Search results for: decision based artificial neural network

Authors: Yang Zhang, Jian He

Abstract:

Heart disease is one of the leading causes of death in the world, and coronary heart disease (CHD) is one of the major heart diseases. Electrocardiogram (ECG) is widely used in the detection of heart diseases, but the traditional manual method for CHD prediction by analyzing ECG requires lots of professional knowledge for doctors. This paper introduces sliding window and continuous wavelet transform (CWT) to transform ECG signals into images, and then ResNet and Bi-LSTM are introduced to build the ECG feature extraction network (namely ECGNet). At last, an auxiliary system for coronary heart disease prediction was developed based on modified ResNet18 and Bi-LSTM, and the public ECG dataset of CHD from MIMIC-3 was used to train and test the system. The experimental results show that the accuracy of the method is 83%, and the F1-score is 83%. Compared with the available methods for CHD prediction based on ECG, such as kNN, decision tree, VGGNet, etc., this method not only improves the prediction accuracy but also could avoid the degradation phenomenon of the deep learning network.

Keywords: Bi-LSTM, CHD, ECG, ResNet, sliding window

Procedia PDF Downloads 89

Authors: Jyoti Rani, Ashima Anand, Shivendra Shivani

Abstract:

In recent years, physiological signals obtained in telemedicine have been stored independently from patient information. In addition, people have increasingly turned to mobile devices for information on health-related topics. Major authentication and security issues may arise from this storing, degrading the reliability of diagnostics. This study introduces an approach to reversible watermarking, which ensures security by utilizing the electrocardiogram (ECG) signal as a carrier for embedding patient information. In the proposed work, Pan-Tompkins++ is employed to convert the 1D ECG signal into a 2D signal. The frequency subbands of a signal are extracted using RDWT(Redundant discrete wavelet transform), and then one of the subbands is subjected to MSVD (Multiresolution singular valued decomposition for masking. Finally, the encrypted watermark is embedded within the signal. The experimental results show that the watermarked signal obtained is indistinguishable from the original signals, ensuring the preservation of all diagnostic information. In addition, the DnCNN (Denoising convolutional neural network) concept is used to denoise the retrieved watermark for improved accuracy. The proposed ECG signal-based watermarking method is supported by experimental results and evaluations of its effectiveness. The results of the robustness tests demonstrate that the watermark is susceptible to the most prevalent watermarking attacks.

Keywords: ECG, VMD, watermarking, PanTompkins++, RDWT, DnCNN, MSVD, chaotic encryption, attacks

Procedia PDF Downloads 101

Authors: Rezaei Hachesu Peyman, Oliyaee Azadeh, Salahzadeh Zahra, Alizadeh Somayyeh, Safaei Naser

Abstract:

Coronary Artery Disease (CAD) is one major cause of disability in adults and one main cause of death in developed. In this study, data mining techniques including Decision Trees, Artificial neural networks (ANNs), and Support Vector Machine (SVM) analyze CAD data. Data of 4948 patients who had suffered from heart diseases were included in the analysis. CAD is the target variable, and 24 inputs or predictor variables are used for the classification. The performance of these techniques is compared in terms of sensitivity, specificity, and accuracy. The most significant factor influencing CAD is chest pain. Elderly males (age > 53) have a high probability to be diagnosed with CAD. SVM algorithm is the most useful way for evaluation and prediction of CAD patients as compared to non-CAD ones. Application of data mining techniques in analyzing coronary artery diseases is a good method for investigating the existing relationships between variables.

Keywords: classification, coronary artery disease, data-mining, knowledge discovery, extract

Procedia PDF Downloads 657

Authors: Anurag Sharma, Rahul Malhotra, Love Kumar, Harjit Pal Singh

Abstract:

This paper demonstrates OCDM-ROF based hybrid architecture where data/voice communication is enabled via a permutation of Optical Code Division Multiplexing (OCDM) and Radio-over-Fiber (RoF) techniques under various diverse conditions. OCDM-RoF hybrid network of 16 users with DPSK modulation format has been designed and performance of proposed network is analyzed for 100, 150, and 200 km fiber span length under the influence of linear and nonlinear effect. It has been reported that Polarization Mode Dispersion (PMD) has the least effect while other nonlinearity affects the performance of proposed network.

Keywords: OCDM, RoF, DPSK, PMD, eye diagram, BER, Q factor

Procedia PDF Downloads 638

Authors: Michał Rogala, Jakub Gajewski

Abstract:

As the automotive industry develops, passive safety is becoming an increasingly important aspect when designing motor vehicles. A commonly used solution is energy absorption by thin-walled construction. One such structure is a closed thin-walled profile fixed to the vehicle stringers. The article presents numerical tests of conical thin-walled profiles filled with aluminum foam. The columns were loaded axially with constant energy. On the basis of the results obtained, efficiency indicators were calculated. The efficiency of the foam filling was evaluated. Artificial neural networks were used for data analysis. The application of regression analysis was used as a tool to study the relationship between the quantities characteristic of the dynamic crush.

Keywords: aluminium foam, crashworthiness, neural networks, thin-walled structure

Procedia PDF Downloads 146

Authors: Anika Chebrolu

Abstract:

Mono-targeted drugs can be of limited efficacy against complex diseases. Recently, multi-target drug design has been approached as a promising tool to fight against these challenging diseases. However, the scope of current computational approaches for multi-target drug design is limited. DeepLig presents a de-novo drug discovery platform that uses reinforcement learning to generate and optimize novel, potent, and multitargeted drug candidates against protein targets. DeepLig’s model consists of two networks in interplay: a generative network and a predictive network. The generative network, a Stack- Augmented Recurrent Neural Network, utilizes a stack memory unit to remember and recognize molecular patterns when generating novel ligands from scratch. The generative network passes each newly created ligand to the predictive network, which then uses multiple Graph Attention Networks simultaneously to forecast the average binding affinity of the generated ligand towards multiple target proteins. With each iteration, given feedback from the predictive network, the generative network learns to optimize itself to create molecules with a higher average binding affinity towards multiple proteins. DeepLig was evaluated based on its ability to generate multi-target ligands against two distinct proteins, multi-target ligands against three distinct proteins, and multi-target ligands against two distinct binding pockets on the same protein. With each test case, DeepLig was able to create a library of valid, synthetically accessible, and novel molecules with optimal and equipotent binding energies. We propose that DeepLig provides an effective approach to design multi-targeted drug therapies that can potentially show higher success rates during in-vitro trials.

Keywords: drug design, multitargeticity, de-novo, reinforcement learning

Procedia PDF Downloads 97

Authors: Amirreza Fazely Hamedani, Muzzamil Aziz, Philipp Wieder, Ramin Yahyapour

Abstract:

Software-defined networking in recent years came into the sight of so many network designers as a successor to the traditional networking. Unlike traditional networks where control and data planes engage together within a single device in the network infrastructure such as switches and routers, the two planes are kept separated in software-defined networks (SDNs). All critical decisions about packet routing are made on the network controller, and the data level devices forward the packets based on these decisions. This type of network is vulnerable to DDoS attacks, degrading the overall functioning and performance of the network by continuously injecting the fake flows into it. This increases substantial burden on the controller side, and the result ultimately leads to the inaccessibility of the controller and the lack of network service to the legitimate users. Thus, the protection of this novel network architecture against denial of service attacks is essential. In the world of cybersecurity, attacks and new threats emerge every day. It is essential to have tools capable of managing and analyzing all this new information to detect possible attacks in real-time. These tools should provide a comprehensive solution to automatically detect, predict and prevent abnormalities in the network. Big data encompasses a wide range of studies, but it mainly refers to the massive amounts of structured and unstructured data that organizations deal with on a regular basis. On the other hand, it regards not only the volume of the data; but also that how data-driven information can be used to enhance decision-making processes, security, and the overall efficiency of a business. This paper presents an intelligent big data framework as a solution to handle illegitimate traffic burden on the SDN network created by the numerous DDoS attacks. The framework entails an efficient defence and monitoring mechanism against DDoS attacks by employing the state of the art machine learning techniques.

Keywords: apache spark, apache kafka, big data, DDoS attack, machine learning, SDN network

Procedia PDF Downloads 169

Authors: Qin Long, Li Xiaoge

Abstract:

The Knowledge Graphs have now become a new form of knowledge representation. However, there is no consensus in regard to a plausible and definition of entities and relationships in the domain-specific knowledge graph. Further, in conjunction with several limitations and deficiencies, various domain-specific entities and relationships recognition approaches are far from perfect. Specifically, named entity recognition in Chinese domain is a critical task for the natural language process applications. However, a bottleneck problem with Chinese named entity recognition in new domains is the lack of annotated data. To address this challenge, a domain distant supervised named entity recognition framework is proposed. The framework is divided into two stages: first, the distant supervised corpus is generated based on the entity linking model of graph attention neural network; secondly, the generated corpus is trained as the input of the distant supervised named entity recognition model to train to obtain named entities. The link model is verified in the ccks2019 entity link corpus, and the F1 value is 2% higher than that of the benchmark method. The re-pre-trained BERT language model is added to the benchmark method, and the results show that it is more suitable for distant supervised named entity recognition tasks. Finally, it is applied in the computer field, and the results show that this framework can obtain domain named entities.

Keywords: distant named entity recognition, entity linking, knowledge graph, graph attention neural network

Procedia PDF Downloads 95

Authors: Musarrat Jabeen

Abstract:

Thoughtful intelligence offers a sustainable position to enhance the influence of decision-makers. Thoughtful Intelligence implies the understanding to realize the impact of one’s thoughts, words and actions on the survival, dignity and development of the individuals, groups and nations. Thoughtful intelligence has received minimal consideration in the area of Decision Support Systems, with an end goal to evaluate the quantity of knowledge and its viability. This pattern degraded the imbibed contribution of thoughtful intelligence required for sustainable decision making. Given the concern, this paper concentrates on the question: How to present a model of Thoughtful Decision Support System (TDSS)? The aim of this paper is to appreciate the concepts of thoughtful intelligence and insinuate a Decision Support System based on thoughtful intelligence. Thoughtful intelligence includes three dynamic competencies: i) Realization about long term impacts of decisions that are made in a specific time and space, ii) A great sense of taking actions, iii) Intense interconnectivity with people and nature and; seven associate competencies, of Righteousness, Purposefulness, Understanding, Contemplation, Sincerity, Mindfulness, and Nurturing. The study utilizes two methods: Focused group discussion to count prevailing Decision Support Systems; 70% results of focus group discussions found six decision support systems and the positive inexistence of thoughtful intelligence among decision support systems regarding sustainable decision making. Delphi focused on defining thoughtful intelligence to model (TDSS). 65% results helped to conceptualize (definition and description) of thoughtful intelligence. TDSS is offered here as an addition in the decision making literature. The clients are top leaders.

Keywords: thoughtful intelligence, sustainable decision making, thoughtful decision support system

Procedia PDF Downloads 136

Authors: E. Behmanesh, J. Pannek

Abstract:

Logistics network design is known as one of the strategic decision problems. As these kinds of problems belong to the category of NP-hard problems, traditional ways are failed to find an optimal solution in short time. In this study, we attempt to involve reverse flow through an integrated design of forward/reverse supply chain network that formulated into a mixed integer linear programming. This Integrated, multi-stages model is enriched by three different delivery path which makes the problem more complex. To tackle with such an NP-hard problem a revised random path direct encoding method based memetic algorithm is considered as the solution methodology. Each algorithm has some parameters that need to be investigate to reveal the best performance. In this regard, Taguchi method is adapted to identify the optimum operating condition of the proposed memetic algorithm to improve the results. In this study, four factors namely, population size, crossover rate, local search iteration and a number of iteration are considered. Analyzing the parameters and improvement in results are the outlook of this research.

Keywords: integrated logistics network, flexible path, memetic algorithm, Taguchi method

Procedia PDF Downloads 187

Authors: Hans Schumann, Colin Domnauer, Louis Rosenberg

Abstract:

In this study, machine learning techniques were deployed on real-time human swarm data to forecast the likelihood of outcomes for English Premier League matches in the 2020/21 season. These techniques included ensemble models in combination with neural networks and were tested against an industry standard of Vegas Oddsmakers. Predictions made from the collective intelligence of human swarm participants managed to achieve a positive return on investment over a full season on matches, empirically proving the usefulness of a new artificial intelligence valuing human instinct and intelligence.

Keywords: artificial intelligence, data science, English Premier League, human swarming, machine learning, sports betting, swarm intelligence

Procedia PDF Downloads 213

Authors: Manjitsingh Rajput

Abstract:

Visual communication plays an important role in artificial intelligence (AI) because it enables machines to understand and interpret visual information, similar to how humans do. This abstract explores the importance of visual communication in AI and emphasizes the importance of various applications such as computer vision, object emphasis recognition, image classification and autonomous systems. In going deeper, with deep learning techniques and neural networks that modify visual understanding, In addition to AI programming, the abstract discusses challenges facing visual interfaces for AI, such as data scarcity, domain optimization, and interpretability. Visual communication and other approaches, such as natural language processing and speech recognition, have also been explored. Overall, this abstract highlights the critical role that visual communication plays in advancing AI capabilities and enabling machines to perceive and understand the world around them. The abstract also explores the integration of visual communication with other modalities like natural language processing and speech recognition, emphasizing the critical role of visual communication in AI capabilities. This methodology explores the importance of visual communication in AI development and implementation, highlighting its potential to enhance the effectiveness and accessibility of AI systems. It provides a comprehensive approach to integrating visual elements into AI systems, making them more user-friendly and efficient. In conclusion, Visual communication is crucial in AI systems for object recognition, facial analysis, and augmented reality, but challenges like data quality, interpretability, and ethics must be addressed. Visual communication enhances user experience, decision-making, accessibility, and collaboration. Developers can integrate visual elements for efficient and accessible AI systems.

Keywords: visual communication AI, computer vision, visual aid in communication, essence of visual communication.

Procedia PDF Downloads 95

Authors: Arun Prasad Jaganathan

Abstract:

In today's dynamic industrial world, traditional task allocation methods often fall short in adapting to evolving operational conditions. This paper introduces an AI-enabled task assistance and management system designed to overcome the limitations of conventional approaches. By using artificial intelligence (AI) and machine learning (ML), the system intelligently interprets user instructions, analyzes tasks, and allocates resources based on real-time data and environmental factors. Additionally, geolocation tracking enables proactive identification of potential delays, ensuring timely interventions. With its transparent reporting mechanisms, the system provides stakeholders with clear insights into task progress, fostering accountability and informed decision-making. The paper presents a comprehensive overview of the system architecture, algorithm, and implementation, highlighting its potential to revolutionize task management across diverse industries.

Keywords: artificial intelligence, machine learning, task allocation, operational efficiency, resource optimization

Procedia PDF Downloads 59

Authors: Hafiz Gulfam Ahmad, Chuangdong Li, Zeeshan Ahmad

Abstract:

In this paper, we proposed a parallel IDS and honeypot based approach to detect and analyze the unknown and known attack taxonomy for improving the IDS performance and protecting the network from intruders. The main theme of our approach is to record and analyze the intruder activities by using both the low and high interaction honeypots. Our architecture aims to achieve the required goals by combing signature based IDS, honeypots and generate the new signatures. The paper describes the basic component, design and implementation of this approach and also demonstrates the effectiveness of this approach reducing the probability of network attacks.

Keywords: network security, intrusion detection, honeypot, snort, nmap

Procedia PDF Downloads 568

Authors: Tobias Milz, L. Macpherson, Varvara Vetrova

Abstract:

The law is a fundamental pillar of human societies as it shapes, controls and governs how humans conduct business, behave and interact with each other. Recent advances in computer-assisted technologies such as NLP, data science and AI are creating opportunities to support the practice, research and study of this pervasive domain. It is therefore not surprising that there has been an increase in investments into supporting technologies for the legal industry (also known as “legal tech” or “law tech”) over the last decade. A sub-discipline of particular appeal is concerned with assisted legal research. Supporting law researchers and practitioners to retrieve information from the vast amount of ever-growing legal documentation is of natural interest to the legal research community. One tool that has been in use for this purpose since the early nineteenth century is legal citation indexing. Among other use cases, they provided an effective means to discover new precedent cases. Nowadays, computer-assisted network analysis tools can allow for new and more efficient ways to reveal the “hidden” information that is conveyed through citation behavior. Unfortunately, access to openly available legal data is still lacking in New Zealand and access to such networks is only commercially available via providers such as LexisNexis. Consequently, there is a need to create, analyze and provide a legal citation network with sufficient data to support legal research tasks. This paper describes the development and analysis of a legal citation Network for New Zealand containing over 300.000 decisions from 125 different courts of all areas of law and jurisdiction. Using python, the authors assembled web crawlers, scrapers and an OCR pipeline to collect and convert court decisions from openly available sources such as NZLII into uniform and machine-readable text. This facilitated the use of regular expressions to identify references to other court decisions from within the decision text. The data was then imported into a graph-based database (Neo4j) with the courts and their respective cases represented as nodes and the extracted citations as links. Furthermore, additional links between courts of connected cases were added to indicate an indirect citation between the courts. Neo4j, as a graph-based database, allows efficient querying and use of network algorithms such as PageRank to reveal the most influential/most cited courts and court decisions over time. This paper shows that the in-degree distribution of the New Zealand legal citation network resembles a power-law distribution, which indicates a possible scale-free behavior of the network. This is in line with findings of the respective citation networks of the U.S. Supreme Court, Austria and Germany. The authors of this paper provide the database as an openly available data source to support further legal research. The decision texts can be exported from the database to be used for NLP-related legal research, while the network can be used for in-depth analysis. For example, users of the database can specify the network algorithms and metrics to only include specific courts to filter the results to the area of law of interest.

Keywords: case citation network, citation analysis, network analysis, Neo4j

Procedia PDF Downloads 107

Authors: Giselle Maggie Fer Castañeda, Diego Iván González

Abstract:

The objective of this work was to study the autoshaped choice behavior in the Donahoe, Burgos and Palmer (DBP) neural network model and analyze it under the matching law. Autoshaped choice can be viewed as a form of economic behavior defined as the preference between alternatives according to their relative outcomes. The Donahoe, Burgos and Palmer (DBP) model is a connectionist proposal that unifies operant and Pavlovian conditioning. This model has been used for more than three decades as a neurobehavioral explanation of conditioning phenomena, as well as a generator of predictions suitable for experimental testing with non-human animals and humans. The study consisted of different simulations in which, in each one, a ratio of reinforcement was established for two alternatives, and the responses (i.e., activations) in each of them were measured. Choice studies with animals have demonstrated that the data generally conform closely to the generalized matching law equation, which states that the response ratio equals proportionally to the reinforcement ratio; therefore, it was expected to find similar results with the neural networks of the Donahoe, Burgos and Palmer (DBP) model since these networks have simulated and predicted various conditioning phenomena. The results were analyzed by the generalized matching law equation, and it was observed that under some contingencies, the data from the networks adjusted approximately to what was established by the equation. Implications and limitations are discussed.

Keywords: matching law, neural networks, computational models, behavioral sciences

Procedia PDF Downloads 74

Authors: Wei-Han Wang, Hsiang-Yu Yu, Mau-Sun Hua

Abstract:

Theory of Mind (ToM) refers to the ability to infer another’s mental state. With appropriate ToM, one can behave well in social interactions. A growing body of evidence has demonstrated that patients with temporal lobe epilepsy (TLE) may have damaged ToM due to impact on regions of the underlying neural network of ToM. However, the question of whether there is cerebral laterality for ToM functions remains open. This study aimed to examine whether there is cerebral lateralization for ToM abilities in TLE patients. Sixty-seven adult TLE patients and 30 matched healthy controls (HC) were recruited. Patients were classified into right (RTLE), left (LTLE), and bilateral (BTLE) TLE groups on the basis of a consensus panel review of their seizure semiology, EEG findings, and brain imaging results. All participants completed an intellectual test and four tasks measuring basic and advanced ToM. The results showed that, on all ToM tasks; (1)each patient group performed worse than HC; (2)there were no significant differences between LTLE and RTLE groups; (3)the BTLE group performed the worst. It appears that the neural network responsible for ToM is distributed evenly between the cerebral hemispheres.

Keywords: cerebral lateralization, social cognition, temporal lobe epilepsy, theory of mind

Procedia PDF Downloads 420

Authors: Ashish James, Anusha James

Abstract:

The impressive predictive performance of deep learning techniques on a wide range of tasks has led to its widespread use. Estimating the confidence of these predictions is paramount for improving the safety and reliability of such systems. However, the uncertainty estimates provided by neural networks (NNs) tend to be overconfident and unreasonable. Ensemble of NNs typically produce good predictions but uncertainty estimates tend to be inconsistent. Inspired by these, this paper presents a framework that can quantitatively estimate the uncertainties by leveraging the advances in transfer learning through slight modification to the existing training pipelines. This promising algorithm is developed with an intention of deployment in real world problems which already boast a good predictive performance by reusing those pretrained models. The idea is to capture the behavior of the trained NNs for the base task by augmenting it with the uncertainty estimates from a supplementary network. A series of experiments with known and unknown distributions show that the proposed approach produces well calibrated uncertainty estimates with high quality predictions.

Keywords: uncertainty estimation, neural networks, transfer learning, regression

Procedia PDF Downloads 135

Authors: Kefaya Qaddoum

Abstract:

The aim of this study is to predict breast cancer and to construct a supportive model that will stimulate a more reliable prediction as a factor that is fundamental for public health. In this study, we utilize general regression neural networks (GRNN) to replace the normal predictions with prediction periods to achieve a reasonable percentage of confidence. The mechanism employed here utilises a machine learning system called conformal prediction (CP), in order to assign consistent confidence measures to predictions, which are combined with GRNN. We apply the resulting algorithm to the problem of breast cancer diagnosis. The results show that the prediction constructed by this method is reasonable and could be useful in practice.

Keywords: neural network, conformal prediction, cancer classification, regression

Procedia PDF Downloads 291

Authors: Deyu Zhou, Xiao Xue, Lizhen Cui

Abstract:

With the increasing collaboration among various services and the growing complexity of user demands, there are more and more factors affecting the stable development of the cloud manufacturing service economic system (CMSE). This poses new challenges to the evolution analysis of the CMSE. Many researchers have modeled and analyzed the evolution process of CMSE from the perspectives of individual learning and internal factors influencing the system, but without considering other important characteristics of the system's individuals (such as heterogeneity, bounded rationality, etc.) and the impact of external environmental factors. Therefore, this paper proposes an integrated artificial social model for the cloud manufacturing service economic system, which considers both the characteristics of the system's individuals and the internal and external influencing factors of the system. The model consists of three parts: the Agent model, environment model, and rules model (Agent-Environment-Rules, AER): (1) the Agent model considers important features of the individuals, such as heterogeneity and bounded rationality, based on the adaptive behavior mechanisms of perception, action, and decision-making; (2) the environment model describes the activity space of the individuals (real or virtual environment); (3) the rules model, as the driving force of system evolution, describes the mechanism of the entire system's operation and evolution. Finally, this paper verifies the effectiveness of the AER model through computational and experimental results.

Keywords: cloud manufacturing service economic system (CMSE), AER model, artificial social modeling, integrated framework, computing experiment, agent-based modeling, social networks

Procedia PDF Downloads 79

Authors: Abdal-Hafeez Alhussein

Abstract:

Artificial Intelligence (AI) has become a transformative force in the field of information technologies, reshaping how data is processed, analyzed, and utilized across various domains. This paper explores the multifaceted applications of AI within information technology, focusing on three key areas: automation, scalability, and data-driven decision-making. We delve into how AI-powered automation is optimizing operational efficiency in IT infrastructures, from automated network management to self-healing systems that reduce downtime and enhance performance. Scalability, another critical aspect, is addressed through AI’s role in cloud computing and distributed systems, enabling the seamless handling of increasing data loads and user demands. Additionally, the paper highlights the use of AI in cybersecurity, where real-time threat detection and adaptive response mechanisms significantly improve resilience against sophisticated cyberattacks. In the realm of data analytics, AI models—especially machine learning and natural language processing—are driving innovation by enabling more precise predictions, automated insights extraction, and enhanced user experiences. The paper concludes with a discussion on the ethical implications of AI in information technologies, underscoring the importance of transparency, fairness, and responsible AI use. It also offers insights into future trends, emphasizing the potential of AI to further revolutionize the IT landscape by integrating with emerging technologies like quantum computing and IoT.

Keywords: artificial intelligence, information technology, automation, scalability

Procedia PDF Downloads 17

Authors: Tim Farrelly

Abstract:

In recent years, AI-powered object detection systems have opened the doors for innovative new applications and products, especially those operating in the real world or ‘on edge’ – namely, in sport. This paper investigates the viability of an ultra-low parameter convolutional neural network specially designed for the detection of footballs on ‘on the edge’ devices. The main contribution of this paper is the exploration of integrating new design features (depth-wise separable convolutional blocks and squeezed and excitation modules) into an ultra-low parameter network and demonstrating subsequent improvements in performance. The results show that tracking the ball from Full HD images with negligibly high accu-racy is possible in real-time.

Keywords: deep learning, object detection, machine vision applications, sport, network design

Procedia PDF Downloads 146

Authors: Redouane Tlemsani, Abdelkader Benyettou

Abstract:

Work is in on line Arabic character recognition and the principal motivation is to study the Arab manuscript with on line technology. This system is a Markovian system, which one can see as like a Dynamic Bayesian Network (DBN). One of the major interests of these systems resides in the complete models training (topology and parameters) starting from training data. Our approach is based on the dynamic Bayesian Networks formalism. The DBNs theory is a Bayesians networks generalization to the dynamic processes. Among our objective, amounts finding better parameters, which represent the links (dependences) between dynamic network variables. In applications in pattern recognition, one will carry out the fixing of the structure, which obliges us to admit some strong assumptions (for example independence between some variables). Our application will relate to the Arabic isolated characters on line recognition using our laboratory database: NOUN. A neural tester proposed for DBN external optimization. The DBN scores and DBN mixed are respectively 70.24% and 62.50%, which lets predict their further development; other approaches taking account time were considered and implemented until obtaining a significant recognition rate 94.79%.

Keywords: Arabic on line character recognition, dynamic Bayesian network, pattern recognition, computer vision

Procedia PDF Downloads 428

Authors: Sima Aznavi, Poria Fajri, Hanif Livani

Abstract:

Smart homes are small energy systems which may be equipped with renewable energy sources, storage devices, and loads. Energy management strategy plays a main role in the efficient operation of smart homes. Effective energy scheduling of the renewable energy sources and storage devices guarantees efficient energy management in households while reducing the energy imports from the grid. Nevertheless, despite such strategies, independently day ahead energy schedules for multiple households can cause undesired effects such as high power exchange with the grid at certain times of the day. Therefore, the interactions between multiple smart home day ahead energy projections is a challenging issue in a smart grid system and if not managed appropriately, the imported energy from the power network can impose additional burden on the distribution grid. In this paper, a central energy management strategy for a network consisting of multiple households each equipped with renewable energy sources, storage devices, and Plug-in Electric Vehicles (PEV) is proposed. The decision-making strategy alongside the smart home energy management system, minimizes the energy purchase cost of the end users, while at the same time reducing the stress on the utility grid. In this approach, the smart home energy management system determines different operating scenarios based on the forecasted household daily load and the components connected to the household with the objective of minimizing the end user overall cost. Then, selected projections for each household that are within the same cost range are sent to the central decision-making system. The central controller then organizes the schedules to reduce the overall peak to average ratio of the total imported energy from the grid. To validate this approach simulations are carried out for a network of five smart homes with different load requirements and the results confirm that by applying the proposed central energy management strategy, the overall power demand from the grid can be significantly flattened. This is an effective approach to alleviate the stress on the network by distributing its energy to a network of multiple households over a 24- hour period.

Keywords: energy management, renewable energy sources, smart grid, smart home

Procedia PDF Downloads 248

Authors: Evagelos Korobilis-Magas, Adekunle Oke

Abstract:

The constantly increasing tendency towards a global economy and the subsequent increase in exporting, as a result, has inevitably led to a growing interest in the topic of export success as well. Numerous studies, particularly in the past three decades, have examined a plethora of determinants to export performance. However, to the authors' best knowledge, no study up to date has ever considered decision quality as a potential antecedent to export success by attempting to test the relationship between decision quality and export performance. This is a surprising deficiency given that the export marketing literature has long ago suggested that quality decisions are regarded as the crucial intervening variable between sound decision–making and export performance. This study integrates the different definitions of decision quality proposed in the literature and the key themes incorporated therein and adapts it to an export context. Apart from laying the conceptual foundations for the delineation of this elusive but very important construct, this study is the first ever to test the relationship between decision quality and export performance. Based on survey data from a sample of 189 British export decision-makers and within a contingency theory framework, the results reveal that there is a direct, positive link between decision quality and export performance. This finding opens significant future research avenues and has very important implications for both theory and practice.

Keywords: export performance, decision quality, mixed methods, contingency theory

Procedia PDF Downloads 95

Authors: Tulio Sulbaran, Sandeep Langar

Abstract:

Architects are an integral part of the construction industry and are continuously incorporating decisions that influence projects during their life cycle. These decisions aim at selecting best alternative from the ones available. Unfortunately, this decision making process is mainly unexplored in the construction industry. No instrument to measure construction decision, based on knowledgebase of decision-makers, has existed. Additionally, limited literature is available on the topic. Recently, an instrument to gain an understanding of the construction decision-making process was developed by Dr. Tulio Sulbaran from the University of Texas, San Antonio. The instrument’s name is 'Construction Decision Making Inventory (CDMI)'. The CDMI is an innovative idea to measure the 'What? When? How? Moreover, Who?' of the construction decision-making process. As an innovative idea, its statistical validity (accuracy of the assessment) is yet to be assessed. Thus, the purpose of this paper is to describe the results of a case study with architects in the south-east of the United States aimed to determine the CDMI validity. The results of the case study are important because they assess the validity of the tool. Furthermore, as the architects evaluated each question within the measurements, this study is also guiding the enhancement of the CDMI.

Keywords: decision, support, inventory, architect

Procedia PDF Downloads 329

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, with the development of large-scale pre-trained lan-guage models, building vector representations of text through deep neural network models has become a standard practice for natural language processing tasks. From the performance on downstream tasks, we can know that the text representation constructed by these models contains linguistic information, but its encoding mode and extent are unclear. In this work, a structural probe is proposed to detect whether the vector representation produced by a deep neural network is embedded with a syntax tree. The probe is trained with the deep metric learning method, so that the distance between word vectors in the metric space it defines encodes the distance of words on the syntax tree, and the norm of word vectors encodes the depth of words on the syntax tree. The experiment results on ELMo and BERT show that the syntax tree is encoded in their parameters and the word representations they produce.

Keywords: deep metric learning, syntax tree probing, natural language processing, word representations

Procedia PDF Downloads 68

Authors: Doyin Afolabi, Phillip Adewole, Oladipupo Sennaike

Abstract:

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

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

Procedia PDF Downloads 137

Authors: Arwa Khannoussi, Alexandru-Liviu Olteanu, Pritesh Narayan, Catherine Dezan, Jean-Philippe Diguet, Patrick Meyer, Jacques Petit-Frere

Abstract:

Due to the nature of autonomous Unmanned Aerial Vehicles (UAV) missions, it is important that the decisions of a UAV stay consistent with the priorities of an operator, while at the same time allowing them to be easily audited and explained. We propose a multi-layer decision engine that integrates the operator (human) preferences by using the Multi-Criteria Decision Aiding (MCDA) methods. A software implementation of a UAV simulator and of the decision engine is presented to highlight the advantage of using such techniques on high-level decisions. We demonstrate that, with such a preference-based decision engine, the decisions of the UAV are compatible with the priorities of the operator, which in turn increases her/his confidence in its autonomous behavior.

Keywords: autonomous UAV, multi-criteria decision aiding, multi-layers decision engine, operator's preferences, traceable decisions, UAV simulation

Procedia PDF Downloads 256

Authors: S. Sabatino, V. Calderaro, V. Galdi, G. Graber, L. Ippolito

Abstract:

Climate change is a rapidly growing global threat caused mainly by increased emissions of carbon dioxide (CO₂) into the atmosphere. These emissions come from multiple sources, including industry, power generation, and the transport sector. The need to tackle climate change and reduce CO₂ emissions is indisputable. A crucial solution to achieving decarbonization in the transport sector is the adoption of electric vehicles (EVs). These vehicles use lithium (Li-Ion) batteries as an energy source, making them extremely efficient and with low direct emissions. However, Li-Ion batteries are not without problems, including the risk of overheating and performance degradation. To ensure its safety and longevity, it is essential to use a battery management system (BMS). The BMS constantly monitors battery status, adjusts temperature and cell balance, ensuring optimal performance and preventing dangerous situations. From the monitoring carried out, it is also able to optimally manage the battery to increase its life. Among the parameters monitored by the BMS, the main ones are State of Charge (SoC), State of Health (SoH), and State of Power (SoP). The evaluation of these parameters can be carried out in two ways: offline, using benchtop batteries tested in the laboratory, or online, using batteries installed in moving vehicles. Online estimation is the preferred approach, as it relies on capturing real-time data from batteries while operating in real-life situations, such as in everyday EV use. Actual battery usage conditions are highly variable. Moving vehicles are exposed to a wide range of factors, including temperature variations, different driving styles, and complex charge/discharge cycles. This variability is difficult to replicate in a controlled laboratory environment and can greatly affect performance and battery life. Online estimation captures this variety of conditions, providing a more accurate assessment of battery behavior in real-world situations. In this article, a hybrid approach based on a neural network and a statistical method for real-time estimation of SoC, SoH, and SoP parameters of interest is proposed. These parameters are estimated from the analysis of a one-day driving profile of an electric vehicle, assumed to be divided into the following four phases: (i) Partial discharge (SoC 100% - SoC 50%), (ii) Partial discharge (SoC 50% - SoC 80%), (iii) Deep Discharge (SoC 80% - SoC 30%) (iv) Full charge (SoC 30% - SoC 100%). The neural network predicts the values of ohmic resistance and incremental capacity, while the statistical method is used to estimate the parameters of interest. This reduces the complexity of the model and improves its prediction accuracy. The effectiveness of the proposed model is evaluated by analyzing its performance in terms of square mean error (RMSE) and percentage error (MAPE) and comparing it with the reference method found in the literature.

Keywords: electric vehicle, Li-Ion battery, BMS, state-of-charge, state-of-health, state-of-power, artificial neural networks

Procedia PDF Downloads 67