Search results for: Bayesian neural network

Authors: Sepideh Jabbari Behnam, Shadabeh Gashtasbi Iraei, Elnaz Mohsenin, MohammadAli Aghajani

Abstract:

Urban neighborhoods, as important urban forming cells, play a key role in creating urban texture and integrated form. Nowadays, most of neighborhood divisions are based on urban management systems but without considering social issues and the other aspects of urban life. This can cause problems such as providing inappropriate services for city dwellers, the loss of local identity and etc. In this regard for regenerating of such neighborhoods, it is essential to locate neighborhood centers with appropriate access and services for all residents. The main objective of this article is reaching to the location of neighborhood centers in a way that, most of issues relating to the physical features (such as the form of access network and texture permeability and etc.) and other qualities such as land uses, densities and social and economic features can be done simultaneously. This paper attempts to use methods of spatial analysis in order to surveying spatial structure and space syntax of urban textures and Urban Network Analysis Systems. This can be done by one of GIS toolbars which is named UNA (Urban Network Analysis) with the use of its five functions (include: Reach, Betweenness, Gravity, Closeness, Straightness).These functions were written according to space syntax theory and offer its relating output. This paper tries to locate and evaluate the optimal location of neighborhood centers in order to create local centers. This is done through weighing of each of these functions and taking into account of spatial features.

Keywords: evaluate optimal location, Local centers, location of neighborhood centers, Spatial analysis, Urban network

Procedia PDF Downloads 463

Authors: Dalia Elleuch

Abstract:

Narcissistic Personality Disorder (NPD) manifests as a personality disorder marked by inflated self-importance, heightened sensitivity to criticism, a lack of empathy, a preoccupation with appearance over substance, and features such as arrogance, grandiosity, a constant need for admiration, a tendency to exploit others, and an inclination towards demanding special treatment due to a sense of excessive entitlement (APA, 2013). This interdisciplinary study delves into NPD through the systematic synthesis of psycholinguistic analysis and neuroscientific correlates. The cognitive and emotional dimensions of NPD reveal linguistic patterns, including grandiosity, entitlement, and manipulative communication. Neuroscientific investigations reveal structural brain differences and alterations in functional connectivity, further explaining the neural underpinnings of social cognition deficits observed in individuals with NPD. Genetic predispositions and neurotransmitter imbalances add a layer of complexity to the understanding of NPD. The necessity for linguistic intervention in diagnosing and treating Narcissistic Personality Disorder is underscored by an interdisciplinary study that intricately synthesizes psycholinguistic analysis and neuroscientific correlates, offering a comprehensive understanding of NPD’s cognitive, emotional, and neural dimensions and paving the way for future practical, theoretical, and pedagogical approaches to address the complexities of this personality disorder.

Keywords: Narcissistic Personality Disorder (NPD), psycholinguistic analysis, neuroscientific correlates, interpersonal dysfunction, cognitive empathy

Procedia PDF Downloads 65

Authors: A. Andreasyan, C. Connors

Abstract:

The Elliptic Curve Digital Signature algorithm-based X509v3 certificates are becoming more popular due to their short public and private key sizes. Moreover, these certificates can be stored in Internet of Things (IoT) devices, with limited resources, using less memory and transmitted in network security protocols, such as Internet Key Exchange (IKE), Transport Layer Security (TLS) and Secure Shell (SSH) with less bandwidth. The proposed method gives another advantage, in that it increases the performance of the above-mentioned protocols in terms of key exchange by saving one scalar multiplication operation.

Keywords: cryptography, elliptic curve digital signature algorithm, key exchange, network security protocol

Procedia PDF Downloads 146

Authors: Yeliz Karaca, Carlo Cattani

Abstract:

This study focuses on the local Holder exponent as a measure of the function regularity for time series related to finance data. In this study, the attributes of the finance dataset belonging to 13 countries (India, China, Japan, Sweden, France, Germany, Italy, Australia, Mexico, United Kingdom, Argentina, Brazil, USA) located in 5 different continents (Asia, Europe, Australia, North America and South America) have been examined.These countries are the ones mostly affected by the attributes with regard to financial development, covering a period from 2012 to 2017. Our study is concerned with the most important attributes that have impact on the development of finance for the countries identified. Our method is comprised of the following stages: (a) among the multi fractal methods and Brownian motion Holder regularity functions (polynomial, exponential), significant and self-similar attributes have been identified (b) The significant and self-similar attributes have been applied to the Artificial Neuronal Network (ANN) algorithms (Feed Forward Back Propagation (FFBP) and Cascade Forward Back Propagation (CFBP)) (c) the outcomes of classification accuracy have been compared concerning the attributes that have impact on the attributes which affect the countries’ financial development. This study has enabled to reveal, through the application of ANN algorithms, how the most significant attributes are identified within the relevant dataset via the Holder functions (polynomial and exponential function).

Keywords: artificial neural networks, finance data, Holder regularity, multifractals

Procedia PDF Downloads 246

Authors: Amir Mahyar Khorasani, Ian Gibson, Moshe Goldberg, Mohammad Masoud Movahedi, Guy Littlefair

Abstract:

One of the important factors in manufacturing processes especially machining operations is surface quality. Improving this parameter results in improving fatigue strength, corrosion resistance, creep life and surface friction. The reliability and clearance of removable joints such as thread and nuts are highly related to the surface roughness. In this work, the effect of different cutting parameters such as cutting fluid pressure, feed rate and cutting speed on the surface quality of the crest of thread in the high-speed milling of Brass C3600 have been determined. Two popular neural networks containing MLP and RBF coupling with Taguchi L32 have been used to model surface roughness which was shown to be highly adept for such tasks. The contribution of this work is modelling surface roughness on the crest of the thread by using precise profilometer with nanoscale resolution. Experimental tests have been carried out for validation and approved suitable accuracy of the proposed model. Also analysing the interaction of parameters two by two showed that the most effective cutting parameter on the surface value is feed rate followed by cutting speed and cutting fluid pressure.

Keywords: artificial neural networks, cutting conditions, high-speed machining, surface roughness, thread milling

Procedia PDF Downloads 377

Authors: Tatsuya Otoshi, Masayuki Murata

Abstract:

With the development and diversification of applications on the Internet, applications that require high responsiveness, such as video streaming, are becoming mainstream. Application responsiveness is not only a matter of communication delay but also a matter of time required to grasp changes in network conditions. The tradeoff between accuracy and measurement time is a challenge in network control. We people make countless decisions all the time, and our decisions seem to resolve tradeoffs between time and accuracy. When making decisions, people are known to make appropriate choices based on relatively small samples. Although there have been various studies on models of human decision-making, a model that integrates various cognitive biases, called ”quantum decision-making,” has recently attracted much attention. However, the modeling of small samples has not been examined much so far. In this paper, we extend the model of quantum decision-making to model decision-making with a small sample. In the proposed model, the state is updated by value-based probability amplitude amplification. By analytically obtaining a lower bound on the number of samples required for decision-making, we show that decision-making with a small number of samples is feasible.

Keywords: quantum decision making, small sample, MPEG-DASH, Grover's algorithm

Procedia PDF Downloads 79

Authors: Kavian Khosravinia, Mohd Khair Hassan, Ribhan Zafira Abdul Rahman, Syed Abdul Rahman Al-Haddad

Abstract:

The CAN (controller area network) bus is introduced as a multi-master, message broadcast system. The messages sent on the CAN are used to communicate state information, referred as a signal between different ECUs, which provides data consistency in every node of the system. OBD-II Dongles that are based on request and response method is the wide-spread solution for extracting sensor data from cars among researchers. Unfortunately, most of the past researches do not consider resolution and quantity of their input data extracted through OBD-II technology. The maximum feasible scan rate is only 9 queries per second which provide 8 data points per second with using ELM327 as well-known OBD-II dongle. This study aims to develop and design a programmable, and latency-sensitive vehicle data acquisition system that improves the modularity and flexibility to extract exact, trustworthy, and fresh car sensor data with higher frequency rates. Furthermore, the researcher must break apart, thoroughly inspect, and observe the internal network of the vehicle, which may cause severe damages to the expensive ECUs of the vehicle due to intrinsic vulnerabilities of the CAN bus during initial research. Desired sensors data were collected from various vehicles utilizing Raspberry Pi3 as computing and processing unit with using OBD (request-response) and direct CAN method at the same time. Two types of data were collected for this study. The first, CAN bus frame data that illustrates data collected for each line of hex data sent from an ECU and the second type is the OBD data that represents some limited data that is requested from ECU under standard condition. The proposed system is reconfigurable, human-readable and multi-task telematics device that can be fitted into any vehicle with minimum effort and minimum time lag in the data extraction process. The standard operational procedure experimental vehicle network test bench is developed and can be used for future vehicle network testing experiment.

Keywords: CAN bus, OBD-II, vehicle data acquisition, connected cars, telemetry, Raspberry Pi3

Procedia PDF Downloads 205

Authors: A. Hadadi, M. Abdollahi, A. Dustmohammadi

Abstract:

The growing use of DGs in distribution networks provide many advantages and also cause new problems which should be anticipated and be solved with appropriate solutions. One of the problems is transient voltage drop and short circuit in the electrical network, in the presence of distributed generation - which can lead to instability. The appearance of the short circuit will cause loss of generator synchronism, even though if it would be able to recover synchronizing mode after removing faulty generator, it will be stable. In order to increase system reliability and generator lifetime, some strategies should be planned to apply even in some situations which a fault prevent generators from separation. In this paper, one fault current limiter is installed due to prevent DGs separation from the grid when fault occurs. Furthermore, an innovative objective function is applied to determine the impedance optimal amount of fault current limiter in order to improve transient stability of distributed generation. Fault current limiter can prevent generator rotor's sudden acceleration after fault occurrence and thereby improve the network transient stability by reducing the current flow in a fast and effective manner. In fact, by applying created impedance by fault current limiter when a short circuit happens on the path of current injection DG to the fault location, the critical fault clearing time improve remarkably. Therefore, protective relay has more time to clear fault and isolate the fault zone without any instability. Finally, different transient scenarios of connection plan sustainability of small scale synchronous generators to the distribution network are presented.

Keywords: critical clearing time, fault current limiter, synchronous generator, transient stability, transient states

Procedia PDF Downloads 197

Authors: John Segars

Abstract:

Built out of a real-world need to have better, more detailed, asset and infrastructure documentation, this project will lay out the case for using the database functionality of ArcGIS as a tool to track and maintain infrastructure location, status, maintenance and serviceability. Workflows and processes will be presented and detailed which may be applied to an organizations’ infrastructure needs that might allow them to make use of the robust tools which surround the ArcGIS platform. The end result is a value-added information system framework with a geographic component e.g., the spatial location of various I.T. assets, a detailed set of records which not only documents location but also captures the maintenance history for assets along with photographs and documentation of these various assets as attachments to the numerous feature class items. In addition to the asset location and documentation benefits, the staff will be able to log into the devices and pull SNMP (Simple Network Management Protocol) based query information from within the user interface. The entire collection of information may be displayed in ArcGIS, via a JavaScript based web application or via queries to the back-end database. The project is applicable to all organizations which maintain an IT infrastructure but specifically targets post-secondary educational institutions where access to ESRI resources is generally already available in house.

Keywords: ESRI, GIS, infrastructure, network documentation, PostgreSQL

Procedia PDF Downloads 181

Authors: Seyoung Kim, Jeongmin Kim, Kwang Ryel Ryu

Abstract:

A database that records average traffic speeds measured at five-minute intervals for all the links in the traffic network of a metropolitan city. While learning from this data the models that can predict future traffic speed would be beneficial for the applications such as the car navigation system, building predictive models for every link becomes a nontrivial job if the number of links in a given network is huge. An advantage of adopting k-nearest neighbor (k-NN) as predictive models is that it does not require any explicit model building. Instead, k-NN takes a long time to make a prediction because it needs to search for the k-nearest neighbors in the database at prediction time. In this paper, we investigate how much we can speed up k-NN in making traffic speed predictions by reducing the amount of data to be searched for without a significant sacrifice of prediction accuracy. The rationale behind this is that we had a better look at only the recent data because the traffic patterns not only repeat daily or weekly but also change over time. In our experiments, we build several different k-NN models employing different sets of features which are the current and past traffic speeds of the target link and the neighbor links in its up/down-stream. The performances of these models are compared by measuring the average prediction accuracy and the average time taken to make a prediction using various amounts of data.

Keywords: big data, k-NN, machine learning, traffic speed prediction

Procedia PDF Downloads 363

Authors: Masoud Hassanzade Novin, Bahloul Salmani

Abstract:

The process of the translation is not merely the linguistic aspects. It is also considered in the cultural framework of both the source and target text cultures. The translation process and translated texts are confronted the new aspect in 20th century which is considered mostly in the patronage framework and ideological grillwork of the target language. To have these factors scrutinized in the process of the translation both micro-element factors and macro-element factors can be taken into consideration. For the purpose of this study through a qualitative type of research based on critical discourse analysis approach, the case study of the novel “1984” written by George Orwell was chosen as the corpus of the study to have the contrastive analysis by its Persian translated texts. Results of the study revealed some distortions embedded in the target texts which were overshadowed by ideological aspect and patronage network. The outcomes of the manipulated terms were different in various categories which revealed the manipulation aspects in the texts translated.

Keywords: critical discourse analysis, ideology, patronage network, translated texts

Procedia PDF Downloads 322

Authors: Kai Chen, Shuguang Cui, Feng Yin

Abstract:

Gaussian process (GP) with spectral mixture (SM) kernel demonstrates flexible non-parametric Bayesian learning ability in modeling unknown function. In this work a novel time-varying and non-stationary convolution spectral mixture (TN-CSM) kernel with a significant enhancing of interpretability by using process convolution is introduced. A way decomposing the SM component into an auto-convolution of base SM component and parameterizing it to be input dependent is outlined. Smoothly, performing a convolution between two base SM component yields a novel structure of non-stationary SM component with much better generalized expression and interpretation. The TN-CSM perfectly allows compatibility with the stationary SM kernel in terms of kernel form and spectral base ignored and confused by previous non-stationary kernels. On synthetic and real-world datatsets, experiments show the time-varying characteristics of hyper-parameters in TN-CSM and compare the learning performance of TN-CSM with popular and representative non-stationary GP.

Keywords: Gaussian process, spectral mixture, non-stationary, convolution

Procedia PDF Downloads 196

Authors: Simiao Ren, En Wei

Abstract:

Drowning is a significant safety issue worldwide, and a robust computer vision-based alert system can easily prevent such tragedies in swimming pools. However, due to domain shift caused by the visual gap (potentially due to lighting, indoor scene change, pool floor color etc.) between the training swimming pool and the test swimming pool, the robustness of such algorithms has been questionable. The annotation cost for labeling each new swimming pool is too expensive for mass adoption of such a technique. To address this issue, we propose a domain-aware data augmentation pipeline based on Gaussian Poisson Generative Adversarial Network (GP-GAN). Combined with YOLOv8, we demonstrate that such a domain adaptation technique can significantly improve the model performance (from 0.24 mAP to 0.82 mAP) on new test scenes. As the augmentation method only require background imagery from the new domain (no annotation needed), we believe this is a promising, practical route for preventing swimming pool drowning.

Keywords: computer vision, deep learning, YOLOv8, detection, swimming pool, drowning, domain adaptation, generative adversarial network, GAN, GP-GAN

Procedia PDF Downloads 101

Authors: Cheng-yu Hsieh, Bo Zhang, Ahmed Hambaba

Abstract:

Stock market prediction has long been an area of interest for both expert analysts and investors, driven by its complexity and the noisy, volatile conditions it operates under. This research examines the efficacy of combining the Patch Time Series Transformer (PatchTST) with wavelet transforms, specifically focusing on Haar and Daubechies wavelets, in forecasting the adjusted closing price of the S&P 500 index for the following day. By comparing the performance of the augmented PatchTST models with traditional predictive models such as Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Transformers, this study highlights significant enhancements in prediction accuracy. The integration of the Daubechies wavelet with PatchTST notably excels, surpassing other configurations and conventional models in terms of Mean Absolute Error (MAE) and Mean Squared Error (MSE). The success of the PatchTST model paired with Daubechies wavelet is attributed to its superior capability in extracting detailed signal information and eliminating irrelevant noise, thus proving to be an effective approach for financial time series forecasting.

Keywords: deep learning, financial forecasting, stock market prediction, patch time series transformer, wavelet transform

Procedia PDF Downloads 51

Authors: Wann-Ming Wey

Abstract:

In today's popularity and progress of information technology, the big data set and its analysis are no longer a major conundrum. Now, we could not only use the relevant big data to analysis and emulate the possible status of urban development in the near future, but also provide more comprehensive and reasonable policy implementation basis for government units or decision-makers via the analysis and emulation results as mentioned above. In this research, we set Taipei City as the research scope, and use the relevant big data variables (e.g., population, facility utilization and related social policy ratings) and Analytic Network Process (ANP) approach to implement in-depth research and discussion for the possible reduction of land use in primary and secondary schools of Taipei City. In addition to enhance the prosperous urban activities for the urban public facility utilization, the final results of this research could help improve the efficiency of urban land use in the future. Furthermore, the assessment model and research framework established in this research also provide a good reference for schools or other public facilities land use and adaptive reuse strategies in the future.

Keywords: adaptive reuse, analytic network process, big data, land use strategy

Procedia PDF Downloads 203

Authors: N. R. Harris, J. Curry

Abstract:

This paper describes the construction and operation of an experimental LoRaWAN network surrounding the University of Southampton in the United Kingdom. Following successful installation, an experimental node design is built and characterised, with particular emphasis on radio range. Several configurations are investigated, including different data rates, and varying heights of node. It is concluded that although range can be great (over 8 km in this case), environmental topology is critical. However, shorter range implementations, up to about 2 km in an urban environment, are relatively insensitive although care is still needed. The example node and the relatively simple base station reported demonstrate that LoraWan can be a very low cost and practical solution to Internet of Things type applications for distributed monitoring systems with sensors spread over distances of several km.

Keywords: long-range, wireless, sensor, network

Procedia PDF Downloads 137

Authors: Bhuvanesh Baniya

Abstract:

Alzheimer disease is illnesses that are responsible for neuronal cell death and resulting in lifelong cognitive problems. Due to their unclear mechanism, there are no effective drugs available for the treatment. For a long time, herbal drugs have been used as a role model in the field of the drug discovery process. Holy basil in the Indian medicinal system (Ayurveda) is used for several neuronal disorders like insomnia and memory loss for decades. This study aims to identify active components of holy basil as potential inhibitors for the treatment of Alzheimer disease. To fulfill this objective, the Network pharmacology approach, gene ontology, pharmacokinetics analysis, molecular docking, and molecular dynamics simulation (MDS) studies were performed. A total of 7 active components in holy basil, 12 predicted neurodegenerative targets of holy basil, and 8063 Alzheimer-related targets were identified from different databases. The network analysis showed that the top ten targets APP, EGFR, MAPK1, ESR1, HSPA4, PRKCD, MAPK3, ABL1, JUN, and GSK3B were found as significant target related to Alzheimer disease. On the basis of gene ontology and topology analysis results, APP was found as a significant target related to Alzheimer’s disease pathways. Further, the molecular docking results to found that various compounds showed the best binding affinities. Further, MDS top results suggested could be used as potential inhibitors against APP protein and could be useful for the treatment of Alzheimer’s disease.

Keywords: holy basil, network pharmacology, neurodegeneration, active phytochemicals, molecular docking and simulation

Procedia PDF Downloads 101

Authors: Muhammad Naveed Tahir, Wang Yingkuan, Huang Wenjiang, Raheel Osman

Abstract:

Numerous models used in prediction and decision-making process but most of them are linear in natural environment, and linear models reach their limitations with non-linearity in data. Therefore accurate estimation is difficult. Artificial Neural Networks (ANN) found extensive acceptance to address the modeling of the complex real world for the non-linear environment. ANN’s have more general and flexible functional forms than traditional statistical methods can effectively deal with. The link between information technology and agriculture will become more firm in the near future. Monitoring crop biophysical properties non-destructively can provide a rapid and accurate understanding of its response to various environmental influences. Crop chlorophyll content is an important indicator of crop health and therefore the estimation of crop yield. In recent years, remote sensing has been accepted as a robust tool for site-specific management by detecting crop parameters at both local and large scales. The present research combined the ANN model with satellite-derived chlorophyll indices from LANDSAT 8 imagery for predicting real-time wheat chlorophyll estimation. The cloud-free scenes of LANDSAT 8 were acquired (Feb-March 2016-17) at the same time when ground-truthing campaign was performed for chlorophyll estimation by using SPAD-502. Different vegetation indices were derived from LANDSAT 8 imagery using ERADAS Imagine (v.2014) software for chlorophyll determination. The vegetation indices were including Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Chlorophyll Absorbed Ratio Index (CARI), Modified Chlorophyll Absorbed Ratio Index (MCARI) and Transformed Chlorophyll Absorbed Ratio index (TCARI). For ANN modeling, MATLAB and SPSS (ANN) tools were used. Multilayer Perceptron (MLP) in MATLAB provided very satisfactory results. For training purpose of MLP 61.7% of the data, for validation purpose 28.3% of data and rest 10% of data were used to evaluate and validate the ANN model results. For error evaluation, sum of squares error and relative error were used. ANN model summery showed that sum of squares error of 10.786, the average overall relative error was .099. The MCARI and NDVI were revealed to be more sensitive indices for assessing wheat chlorophyll content with the highest coefficient of determination R²=0.93 and 0.90 respectively. The results suggested that use of high spatial resolution satellite imagery for the retrieval of crop chlorophyll content by using ANN model provides accurate, reliable assessment of crop health status at a larger scale which can help in managing crop nutrition requirement in real time.

Keywords: ANN, chlorophyll content, chlorophyll indices, satellite images, wheat

Procedia PDF Downloads 146

Authors: Vanaja Rao

Abstract:

In the recent times, the need for the integration of Renewable Energy Sources (RES) in a Smart Grid is on the rise. As a result of this, associated energy storage systems are known to play important roles in sustaining the efficient operation of such RES like wind power and solar power. This paper investigates the importance of location selection of Energy Storage Systems (ESSs) in a Smart Grid. Three scenarios of ESS location is studied and analyzed in a Smart Grid, which are – 1. Near the generation/source, 2. In the middle of the Grid and, 3. Near the demand/consumption. This is explained with the aim of assisting any Distribution Network Operator (DNO) in deploying the ESSs in a power network, which will significantly help reduce the costs and time of planning and avoid any damages incurred as a result of installing them at an incorrect location of a Smart Grid. To do this, the outlined scenarios mentioned above are modelled and analyzed with the National Grid’s datasets of energy generation and consumption in the UK power network. As a result, the outcome of this analysis aims to provide a better overview for the location selection of the ESSs in a Smart Grid. This ensures power system stability and security along with the optimum usage of the ESSs.

Keywords: distribution networks, energy storage system, energy security, location planning, power stability, smart grid

Procedia PDF Downloads 299

Authors: Jonas Colin

Abstract:

Standing at the vanguard of AI development, Alpha represents an unprecedented synthesis of logical rigor and human abstraction, meticulously crafted to mirror the user's unique persona and personality, a feat previously unattainable in AI development. Alpha, an avant-garde artefact in the realm of artificial intelligence, epitomizes a paradigmatic shift in personalized digital interaction, amalgamating user-specific dialogic patterns with the sophisticated algorithmic prowess of OpenAI's GPT-3.5 to engender a platform for enhanced metacognitive engagement and individualized user experience. Underpinned by a sophisticated algorithmic framework, Alpha integrates vast datasets through a complex interplay of neural network models and symbolic AI, facilitating a dynamic, adaptive learning process. This integration enables the system to construct a detailed user profile, encompassing linguistic preferences, emotional tendencies, and cognitive styles, tailoring interactions to align with individual characteristics and conversational contexts. Furthermore, Alpha incorporates advanced metacognitive elements, enabling real-time reflection and adaptation in communication strategies. This self-reflective capability ensures continuous refinement of its interaction model, positioning Alpha not just as a technological marvel but as a harbinger of a new era in human-computer interaction, where machines engage with us on a deeply personal and cognitive level, transforming our interaction with the digital world.

Keywords: chatbot, GPT 3.5, metacognition, symbiose

Procedia PDF Downloads 70

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 123

Authors: Farshad Zeinali, Sajedeh Norouzi, Nader Mokari, Eduard Jorswieck

Abstract:

The capacity of fifth-generation (5G) vehicle-to-everything (V2X) networks poses significant challenges. To ad- dress this challenge, this paper utilizes New Radio (NR) and New Radio Unlicensed (NR-U) networks to develop a heterogeneous vehicular network (HetNet). We propose a new framework, named joint BS assignment and resource allocation (JBSRA) for mobile V2X users and also consider coexistence schemes based on flexible duty cycle (DC) mechanism for unlicensed bands. Our objective is to maximize the average throughput of vehicles while guaranteeing the WiFi users' throughput. In simulations based on deep reinforcement learning (DRL) algorithms such as deep deterministic policy gradient (DDPG) and deep Q network (DQN), our proposed framework outperforms existing solutions that rely on fixed DC or schemes without consideration of unlicensed bands.

Keywords: vehicle-to-everything (V2X), resource allocation, BS assignment, new radio (NR), new radio unlicensed (NR-U), coexistence NR-U and WiFi, deep deterministic policy gradient (DDPG), deep Q-network (DQN), joint BS assignment and resource allocation (JBSRA), duty cycle mechanism

Procedia PDF Downloads 103

Authors: Juliza Hidayati, Yesie M. Sinuhaji, Sawarni Hasibuan

Abstract:

A company producing drinking water through many incompatibility issues that affect supply chain performance. The study was conducted to determine the factors that affect the performance of the supply chain and improve it. To obtain the dominant factors affecting the performance of the supply chain used Analytic Network Process, while to improve performance is done by using Kaizen. Factors affecting the performance of the supply chain to be a reference to identify the cause of the non-conformance. Results weighting using ANP indicates that the dominant factor affecting the level of performance is the precision of the number of shipments (15%), the ability of the fulfillment of the booking amount (12%), and the number of rejected products when signing (12%). Incompatibility of the factors that affect the performance of the supply chain are identified, so that found the root cause of the problem is most dominant. Based on the weight of Risk Priority Number (RPN) gained the most dominant root cause of the problem, namely the poorly maintained engine, the engine worked for three shifts, machine parts that are not contained in the plant. Improvements then performed using the Kaizen method of systematic and sustainable.

Keywords: analytic network process, booking amount, risk priority number, supply chain performance

Procedia PDF Downloads 294

Authors: Tzu-Yang Lin, Chuan-Ching Sue

Abstract:

Sleep mechanisms are commonly used to ensure the energy efficiency of each optical network unit (ONU) that concerns a single class delay constraint in the Ethernet Passive Optical Network (EPON). How long the ONUs can sleep without violating the delay constraint has become a research problem. Particularly, we can derive an analytical model to determine the optimal sleep time of ONUs in every cycle without violating the maximum class delay constraint. The bandwidth allocation considering such optimal sleep time is called Green Bandwidth Allocation (GBA). Although the GBA mechanism guarantees that the different class delay constraints do not violate the maximum class delay constraint, packets with a more relaxed delay constraint will be treated as those with the most stringent delay constraint and may be sent early. This means that the ONU will waste energy in active mode to send packets in advance which did not need to be sent at the current time. Accordingly, we proposed a QoS-aware GBA using a novel intra-ONU scheduling to control the packets to be sent according to their respective delay constraints, thereby enhancing energy efficiency without deteriorating delay performance. If packets are not explicitly classified but with different packet delay constraints, we can modify the intra-ONU scheduling to classify packets according to their packet delay constraints rather than their classes. Moreover, we propose the switchable ONU architecture in which the ONU can switch the architecture according to the sleep time length, thus improving energy efficiency in the QoS-aware GBA. The simulation results show that the QoS-aware GBA ensures that packets in different classes or with different delay constraints do not violate their respective delay constraints and consume less power than the original GBA.

Keywords: Passive Optical Networks, PONs, Optical Network Unit, ONU, energy efficiency, delay constraint

Procedia PDF Downloads 284

Authors: Riaan Kleyn

Abstract:

Mass wine production companies across the globe are provided with grapes from winegrowers that predominantly utilize mechanical harvesting machines to harvest wine grapes. Mechanical harvesting accelerates the rate at which grapes are harvested, allowing grapes to be delivered faster to meet the demands of wine cellars. The disadvantage of the mechanical harvesting method is the inclusion of material-other-than-grapes (MOG) in the harvested wine grape loads arriving at the cellar which degrades the quality of wine that can be produced. Currently, wine cellars do not have a method to determine the amount of MOG present within wine grape loads. This paper seeks to find an optimal computer vision method capable of detecting the amount of MOG within a wine grape load. A MOG detection method will encourage winegrowers to deliver MOG-free wine grape loads to avoid penalties which will indirectly enhance the quality of the wine to be produced. Traditional image segmentation methods were compared to deep learning segmentation methods based on images of wine grape loads that were captured at a wine cellar. The Mask R-CNN model with a ResNet-50 convolutional neural network backbone emerged as the optimal method for this study to determine the amount of MOG in an image of a wine grape load. Furthermore, a statistical analysis was conducted to determine how the MOG on the surface of a grape load relates to the mass of MOG within the corresponding grape load.

Keywords: computer vision, wine grapes, machine learning, machine harvested grapes

Procedia PDF Downloads 96

Authors: Mohamad Mahdi Namdari

Abstract:

In today's rapidly changing and evolving business competition, companies and organizations require advanced and efficient tools to manage their markets and sales networks. Big data analysis, quick response in competitive markets, process and operations optimization, and forecasting customer behavior are among the concerns of executive managers. Artificial intelligence, as one of the emerging technologies, has provided extensive capabilities in this regard. The use of artificial intelligence in market and sales network management can lead to improved efficiency, increased decision-making accuracy, and enhanced customer satisfaction. Specifically, AI algorithms can analyze vast amounts of data, identify complex patterns, and offer strategic suggestions to improve sales performance. However, many companies are still distant from effectively leveraging this technology, and those that do face challenges in fully exploiting AI's potential in market and sales network management. It appears that the general public's and even the managerial and academic communities' lack of knowledge of this technology has caused the managerial structure to lag behind the progress and development of artificial intelligence. Additionally, high costs, fear of change and employee resistance, lack of quality data production processes, the need for updating structures and processes, implementation issues, the need for specialized skills and technical equipment, and ethical and privacy concerns are among the factors preventing widespread use of this technology in organizations. Clarifying and explaining this technology, especially to the academic, managerial, and elite communities, can pave the way for a transformative beginning. The aim of this research is to elucidate the capacities of artificial intelligence in market and sales network management, identify its opportunities and benefits, and examine the existing challenges and obstacles. This research aims to leverage AI capabilities to provide a framework for enhancing market and sales network performance for managers. The results of this research can help managers and decision-makers adopt more effective strategies for business growth and development by better understanding the capabilities and limitations of artificial intelligence.

Keywords: artificial intelligence, market management, sales network, big data analysis, decision-making, digital marketing

Procedia PDF Downloads 43

Authors: Hyeongbok Kim, Lingling Zhao, Xiaohong Su, Junjie Wang

Abstract:

The Bernoulli filter is a precise Bayesian filter for single target tracking based on the random finite set theory. The standard Bernoulli filter often underestimates the number of targets. This study proposes a Gaussian particle flow (GPF) Bernoulli filter employing particle flow to migrate particles from prior to posterior positions to improve the performance of the standard Bernoulli filter. By employing the particle flow filter, the computational speed of the Bernoulli filters is significantly improved. In addition, the GPF Bernoulli filter provides a more accurate estimation compared with that of the standard Bernoulli filter. Simulation results confirm the improved tracking performance and computational speed in two- and three-dimensional scenarios compared with other algorithms.

Keywords: Bernoulli filter, particle filter, particle flow filter, random finite sets, target tracking

Procedia PDF Downloads 92

Authors: Sinan Alsaadi, Mustafa Merdan

Abstract:

Communication and access systems can be made with many methods in today’s world. These systems are such standards as Wifi, Wimax, Bluetooth, GPS and GPRS. Devices which use these standards also use system resources excessively in direct proportion to their transmission speed. However, large-scale data communication is not always needed. In such cases, a technology which will use system resources as little as possible and support smart network topologies has been needed in order to enable the transmissions of such small packet data and provide the control for this kind of devices. IEEE issued 802.15.4 standard upon this necessity and enabled the production of Zigbee protocol which takes these standards as its basis and devices which support this protocol. In our project, this communication protocol was preferred. The aim of this study is to provide the immediate data transmission of our robot from the field within the scope of the project. In addition, making the communication with the robot through Zigbee Protocol has also been aimed. While sitting on the computer, obtaining the desired data from the region where the robot is located has been taken as the basis. Arduino Uno R3 microcontroller which provides the control mechanism, 1298 shield as the motor driver.

Keywords: ZigBee, wireless network, remote monitoring, smart home, agricultural industry

Procedia PDF Downloads 278

Authors: Yeonjeong Lee, Kyoung-jae Kim, Youngtae Kim

Abstract:

This study proposes a novel recommender system that uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user’s preference. The proposed model consists of two steps. In the first step, this study uses logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. Then, this study combines the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. In the second step, this study uses the market basket analysis to extract association rules for co-purchased products. Finally, the system selects customers who have high likelihood to purchase products in each product group and recommends proper products from same or different product groups to them through above two steps. We test the usability of the proposed system by using prototype and real-world transaction and profile data. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The results also show that the proposed system may be useful in real-world online shopping store.

Keywords: product recommender system, ensemble technique, association rules, decision tree, artificial neural networks

Procedia PDF Downloads 294

Authors: Kishore Kumar R., Kaustav Sengupta, Shalini Sood Sehgal, Poornima Santhanam

Abstract:

Fashion is a human expression that is constantly changing. One of the prime factors that consistently influences fashion is the change in colour preferences. The role of colour in our everyday lives is very significant. It subconsciously explains a lot about one’s mindset and mood. Analyzing the colours by extracting them from the outfit images is a critical study to examine the individual’s/consumer behaviour. Several research works have been carried out on extracting colours from images, but to the best of our knowledge, there were no studies that extract colours to specific apparel and identify colour patterns geographically. This paper proposes a framework for accurately extracting colours from T-shirt images and predicting dominant colours geographically. The proposed method consists of two stages: first, a U-Net deep learning model is adopted to segment the T-shirts from the images. Second, the colours are extracted only from the T-shirt segments. The proposed method employs the iMaterialist (Fashion) 2019 dataset for the semantic segmentation task. The proposed framework also includes a mechanism for gathering data and analyzing India’s general colour preferences. From this research, it was observed that black and grey are the dominant colour in different regions of India. The proposed method can be adapted to study fashion’s evolving colour preferences.

Keywords: colour analysis in t-shirts, convolutional neural network, encoder-decoder, k-means clustering, semantic segmentation, U-Net model

Procedia PDF Downloads 111