinose, ribose, cellobiose, lactose, xylose, xylan, lactate and mannitol. Acetate, hydrogen (H2) and carbon dioxide (CO2) are supposed to be end products of the fermentation process. The latter gene products are metabolites for methanogenic archaea, the key players in the final step of the anaerobic digestion process. To determine the degree of relatedness of dominant biogas community members within selected digester systems to D. tunisiensis L3, metagenome sequences from corresponding communities were mapped on the L3 genome. These fragment recruitments revealed that metagenome reads originating from a thermophilic biogas plant covered 95% of D. tunisiensis L3 genome sequence. In conclusion, availability of the D. tunisiensis L3 genome sequence and insights into its metabolic capabilities provide the basis for biotechnological exploitation of genome features involved in thermophilic fermentation processes utilizing renewable primary products.Keywords: genome sequence, thermophilic biogas plant, Thermotogae, Defluviitoga tunisiensis
Procedia PDF Downloads 5012960 Communication through Technology: SMS Taking Most of the Time Impacting the Standard English
Authors: Nazia Sulemna, Sadia Gul
Abstract:
With the invade of mobile phones text messaging has become a popular medium of communication. Its users are multiplying with every passing day. Its use is not only limites to informal but to formal communication as well. Students are the advent users of mobile phones and of SMS as well. The present study manifests the fact that students are practicing SMS for a number of reasons and a good amount of time is spent upon it which is resulting in typographical features, graphones and rebus writing. Data was collected through questionnaires and came to the conclusion that its effect is obvious in the L2 users and in exam as well.Keywords: text messaging, technology, exams, formal writing
Procedia PDF Downloads 7452959 Analytical Modeling of Globular Protein-Ferritin in α-Helical Conformation: A White Noise Functional Approach
Authors: Vernie C. Convicto, Henry P. Aringa, Wilson I. Barredo
Abstract:
This study presents a conformational model of the helical structures of globular protein particularly ferritin in the framework of white noise path integral formulation by using Associated Legendre functions, Bessel and convolution of Bessel and trigonometric functions as modulating functions. The model incorporates chirality features of proteins and their helix-turn-helix sequence structural motif.Keywords: globular protein, modulating function, white noise, winding probability
Procedia PDF Downloads 4802958 Locket Application
Authors: Farah Al-Fityani, Aljohara Alsowail, Shatha Bindawood, Heba Balrbeah
Abstract:
Locket is a popular app that lets users share spontaneous photos with a close circle of friends. The app offers a unique way to stay connected with loved ones by allowing users to see glimpses of their day through photos displayed on a widget on their home screen. This summary outlines the process of developing an app like Locket, highlighting the importance of user privacy and security. It also details the findings of a study on user engagement with the Locket app, revealing positive sentiment towards its features and concept but also identifying areas for improvement. Overall, the summary portrays Locket as a successful app that is changing the way people connect on social media.Keywords: locket, app, machine learning, connect
Procedia PDF Downloads 492957 A Task Scheduling Algorithm in Cloud Computing
Authors: Ali Bagherinia
Abstract:
Efficient task scheduling method can meet users' requirements, and improve the resource utilization, then increase the overall performance of the cloud computing environment. Cloud computing has new features, such as flexibility, virtualization and etc., in this paper we propose a two levels task scheduling method based on load balancing in cloud computing. This task scheduling method meet user's requirements and get high resource utilization, that simulation results in CloudSim simulator prove this.Keywords: cloud computing, task scheduling, virtualization, SLA
Procedia PDF Downloads 4052956 Load-Deflecting Characteristics of a Fabricated Orthodontic Wire with 50.6Ni 49.4Ti Alloy Composition
Authors: Aphinan Phukaoluan, Surachai Dechkunakorn, Niwat Anuwongnukroh, Anak Khantachawana, Pongpan Kaewtathip, Julathep Kajornchaiyakul, Peerapong Tua-Ngam
Abstract:
Aims: The objectives of this study was to determine the load-deflecting characteristics of a fabricated orthodontic wire with alloy composition of 50.6% (atomic weight) Ni and 49.4% (atomic weight) Ti and to compare the results with Ormco, a commercially available pre-formed NiTi orthodontic archwire. Materials and Methods: The ingots alloys with atomic weight ratio 50.6 Ni: 49.4 Ti alloy were used in this study. Three specimens were cut to have wire dimensions of 0.016 inch x0.022 inch. For comparison, a commercially available pre-formed NiTi archwire, Ormco, with dimensions of 0.016 inch x 0.022 inch was used. Three-point bending tests were performed at the temperature 36+1 °C using a Universal Testing Machine on the newly fabricated and commercial archwires to assess the characteristics of the load-deflection curve with loading and unloading forces. The loading and unloading features at the deflection points 0.25, 0.50, 0.75. 1.0, 1.25, and 1.5 mm were compared. Descriptive statistics was used to evaluate each variables, and independent t-test at p < 0.05 was used to analyze the mean differences between the two groups. Results: The load-deflection curve of the 50.6Ni: 49.4Ti wires exhibited the characteristic features of superelasticity. The curves at the loading and unloading slope of Ormco NiTi archwire were more parallel than the newly fabricated NiTi wires. The average deflection force of the 50.6Ni: 49.4Ti wire was 304.98 g and 208.08 g for loading and unloading, respectively. Similarly, the values were 358.02 g loading and 253.98 g for unloading of Ormco NiTi archwire. The interval difference forces between each deflection points were in the range 20.40-121.38 g and 36.72-92.82 g for the loading and unloading curve of 50.6Ni: 49.4Ti wire, respectively, and 4.08-157.08 g and 14.28-90.78 g for the loading and unloading curve of commercial wire, respectively. The average deflection force of the 50.6Ni: 49.4Ti wire was less than that of Ormco NiTi archwire, which could have been due to variations in the wire dimensions. Although a greater force was required for each deflection point of loading and unloading for the 50.6Ni: 49.4Ti wire as compared to Ormco NiTi archwire, the values were still within the acceptable limits to be clinically used in orthodontic treatment. Conclusion: The 50.6Ni: 49.4Ti wires presented the characteristics of a superelastic orthodontic wire. The loading and unloading force were also suitable for orthodontic tooth movement. These results serve as a suitable foundation for further studies in the development of new orthodontic NiTi archwires.Keywords: 50.6 ni 49.4 Ti alloy wire, load deflection curve, loading and unloading force, orthodontic
Procedia PDF Downloads 3032955 Influence of a High-Resolution Land Cover Classification on Air Quality Modelling
Authors: C. Silveira, A. Ascenso, J. Ferreira, A. I. Miranda, P. Tuccella, G. Curci
Abstract:
Poor air quality is one of the main environmental causes of premature deaths worldwide, and mainly in cities, where the majority of the population lives. It is a consequence of successive land cover (LC) and use changes, as a result of the intensification of human activities. Knowing these landscape modifications in a comprehensive spatiotemporal dimension is, therefore, essential for understanding variations in air pollutant concentrations. In this sense, the use of air quality models is very useful to simulate the physical and chemical processes that affect the dispersion and reaction of chemical species into the atmosphere. However, the modelling performance should always be evaluated since the resolution of the input datasets largely dictates the reliability of the air quality outcomes. Among these data, the updated LC is an important parameter to be considered in atmospheric models, since it takes into account the Earth’s surface changes due to natural and anthropic actions, and regulates the exchanges of fluxes (emissions, heat, moisture, etc.) between the soil and the air. This work aims to evaluate the performance of the Weather Research and Forecasting model coupled with Chemistry (WRF-Chem), when different LC classifications are used as an input. The influence of two LC classifications was tested: i) the 24-classes USGS (United States Geological Survey) LC database included by default in the model, and the ii) CLC (Corine Land Cover) and specific high-resolution LC data for Portugal, reclassified according to the new USGS nomenclature (33-classes). Two distinct WRF-Chem simulations were carried out to assess the influence of the LC on air quality over Europe and Portugal, as a case study, for the year 2015, using the nesting technique over three simulation domains (25 km2, 5 km2 and 1 km2 horizontal resolution). Based on the 33-classes LC approach, particular emphasis was attributed to Portugal, given the detail and higher LC spatial resolution (100 m x 100 m) than the CLC data (5000 m x 5000 m). As regards to the air quality, only the LC impacts on tropospheric ozone concentrations were evaluated, because ozone pollution episodes typically occur in Portugal, in particular during the spring/summer, and there are few research works relating to this pollutant with LC changes. The WRF-Chem results were validated by season and station typology using background measurements from the Portuguese air quality monitoring network. As expected, a better model performance was achieved in rural stations: moderate correlation (0.4 – 0.7), BIAS (10 – 21µg.m-3) and RMSE (20 – 30 µg.m-3), and where higher average ozone concentrations were estimated. Comparing both simulations, small differences grounded on the Leaf Area Index and air temperature values were found, although the high-resolution LC approach shows a slight enhancement in the model evaluation. This highlights the role of the LC on the exchange of atmospheric fluxes, and stresses the need to consider a high-resolution LC characterization combined with other detailed model inputs, such as the emission inventory, to improve air quality assessment.Keywords: land use, spatial resolution, WRF-Chem, air quality assessment
Procedia PDF Downloads 1592954 Assessing Circularity Potentials and Customer Education to Drive Ecologically and Economically Effective Materials Design for Circular Economy - A Case Study
Authors: Mateusz Wielopolski, Asia Guerreschi
Abstract:
Circular Economy, as the counterargument to the ‘make-take-dispose’ linear model, is an approach that includes a variety of schools of thought looking at environmental, economic, and social sustainability. This, in turn, leads to a variety of strategies and often confusion when it comes to choosing the right one to make a circular transition as effective as possible. Due to the close interplay of circular product design, business model and social responsibility, companies often struggle to develop strategies that comply with all three triple-bottom-line criteria. Hence, to transition to circularity effectively, product design approaches must become more inclusive. In a case study conducted with the University of Bayreuth and the ISPO, we correlated aspects of material choice in product design, labeling and technological innovation with customer preferences and education about specific material and technology features. The study revealed those attributes of the consumers’ environmental awareness that directly translate into an increase of purchase power - primarily connected with individual preferences regarding sports activity and technical knowledge. Based on this outcome, we constituted a product development approach that incorporates the consumers’ individual preferences towards sustainable product features as well as their awareness about materials and technology. It allows deploying targeted customer education campaigns to raise the willingness to pay for sustainability. Next, we implemented the customer preference and education analysis into a circularity assessment tool that takes into account inherent company assets as well as subjective parameters like customer awareness. The outcome is a detailed but not cumbersome scoring system, which provides guidance for material and technology choices for circular product design while considering business model and communication strategy to the attentive customers. By including customer knowledge and complying with corresponding labels, companies develop more effective circular design strategies, while simultaneously increasing customers’ trust and loyalty.Keywords: circularity, sustainability, product design, material choice, education, awareness, willingness to pay
Procedia PDF Downloads 2032953 A Political-Economic Analysis of Next Generation EU Recovery Fund
Authors: Fernando Martín-Espejo, Christophe Crombez
Abstract:
This paper presents a political-economic analysis of the reforms introduced during the coronavirus crisis at the EU level with a special emphasis on the recovery fund Next Generation EU (NGEU). It also introduces a spatial model to evaluate whether the governmental features of the recovery fund can be framed inside the community method. Particularly, by evaluating the brake clause in the NGEU legislation, this paper analyses theoretically the political and legislative implications of the introduction of flexibility clauses in the EU decision-making process.Keywords: EU, legislative procedures, spatial model, coronavirus
Procedia PDF Downloads 1802952 Caged Compounds as Light-Dependent Initiators for Enzyme Catalysis Reactions
Authors: Emma Castiglioni, Nigel Scrutton, Derren Heyes, Alistair Fielding
Abstract:
By using light as trigger, it is possible to study many biological processes, such as the activity of genes, proteins, and other molecules, with precise spatiotemporal control. Caged compounds, where biologically active molecules are generated from an inert precursor upon laser photolysis, offer the potential to initiate such biological reactions with high temporal resolution. As light acts as the trigger for cleaving the protecting group, the ‘caging’ technique provides a number of advantages as it can be intracellular, rapid and controlled in a quantitative manner. We are developing caging strategies to study the catalytic cycle of a number of enzyme systems, such as nitric oxide synthase and ethanolamine ammonia lyase. These include the use of caged substrates, caged electrons and the possibility of caging the enzyme itself. In addition, we are developing a novel freeze-quench instrument to study these reactions, which combines rapid mixing and flashing capabilities. Reaction intermediates will be trapped at low temperatures and will be analysed by using electron paramagnetic resonance (EPR) spectroscopy to identify the involvement of any radical species during catalysis. EPR techniques typically require relatively long measurement times and very often, low temperatures to fully characterise these short-lived species. Therefore, common rapid mixing techniques, such as stopped-flow or quench-flow are not directly suitable. However, the combination of rapid freeze-quench (RFQ) followed by EPR analysis provides the ideal approach to kinetically trap and spectroscopically characterise these transient radical species. In a typical RFQ experiment, two reagent solutions are delivered to the mixer via two syringes driven by a pneumatic actuator or stepper motor. The new mixed solution is then sprayed into a cryogenic liquid or surface, and the frozen sample is then collected and packed into an EPR tube for analysis. The earliest RFQ instrument consisted of a hydraulic ram unit as a drive unit with direct spraying of the sample into a cryogenic liquid (nitrogen, isopentane or petroleum). Improvements to the RFQ technique have arisen from the design of new mixers in order to reduce both the volume and the mixing time. In addition, the cryogenic isopentane bath has been coupled to a filtering system or replaced by spraying the solution onto a surface that is frozen via thermal conductivity with a cryogenic liquid. In our work, we are developing a novel RFQ instrument which combines the freeze-quench technology with flashing capabilities to enable the studies of both thermally-activated and light-activated biological reactions. This instrument also uses a new rotating plate design based on magnetic couplings and removes the need for mechanical motorised rotation, which can otherwise be problematic at cryogenic temperatures.Keywords: caged compounds, freeze-quench apparatus, photolysis, radicals
Procedia PDF Downloads 2092951 Centrality and Patent Impact: Coupled Network Analysis of Artificial Intelligence Patents Based on Co-Cited Scientific Papers
Authors: Xingyu Gao, Qiang Wu, Yuanyuan Liu, Yue Yang
Abstract:
In the era of the knowledge economy, the relationship between scientific knowledge and patents has garnered significant attention. Understanding the intricate interplay between the foundations of science and technological innovation has emerged as a pivotal challenge for both researchers and policymakers. This study establishes a coupled network of artificial intelligence patents based on co-cited scientific papers. Leveraging centrality metrics from network analysis offers a fresh perspective on understanding the influence of information flow and knowledge sharing within the network on patent impact. The study initially obtained patent numbers for 446,890 granted US AI patents from the United States Patent and Trademark Office’s artificial intelligence patent database for the years 2002-2020. Subsequently, specific information regarding these patents was acquired using the Lens patent retrieval platform. Additionally, a search and deduplication process was performed on scientific non-patent references (SNPRs) using the Web of Science database, resulting in the selection of 184,603 patents that cited 37,467 unique SNPRs. Finally, this study constructs a coupled network comprising 59,379 artificial intelligence patents by utilizing scientific papers co-cited in patent backward citations. In this network, nodes represent patents, and if patents reference the same scientific papers, connections are established between them, serving as edges within the network. Nodes and edges collectively constitute the patent coupling network. Structural characteristics such as node degree centrality, betweenness centrality, and closeness centrality are employed to assess the scientific connections between patents, while citation count is utilized as a quantitative metric for patent influence. Finally, a negative binomial model is employed to test the nonlinear relationship between these network structural features and patent influence. The research findings indicate that network structural features such as node degree centrality, betweenness centrality, and closeness centrality exhibit inverted U-shaped relationships with patent influence. Specifically, as these centrality metrics increase, patent influence initially shows an upward trend, but once these features reach a certain threshold, patent influence starts to decline. This discovery suggests that moderate network centrality is beneficial for enhancing patent influence, while excessively high centrality may have a detrimental effect on patent influence. This finding offers crucial insights for policymakers, emphasizing the importance of encouraging moderate knowledge flow and sharing to promote innovation when formulating technology policies. It suggests that in certain situations, data sharing and integration can contribute to innovation. Consequently, policymakers can take measures to promote data-sharing policies, such as open data initiatives, to facilitate the flow of knowledge and the generation of innovation. Additionally, governments and relevant agencies can achieve broader knowledge dissemination by supporting collaborative research projects, adjusting intellectual property policies to enhance flexibility, or nurturing technology entrepreneurship ecosystems.Keywords: centrality, patent coupling network, patent influence, social network analysis
Procedia PDF Downloads 562950 Enhanced Multi-Scale Feature Extraction Using a DCNN by Proposing Dynamic Soft Margin SoftMax for Face Emotion Detection
Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy
Abstract:
Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks
Procedia PDF Downloads 752949 Testing the Simplification Hypothesis in Constrained Language Use: An Entropy-Based Approach
Authors: Jiaxin Chen
Abstract:
Translations have been labeled as more simplified than non-translations, featuring less diversified and more frequent lexical items and simpler syntactic structures. Such simplified linguistic features have been identified in other bilingualism-influenced language varieties, including non-native and learner language use. Therefore, it has been proposed that translation could be studied within a broader framework of constrained language, and simplification is one of the universal features shared by constrained language varieties due to similar cognitive-physiological and social-interactive constraints. Yet contradicting findings have also been presented. To address this issue, this study intends to adopt Shannon’s entropy-based measures to quantify complexity in language use. Entropy measures the level of uncertainty or unpredictability in message content, and it has been adapted in linguistic studies to quantify linguistic variance, including morphological diversity and lexical richness. In this study, the complexity of lexical and syntactic choices will be captured by word-form entropy and pos-form entropy, and a comparison will be made between constrained and non-constrained language use to test the simplification hypothesis. The entropy-based method is employed because it captures both the frequency of linguistic choices and their evenness of distribution, which are unavailable when using traditional indices. Another advantage of the entropy-based measure is that it is reasonably stable across languages and thus allows for a reliable comparison among studies on different language pairs. In terms of the data for the present study, one established (CLOB) and two self-compiled corpora will be used to represent native written English and two constrained varieties (L2 written English and translated English), respectively. Each corpus consists of around 200,000 tokens. Genre (press) and text length (around 2,000 words per text) are comparable across corpora. More specifically, word-form entropy and pos-form entropy will be calculated as indicators of lexical and syntactical complexity, and ANOVA tests will be conducted to explore if there is any corpora effect. It is hypothesized that both L2 written English and translated English have lower entropy compared to non-constrained written English. The similarities and divergences between the two constrained varieties may provide indications of the constraints shared by and peculiar to each variety.Keywords: constrained language use, entropy-based measures, lexical simplification, syntactical simplification
Procedia PDF Downloads 962948 Photocatalytic Eco-Active Ceramic Slabs to Abate Air Pollution under LED Light
Authors: Claudia L. Bianchi, Giuseppina Cerrato, Federico Galli, Federica Minozzi, Valentino Capucci
Abstract:
At the beginning of the industrial productions, porcelain gres tiles were considered as just a technical material, aesthetically not very beautiful. Today thanks to new industrial production methods, both properties, and beauty of these materials completely fit the market requests. In particular, the possibility to prepare slabs of large sizes is the new frontier of building materials. Beside these noteworthy architectural features, new surface properties have been introduced in the last generation of these materials. In particular, deposition of TiO₂ transforms the traditional ceramic into a photocatalytic eco-active material able to reduce polluting molecules present in air and water, to eliminate bacteria and to reduce the surface dirt thanks to the self-cleaning property. The problem of photocatalytic materials resides in the fact that it is necessary a UV light source to activate the oxidation processes on the surface of the material, processes that are turned off inexorably when the material is illuminated by LED lights and, even more so, when we are in darkness. First, it was necessary a thorough study change the existing plants to deposit the photocatalyst very evenly and this has been done thanks to the advent of digital printing and the development of an ink custom-made that stabilizes the powdered TiO₂ in its formulation. In addition, the commercial TiO₂, which is used for the traditional photocatalytic coating, has been doped with metals in order to activate it even in the visible region and thus in the presence of sunlight or LED. Thanks to this active coating, ceramic slabs are able to purify air eliminating odors and VOCs, and also can be cleaned with very soft detergents due to the self-cleaning properties given by the TiO₂ present at the ceramic surface. Moreover, the presence of dopant metals (patent WO2016157155) also allows the material to work as well as antibacterial in the dark, by eliminating one of the negative features of photocatalytic building materials that have so far limited its use on a large scale. Considering that we are constantly in contact with bacteria, some of which are dangerous for health. Active tiles are 99,99% efficient on all bacteria, from the most common such as Escherichia coli to the most dangerous such as Staphilococcus aureus Methicillin-resistant (MRSA). DIGITALIFE project LIFE13 ENV/IT/000140 – award for best project of October 2017.Keywords: Ag-doped microsized TiO₂, eco-active ceramic, photocatalysis, digital coating
Procedia PDF Downloads 2332947 Recognition of Tifinagh Characters with Missing Parts Using Neural Network
Authors: El Mahdi Barrah, Said Safi, Abdessamad Malaoui
Abstract:
In this paper, we present an algorithm for reconstruction from incomplete 2D scans for tifinagh characters. This algorithm is based on using correlation between the lost block and its neighbors. This system proposed contains three main parts: pre-processing, features extraction and recognition. In the first step, we construct a database of tifinagh characters. In the second step, we will apply “shape analysis algorithm”. In classification part, we will use Neural Network. The simulation results demonstrate that the proposed method give good results.Keywords: Tifinagh character recognition, neural networks, local cost computation, ANN
Procedia PDF Downloads 3372946 About the Number of Fundamental Physical Interactions
Authors: Andrey Angorsky
Abstract:
In the article an issue about the possible number of fundamental physical interactions is studied. The theory of similarity on the dimensionless quantity as the damping ratio serves as the instrument of analysis. The structure with the features of Higgs field comes out from non-commutative expression for this ratio. The experimentally checked up supposition about the nature of dark energy is spoken out.Keywords: damping ratio, dark energy, dimensionless quantity, fundamental physical interactions, Higgs field, non-commutative expression
Procedia PDF Downloads 1432945 Google Translate: AI Application
Authors: Shaima Almalhan, Lubna Shukri, Miriam Talal, Safaa Teskieh
Abstract:
Since artificial intelligence is a rapidly evolving topic that has had a significant impact on technical growth and innovation, this paper examines people's awareness, use, and engagement with the Google Translate application. To see how familiar aware users are with the app and its features, quantitative and qualitative research was conducted. The findings revealed that consumers have a high level of confidence in the application and how far people they benefit from this sort of innovation and how convenient it makes communication.Keywords: artificial intelligence, google translate, speech recognition, language translation, camera translation, speech to text, text to speech
Procedia PDF Downloads 1572944 Design of Broadband Power Divider for 3G and 4G Applications
Authors: A. M. El-Akhdar, A. M. El-Tager, H. M. El-Hennawy
Abstract:
This paper presents a broadband power divider with equal power division ratio. Two sections of transmission line transformers based on coupled microstrip lines are applied to obtain broadband performance. In addition, design methodology is proposed for the novel structure. A prototype is designed, simulated to operate in the band from 2.1 to 3.8 GHz to fulfill the requirements of 3G and 4G applications. The proposed structure features reduced size and less resistors than other conventional techniques. Simulation verifies the proposed idea and design methodology.Keywords: power dividers, coupled lines, microstrip, 4G applications
Procedia PDF Downloads 4792943 A Semantic and Concise Structure to Represent Human Actions
Authors: Tobias Strübing, Fatemeh Ziaeetabar
Abstract:
Humans usually manipulate objects with their hands. To represent these actions in a simple and understandable way, we need to use a semantic framework. For this purpose, the Semantic Event Chain (SEC) method has already been presented which is done by consideration of touching and non-touching relations between manipulated objects in a scene. This method was improved by a computational model, the so-called enriched Semantic Event Chain (eSEC), which incorporates the information of static (e.g. top, bottom) and dynamic spatial relations (e.g. moving apart, getting closer) between objects in an action scene. This leads to a better action prediction as well as the ability to distinguish between more actions. Each eSEC manipulation descriptor is a huge matrix with thirty rows and a massive set of the spatial relations between each pair of manipulated objects. The current eSEC framework has so far only been used in the category of manipulation actions, which eventually involve two hands. Here, we would like to extend this approach to a whole body action descriptor and make a conjoint activity representation structure. For this purpose, we need to do a statistical analysis to modify the current eSEC by summarizing while preserving its features, and introduce a new version called Enhanced eSEC or (e2SEC). This summarization can be done from two points of the view: 1) reducing the number of rows in an eSEC matrix, 2) shrinking the set of possible semantic spatial relations. To achieve these, we computed the importance of each matrix row in an statistical way, to see if it is possible to remove a particular one while all manipulations are still distinguishable from each other. On the other hand, we examined which semantic spatial relations can be merged without compromising the unity of the predefined manipulation actions. Therefore by performing the above analyses, we made the new e2SEC framework which has 20% fewer rows, 16.7% less static spatial and 11.1% less dynamic spatial relations. This simplification, while preserving the salient features of a semantic structure in representing actions, has a tremendous impact on the recognition and prediction of complex actions, as well as the interactions between humans and robots. It also creates a comprehensive platform to integrate with the body limbs descriptors and dramatically increases system performance, especially in complex real time applications such as human-robot interaction prediction.Keywords: enriched semantic event chain, semantic action representation, spatial relations, statistical analysis
Procedia PDF Downloads 1282942 Artificial Intelligence and Development: The Missing Link
Authors: Driss Kettani
Abstract:
ICT4D actors are naturally attempted to include AI in the range of enabling technologies and tools that could support and boost the Development process, and to refer to these as AI4D. But, doing so, assumes that AI complies with the very specific features of ICT4D context, including, among others, affordability, relevance, openness, and ownership. Clearly, none of these is fulfilled, and the enthusiastic posture that AI4D is a natural part of ICT4D is not grounded and, to certain extent, does not serve the purpose of Technology for Development at all. In the context of Development, it is important to emphasize and prioritize ICT4D, in the national digital transformation strategies, instead of borrowing "trendy" waves of the IT Industry that are motivated by business considerations, with no specific care/consideration to Development.Keywords: AI, ICT4D, technology for development, position paper
Procedia PDF Downloads 972941 NanoFrazor Lithography for advanced 2D and 3D Nanodevices
Authors: Zhengming Wu
Abstract:
NanoFrazor lithography systems were developed as a first true alternative or extension to standard mask-less nanolithography methods like electron beam lithography (EBL). In contrast to EBL they are based on thermal scanning probe lithography (t-SPL). Here a heatable ultra-sharp probe tip with an apex of a few nm is used for patterning and simultaneously inspecting complex nanostructures. The heat impact from the probe on a thermal responsive resist generates those high-resolution nanostructures. The patterning depth of each individual pixel can be controlled with better than 1 nm precision using an integrated in-situ metrology method. Furthermore, the inherent imaging capability of the Nanofrazor technology allows for markerless overlay, which has been achieved with sub-5 nm accuracy as well as it supports stitching layout sections together with < 10 nm error. Pattern transfer from such resist features below 10 nm resolution were demonstrated. The technology has proven its value as an enabler of new kinds of ultra-high resolution nanodevices as well as for improving the performance of existing device concepts. The application range for this new nanolithography technique is very broad spanning from ultra-high resolution 2D and 3D patterning to chemical and physical modification of matter at the nanoscale. Nanometer-precise markerless overlay and non-invasiveness to sensitive materials are among the key strengths of the technology. However, while patterning at below 10 nm resolution is achieved, significantly increasing the patterning speed at the expense of resolution is not feasible by using the heated tip alone. Towards this end, an integrated laser write head for direct laser sublimation (DLS) of the thermal resist has been introduced for significantly faster patterning of micrometer to millimeter-scale features. Remarkably, the areas patterned by the tip and the laser are seamlessly stitched together and both processes work on the very same resist material enabling a true mix-and-match process with no developing or any other processing steps in between. The presentation will include examples for (i) high-quality metal contacting of 2D materials, (ii) tuning photonic molecules, (iii) generating nanofluidic devices and (iv) generating spintronic circuits. Some of these applications have been enabled only due to the various unique capabilities of NanoFrazor lithography like the absence of damage from a charged particle beam.Keywords: nanofabrication, grayscale lithography, 2D materials device, nano-optics, photonics, spintronic circuits
Procedia PDF Downloads 742940 Estimating Algae Concentration Based on Deep Learning from Satellite Observation in Korea
Authors: Heewon Jeong, Seongpyo Kim, Joon Ha Kim
Abstract:
Over the last few tens of years, the coastal regions of Korea have experienced red tide algal blooms, which are harmful and toxic to both humans and marine organisms due to their potential threat. It was accelerated owing to eutrophication by human activities, certain oceanic processes, and climate change. Previous studies have tried to monitoring and predicting the algae concentration of the ocean with the bio-optical algorithms applied to color images of the satellite. However, the accurate estimation of algal blooms remains problems to challenges because of the complexity of coastal waters. Therefore, this study suggests a new method to identify the concentration of red tide algal bloom from images of geostationary ocean color imager (GOCI) which are representing the water environment of the sea in Korea. The method employed GOCI images, which took the water leaving radiances centered at 443nm, 490nm and 660nm respectively, as well as observed weather data (i.e., humidity, temperature and atmospheric pressure) for the database to apply optical characteristics of algae and train deep learning algorithm. Convolution neural network (CNN) was used to extract the significant features from the images. And then artificial neural network (ANN) was used to estimate the concentration of algae from the extracted features. For training of the deep learning model, backpropagation learning strategy is developed. The established methods were tested and compared with the performances of GOCI data processing system (GDPS), which is based on standard image processing algorithms and optical algorithms. The model had better performance to estimate algae concentration than the GDPS which is impossible to estimate greater than 5mg/m³. Thus, deep learning model trained successfully to assess algae concentration in spite of the complexity of water environment. Furthermore, the results of this system and methodology can be used to improve the performances of remote sensing. Acknowledgement: This work was supported by the 'Climate Technology Development and Application' research project (#K07731) through a grant provided by GIST in 2017.Keywords: deep learning, algae concentration, remote sensing, satellite
Procedia PDF Downloads 1862939 Feature Selection Approach for the Classification of Hydraulic Leakages in Hydraulic Final Inspection using Machine Learning
Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter
Abstract:
Manufacturing companies are facing global competition and enormous cost pressure. The use of machine learning applications can help reduce production costs and create added value. Predictive quality enables the securing of product quality through data-supported predictions using machine learning models as a basis for decisions on test results. Furthermore, machine learning methods are able to process large amounts of data, deal with unfavourable row-column ratios and detect dependencies between the covariates and the given target as well as assess the multidimensional influence of all input variables on the target. Real production data are often subject to highly fluctuating boundary conditions and unbalanced data sets. Changes in production data manifest themselves in trends, systematic shifts, and seasonal effects. Thus, Machine learning applications require intensive pre-processing and feature selection. Data preprocessing includes rule-based data cleaning, the application of dimensionality reduction techniques, and the identification of comparable data subsets. Within the used real data set of Bosch hydraulic valves, the comparability of the same production conditions in the production of hydraulic valves within certain time periods can be identified by applying the concept drift method. Furthermore, a classification model is developed to evaluate the feature importance in different subsets within the identified time periods. By selecting comparable and stable features, the number of features used can be significantly reduced without a strong decrease in predictive power. The use of cross-process production data along the value chain of hydraulic valves is a promising approach to predict the quality characteristics of workpieces. In this research, the ada boosting classifier is used to predict the leakage of hydraulic valves based on geometric gauge blocks from machining, mating data from the assembly, and hydraulic measurement data from end-of-line testing. In addition, the most suitable methods are selected and accurate quality predictions are achieved.Keywords: classification, achine learning, predictive quality, feature selection
Procedia PDF Downloads 1642938 Great Art for Little Children - Games in School Education as Integration of Polish-Language, Eurhythmics, Artistic and Mathematical Subject Matter
Authors: Małgorzata Anna Karczmarzyk
Abstract:
Who is the contemporary child? What are his/her distinctive features making him/her different from earlier generations? And how to teach in the dissimilar social reality? These questions will constitute the key to my reflections on contemporary early school education. For, to my mind, games have become highly significant for the modern model of education. There arise publications and research employing games to increase competence both in business, tutoring, or coaching, as well as in academic education . Thanks to games students and subordinates can be taught such abilities as problem thinking, creativity, consistent fulfillment of goals, resourcefulness and skills of communication.Keywords: games, art, children, school education, integration
Procedia PDF Downloads 8582937 Brainwave Classification for Brain Balancing Index (BBI) via 3D EEG Model Using k-NN Technique
Authors: N. Fuad, M. N. Taib, R. Jailani, M. E. Marwan
Abstract:
In this paper, the comparison between k-Nearest Neighbor (kNN) algorithms for classifying the 3D EEG model in brain balancing is presented. The EEG signal recording was conducted on 51 healthy subjects. Development of 3D EEG models involves pre-processing of raw EEG signals and construction of spectrogram images. Then, maximum PSD values were extracted as features from the model. There are three indexes for the balanced brain; index 3, index 4 and index 5. There are significant different of the EEG signals due to the brain balancing index (BBI). Alpha-α (8–13 Hz) and beta-β (13–30 Hz) were used as input signals for the classification model. The k-NN classification result is 88.46% accuracy. These results proved that k-NN can be used in order to predict the brain balancing application.Keywords: power spectral density, 3D EEG model, brain balancing, kNN
Procedia PDF Downloads 4902936 Effects of Cellular Insulin Receptor Stimulators with Alkaline Water on Performance, Plasma Cholesterol, Glucose, Triglyceride Levels and Hatchability in Breeding Japanese Quail
Authors: Rabia Göçmen, Gülşah Kanbur, Sinan Sefa Parlat
Abstract:
Aim of this study is to determine the effects of cellular insulin receptor stimulators on performance, plasma glucose, high density lipoprotein (HDL), low density lipoprotein (LDL), total cholesterol, triglyceride, triiodothyronine (T3) and thyroxine (T4) hormone levels, and incubation features in the breeding Japanese quails (Coturnix japonica). In the study, a total of 84 breeding quails was used, 6 weeks’ age, 24 are male and 60, female. Rations used in experiment are 2900 kcal/kg metabolic energy and 20% crude protein. Water pH is calibrated to 7.45. Ration and water were administered ad-libitum to the animals. As metformin source, metformin-HCl was used and as chrome resource, chromium picolinate was used. Trial groups were formed as control group (basal ration), metformin group (basal ration, added metformin at the level of feed of 20 mg/kg), and chromium picolinate (basal ration, added feed of 1500 ppb Cr) group. When regarded to the results of performance at the end of experiment, it is seen that live weight gain, feed consumption, egg weight, feed conversion ratio (Feed consumption/ egg weight), and egg production were affected at the significant level (p < 0.05). When the results are evaluated in terms of incubation features, hatchability and hatchability of fertile egg ratio were not affected from the treatments. Fertility ratio was significantly affected by metformin and chromium picolinate treatments and fertility rose at the significant level compared to control group (p < 0.05). According to results of experiment, plasma glucose level was not affected by metformin and chromium picolinate treatments. Plasma, total cholesterol, HDL, LDL, and triglyceride levels were significantly affected from insulin receptor stimulators added to ration (p < 0.05). Hormone level of Plasma T3 and T4 were also affected at the significant level from insulin receptor stimulators added to ration (p < 0.05).Keywords: chromium picolinate, cholesterol, hormone, metformin, quail
Procedia PDF Downloads 222