Search results for: intelligent algorithms

Authors: Sara ElElimy, Samir Moustafa

Abstract:

Mobile network operators start to face many challenges in the digital era, especially with high demands from customers. Since mobile network operators are considered a source of big data, traditional techniques are not effective with new era of big data, Internet of things (IoT) and 5G; as a result, handling effectively different big datasets becomes a vital task for operators with the continuous growth of data and moving from long term evolution (LTE) to 5G. So, there is an urgent need for effective Big data analytics to predict future demands, traffic, and network performance to full fill the requirements of the fifth generation of mobile network technology. In this paper, we introduce data science techniques using machine learning and deep learning algorithms: the autoregressive integrated moving average (ARIMA), Bayesian-based curve fitting, and recurrent neural network (RNN) are employed for a data-driven application to mobile network operators. The main framework included in models are identification parameters of each model, estimation, prediction, and final data-driven application of this prediction from business and network performance applications. These models are applied to Telecom Italia Big Data challenge call detail records (CDRs) datasets. The performance of these models is found out using a specific well-known evaluation criteria shows that ARIMA (machine learning-based model) is more accurate as a predictive model in such a dataset than the RNN (deep learning model).

Keywords: big data analytics, machine learning, CDRs, 5G

Procedia PDF Downloads 113

Authors: Shohreh Ghasemi

Abstract:

Introduction: Melanoma is a complex disease with various clinical and histopathological features that impact prognosis and treatment decisions. Traditional methods of melanoma prognosis involve manual examination and interpretation of clinical and histopathological data by dermatologists and pathologists. However, the subjective nature of these assessments can lead to inter-observer variability and suboptimal prognostic accuracy. AI, with its ability to analyze vast amounts of data and identify patterns, has emerged as a promising tool for improving melanoma prognosis. Methods: A comprehensive literature search was conducted to identify studies that employed AI techniques for melanoma prognosis. The search included databases such as PubMed and Google Scholar, using keywords such as "artificial intelligence," "melanoma," and "prognosis." Studies published between 2010 and 2022 were considered. The selected articles were critically reviewed, and relevant information was extracted. Results: The review identified various AI methodologies utilized in melanoma prognosis, including machine learning algorithms, deep learning techniques, and computer vision. These techniques have been applied to diverse data sources, such as clinical images, dermoscopy images, histopathological slides, and genetic data. Studies have demonstrated the potential of AI in accurately predicting melanoma prognosis, including survival outcomes, recurrence risk, and response to therapy. AI-based prognostic models have shown comparable or even superior performance compared to traditional methods.

Keywords: artificial intelligence, melanoma, accuracy, prognosis prediction, image analysis, personalized medicine

Procedia PDF Downloads 51

Authors: Dong Seop Lee, Byung Sik Kim

Abstract:

In the 4th Industrial Revolution, various intelligent technologies have been developed in many fields. These artificial intelligence technologies are applied in various services, including disaster management. Disaster information management does not just support disaster work, but it is also the foundation of smart disaster management. Furthermore, it gets historical disaster information using artificial intelligence technology. Disaster information is one of important elements of entire disaster cycle. Disaster information management refers to the act of managing and processing electronic data about disaster cycle from its’ occurrence to progress, response, and plan. However, information about status control, response, recovery from natural and social disaster events, etc. is mainly managed in the structured and unstructured form of reports. Those exist as handouts or hard-copies of reports. Such unstructured form of data is often lost or destroyed due to inefficient management. It is necessary to manage unstructured data for disaster information. In this paper, the Optical Character Recognition approach is used to convert handout, hard-copies, images or reports, which is printed or generated by scanners, etc. into electronic documents. Following that, the converted disaster data is organized into the disaster code system as disaster information. Those data are stored in the disaster database system. Gathering and creating disaster information based on Optical Character Recognition for unstructured data is important element as realm of the smart disaster management. In this paper, Korean characters were improved to over 90% character recognition rate by using upgraded OCR. In the case of character recognition, the recognition rate depends on the fonts, size, and special symbols of character. We improved it through the machine learning algorithm. These converted structured data is managed in a standardized disaster information form connected with the disaster code system. The disaster code system is covered that the structured information is stored and retrieve on entire disaster cycle such as historical disaster progress, damages, response, and recovery. The expected effect of this research will be able to apply it to smart disaster management and decision making by combining artificial intelligence technologies and historical big data.

Keywords: disaster information management, unstructured data, optical character recognition, machine learning

Procedia PDF Downloads 101

Authors: Mustapha Ouardouz, Mina Amharref, Abdessamed Bernoussi

Abstract:

The future energy, for limited energy resources countries, goes through renewable energies (solar, wind etc.). The renewable energies constitute a major component of the energy strategy to cover a substantial part of the growing needs and contribute to environmental protection by replacing fossil fuels. Indeed, sustainable development involves the promotion of renewable energy and the preservation of the environment by the use of clean energy technologies to limit emissions of greenhouse gases and reducing the pressure exerted on the forest cover. So the impact studies, of the energy use on the environment and farm-related risks are necessary. For that, a global approach integrating all the various sectors involved in such project seems to be the best approach. In this paper we present an approach based on the multi criteria analysis and the realization of one pilot to achieve the development of an innovative geo-intelligent environmental platform. An implementation of this platform will collect, process, analyze and manage environmental data in connection with the nature of used energy in the studied region. As an application we consider a region in the north of Morocco characterized by intense agricultural and industrials activities and using diverse renewable energy. The strategic goals of this platform are; the decision support for better governance, improving the responsiveness of public and private companies connected by providing them in real time with reliable data, modeling and simulation possibilities of energy scenarios, the identification of socio-technical solutions to introduce renewable energies and estimate technical and implantable potential by socio-economic analyzes and the assessment of infrastructure for the region and the communities, the preservation and enhancement of natural resources for better citizenship governance through democratization of access to environmental information, the tool will also perform simulations integrating environmental impacts of natural disasters, particularly those linked to climate change. Indeed extreme cases such as floods, droughts and storms will be no longer rare and therefore should be integrated into such projects.

Keywords: renewable energies, decision aided tool, environment, simulation

Procedia PDF Downloads 437

Authors: Ming-Jyh Chen, Wen-Ming Huang, Yi-Chu Liu, Li-Hui Yang

Abstract:

Introduction: Social responsibility is the key to sustainable organizational development. Under the ground Green Health Hospital Declaration signed by our superintendent, we have launched comprehensive energy conservation management in medical services, the community, and the staff’s life. To execute environment-friendly promotion with robust strategies, we build up a low-carbon medical system and community with smart green public construction promotion as well as intensifying energy conservation education and communication. Purpose/Methods: With the support of the board and the superintendent, we construct an energy management team, commencing with an environment-friendly system, management, education, and ISO 50001 energy management system; we have ameliorated energy performance and energy efficiency and continuing. Results: In the year 2021, we have achieved multiple goals. The energy management system efficiently controls diesel, natural gas, and electricity usage. About 5% of the consumption is saved when compared to the numbers from 2018 and 2021. Our company develops intelligent services and promotes various paperless electronic operations to provide people with a vibrant and environmentally friendly lifestyle. The goal is to save 68.6% on printing and photocopying by reducing 35.15 million sheets of paper yearly. We strengthen the concept of environmental protection classification among colleagues. In the past two years, the amount of resource recycling has reached more than 650 tons, and the resource recycling rate has reached 70%. The annual growth rate of waste recycling is about 28 metric tons. Conclusions: To build a green medical system with “high efficacy, high value, low carbon, low reliance,” energy stewardship, economic prosperity, and social responsibility are our principles when it comes to formulation of energy conservation management strategies, converting limited sources to efficient usage, developing clean energy, and continuing with sustainable energy.

Keywords: energy efficiency, environmental education, green hospital, sustainable development

Procedia PDF Downloads 54

Authors: Ahlem Bouziri, Chiraz Latiri, Eric Gaussier

Abstract:

The steady growth in the size of textual document collections is a key progress-driver for modern information retrieval techniques whose effectiveness and efficiency are constantly challenged. Given a user query, the number of retrieved documents can be overwhelmingly large, hampering their efficient exploitation by the user. In addition, retaining only relevant documents in a query answer is of paramount importance for an effective meeting of the user needs. In this situation, the query expansion technique offers an interesting solution for obtaining a complete answer while preserving the quality of retained documents. This mainly relies on an accurate choice of the added terms to an initial query. Interestingly enough, query expansion takes advantage of large text volumes by extracting statistical information about index terms co-occurrences and using it to make user queries better fit the real information needs. In this respect, a promising track consists in the application of data mining methods to extract dependencies between terms, namely a generic basis of association rules between terms. The key feature of our approach is a better trade off between the size of the mining result and the conveyed knowledge. Thus, face to the huge number of derived association rules and in order to select the optimal combination of query terms from the generic basis, we propose to model the problem as a classification problem and solve it using a supervised learning algorithm such as SVM or k-means. For this purpose, we first generate a training set using a genetic algorithm based approach that explores the association rules space in order to find an optimal set of expansion terms, improving the MAP of the search results. The experiments were performed on SDA 95 collection, a data collection for information retrieval. It was found that the results were better in both terms of MAP and NDCG. The main observation is that the hybridization of text mining techniques and query expansion in an intelligent way allows us to incorporate the good features of all of them. As this is a preliminary attempt in this direction, there is a large scope for enhancing the proposed method.

Keywords: supervised leaning, classification, query expansion, association rules

Procedia PDF Downloads 302

Authors: Rihab Idoudi, Karim Saheb Ettabaa, Basel Solaiman, Kamel Hamrouni

Abstract:

Medical association rules induction is used to discover useful correlations between pertinent concepts from large medical databases. Nevertheless, ARs algorithms produce huge amount of delivered rules and do not guarantee the usefulness and interestingness of the generated knowledge. To overcome this drawback, we propose an ontology based interestingness measure for ARs ranking. According to domain expert, the goal of the use of ARs is to discover implicit relationships between items of different categories such as ‘clinical features and disorders’, ‘clinical features and radiological observations’, etc. That’s to say, the itemsets which are composed of ‘similar’ items are uninteresting. Therefore, the dissimilarity between the rule’s items can be used to judge the interestingness of association rules; the more different are the items, the more interesting the rule is. In this paper, we design a distinct approach for ranking semantically interesting association rules involving the use of an ontology knowledge mining approach. The basic idea is to organize the ontology’s concepts into a hierarchical structure of conceptual clusters of targeted subjects, where each cluster encapsulates ‘similar’ concepts suggesting a specific category of the domain knowledge. The interestingness of association rules is, then, defined as the dissimilarity between corresponding clusters. That is to say, the further are the clusters of the items in the AR, the more interesting the rule is. We apply the method in our domain of interest – mammographic domain- using an existing mammographic ontology called Mammo with the goal of deriving interesting rules from past experiences, to discover implicit relationships between concepts modeling the domain.

Keywords: association rule, conceptual clusters, interestingness measures, ontology knowledge mining, ranking

Procedia PDF Downloads 301

Authors: Yulin Rao, Zhixuan Li, Burra Venkata Durga Kumar

Abstract:

Intrusion detection refers to monitoring the actions of internal and external intruders on the system and detecting the behaviours that violate security policies in real-time. In intrusion detection, there has been much discussion about the application of neural network technology and artificial immune system (AIS). However, many solutions use static methods (signature-based and stateful protocol analysis) or centralized intrusion detection systems (CIDS), which are unsuitable for real-time intrusion detection systems that need to process large amounts of data and detect unknown intrusions. This article proposes a framework for a distributed intrusion detection system (DIDS) with multi-agents based on the concept of AIS and neural network technology to detect anomalies and intrusions. In this framework, multiple agents are assigned to each host and work together, improving the system's detection efficiency and robustness. The trainer agent in the central server of the framework uses the artificial neural network (ANN) rather than the negative selection algorithm of AIS to generate mature detectors. Mature detectors can distinguish between self-files and non-self-files after learning. Our analyzer agents use genetic algorithms to generate memory cell detectors. This kind of detector will effectively reduce false positive and false negative errors and act quickly on known intrusions.

Keywords: artificial immune system, distributed artificial intelligence, multi-agent, intrusion detection system, neural network

Procedia PDF Downloads 83

Authors: Nishant Rodrigues, Nicole Spanedda, Chilukuri K. Mohan, Arindam Chakraborty

Abstract:

A crucial objective in quantum chemistry is the computation of the energy levels of chemical systems. This task requires electron-repulsion integrals as inputs, and the steep computational cost of evaluating these integrals poses a major numerical challenge in efficient implementation of quantum chemical software. This work presents a moment-based machine-learning approach for the efficient evaluation of electron-repulsion integrals. These integrals were approximated using linear combinations of a small number of moments. Machine learning algorithms were applied to estimate the coefficients in the linear combination. A random forest approach was used to identify promising features using a recursive feature elimination approach, which performed best for learning the sign of each coefficient but not the magnitude. A neural network with two hidden layers were then used to learn the coefficient magnitudes along with an iterative feature masking approach to perform input vector compression, identifying a small subset of orbitals whose coefficients are sufficient for the quantum state energy computation. Finally, a small ensemble of neural networks (with a median rule for decision fusion) was shown to improve results when compared to a single network.

Keywords: quantum energy calculations, atomic orbitals, electron-repulsion integrals, ensemble machine learning, random forests, neural networks, feature extraction

Procedia PDF Downloads 79

Authors: Hilal Naimi, Amelbahahouda Adamou-Mitiche, Lahcene Mitiche

Abstract:

The main problem in the area of medical imaging has been image denoising. The most defying for image denoising is to secure data carrying structures like surfaces and edges in order to achieve good visual quality. Different algorithms with different denoising performances have been proposed in previous decades. More recently, models focused on deep learning have shown a great promise to outperform all traditional approaches. However, these techniques are limited to the necessity of large sample size training and high computational costs. This research proposes a denoising approach basing on LDTCWT (Lifting Dual Tree Complex Wavelet Transform) using Hybrid Thresholding with Wiener filter to enhance the quality image. This research describes the LDTCWT as a type of lifting wavelets remodeling that produce complex coefficients by employing a dual tree of lifting wavelets filters to get its real part and imaginary part. Permits the remodel to produce approximate shift invariance, directionally selective filters and reduces the computation time (properties lacking within the classical wavelets transform). To develop this approach, a hybrid thresholding function is modeled by integrating the Wiener filter into the thresholding function.

Keywords: lifting wavelet transform, image denoising, dual tree complex wavelet transform, wavelet shrinkage, wiener filter

Procedia PDF Downloads 137

Authors: Werner Grommes

Abstract:

The institute of occupational safety and health works in a working group for building a normative standard for illuminated warning vests and did a lot of experiments and measurements as basic work (cooperation). Intelligent car headlamps are able to suppress conventional warning vests with retro-reflective stripes as a disturbing light. Illuminated warning vests are therefore required for occupational safety. However, they must not pose any danger to the wearer or other persons. Here, the risks of the batteries (lithium types), the maximum brightness (glare) and possible interference radiation from the electronics on the implant carrier must be taken into account. The all-around visibility, as well as the required range, play an important role here. For the study, many luminance measurements of already commercially available LEDs and electroluminescent warning vests, as well as their electromagnetic interference fields and aspects of electrical safety, were measured. The results of this study showed that LED lighting is all far too bright and causes strong glare. The integrated controls with pulse modulation and switching regulators cause electromagnetic interference fields. Rechargeable lithium batteries can explode depending on the temperature range. Electroluminescence brings even more hazards. A test method was developed for the evaluation of visibility at distances of 50, 100, and 150 m, including the interview of test persons. A measuring method was developed for the detection of glare effects at close range with the assignment of the maximum permissible luminance. The electromagnetic interference fields were tested in the time and frequency ranges. A risk and hazard analysis were prepared for the use of lithium batteries. The range of values for luminance and risk analysis for lithium batteries were discussed in the standards working group. These will be integrated into the standard. This paper gives a brief overview of the topics of illuminated warning vests, which takes into account the risks and hazards for the vest wearer or others

Keywords: illuminated warning vest, optical tests and measurements, risks, hazards, optical glare effects, LED, E-light, electric luminescent

Procedia PDF Downloads 92

Authors: Abobaker Mohammed Qasem Farhan, Shangming Yang, Mohammed Al-Nehari

Abstract:

Pneumonia is a kind of lung disease that creates congestion in the chest. Such pneumonic conditions lead to loss of life of the severity of high congestion. Pneumonic lung disease is caused by viral pneumonia, bacterial pneumonia, or Covidi-19 induced pneumonia. The early prediction and classification of such lung diseases help to reduce the mortality rate. We propose the automatic Computer-Aided Diagnosis (CAD) system in this paper using the deep learning approach. The proposed CAD system takes input from raw computerized tomography (CT) scans of the patient's chest and automatically predicts disease classification. We designed the Hybrid Deep Learning Algorithm (HDLA) to improve accuracy and reduce processing requirements. The raw CT scans have pre-processed first to enhance their quality for further analysis. We then applied a hybrid model that consists of automatic feature extraction and classification. We propose the robust 2D Convolutional Neural Network (CNN) model to extract the automatic features from the pre-processed CT image. This CNN model assures feature learning with extremely effective 1D feature extraction for each input CT image. The outcome of the 2D CNN model is then normalized using the Min-Max technique. The second step of the proposed hybrid model is related to training and classification using different classifiers. The simulation outcomes using the publically available dataset prove the robustness and efficiency of the proposed model compared to state-of-art algorithms.

Keywords: CT scan, Covid-19, deep learning, image processing, lung disease classification

Procedia PDF Downloads 115

Authors: Zhu Weimin, Allegorico Carmine, Ruggiero Gionata

Abstract:

During decades of Baker Hughes (BH) iCenter experience, it is demonstrated that in addition to conventional insights on equipment steady operation conditions, insights on transient conditions can add significant and exclusive value for anomaly detection, downtime saving, and predictive maintenance. Our work shows examples from the BH iCenter experience to introduce the advantages and features of using transient condition analytics: (i) Operation under critical engine conditions: e.g., high level or high change rate of temperature, pressure, flow, vibration, etc., that would not be reachable in normal operation, (ii) Management of dedicated sub-systems or components, many of which are often bottlenecks for reliability and maintenance, (iii) Indirect detection of anomalies in the absence of instrumentation, (iv) Repetitive sequences: if data is properly processed, the engineering features of transients provide not only anomaly detection but also problem characterization and prognostic indicators for predictive maintenance, (v) Engine variables accounting for fatigue analysis. iCenter has been developing and deploying a series of analytics based on transient conditions. They are contributing to exclusive value adding in the following areas: (i) Reliability improvement, (ii) Startup reliability improvement, (iii) Predictive maintenance, (iv) Repair/overhaul cost down. Illustrative examples for each of the above areas are presented in our study, focusing on challenges and adopted techniques ranging from purely statistical approaches to the implementation of machine learning algorithms. The obtained results demonstrate how the value is obtained using transient condition analytics in the BH iCenter experience.

Keywords: analytics, diagnostics, monitoring, turbomachinery

Procedia PDF Downloads 51

Authors: Anastasios Papathanasiou, George Liontos, Athanasios Katsouras, Vasiliki Liagkou, Euripides Glavas

Abstract:

Email remains a crucial communication tool due to its efficiency, accessibility and cost-effectiveness, enabling rapid information exchange across global networks. However, the global adoption of email has also made it a prime target for cyber threats, including phishing, malware and Business Email Compromise (BEC) attacks, which exploit its integral role in personal and professional realms in order to perform fraud and data breaches. To combat these threats, this research advocates for a multi-layered defense strategy incorporating advanced technological tools such as anti-spam and anti-malware software, machine learning algorithms and authentication protocols. Moreover, we developed an artificial intelligence model specifically designed to analyze email headers and assess their security status. This AI-driven model examines various components of email headers, such as "From" addresses, ‘Received’ paths and the integrity of SPF, DKIM and DMARC records. Upon analysis, it generates comprehensive reports that indicate whether an email is likely to be malicious or benign. This capability empowers users to identify potentially dangerous emails promptly, enhancing their ability to avoid phishing attacks, malware infections and other cyber threats.

Keywords: email security, artificial intelligence, header analysis, threat detection, phishing, DMARC, DKIM, SPF, ai model

Procedia PDF Downloads 18

Authors: Hasan Basaran, Emre Unal

Abstract:

Formation flying of satellites is a mission that involves a relative position keeping of different satellites in the constellation. In this study, different control algorithms are compared with one another in terms of ΔV, velocity increment, and tracking error. Various control methods, covering continuous and impulsive approaches are implemented and tested for satellites flying in low Earth orbit. Feedback linearization, sliding mode control, and model predictive control are designed and compared with an impulsive feedback law, which is based on mean orbital elements. Feedback linearization and sliding mode control approaches have identical mathematical models that include second order Earth oblateness effects. The model predictive control, on the other hand, does not include any perturbations and assumes circular chief orbit. The comparison is done with 4 different initial errors and achieved with velocity increment, root mean square error, maximum steady state error, and settling time. It was observed that impulsive law consumed the least ΔV, while produced the highest maximum error in the steady state. The continuous control laws, however, consumed higher velocity increments and produced lower amounts of tracking errors. Finally, the inversely proportional relationship between tracking error and velocity increment was established.

Keywords: chief-deputy satellites, feedback linearization, follower-leader satellites, formation flight, fuel consumption, model predictive control, rendezvous, sliding mode

Procedia PDF Downloads 79

Authors: Rob van den Dam

Abstract:

Today’s Internet of Things (IoT) comprises more than a billion intelligent devices, connected via wired/wireless communications. The expected proliferation of hundreds of billions more places us at the threshold of a transformation sweeping across the communications industry. Yet, we found that the IoT architecture and solutions that currently work for billions of devices won’t necessarily scale to tomorrow’s hundreds of billions of devices because of high cost, lack of privacy, not future-proof, lack of functional value and broken business models. As the IoT scales exponentially, decentralized networks have the potential to reduce infrastructure and maintenance costs to manufacturers. Decentralization also promises increased robustness by removing single points of failure that could exist in traditional centralized networks. By shifting the power in the network from the center to the edges, devices gain greater autonomy and can become points of transactions and economic value creation for owners and users. To validate the underlying technology vision, IBM jointly developed with Samsung Electronics the autonomous decentralized peer-to- peer proof-of-concept (PoC). The primary objective of this PoC was to establish a foundation on which to demonstrate several capabilities that are fundamental to building a decentralized IoT. Though many commercial systems in the future will exist as hybrid centralized-decentralized models, the PoC demonstrated a fully distributed proof. The PoC (a) validated the future vision for decentralized systems to extensively augment today’s centralized solutions, (b) demonstrated foundational IoT tasks without the use of centralized control, (c) proved that empowered devices can engage autonomously in marketplace transactions. The PoC opens the door for the communications and electronics industry to further explore the challenges and opportunities of potential hybrid models that can address the complexity and variety of requirements posed by the internet that continues to scale. Contents: (a) The new approach for an IoT that will be secure and scalable, (b) The three foundational technologies that are key for the future IoT, (c) The related business models and user experiences, (d) How such an IoT will create an 'Economy of Things', (e) The role of users, devices, and industries in the IoT future, (f) The winners in the IoT economy.

Keywords: IoT, internet, wired, wireless

Procedia PDF Downloads 314

Authors: Ekin Nurbaş

Abstract:

One of the essential challenges in array signal processing, which has drawn enormous research interest over the past several decades, is estimating the direction of arrival (DOA) of plane waves impinging on an array of sensors. In recent years, the Compressive Sensing based DoA estimation methods have been proposed by researchers, and it has been discovered that the Compressive Sensing (CS)-based algorithms achieved significant performances for DoA estimation even in scenarios where there are multiple coherent sources. On the other hand, the Genetic Algorithm, which is a method that provides a solution strategy inspired by natural selection, has been used in sparse representation problems in recent years and provides significant improvements in performance. With all of those in consideration, in this paper, a method that combines the Genetic Algorithm (GA) and the Multi-Criteria Decision Making (MCDM) approaches for Direction of Arrival (DoA) estimation in the Compressive Sensing (CS) framework is proposed. In this method, we generate a multi-objective optimization problem by splitting the norm minimization and reconstruction loss minimization parts of the Compressive Sensing algorithm. With the help of the Genetic Algorithm, multiple non-dominated solutions are achieved for the defined multi-objective optimization problem. Among the pareto-frontier solutions, the final solution is obtained with the multiple MCDM methods. Moreover, the performance of the proposed method is compared with the CS-based methods in the literature.

Keywords: genetic algorithm, direction of arrival esitmation, multi criteria decision making, compressive sensing

Procedia PDF Downloads 116

Authors: Virender Singh, Mathew Rees, Simon Hampton, Sivaram Annadurai

Abstract:

Plant identification is a challenging task that aims to identify the family, genus, and species according to plant morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users narrow down the possibilities. However, numerous morphological similarities between and within species render correct classification difficult. In this paper, we tested custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88,000 provided by the Royal Horticultural Society (RHS) and a smaller dataset of 16,000 images from the PlantClef 2015 dataset for classifying plants at genus and species levels, respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420 and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. For classifying plants at the species level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success. In conclusion, these results could help end users, professionals and the general public alike in identifying plants quicker and with improved accuracy.

Keywords: plant identification, CNN, image processing, vision transformer, classification

Procedia PDF Downloads 68

Authors: Jameela Ali, Hamid A. Jalab, Loay E. George, Abdul Rahim Ahmad, Azizah Suliman, Karim Al-Jashamy

Abstract:

Red blood cells (RBC) are the most common types of blood cells and are the most intensively studied in cell biology. The lack of RBCs is a condition in which the amount of hemoglobin level is lower than normal and is referred to as “anemia”. Abnormalities in RBCs will affect the exchange of oxygen. This paper presents a comparative study for various techniques for classifying the RBCs as normal, or abnormal (anemic) using WEKA. WEKA is an open source consists of different machine learning algorithms for data mining applications. The algorithm tested are Radial Basis Function neural network, Support vector machine, and K-Nearest Neighbors algorithm. Two sets of combined features were utilized for classification of blood cells images. The first set, exclusively consist of geometrical features, was used to identify whether the tested blood cell has a spherical shape or non-spherical cells. While the second set, consist mainly of textural features was used to recognize the types of the spherical cells. We have provided an evaluation based on applying these classification methods to our RBCs image dataset which were obtained from Serdang Hospital-alaysia, and measuring the accuracy of test results. The best achieved classification rates are 97%, 98%, and 79% for Support vector machines, Radial Basis Function neural network, and K-Nearest Neighbors algorithm respectively.

Keywords: K-nearest neighbors algorithm, radial basis function neural network, red blood cells, support vector machine

Procedia PDF Downloads 383

Authors: Abdelkader Elhanaoui, Mhamed Hadji, Rachid Skouri, Said Agounad

Abstract:

The purpose of this paper is to study the phenomenon of acoustic scattering by using a new method. The signal processing (Fast Fourier Transform FFT Inverse Fast Fourier Transform iFFT and BESSEL functions) is widely applied to obtain information with high precision accuracy. Signal processing has a wider implementation in general-purpose pro-cessors. Our interest was focused on the use of FPGAs (Field-Programmable Gate Ar-rays) in order to minimize the computational complexity in single processor architecture, then be accelerated on FPGA and meet real-time and energy efficiency requirements. Gen-eral-purpose processors are not efficient for signal processing. We implemented the acous-tic backscattered signal processing model on the Altera DE-SOC board and compared it to Odroid xu4. By comparison, the computing latency of Odroid xu4 and FPGA is 60 sec-onds and 3 seconds, respectively. The detailed SoC FPGA-based system has shown that acoustic spectra are performed up to 20 times faster than the Odroid xu4 implementation. FPGA-based system of processing algorithms is realized with an absolute error of about 10⁻³. This study underlines the increasing importance of embedded systems in underwater acoustics, especially in non-destructive testing. It is possible to obtain information related to the detection and characterization of submerged cells. So we have achieved good exper-imental results in real-time and energy efficiency.

Keywords: DE1 FPGA, acoustic scattering, form function, signal processing, non-destructive testing

Procedia PDF Downloads 53

Authors: Soumya Sajjan

Abstract:

Liver cancer is the most common cancer disease worldwide in men and women, and is one of the few cancers still on the rise. Liver disease is the 4th leading cause of death. According to new NHS (National Health Service) figures, deaths from liver diseases have reached record levels, rising by 25% in less than a decade; heavy drinking, obesity, and hepatitis are believed to be behind the rise. In this study, we focus on Development of Diagnostic Classifier for Ultrasound liver lesion. Ultrasound (US) Sonography is an easy-to-use and widely popular imaging modality because of its ability to visualize many human soft tissues/organs without any harmful effect. This paper will provide an overview of underlying concepts, along with algorithms for processing of liver ultrasound images Naturaly, Ultrasound liver lesion images are having more spackle noise. Developing classifier for ultrasound liver lesion image is a challenging task. We approach fully automatic machine learning system for developing this classifier. First, we segment the liver image by calculating the textural features from co-occurrence matrix and run length method. For classification, Support Vector Machine is used based on the risk bounds of statistical learning theory. The textural features for different features methods are given as input to the SVM individually. Performance analysis train and test datasets carried out separately using SVM Model. Whenever an ultrasonic liver lesion image is given to the SVM classifier system, the features are calculated, classified, as normal and diseased liver lesion. We hope the result will be helpful to the physician to identify the liver cancer in non-invasive method.

Keywords: segmentation, Support Vector Machine, ultrasound liver lesion, co-occurance Matrix

Procedia PDF Downloads 386

Authors: Hichem Sassi

Abstract:

Pneumonia, being a respiratory infection, has garnered global attention due to its rapid transmission and relatively high mortality rates. Timely detection and treatment play a crucial role in significantly reducing mortality associated with pneumonia. Presently, X-ray diagnosis stands out as a reasonably effective method. However, the manual scrutiny of a patient's X-ray chest radiograph by a proficient practitioner usually requires 5 to 15 minutes. In situations where cases are concentrated, this places immense pressure on clinicians for timely diagnosis. Relying solely on the visual acumen of imaging doctors proves to be inefficient, particularly given the low speed of manual analysis. Therefore, the integration of artificial intelligence into the clinical image diagnosis of pneumonia becomes imperative. Additionally, AI recognition is notably rapid, with convolutional neural networks (CNNs) demonstrating superior performance compared to human counterparts in image identification tasks. To conduct our study, we utilized a dataset comprising chest X-ray images obtained from Kaggle, encompassing a total of 5216 training images and 624 test images, categorized into two classes: normal and pneumonia. Employing five mainstream network algorithms, we undertook a comprehensive analysis to classify these diseases within the dataset, subsequently comparing the results. The integration of artificial intelligence, particularly through improved network architectures, stands as a transformative step towards more efficient and accurate clinical diagnoses across various medical domains.

Keywords: deep learning, computer vision, pneumonia, models, comparative study

Procedia PDF Downloads 28

Authors: R. Hellmuth

Abstract:

The orientation of flexibility and adaptability with regard to factory planning is at machine and process level. Factory buildings are not the focus of current research. Factory planning has the task of designing products, plants, processes, organization, areas and the construction of a factory. The adaptability of a factory can be divided into three types: spatial, organizational and technical adaptability. Spatial adaptability indicates the ability to expand and reduce the size of a factory. Here, the area-related breathing capacity plays the essential role. It mainly concerns the factory site, the plant layout and the production layout. The organizational ability to change enables the change and adaptation of organizational structures and processes. This includes structural and process organization as well as logistical processes and principles. New and reconfigurable operating resources, processes and factory buildings are referred to as technical adaptability. These three types of adaptability can be regarded independently of each other as undirected potentials of different characteristics. If there is a need for change, the types of changeability in the change process are combined to form a directed, complementary variable that makes change possible. When planning adaptability, importance must be attached to a balance between the types of adaptability. The vision of the intelligent factory building and the 'Internet of Things' presupposes the comprehensive digitalization of the spatial and technical environment. Through connectivity, the factory building must be empowered to support a company's value creation process by providing media such as light, electricity, heat, refrigeration, etc. In the future, communication with the surrounding factory building will take place on a digital or automated basis. In the area of industry 4.0, the function of the building envelope belongs to secondary or even tertiary processes, but these processes must also be included in the communication cycle. An integrative view of a continuous communication of primary, secondary and tertiary processes is currently not yet available and is being developed with the aid of methods in this research work. A comparison of the digital twin from the point of view of production and the factory building will be developed. Subsequently, a tool will be elaborated to classify digital twins from the perspective of data, degree of visualization, and the trades. Thus a contribution is made to better integrate the secondary and tertiary processes in a factory into the added value.

Keywords: adaptability, digital factory twin, factory planning, industry 4.0

Procedia PDF Downloads 133

Authors: Yazan Al-Kofahi, Jamal Alqawasmi.

Abstract:

In this study, a comprehensive literature review (SLR) was conducted, with the main goal of assessing the existing literature about how artificial intelligence (AI), machine learning (ML), deep learning (DL) models are used in sustainable architecture applications and issues including thermal comfort satisfaction, energy efficiency, cost prediction and many others issues. For this reason, the search strategy was initiated by using different databases, including Scopus, Springer and Google Scholar. The inclusion criteria were used by two research strings related to DL, ML and sustainable architecture. Moreover, the timeframe for the inclusion of the papers was open, even though most of the papers were conducted in the previous four years. As a paper filtration strategy, conferences and books were excluded from database search results. Using these inclusion and exclusion criteria, the search was conducted, and a sample of 59 papers was selected as the final included papers in the analysis. The data extraction phase was basically to extract the needed data from these papers, which were analyzed and correlated. The results of this SLR showed that there are many applications of ML and DL in Sustainable buildings, and that this topic is currently trendy. It was found that most of the papers focused their discussions on addressing Environmental Sustainability issues and factors using machine learning predictive models, with a particular emphasis on the use of Decision Tree algorithms. Moreover, it was found that the Random Forest repressor demonstrates strong performance across all feature selection groups in terms of cost prediction of the building as a machine-learning predictive model.

Keywords: machine learning, deep learning, artificial intelligence, sustainable building

Procedia PDF Downloads 36

Authors: Junbeom Lee, Jaehyuck Cho, Wookyeong Jeong, Jonghan Won, Jungmin Hwang, Youngseok Song, Taikyeong Jeong

Abstract:

This paper investigates and analyzes meta-learning technologies that use multiple-cameras to monitor and check abnormal behavior in people in real-time in the area of healthcare fields. Advances in artificial intelligence and computer vision technologies have confirmed that cameras can be useful for individual health monitoring and abnormal behavior detection. Through this, it is possible to establish a system that can respond early by automatically detecting abnormal behavior of the elderly, such as patients and the elderly. In this paper, we use a technique called meta-learning to analyze image data collected from cameras and develop a commercial product to determine abnormal behavior. Meta-learning applies machine learning algorithms to help systems learn and adapt quickly to new real data. Through this, the accuracy and reliability of the abnormal behavior discrimination system can be improved. In addition, this study proposes a meta-learning-based abnormal behavior detection system that includes steps such as data collection and preprocessing, feature extraction and selection, and classification model development. Various healthcare scenarios and experiments analyze the performance of the proposed system and demonstrate excellence compared to other existing methods. Through this study, we present the possibility that camera-based meta-learning technology can be useful for monitoring and testing abnormal behavior in the healthcare area.

Keywords: artificial intelligence, abnormal behavior, early detection, health monitoring

Procedia PDF Downloads 60

Authors: Hamed Yousefi, Farnaz Mohammadi, Niloufar Mirian, Navid Amini

Abstract:

Investigating possible capacities of visual functions where adapted mechanisms can enhance the capability of sports trainees is a promising area of research, not only from the cognitive viewpoint but also in terms of unlimited applications in sports training. In this paper, the visual evoked potential (VEP) and event-related potential (ERP) signals of amateur and trained volleyball players in a pilot study were processed. Two groups of amateur and trained subjects are asked to imagine themselves in the state of receiving a ball while they are shown a simulated volleyball field. The proposed method is based on a set of time-frequency features using algorithms such as Gabor filter, continuous wavelet transform, and a multi-stage wavelet decomposition that are extracted from VEP signals that can be indicative of being amateur or trained. The linear discriminant classifier achieves the accuracy, sensitivity, and specificity of 100% when the average of the repetitions of the signal corresponding to the task is used. The main purpose of this study is to investigate the feasibility of a fast, robust, and reliable feature/model determination as a neurofeedback parameter to be utilized for improving the volleyball players’ performance. The proposed measure has potential applications in brain-computer interface technology where a real-time biomarker is needed.

Keywords: visual evoked potential, time-frequency feature extraction, short-time Fourier transform, event-related spectrum potential classification, linear discriminant analysis

Procedia PDF Downloads 113

Authors: Elham Mansouri, Asghar Mesbahi

Abstract:

Purpose: In the current study, we aimed to investigate the macroscopic and microscopic dose enhancement effect of metallic nanoparticles in interstitial brachytherapy of uterus cancer by Iodin-125 source using a nano-lattice model in MCNPX (5) and MCNP6.1 codes. Materials and methods: Based on a nano-lattice simulation model containing a radiation source and a tumor tissue with cellular compartments loaded with 7mg/g spherical nanoparticles (bismuth, gold, and gadolinium), the energy deposited by the secondary electrons in microscopic and macroscopic level was estimated. Results: The results show that the values of macroscopic DEF is higher than microscopic DEF values and the macroscopic DEF values decreases as a function of distance from the brachytherapy source surface. Also, the results revealed a remarkable discrepancy between the DEF and secondary electron spectra calculated by MCNPX (5) and MCNP6.1 codes, which could be justified by the difference in energy cut-off and electron transport algorithms of two codes. Conclusion: According to the both MCNPX (5) and MCNP6.1 outputs, it could be concluded that the presence of metallic nanoparticles in the tumor tissue of uteruscancer increases the physical effectiveness of brachytherapy by I-125 source. The results presented herein give a physical view of radiosensitization potential of different metallic nanoparticles and could be considered in design of analytical and experimental radiosensitization studies in tumor regions using various radiotherapy modalities in the presence of heavy nanomaterials.

Keywords: MCNPX, MCNP6, nanoparticle, brachytherapy

Procedia PDF Downloads 79

Authors: Timir Baran Roy, Luis Guerreiro, Ashutosh Bagchi

Abstract:

Dynamic study is important in order to design, repair and rehabilitation of structures. It has played an important role in the behavior characterization of structures; such as bridges, dams, high-rise buildings etc. There had been a substantial development in this area over the last few decades, especially in the field of dynamic identification techniques of structural systems. Frequency Domain Decomposition (FDD) and Time Domain Decomposition are most commonly used methods to identify modal parameters; such as natural frequency, modal damping, and mode shape. The focus of the present research is to study the dynamic characteristics of typical timber masonry walls commonly used in Portugal. For that purpose, a multi-storey structural prototypes of such walls have been tested on a seismic shake table at the National Laboratory for Civil Engineering, Portugal (LNEC). Signal processing has been performed of the output response, which is collected from the shaking table experiment of the prototype using accelerometers. In the present work signal processing of the output response, based on the input response has been done in two ways: FDD and Stochastic Subspace Identification (SSI). In order to estimate the values of the modal parameters, algorithms for FDD are formulated, and parametric functions for the SSI are computed. Finally, estimated values from both the methods are compared to measure the accuracy of both the techniques.

Keywords: frequency domain decomposition (fdd), modal parameters, signal processing, stochastic subspace identification (ssi), time domain decomposition

Procedia PDF Downloads 243

Authors: Kamand Bagherian, Nariman Niknejad

Abstract:

A vibration isolation technology for precise position control of a rotary system powered by two permanent magnet DC (PMDC) motors is proposed, where this system is mounted on an oscillatory frame. To achieve vibration isolation for this system, active damping and disturbance rejection (ADDR) technology is presented which introduces a cooperation of a main and an auxiliary PMDC, controlled by discrete-time sliding mode control (DTSMC) based schemes. The controller of the main actuator tracks a desired position and the auxiliary actuator simultaneously isolates the induced vibration, as its controller follows a torque trend. To determine this torque trend, a combination of two algorithms is introduced by the ADDR technology. The first torque-trend producing algorithm rejects the disturbance by counteracting the perturbation, estimated using a model-based observer. The second torque trend applies active variable damping to minimize the oscillation of the output shaft. In this practice, the presented technology is implemented on a rotary system with a pendulum attached, mounted on a linear actuator simulating an oscillation-transmitting structure. In addition, the obtained results illustrate the functionality of the proposed technology.

Keywords: active damping, discrete-time nonlinear controller, disturbance tracking algorithm, oscillation transmitting support, position control, stability robustness, vibration isolation

Procedia PDF Downloads 80

Authors: Arfan Ali Nagra, Tariq Shahzad, Meshal Alharbi, Khalid Masood Khan, Muhammad Mugees Asif, Taher M. Ghazal, Khmaies Ouahada

Abstract:

Gene selection is an essential step for the classification of microarray cancer data. Gene expression cancer data (DNA microarray) facilitates computing the robust and concurrent expression of various genes. Particle swarm optimization (PSO) requires simple operators and less number of parameters for tuning the model in gene selection. The selection of a prognostic gene with small redundancy is a great challenge for the researcher as there are a few complications in PSO based selection method. In this research, a new variant of PSO (Self-inertia weight adaptive PSO) has been proposed. In the proposed algorithm, SIW-APSO-ELM is explored to achieve gene selection prediction accuracies. This new algorithm balances the exploration capabilities of the improved inertia weight adaptive particle swarm optimization and the exploitation. The self-inertia weight adaptive particle swarm optimization (SIW-APSO) is used to search the solution. The SIW-APSO is updated with an evolutionary process in such a way that each particle iteratively improves its velocities and positions. The extreme learning machine (ELM) has been designed for the selection procedure. The proposed method has been to identify a number of genes in the cancer dataset. The classification algorithm contains ELM, K- centroid nearest neighbor (KCNN), and support vector machine (SVM) to attain high forecast accuracy as compared to the start-of-the-art methods on microarray cancer datasets that show the effectiveness of the proposed method.

Keywords: microarray cancer, improved PSO, ELM, SVM, evolutionary algorithms

Procedia PDF Downloads 58