Search results for: temporal convolutional net

Authors: Ibrahim Ozkan

Abstract:

In this study, a cross-layer design which combines adaptive modulation and coding (AMC) and hybrid automatic repeat request (HARQ) techniques for a cooperative wireless network is investigated analytically. Previous analyses of such systems in the literature are confined to the case where the fading channel is independent at each retransmission, which can be unrealistic unless the channel is varying very fast. On the other hand, temporal channel correlation can have a significant impact on the performance of HARQ systems. In this study, utilizing a Markov channel model which accounts for the temporal correlation, the performance of non-cooperative and cooperative networks are investigated in terms of packet loss rate and throughput metrics for Chase combining HARQ strategy.

Keywords: cooperative network, adaptive modulation and coding, hybrid ARQ, correlated fading

Procedia PDF Downloads 112

Authors: Shuen-Tai Wang, Fang-An Kuo, Chau-Yi Chou, Yu-Bin Fang

Abstract:

2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn  features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.

Keywords: artificial intelligence, machine learning, deep learning, convolutional neural networks

Procedia PDF Downloads 175

Authors: Deng Zengming, Wang Mingjiang

Abstract:

As 3D video is explored as a hot research topic in the last few decades, free-viewpoint TV (FTV) is no doubt a promising field for its better visual experience and incomparable interactivity. View synthesis is obviously a crucial technology for FTV; it enables to render images in unlimited numbers of virtual viewpoints with the information from limited numbers of reference view. In this paper, a novel hybrid synthesis framework is proposed and blending priority is explored. In contrast to the commonly used View Synthesis Reference Software (VSRS), the presented synthesis process is driven in consideration of the temporal correlation of image sequences. The temporal correlations will be exploited to produce fine synthesis results even near the foreground boundaries. As for the blending priority, this scheme proposed that one of the two reference views is selected to be the main reference view based on the distance between the reference views and virtual view, another view is chosen as the auxiliary viewpoint, just assist to fill the hole pixel with the help of background information. Significant improvement of the proposed approach over the state-of –the-art pixel-based virtual view synthesis method is presented, the results of the experiments show that subjective gains can be observed, and objective PSNR average gains range from 0.5 to 1.3 dB, while SSIM average gains range from 0.01 to 0.05.

Keywords: fusion method, Gaussian mixture model, hybrid framework, view synthesis

Procedia PDF Downloads 222

Authors: Lauren Schuldt Wilson

Abstract:

Felicia Hemans’ memorializing of the unwritten lives of women and the consequent allowance for marginalized voices to remember and be remembered has been considered by many critics in terms of ekphrasis and elegy, terms which privilege the question of whether Hemans’ poeticizing can represent lost voices of history or only her poetic expression. Amy Gates, Brian Elliott, and others point out Hemans’ acknowledgement of the self-projection necessary for imaginatively filling the absences of unrecorded histories. Yet, few have examined the complex temporal positioning Hemans inscribes in these moments of self-projection and imaginative historicizing. In poems like ‘The Image in Lava,’ Hemans maps not only a lost past, but also a lost potential future onto the image of a dead infant in its mother’s arms, the discovery and consideration of which moves the imagined viewer to recover and incorporate the ‘hope’ encapsulated in the figure of the infant into a reevaluation of national time embodied by the ‘relics / Left by the pomps of old.’ By examining Hemans’ acknowledgement and response to Percy Bysshe Shelley’s ‘Ozymandias,’ this essay explores how Hemans’ depictions of imaginative historicizing open new horizons of possibility and reevaluate temporal value structures by imagining previously undiscovered or unexplored potentialities of the past. Where Shelley’s poem mocks the futility of national power and time, this essay outlines Hemans’ suggestion of alternative threads of identity and temporal meaning-making which, regardless of historical veracity, exist outside of and against the structures Shelley challenges. Counter to previous readings of Hemans’ poem as celebration of either recovered or poetically constructed maternal love, this essay argues that Hemans offers a meditation on sites of reproduction—both of personal reproductive futurity and of national reproduction of power. This meditation culminates in Hemans’ gesturing towards a method of historicism by which the imagined viewer reinvigorates the sterile, ‘shattered visage’ of national time by forming temporal identity through the imagining of trans-historical hope inscribed on the infant body of the universal, individual subject rather than the broken monument of the king.

Keywords: futurity, national temporalities, reproduction, revisionary histories

Procedia PDF Downloads 139

Authors: Alireza Javed, Keivan Jamshidi

Abstract:

Reactive amyloidosis is a condition that complicates a long list of chronic inflammation, chronic infectious, malignant, and hereditary disorders. In the present study the potential effects of two amyloidogenic substances: ie. AgNO3 and Freund's Adjuvant (AF) with that of vitamin free casein, on spatio-temporal pattern of experimental amyloidosis in mice, were compared. For this purpose, a total of 40 male Swees mice, obtained from Pasteur Institute Tehran, after being weighted were randomly divided into 4 groups including 2 treatments, 1 control (vitamin free casein) and 1 positive control (normal saline). At the end of 3rd, 5th and 7th weeks of experiment 3 mice were randomly selected and euthnised. Spleen sample of each animal obtained and preserved in 10% neutral buffer formalin. Sample were then processed through different stages of dehydration, clearing and impregnation and finally embedded in paraffin blocks. Sections of 5µm thickness then cut and stained by alkaline Congo red techniques. Spleen weights and the data obtained from the microscopic quantitative analysis did show no significant differences between groups A and B, A and C, and B and C. However, significant differences were observed between groups A and D, B and D, and C and D respectively. It is concluded that two compounds ie; AgNO3 and Freund's Adjuvant have the same potential, as does vitamin free casein have, in spatio – temporal pattern of experimental amyloidosis in mice.

Keywords: amyloidosis, mice, AgNO3, Freund's Adjuvant

Procedia PDF Downloads 346

Authors: Kwaku Damoah

Abstract:

This study presents a comprehensive data-driven analysis to understand the evolution of adverse events (AEs) in pharmacovigilance. Utilizing data from the FDA Adverse Event Reporting System (FAERS), we employed three analytical methods: rank-based, frequency-based, and percentage change analyses. These methods assessed temporal trends and patterns in AE reporting, focusing on various drug-active ingredients and patient demographics. Our findings reveal significant trends in AE occurrences, with both increasing and decreasing patterns from 2000 to 2023. This research highlights the importance of continuous monitoring and advanced analysis in pharmacovigilance, offering valuable insights for healthcare professionals and policymakers to enhance drug safety.

Keywords: event analysis, FDA adverse event reporting system, pharmacovigilance, temporal trend analysis

Procedia PDF Downloads 24

Authors: Reggie Chandra

Abstract:

Trafficaccidents and traffic signal optimization are correlated. However, 70-90% of the traffic signals across the USA are not synchronized. The reason behind that is insufficient resources to create and implement timing plans. In this work, we will discuss the use of a breakthrough Artificial Intelligence (AI) technology to optimize traffic flow and collect 24/7/365 accurate traffic data using a vehicle detection system. We will discuss what are recent advances in Artificial Intelligence technology, how does AI work in vehicles, pedestrians, and bike data collection, creating timing plans, and what is the best workflow for that. Apart from that, this paper will showcase how Artificial Intelligence makes signal timing affordable. We will introduce a technology that uses Convolutional Neural Networks (CNN) and deep learning algorithms to detect, collect data, develop timing plans and deploy them in the field. Convolutional Neural Networks are a class of deep learning networks inspired by the biological processes in the visual cortex. A neural net is modeled after the human brain. It consists of millions of densely connected processing nodes. It is a form of machine learning where the neural net learns to recognize vehicles through training - which is called Deep Learning. The well-trained algorithm overcomes most of the issues faced by other detection methods and provides nearly 100% traffic data accuracy. Through this continuous learning-based method, we can constantly update traffic patterns, generate an unlimited number of timing plans and thus improve vehicle flow. Convolutional Neural Networks not only outperform other detection algorithms but also, in cases such as classifying objects into fine-grained categories, outperform humans. Safety is of primary importance to traffic professionals, but they don't have the studies or data to support their decisions. Currently, one-third of transportation agencies do not collect pedestrian and bike data. We will discuss how the use of Artificial Intelligence for data collection can help reduce pedestrian fatalities and enhance the safety of all vulnerable road users. Moreover, it provides traffic engineers with tools that allow them to unleash their potential, instead of dealing with constant complaints, a snapshot of limited handpicked data, dealing with multiple systems requiring additional work for adaptation. The methodologies used and proposed in the research contain a camera model identification method based on deep Convolutional Neural Networks. The proposed application was evaluated on our data sets acquired through a variety of daily real-world road conditions and compared with the performance of the commonly used methods requiring data collection by counting, evaluating, and adapting it, and running it through well-established algorithms, and then deploying it to the field. This work explores themes such as how technologies powered by Artificial Intelligence can benefit your community and how to translate the complex and often overwhelming benefits into a language accessible to elected officials, community leaders, and the public. Exploring such topics empowers citizens with insider knowledge about the potential of better traffic technology to save lives and improve communities. The synergies that Artificial Intelligence brings to traffic signal control and data collection are unsurpassed.

Keywords: artificial intelligence, convolutional neural networks, data collection, signal control, traffic signal

Procedia PDF Downloads 122

Authors: Lopita Pal, Suresh V. Madha

Abstract:

Wetlands are areas of marsh, fen, peat land or water, whether natural or artificial, permanent or temporary, with water that is static or flowing, fresh, brackish or salt, including areas of marine water the depth of which at low tide does not exceed six metres. The rapidly expanding human population, large scale changes in land use/land cover, burgeoning development projects and improper use of watersheds all has caused a substantial decline of wetland resources in the world. Major degradations have been impacted from agricultural, industrial and urban developments leading to various types of pollutions and hydrological perturbations. Regular fishing activities and unsustainable grazing of animals are degrading the wetlands in a slow pace. The paper focuses on the spatio-temporal change detection of the area of the water body and the main cause of this depletion. The total area under study (22°19’87’’ N, 88°20’23’’ E) is a wetland region in West Bengal of 213 sq.km. The procedure used is the Normalized Difference Water Index (NDWI) from multi-spectral imagery and Landsat to detect the presence of surface water, and the datasets have been compared of the years 2016, 2006 and 1996. The result shows a sharp decline in the area of water body due to a rapid increase in the agricultural practices and the growing urbanization.

Keywords: spatio-temporal change, NDWI, urbanization, wetland

Procedia PDF Downloads 259

Authors: Qian Liu, Steve Furber

Abstract:

To explore how the brain may recognize objects in its general,accurate and energy-efficient manner, this paper proposes the use of a neuromorphic hardware system formed from a Dynamic Video Sensor~(DVS) silicon retina in concert with the SpiNNaker real-time Spiking Neural Network~(SNN) simulator. As a first step in the exploration on this platform a recognition system for dynamic hand postures is developed, enabling the study of the methods used in the visual pathways of the brain. Inspired by the behaviours of the primary visual cortex, Convolutional Neural Networks (CNNs) are modeled using both linear perceptrons and spiking Leaky Integrate-and-Fire (LIF) neurons. In this study's largest configuration using these approaches, a network of 74,210 neurons and 15,216,512 synapses is created and operated in real-time using 290 SpiNNaker processor cores in parallel and with 93.0% accuracy. A smaller network using only 1/10th of the resources is also created, again operating in real-time, and it is able to recognize the postures with an accuracy of around 86.4% -only 6.6% lower than the much larger system. The recognition rate of the smaller network developed on this neuromorphic system is sufficient for a successful hand posture recognition system, and demonstrates a much-improved cost to performance trade-off in its approach.

Keywords: spiking neural network (SNN), convolutional neural network (CNN), posture recognition, neuromorphic system

Procedia PDF Downloads 441

Authors: Bipasha Sen, Aditya Agarwal

Abstract:

Multilingual automatic speech recognition (ASR) system is a single entity capable of transcribing multiple languages sharing a common phone space. Performance of such a system is highly dependent on the compatibility of the languages. State of the art speech recognition systems are built using sequential architectures based on recurrent neural networks (RNN) limiting the computational parallelization in training. This poses a significant challenge in terms of time taken to bootstrap and validate the compatibility of multiple languages for building a robust multilingual system. Complex architectural choices based on self-attention networks are made to improve the parallelization thereby reducing the training time. In this work, we propose Reed, a simple system based on 1D convolutions which uses very short context to improve the training time. To improve the performance of our system, we use raw time-domain speech signals directly as input. This enables the convolutional layers to learn feature representations rather than relying on handcrafted features such as MFCC. We report improvement on training and inference times by atleast a factor of 4x and 7.4x respectively with comparable WERs against standard RNN based baseline systems on SpeechOcean's multilingual low resource dataset.

Keywords: convolutional neural networks, language compatibility, low resource languages, multilingual automatic speech recognition

Procedia PDF Downloads 93

Authors: Eric Jacob Bacon, Chaoyang Jin, Dianning He, Shuaishuai Hu, Lanbo Wang, Han Li, Shouliang Qi

Abstract:

Objective: Refractory epilepsy is a complicated type of epilepsy that can be difficult to diagnose. Recent technological advancements have made resting-state functional magnetic resonance (rsfMRI) a vital technique for studying brain activity. However, there is still much to learn about rsfMRI. Investigating rsfMRI connectivity may aid in the detection of abnormal activities. In this paper, we propose studying the functional connectivity of rsfMRI candidates to diagnose epilepsy. Methods: 45 rsfMRI candidates, comprising 26 with refractory epilepsy and 19 healthy controls, were enrolled in this study. A data-driven approach known as independent component analysis (ICA) was used to achieve our goal. First, rsfMRI data from both patients and healthy controls were analyzed using group ICA. The components that were obtained were then spatially sorted to find and select meaningful ones. A two-sample t-test was also used to identify abnormal networks in patients and healthy controls. Finally, based on the fractional amplitude of low-frequency fluctuations (fALFF), a chi-square statistic test was used to distinguish the network properties of the patient and healthy control groups. Results: The two-sample t-test analysis yielded abnormal in the default mode network, including the left superior temporal lobe and the left supramarginal. The right precuneus was found to be abnormal in the dorsal attention network. In addition, the frontal cortex showed an abnormal cluster in the medial temporal gyrus. In contrast, the temporal cortex showed an abnormal cluster in the right middle temporal gyrus and the right fronto-operculum gyrus. Finally, the chi-square statistic test was significant, producing a p-value of 0.001 for the analysis. Conclusion: This study offers evidence that investigating rsfMRI connectivity provides an excellent diagnosis option for refractory epilepsy.

Keywords: ICA, RSN, refractory epilepsy, rsfMRI

Procedia PDF Downloads 42

Authors: Sumiko Anno, Keiji Imaoka, Takeo Tadono, Tamotsu Igarashi, Subramaniam Sivaganesh, Selvam Kannathasan, Vaithehi Kumaran, Sinnathamby Noble Surendran

Abstract:

Dengue outbreaks are affected by biological, ecological, socio-economic and demographic factors that vary over time and space. These factors have been examined separately and still require systematic clarification. The present study aimed to investigate the spatial-temporal clustering relationships between these factors and dengue outbreaks in the northern region of Sri Lanka. Remote sensing (RS) data gathered from a plurality of satellites were used to develop an index comprising rainfall, humidity and temperature data. RS data gathered by ALOS/AVNIR-2 were used to detect urbanization, and a digital land cover map was used to extract land cover information. Other data on relevant factors and dengue outbreaks were collected through institutions and extant databases. The analyzed RS data and databases were integrated into geographic information systems, enabling temporal analysis, spatial statistical analysis and space-time clustering analysis. Our present results showed that increases in the number of the combination of ecological factor and socio-economic and demographic factors with above the average or the presence contribute to significantly high rates of space-time dengue clusters.

Keywords: ALOS/AVNIR-2, dengue, space-time clustering analysis, Sri Lanka

Procedia PDF Downloads 448

Authors: Apostolos Lagarias, Anastasia Stratigea

Abstract:

Coastal urbanization is heavily affecting the Mediterranean, taking the form of linear urban sprawl along the coastal zone. This process is posing extreme pressure on ecosystems, leading to an unsustainable model of growth. The aim of this research is to analyze coastal urbanization patterns in the Mediterranean using High-resolution multi-temporal data provided by the Global Human Settlement Layer (GHSL) database. Methodology involves the estimation of a set of spatial metrics characterizing the density, aggregation/clustering and dispersion of built-up areas. As case study areas, the Spanish Coast and the Adriatic Italian Coast are examined. Coastalization profiles are examined and selected sub-areas massively affected by tourism development and suburbanization trends (Costa Blanca/Murcia, Costa del Sol, Puglia, Emilia-Romagna Coast) are analyzed and compared. Results show that there are considerable differences between the Spanish and the Italian typologies of spatial development, related to the land use structure and planning policies applied in each case. Monitoring and analyzing spatial patterns could inform integrated Mediterranean strategies for coastal areas and redirect spatial/environmental policies towards a more sustainable model of growth

Keywords: coastalization, Mediterranean, multi-temporal, urban sprawl, spatial metrics

Procedia PDF Downloads 106

Authors: Mirvat Shamseddine, Issam Lakkis

Abstract:

We present an efficient, three-dimensional parallel multi-scale Direct Simulation Monte Carlo (DSMC) algorithm for the simulation of unsteady rarefied gas flows in micro/nanosystems. The algorithm employs a novel spatiotemporal adaptivity scheme. The scheme performs a fully dynamic multi-level grid adaption based on the gradients of flow macro-parameters and an automatic temporal adaptation. The computational domain consists of a hierarchical octree-based Cartesian grid representation of the flow domain and a triangular mesh for the solid object surfaces. The hybrid mesh, combined with the spatiotemporal adaptivity scheme, allows for increased flexibility and efficient data management, rendering the framework suitable for efficient particle-tracing and dynamic grid refinement and coarsening. The parallel algorithm is optimized to run DSMC simulations of strongly unsteady, non-equilibrium flows over multiple cores. The presented method is validated by comparing with benchmark studies and then employed to improve the design of micro-scale hotwire thermal sensors in rarefied gas flows.

Keywords: DSMC, oct-tree hierarchical grid, ray tracing, spatial-temporal adaptivity scheme, unsteady rarefied gas flows

Procedia PDF Downloads 279

Authors: Mahdi Bazarganigilani

Abstract:

Computer-aided diagnosis (CAD) systems can play crucial roles in diagnosing crucial diseases such as breast cancer at the earliest. In this paper, a CAD system for the diagnosis of breast cancer was introduced and evaluated. This CAD system was developed by using spatio-temporal analysis of data on a set of consecutive thermographic images by employing wavelet transformation. By using this analysis, a very accurate machine learning model using random forest was obtained. The final results showed a promising accuracy of 91% in terms of the F1 measure indicator among 200 patients' sample data. The CAD system was further extended to obtain a detailed analysis of the effect of smaller sub-areas of each breast on the occurrence of cancer.

Keywords: computer-aided diagnosis systems, thermographic analysis, spatio-temporal analysis, image processing, machine learning

Procedia PDF Downloads 180

Authors: Jia Li, Xing Wei, Yuchen Hong, Yang Lu

Abstract:

Detecting vehicle behavior has always been the focus of intelligent transportation, but with the explosive growth of the number of vehicles and the complexity of the road environment, the vehicle behavior videos captured by traditional surveillance have been unable to satisfy the study of vehicle behavior. The traditional method of manually labeling vehicle behavior is too time-consuming and labor-intensive, but the existing object detection and tracking algorithms have poor practicability and low behavioral location detection rate. This paper proposes a vehicle behavior detection algorithm based on the dual-stream convolution network and the multi-dimensional video dynamic detection network. In the videos, the straight-line behavior of the vehicle will default to the background behavior. The Changing lanes, turning and turning around are set as target behaviors. The purpose of this model is to automatically mark the target behavior of the vehicle from the untrimmed videos. First, the target behavior proposals in the long video are extracted through the dual-stream convolution network. The model uses a dual-stream convolutional network to generate a one-dimensional action score waveform, and then extract segments with scores above a given threshold M into preliminary vehicle behavior proposals. Second, the preliminary proposals are pruned and identified using the multi-dimensional video dynamic detection network. Referring to the hierarchical reinforcement learning, the multi-dimensional network includes a Timer module and a Spacer module, where the Timer module mines time information in the video stream and the Spacer module extracts spatial information in the video frame. The Timer and Spacer module are implemented by Long Short-Term Memory (LSTM) and start from an all-zero hidden state. The Timer module uses the Transformer mechanism to extract timing information from the video stream and extract features by linear mapping and other methods. Finally, the model fuses time information and spatial information and obtains the location and category of the behavior through the softmax layer. This paper uses recall and precision to measure the performance of the model. Extensive experiments show that based on the dataset of this paper, the proposed model has obvious advantages compared with the existing state-of-the-art behavior detection algorithms. When the Time Intersection over Union (TIoU) threshold is 0.5, the Average-Precision (MP) reaches 36.3% (the MP of baselines is 21.5%). In summary, this paper proposes a vehicle behavior detection model based on multi-dimensional dynamic detection network. This paper introduces spatial information and temporal information to extract vehicle behaviors in long videos. Experiments show that the proposed algorithm is advanced and accurate in-vehicle timing behavior detection. In the future, the focus will be on simultaneously detecting the timing behavior of multiple vehicles in complex traffic scenes (such as a busy street) while ensuring accuracy.

Keywords: vehicle behavior detection, convolutional neural network, long short-term memory, deep learning

Procedia PDF Downloads 95

Authors: Geng-Gui Wang, Chia-Hao Chang, Jee-Cheng Wu

Abstract:

A shoreline is a line where a body of water and the shore meet. It provides economic and social security to coastal habitations. However, shorelines face multiple threats due to both natural processes and man-made effects because of disasters, rapid urbanization, industrialization, and sand deposition and erosion, etc. In this study, we analyzed multi-temporal satellite images of the Yilan coast, Taiwan from 1978 to 2016, using the United States Geological Survey (USGS) Digital Shoreline Analysis System (DSAS), weather information (as rainfall records and typhoon routes), and man-made construction project data to explore the causes of shoreline changes. The results showed that the shoreline at Yilan coast is greatly influenced by typhoons and anthropogenic interventions.

Keywords: shoreline change, multi-temporal satellite, digital shoreline analysis system, DSAS, Yi-Lan coast

Procedia PDF Downloads 134

Authors: Evan Lowhorn, Rocio Alba-Flores

Abstract:

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

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

Procedia PDF Downloads 183

Authors: Gabriella Notarianni Burk

Abstract:

The present study investigates the Aspect Hypothesis (AH) in Italian child language in the production of frog story narratives from the CHILDES database. The AH is based on the assumption that children initially encode aspectual and lexical distinctions rather than temporal relations. Children from a variety of first languages have been shown to mark past initially with achievements and accomplishments (telic predicates) and in later stages with states and activities (atelic predicates). Aspectual distinctions in Romance languages are obligatorily and overtly encoded in the inflectional morphology. In Italian the perfective viewpoint is realized by the passato prossimo, which expresses a temporal and aspectual meaning of pastness and perfectivity, whereas the imperfective viewpoint in the past tense is realized by the imperfetto. The aim of this study is to assess the role of lexical aspect in the acquisition of tense and aspect morphology and to understand if Italian children’s mapping of aspectual and temporal distinctions follows consistent developmental patterns across languages. The research methodology aligns with the cross-linguistic designs, tasks and coding procedures previously developed in the frog story literature. Results from two-factor ANOVA show that Italian children (age range: 4-6) exhibited a statistically significant distinction between foregrounded perfective and backgrounded imperfective marking. However, a closer examination of the sixty narratives reveals an idiosyncratic production pattern for Italian children, whereby the marking of imperfetto deviates from the tenets of AH and emerges as deictic tense to entail completed and bounded events in foreground clauses. Instances of ‘perfective’ uses of imperfetto were predominantly found in the four-year old narratives (25%). Furthermore, the analysis of the perfective marking suggests that morphological articulation and diatopic variation may influence the child production of formal linguistic devices in discourse.

Keywords: actionality, aspect, grounding, temporal reference

Procedia PDF Downloads 219

Authors: Tesfaye Mengistu

Abstract:

Power cables play a crucial role in the transmission and distribution of electrical energy. As the electricity generation, transmission, distribution, and storage systems become smarter, there is a growing emphasis on incorporating intelligent approaches to ensure the reliability of power cables. Various types of electrical cables are employed for transmitting and distributing electrical energy, with cross-linked polyethylene (XLPE) cables being widely utilized due to their exceptional electrical and mechanical properties. However, insulation defects can occur in XLPE cables due to subpar manufacturing techniques during production and cable joint installation. To address this issue, experts have proposed different methods for monitoring XLPE cables. Some suggest the use of interdigital capacitive (IDC) technology for online monitoring, while others propose employing continuous wave (CW) terahertz (THz) imaging systems to detect internal defects in XLPE plates used for power cable insulation. In this study, we have developed models that employ a custom dataset collected locally to classify the physical safety status of individual power cables. Our models aim to replace physical inspections with computer vision and image processing techniques to classify defective power cables from non-defective ones. The implementation of our project utilized the Python programming language along with the TensorFlow package and a convolutional neural network (CNN). The CNN-based algorithm was specifically chosen for power cable defect classification. The results of our project demonstrate the effectiveness of CNNs in accurately classifying power cable defects. We recommend the utilization of similar or additional datasets to further enhance and refine our models. Additionally, we believe that our models could be used to develop methodologies for detecting power cable defects from live video feeds. We firmly believe that our work makes a significant contribution to the field of power cable inspection and maintenance. Our models offer a more efficient and cost-effective approach to detecting power cable defects, thereby improving the reliability and safety of power grids.

Keywords: artificial intelligence, computer vision, defect detection, convolutional neural net

Procedia PDF Downloads 71

Authors: Mads Schultz, Galice Hoarau, Marvin Choquet

Abstract:

Members of the genus Calanus are key species in the North Atlantic and Arctic marine ecosystems due to their vast abundance and their ability to accumulate high amounts of lipid. As a link between primary producers and higher trophic levels, the temporal presence of each Calanus species is important in a time of changing communities and northward distribution shifts. This study focused on the temporal niches of the sympatric species Calanus helgolandicus, Calanus finmarchicus, Calanus glacialis, and Calanus hyperboreus in Skjerstad fjord, a Norwegian fjord (67˚14’N, 14 ˚44’E). Three depth intervals were sampled monthly over a year, targeting copepodite stages of the genus Calanus. Species determination was carried out genetically using insertion/deletion markers. In addition, during the reproductive season (Jan-May), weekly samples of the upper 50 meters of the water column targeting nauplii and 5 depth intervals targeting copepodites were collected. Nauplii samples were sorted into two groups (NI-NIII and NIV-NVI), and species were genetically identified. Specimens from stage CIV to adults from each depth interval of copepodite sampling were photographed in order to generate a supporting timeline of visual traits, including gonad maturation stage, presence of stomach content, and total lipid content. The most abundant species were Calanus finmarchicus and Calanus glacialis, followed by Calanus hyperboreus. These species were present in the water column throughout the year, whereas Calanus helgolandicus, the least abundant species, was only present during the summer and autumn period. Each species showed distinct temporal niches, with Calanus finmarchicus occupying the upper 50 meters longer than any of the other species. Calanus hyperboreus dominates in abundance early in the spring but are outnumbered by Calanus glacialis and Calanus finmarchicus after spring bloom sets in. In Skjerstad fjord, Calanus hyperboreus is a clear capital breeder with a long period of nauplii presence before the spring bloom. Calanus glacialis and Calanus finmarchicus both utilize income breeding, with Calanus glacialis developing to the larger nauplii stages quicker than Calanus finmarchicus, but also having a shorter reproduction period. Indeed, the “traditional Arctic” species Calanus hyperboreus and Calanus glacialis appear to end their reproduction period earlier than the North Atlantic Calanus finmarchicus.

Keywords: calanus, depth distribution, reproduction, stage composition, temporal niches

Procedia PDF Downloads 124

Authors: Leah Lee

Abstract:

This paper examines the correlation between deep learning models and emotions with noises to see whether or not noises mask emotions. The deep learning models used are plain convolutional neural networks (CNN), auto-encoder, long short-term memory (LSTM), and Visual Geometry Group-16 (VGG-16). Emotion datasets used are Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Toronto Emotional Speech Set (TESS), and Surrey Audio-Visual Expressed Emotion (SAVEE). To make it four times bigger, audio set files, stretch, and pitch augmentations are utilized. From the augmented datasets, five different features are extracted for inputs of the models. There are eight different emotions to be classified. Noise variations are white noise, dog barking, and cough sounds. The variation in the signal-to-noise ratio (SNR) is 0, 20, and 40. In summation, per a deep learning model, nine different sets with noise and SNR variations and just augmented audio files without any noises will be used in the experiment. To compare the results of the deep learning models, the accuracy and receiver operating characteristic (ROC) are checked.

Keywords: auto-encoder, convolutional neural networks, long short-term memory, speech emotion recognition, visual geometry group-16

Procedia PDF Downloads 43

Authors: Zeina Merabi, Arij Dao

Abstract:

The temporal order of information processing in the brain is an important code in many acoustic signals, including speech, music, and animal vocalizations. Despite its significance, surprisingly little is known about its underlying cellular mechanisms and network manifestations. In the songbird telencephalic nucleus HVC, a subset of neurons shows temporal combination sensitivity (TCS). These neurons show a high temporal specificity, responding differently to distinct patterns of spectral elements and their combinations. HVC neuron types include basal-ganglia-projecting HVCX, forebrain-projecting HVCRA, and interneurons (HVC¬INT), each exhibiting distinct cellular, electrophysiological and functional properties. In this work, we develop conductance-based neural network models connecting the different classes of HVC neurons via different wiring scenarios, aiming to explore possible neural mechanisms that orchestrate the combination sensitivity property exhibited by HVCX, as well as replicating in vivo firing patterns observed when TCS neurons are presented with various auditory stimuli. The ionic and synaptic currents for each class of neurons that are presented in our networks and are based on pharmacological studies, rendering our networks biologically plausible. We present for the first time several realistic scenarios in which the different types of HVC neurons can interact to produce this behavior. The different networks highlight neural mechanisms that could potentially help to explain some aspects of combination sensitivity, including 1) interplay between inhibitory interneurons’ activity and the post inhibitory firing of the HVCX neurons enabled by T-type Ca2+ and H currents, 2) temporal summation of synaptic inputs at the TCS site of opposing signals that are time-and frequency- dependent, and 3) reciprocal inhibitory and excitatory loops as a potent mechanism to encode information over many milliseconds. The result is a plausible network model characterizing auditory processing in HVC. Our next step is to test the predictions of the model.

Keywords: combination sensitivity, songbirds, neural networks, spatiotemporal integration

Procedia PDF Downloads 38

Authors: Belinda Crissman

Abstract:

Serious mental disorder is greatly overrepresented in prisoners compared to the general community, with consequences for prison management, recidivism and the prisoners themselves. Incarcerated individuals with psychotic disorders experience insufficient detection and treatment and higher rates of suicide in custody. However direct evidence to explain the overrepresentation of individuals with psychosis in prisons is sparse. The current study aimed to use a life course criminology perspective to answer two key questions: 1) What is the temporal relationship between psychosis and offending (does first mental health contact precede first recorded offence, or does the offending precede the mental health diagnosis)? 2) Are there key temporal points or system contacts prior to incarceration that could be identified as opportunities for early intervention? Data from the innovative Queensland Linkage project was used to link individuals with their corrections, health and relevant social service systems to answer these questions.

Keywords: mental disorder, crime, life course criminology, prevention

Procedia PDF Downloads 108

Authors: Sikiru Ademola Adewale, Joe Thomas, Bolanle Hafiz Matti, Tosin Ige

Abstract:

This project demonstrates the implementation and use of an encoder-decoder model to perform a many-to-many mapping of video data to text captions. The many-to-many mapping occurs via an input temporal sequence of video frames to an output sequence of words to form a caption sentence. Data preprocessing, model construction, and model training are discussed. Caption correctness is evaluated using 2-gram BLEU scores across the different splits of the dataset. Specific examples of output captions were shown to demonstrate model generality over the video temporal dimension. Predicted captions were shown to generalize over video action, even in instances where the video scene changed dramatically. Model architecture changes are discussed to improve sentence grammar and correctness.

Keywords: decoder, encoder, many-to-many mapping, video captioning, 2-gram BLEU

Procedia PDF Downloads 68

Authors: Chien-kuo Chang, Bo-wei Wu, Yi-yun Tang, Min-chiu Wu

Abstract:

This paper proposes a power equipment diagnosis system based on partial discharge (PD), which is characterized by increasing the readability of experimental data and the convenience of operation. This system integrates a variety of analysis programs of different data formats and different programming languages and then establishes a set of interfaces that can follow and expand the structure, which is also helpful for subsequent maintenance and innovation. This study shows a case of using the developed Convolutional Neural Networks (CNN) to integrate with this system, using the designed model architecture to simplify the complex training process. It is expected that the simplified training process can be used to establish an adaptive deep learning experimental structure. By selecting different test data for repeated training, the accuracy of the identification system can be enhanced. On this platform, the measurement status and partial discharge pattern of each equipment can be checked in real time, and the function of real-time identification can be set, and various training models can be used to carry out real-time partial discharge insulation defect identification and insulation state diagnosis. When the electric power equipment entering the dangerous period, replace equipment early to avoid unexpected electrical accidents.

Keywords: partial discharge, convolutional neural network, partial discharge analysis platform, adaptive deep learning

Procedia PDF Downloads 49

Authors: Jui-Chien Hsieh

Abstract:

Background:12-lead electrocardiography(ECG) is one of frequently-used tools to detect atrial fibrillation (AF), which might degenerate into life-threaten stroke, in clinical Practice. Based on this study, the AF detection by the clinically-used 12-lead ECG device has only 0.73~0.77 positive predictive value (ppv). Objective: It is on great demand to develop a new algorithm to improve the precision of AF detection using 12-lead ECG. Due to the progress on artificial intelligence (AI), we develop an ECG deep model that has the ability to recognize AF patterns and reduce false-positive errors. Methods: In this study, (1) 570-sample 12-lead ECG reports whose computer interpretation by the ECG device was AF were collected as the training dataset. The ECG reports were interpreted by 2 senior cardiologists, and confirmed that the precision of AF detection by the ECG device is 0.73.; (2) 88 12-lead ECG reports whose computer interpretation generated by the ECG device was AF were used as test dataset. Cardiologist confirmed that 68 cases of 88 reports were AF, and others were not AF. The precision of AF detection by ECG device is about 0.77; (3) A parallel 4-layer 1 dimensional convolutional neural network (CNN) was developed to identify AF based on limb-lead ECGs and chest-lead ECGs. Results: The results indicated that this model has better performance on AF detection than traditional computer interpretation of the ECG device in 88 test samples with 0.94 ppv, 0.98 sensitivity, 0.80 specificity. Conclusions: As compared to the clinical ECG device, this AI ECG model promotes the precision of AF detection from 0.77 to 0.94, and can generate impacts on clinical applications.

Keywords: 12-lead ECG, atrial fibrillation, deep learning, convolutional neural network

Procedia PDF Downloads 90

Authors: Md. Jahoor Alam

Abstract:

Recent studies suggest that Glucose controls several lifesaving pathways. Glucose molecule is reported to be responsible for the production of ROS (reactive oxygen species). In the present work, a p53-MDM2-Glucose model is developed in order to study spatiotemporal properties of the p53 pathway. The systematic model is mathematically described. The model is numerically simulated using high computational facility. It is observed that the variation in glucose concentration level triggers the system at different states, namely, oscillation death (stabilized), sustain and damped oscillations which correspond to various cellular states. The transition of these states induced by glucose is phase transition-like behaviour. Further, the amplitude of p53 dynamics with the variation of glucose concentration level follows power law behaviour, As(k) ~ kϒ, where, ϒ is a constant. Further Stochastic approach is needed for understanding of realistic behaviour of the model. The present model predicts the variation of p53 states under the influence of glucose molecule which is also supported by experimental facts reported by various research articles.

Keywords: oscillation, temporal behavior, p53, glucose

Procedia PDF Downloads 271

Authors: Hui Luo, Zhenhong Li, Zhen Dong

Abstract:

The analysis of multi-temporal InSAR (MTInSAR) such as persistent scatterer (PS) and small baseline subset (SBAS) techniques usually relies on temporal/spatial phase unwrapping (PU). Unfortunately, it always fails to unwrap the phase for two reasons: 1) spatial phase jump between adjacent pixels larger than π, such as layover and high discontinuous terrain; 2) temporal phase discontinuities such as time varied atmospheric delay. To overcome these limitations, a least-square based PU method is introduced in this paper, which incorporates baseline-combination interferograms and adjacent phase gradient network. Firstly, permanent scatterers (PS) are selected for study. Starting with the linear baseline-combination method, we obtain equivalent 'small baseline inteferograms' to limit the spatial phase difference. Then, phase different has been conducted between connected PSs (connected by a specific networking rule) to suppress the spatial correlated phase errors such as atmospheric artifact. After that, interval phase difference along arcs can be computed by least square method and followed by an outlier detector to remove the arcs with phase ambiguities. Then, the unwrapped phase can be obtained by spatial integration. The proposed method is tested on real data of TerraSAR-X, and the results are also compared with the ones obtained by StaMPS(a software package with 3D PU capabilities). By comparison, it shows that the proposed method can successfully unwrap the interferograms in urban areas even when high discontinuities exist, while StaMPS fails. At last, precise DEM errors can be got according to the unwrapped interferograms.

Keywords: phase unwrapping, time series, InSAR, urban areas

Procedia PDF Downloads 123

Authors: Yijun Shao, Yan Cheng, Rashmee U. Shah, Charlene R. Weir, Bruce E. Bray, Qing Zeng-Treitler

Abstract:

Deep neural network (DNN) models are being explored in the clinical domain, following the recent success in other domains such as image recognition. For clinical adoption, outcome prediction models require explanation, but due to the multiple non-linear inner transformations, DNN models are viewed by many as a black box. In this study, we developed a deep neural network model for predicting 1-year mortality of patients who underwent major cardio vascular procedures (MCVPs), using temporal image representation of past medical history as input. The dataset was obtained from the electronic medical data warehouse administered by Veteran Affairs Information and Computing Infrastructure (VINCI). We identified 21,355 veterans who had their first MCVP in 2014. Features for prediction included demographics, diagnoses, procedures, medication orders, hospitalizations, and frailty measures extracted from clinical notes. Temporal variables were created based on the patient history data in the 2-year window prior to the index MCVP. A temporal image was created based on these variables for each individual patient. To generate the explanation for the DNN model, we defined a new concept called impact score, based on the presence/value of clinical conditions’ impact on the predicted outcome. Like (log) odds ratio reported by the logistic regression (LR) model, impact scores are continuous variables intended to shed light on the black box model. For comparison, a logistic regression model was fitted on the same dataset. In our cohort, about 6.8% of patients died within one year. The prediction of the DNN model achieved an area under the curve (AUC) of 78.5% while the LR model achieved an AUC of 74.6%. A strong but not perfect correlation was found between the aggregated impact scores and the log odds ratios (Spearman’s rho = 0.74), which helped validate our explanation.

Keywords: deep neural network, temporal data, prediction, frailty, logistic regression model

Procedia PDF Downloads 134