Search results for: routing metrics

Authors: Vivian Guo, Yan Qu

Abstract:

Online marketplaces are not only digital places where consumers buy and sell merchandise, and they are also destinations for brands to connect with real consumers at the moment when customers are in the shopping mindset. For many marketplaces, brands have been important partners through advertising. There can be, however, a risk of advertising impacting a consumer’s shopping journey if it hurts the use experience or takes the user away from the site. Both could lead to the loss of transaction revenue for the marketplace. In this paper, we present user-based methods for cannibalization control by selectively turning off ads to users who are likely to be cannibalized by ads subject to business objectives. We present ways of measuring cannibalization of advertising in the context of an online marketplace and propose novel ways of measuring cannibalization through purchase propensity and uplift modeling. A/B testing has shown that our methods can significantly improve user purchase and engagement metrics while operating within business objectives. To our knowledge, this is the first paper that addresses cannibalization mitigation at the user-level in the context of advertising.

Keywords: cannibalization, machine learning, online marketplace, revenue optimization, yield optimization

Procedia PDF Downloads 142

Authors: Diana Fajardo, Sebastián Ortiz, Oscar Herrera, Angélica Santis

Abstract:

Currently, in Colombia is arising a problem related to collecting used lubricant oils which are generated by the increment of the vehicle fleet. This situation does not allow a proper disposal of this type of waste, which in turn results in a negative impact on the environment. Therefore, through the comparative analysis of various heuristics, the best solution to the VRP (Vehicle Routing Problem) was selected by comparing costs and times for the collection of used lubricant oils in the city of Pereira, Colombia; since there is no presence of management companies engaged in the direct administration of the collection of this pollutant. To achieve this aim, six proposals of through methods of solution of two phases were discussed. First, the assignment of the group of generator points of the residue was made (previously identified). Proposals one and four of through methods are based on the closeness of points. The proposals two and five are using the scanning method and the proposals three and six are considering the restriction of the capacity of collection vehicle. Subsequently, the routes were developed - in the first three proposals by the Clarke and Wright's savings algorithm and in the following proposals by the Traveling Salesman optimization mathematical model. After applying techniques, a comparative analysis of the results was performed and it was determined which of the proposals presented the most optimal values in terms of the distance, cost and travel time.

Keywords: Heuristics, optimization Model, savings algorithm, used vehicular oil, V.R.P.

Procedia PDF Downloads 399

Authors: Noah R. Fram

Abstract:

Although it has been confirmed by multiple studies, the inverted-U relationship between stimulus complexity and preference (liking) remains contentious. Research aimed at substantiating the model are largely reliant upon anecdotal self-assessments of subjects and basic measures of complexity, leaving potential confounds unresolved. This study attempts to address the topic by assessing listening time as a behavioral correlate of liking (with the assumption that engagement prolongs listening time) and by looking for latent factors underlying several measures of rhythmic complexity. Participants listened to groups of rhythms, stopping each one when they started to lose interest and were asked to rate each rhythm in each group in terms of interest, complexity, and preference. Subjects were not informed that the time spent listening to each rhythm was the primary measure of interest. The hypothesis that listening time does demonstrate the same inverted-U relationship with complexity as verbal reports of liking was confirmed using a variety of metrics for rhythmic complexity, including meter-dependent measures of syncopation and meter-independent measures of entropy.

Keywords: complexity, entropy, rhythm, syncopation

Procedia PDF Downloads 154

Authors: Ruchi Makani, B. V. R. Reddy

Abstract:

Mobile Adhoc Networks (MANETs) are gaining popularity due to their potential of providing low-cost mobile connectivity solutions to real-world communication problems. Integrating Intrusion Detection Systems (IDS) in MANETs is a tedious task by reason of its distinctive features such as dynamic topology, de-centralized authority and highly controlled/limited resource environment. IDS primarily use automated soft-computing techniques to monitor the inflow/outflow of traffic packets in a given network to detect intrusion. Use of machine learning techniques in IDS enables system to make decisions on intrusion while continuous keep learning about their dynamic environment. An appropriate IDS model is essential to be selected to expedite this application challenges. Thus, this paper focused on fuzzy-logic based machine learning IDS technique for MANETs and presented their applicability for achieving effectiveness in identifying the intrusions. Further, the selection of appropriate protocol attributes and fuzzy rules generation plays significant role for accuracy of the fuzzy-logic based IDS, have been discussed. This paper also presents the critical attributes of MANET’s routing protocol and its applicability in fuzzy logic based IDS.

Keywords: AODV, mobile adhoc networks, intrusion detection, anomaly detection, fuzzy logic, fuzzy membership function, fuzzy inference system

Procedia PDF Downloads 155

Authors: Maria Christofi, George Plastiras, Rafaella Elia, Vaggelis Tsiourtis, Theocharis Theocharides, Miltiadis Katsaros

Abstract:

The rapidly expanding urban areas of the world constitute a challenge of how we need to make the transition to "the next urbanization", which will be defined by new analytical tools and new sources of data. This paper is about the production of a spatial application, the ‘FUMapp’, where space and its initiative will be available literally, in meters, but also abstractly, at a sensed level. While existing spatial applications typically focus on illustrations of the urban infrastructure, the suggested application goes beyond the existing: It investigates how our environment's perception adapts to the alterations of the built environment through a dataset construction of biophysical measurements (eye-tracking, heart beating), and physical metrics (spatial characteristics, size of stimuli, rhythm of mobility). It explores the intersections between architecture, cognition, and computing where future design can be improved and identifies the flexibility and livability of the ‘available space’ of specific examined urban paths.

Keywords: biophysical data, flexibility of urban, livability, next urbanization, spatial application

Procedia PDF Downloads 116

Authors: Diego Roberto Goncalves De Pontes, Sergio Donizetti Zorzo

Abstract:

Studies show that most users do not read privacy policies from the online services they use. Some authors claim that one of the main causes of this is that policies are long and usually hard to understand, which make users lose interest in reading them. In this scenario, users may agree with terms without knowing what kind of data is being collected and why. Given that, we aimed to develop a model that would present the privacy policies contents in an easy and graphical way for the user to understand. We call it the Privacy Label. Using information recovery techniques, we propose an architecture that is able to extract information about what kind of data is being collected and to what end in the policies and show it to the user in an automated way. To assess our model, we calculated the precision, recall and f-measure metrics on the information extracted by our technique. The results for each metric were 68.53%, 85.61% e 76,13%, respectively, making it possible for the final user to understand which data was being collected without reading the whole policy. Also, our proposal can facilitate the notice-and-choice by presenting privacy policy information in an alternative way for online users.

Keywords: privacy, policies, user behavior, computer human interaction

Procedia PDF Downloads 286

Authors: A. O. Talabi, F. M. Taib, D. J. Jalaludin

Abstract:

The influence of sustainability reporting on Deposit Money Banks (DMBs)' financial performance both before and after mandated environmental, social, and governance (ESG) disclosure is examined in this article. Using a sample size of the top six strategically important listed banks in Nigeria, the study employed the paired sample t-test to assess the pre-mandatory ESG period (2009-2015) and the post-mandatory ESG period (2016-2022). According to the findings, there was no discernible difference between the performance of DMBs in Nigeria before and after the requirement for ESG disclosure. In the pre-mandatory requirement time, sustainability reporting is a major predictor of financial metrics, but in the post-mandatory requirement period, there was no discernible change in financial performance. Market authorities ought to have unrestricted authority to impose severe fines for noncompliance and bring legal action against corporations that fail to disclose ESG. This work contributes to the literature on ESG disclosure and financial performance by considering two different periods.

Keywords: financial, performance, sustainability, reporting

Procedia PDF Downloads 99

Authors: Naomi Grigoryan, Alexandros Loutsioli Daskalakis, Anna Elisse Uy, Yihe Huang, Aude Laurent (Webanck)

Abstract:

In response to the building and construction sectors accounting for a third of all energy demand and emissions, the European Union has placed new laws and regulations in the construction sector that emphasize material circularity, energy efficiency, biodiversity, and social impact. Existing design tools assess sustainability in early-stage design for products or buildings; however, there is no standardized methodology for measuring the circularity performance of building components. Existing assessment methods for building components focus primarily on carbon footprint but lack the comprehensive analysis required to design for circularity. The research conducted in this paper covers the parameters needed to assess sustainability in the design process of architectural products such as doors, windows, and facades. It maps a framework for a tool that assists designers with real-time sustainability metrics. Considering the life cycle of building components such as façades, windows, and doors involves the life cycle stages applied to product design and many of the methods used in the life cycle analysis of buildings. The current industry standards of sustainability assessment for metal building components follow cradle-to-grave life cycle assessment (LCA), track Global Warming Potential (GWP), and document the parameters used for an Environmental Product Declaration (EPD). Developed by the Ellen Macarthur Foundation, the Material Circularity Indicator (MCI) is a methodology utilizing the data from LCA and EPDs to rate circularity, with a "value between 0 and 1 where higher values indicate a higher circularity+". Expanding on the MCI with additional indicators such as the Water Circularity Index (WCI), the Energy Circularity Index (ECI), the Social Circularity Index (SCI), Life Cycle Economic Value (EV), and calculating biodiversity risk and uncertainty, the assessment methodology of an architectural product's impact can be targeted more specifically based on product requirements, performance, and lifespan. Broadening the scope of LCA calculation for products to incorporate aspects of building design allows product designers to account for the disassembly of architectural components. For example, the Material Circularity Indicator for architectural products such as windows and facades is typically low due to the impact of glass, as 70% of glass ends up in landfills due to damage in the disassembly process. The low MCI can be combatted by expanding beyond cradle-to-grave assessment and focusing the design process on disassembly, recycling, and repurposing with the help of real-time assessment tools. Design for Disassembly and Urban Mining has been integrated within the construction field on small scales as project-based exercises, not addressing the entire supply chain of architectural products. By adopting more comprehensive sustainability metrics and incorporating uncertainty calculations, the sustainability assessment of building components can be more accurately assessed with decarbonization and disassembly in mind, addressing the large-scale commercial markets within construction, some of the most significant contributors to climate change.

Keywords: architectural products, early-stage design, life cycle assessment, material circularity indicator

Procedia PDF Downloads 65

Authors: Adeniyi Onasanya, Maher Elshakankiri

Abstract:

In recent years, the Internet of Things (IoT) has constituted a driving force of modern technological advancement, and it has become increasingly common as its impacts are seen in a variety of application domains, including healthcare. IoT is characterized by the interconnectivity of smart sensors, objects, devices, data, and applications. With the unprecedented use of IoT in industrial, commercial and domestic, it becomes very imperative to harness the benefits and functionalities associated with the IoT technology in (re)assessing the provision and positioning of healthcare to ensure efficient and improved healthcare delivery. In this research, we are focusing on two important services in healthcare systems, which are cancer care services and business analytics/cloud services. These services incorporate the implementation of an IoT that provides solution and framework for analyzing health data gathered from IoT through various sensor networks and other smart devices in order to improve healthcare delivery and to help health care providers in their decision-making process for enhanced and efficient cancer treatment. In addition, we discuss the wireless sensor network (WSN), WSN routing and data transmission in the healthcare environment. Finally, some operational challenges and security issues with IoT-based healthcare system are discussed.

Keywords: IoT, smart health care system, business analytics, (wireless) sensor network, cancer care services, cloud services

Procedia PDF Downloads 154

Authors: Yinheng Li

Abstract:

The remarkable advancements in large language models (LLMs) have brought about significant improvements in natural language processing tasks. This paper presents a comprehensive review of in-context learning techniques, focusing on different types of prompts, including discrete, continuous, few-shot, and zero-shot, and their impact on LLM performance. We explore various approaches to prompt design, such as manual design, optimization algorithms, and evaluation methods, to optimize LLM performance across diverse tasks. Our review covers key research studies in prompt engineering, discussing their methodologies and contributions to the field. We also delve into the challenges faced in evaluating prompt performance, given the absence of a single ”best” prompt and the importance of considering multiple metrics. In conclusion, the paper highlights the critical role of prompt design in harnessing the full potential of LLMs and provides insights into the combination of manual design, optimization techniques, and rigorous evaluation for more effective and efficient use of LLMs in various Natural Language Processing (NLP) tasks.

Keywords: in-context learning, prompt engineering, zero-shot learning, large language models

Procedia PDF Downloads 59

Authors: Diana Reckien

Abstract:

Vulnerability assessments are increasingly used to support policy-making in complex environments, like urban areas. Usually, vulnerability studies include the construction of aggregate (sub-) indices and the subsequent mapping of indices across an area of interest. Vulnerability studies show a couple of advantages: they are great communication tools, can inform a wider general debate about environmental issues, and can help allocating and efficiently targeting scarce resources for adaptation policy and planning. However, they also have a number of challenges: Vulnerability assessments are constructed on the basis of a wide range of methodologies and there is no single framework or methodology that has proven to serve best in certain environments, indicators vary highly according to the spatial scale used, different variables and metrics produce different results, and aggregate or composite vulnerability indicators that are mapped easily distort or bias the picture of vulnerability as they hide the underlying causes of vulnerability and level out conflicting reasons of vulnerability in space. So, there is urgent need to further develop the methodology of vulnerability studies towards a common framework, which is one reason of the paper. We introduce a social vulnerability approach, which is compared with other approaches of bio-physical or sectoral vulnerability studies relatively developed in terms of a common methodology for index construction, guidelines for mapping, assessment of sensitivity, and verification of variables. Two approaches are commonly pursued in the literature. The first one is an additive approach, in which all potentially influential variables are weighted according to their importance for the vulnerability aspect, and then added to form a composite vulnerability index per unit area. The second approach includes variable reduction, mostly Principal Component Analysis (PCA) that reduces the number of variables that are interrelated into a smaller number of less correlating components, which are also added to form a composite index. We test these two approaches of constructing indices on the area of New York City as well as two different metrics of variables used as input and compare the outcome for the 5 boroughs of NY. Our analysis yields that the mapping exercise yields particularly different results in the outer regions and parts of the boroughs, such as Outer Queens and Staten Island. However, some of these parts, particularly the coastal areas receive the highest attention in the current adaptation policy. We imply from this that the current adaptation policy and practice in NY might need to be discussed, as these outer urban areas show relatively low social vulnerability as compared with the more central parts, i.e. the high dense areas of Manhattan, Central Brooklyn, Central Queens and the Southern Bronx. The inner urban parts receive lesser adaptation attention, but bear a higher risk of damage in case of hazards in those areas. This is conceivable, e.g., during large heatwaves, which would more affect more the inner and poorer parts of the city as compared with the outer urban areas. In light of the recent planning practice of NY one needs to question and discuss who in NY makes adaptation policy for whom, but the presented analyses points towards an under representation of the needs of the socially vulnerable population, such as the poor, the elderly, and ethnic minorities, in the current adaptation practice in New York City.

Keywords: vulnerability mapping, social vulnerability, additive approach, Principal Component Analysis (PCA), New York City, United States, adaptation, social sensitivity

Procedia PDF Downloads 378

Authors: Rejab Hajlaoui, Tarek Moulahi, Hervé Guyennet

Abstract:

In a highway scenario, the vehicle speed can exceed 120 kmph. Therefore, any vehicle can enter or leave the network within a very short time. This mobility adversely affects the network connectivity and decreases the life time of all established links. To ensure an effective stability in vehicular ad hoc networks with minimum broadcasting storm, we have developed a weighted algorithm based on the k-medoids clustering algorithm (WKCA). Indeed, the number of clusters and the initial cluster heads will not be selected randomly as usual, but considering the available transmission range and the environment size. Then, to ensure optimal assignment of nodes to clusters in both k-medoids phases, the combined weight of any node will be computed according to additional metrics including direction, relative speed and proximity. Empirical results prove that in addition to the convergence speed that characterizes the k-medoids algorithm, our proposed model performs well both AODV-Clustering and OLSR-Clustering protocols under different densities and velocities in term of end-to-end delay, packet delivery ratio, and throughput.

Keywords: communication, clustering algorithm, k-medoids, sensor, vehicular ad hoc network

Procedia PDF Downloads 213

Authors: Kaustubh Chakradeo, Michael Delves, Sofya Titarenko

Abstract:

Malaria is a serious disease which affects hundreds of millions of people around the world, each year. If not treated in time, it can be fatal. Despite recent developments in malaria diagnostics, the microscopy method to detect malaria remains the most common. Unfortunately, the accuracy of microscopic diagnostics is dependent on the skill of the microscopist and limits the throughput of malaria diagnosis. With the development of Artificial Intelligence tools and Deep Learning techniques in particular, it is possible to lower the cost, while achieving an overall higher accuracy. In this paper, we present a VGG-based model and compare it with previously developed models for identifying infected cells. Our model surpasses most previously developed models in a range of the accuracy metrics. The model has an advantage of being constructed from a relatively small number of layers. This reduces the computer resources and computational time. Moreover, we test our model on two types of datasets and argue that the currently developed deep-learning-based methods cannot efficiently distinguish between infected and contaminated cells. A more precise study of suspicious regions is required.

Keywords: convolution neural network, deep learning, malaria, thin blood smears

Procedia PDF Downloads 110

Authors: Golnar Behzadi, Michael O'Sullivan, Tava Olsen, Abraham Zhang

Abstract:

By definition, increasing supply chain resilience improves the supply chain’s ability to return to normal, or to an even more desirable situation, quickly and efficiently after being hit by a disruption. This is especially critical in agribusiness supply chains where the products are perishable and have a short life-cycle. In this paper, we propose a resilience metric to capture and improve the recovery process in terms of both performance and time, of an agribusiness supply chain following either supply or demand-side disruption. We build a model that determines optimal supply chain recovery planning decisions and selects the best resilient strategies that minimize the loss of profit during the recovery time window. The model is formulated as a two-stage stochastic mixed-integer linear programming problem and solved with a branch-and-cut algorithm. The results show that the optimal recovery schedule is highly dependent on the duration of the time-window allowed for recovery. In addition, the profit loss during recovery is reduced by utilizing the proposed resilient actions.

Keywords: agribusiness supply chain, recovery, resilience metric, risk management

Procedia PDF Downloads 373

Authors: Ravindra Dastikop, G. S. Thyagaraju, U. P. Kulkarni

Abstract:

Even though the number of context aware applications is increasing day by day along with the users, till today there is no generic programming paradigm for context aware applications. This situation could be remedied by design and developing the appropriate context modeling and programming paradigm for context aware applications. In this paper, we are proposing the static context model and metrics for validating the expressiveness and understandability of the model. The proposed context modeling is a way of describing a situation of user using context entities , attributes and relationships .The model which is an extended and hybrid version of ER model, ontology model and Graphical model is specifically meant for expressing and understanding the user situation in context aware environment. The model is useful for understanding context aware problems, preparing documentation and designing programs and databases. The model makes use of context entity attributes relationship (CEAR) diagram for representation of association between the context entities and attributes. We have identified a new set of graphical notations for improving the expressiveness and understandability of context from the end user perspective .

Keywords: user context, context entity, context entity attributes, situation, sensors, devices, relationships, actors, expressiveness, understandability

Procedia PDF Downloads 319

Authors: Gon Park

Abstract:

Seoul in South Korea established the 2030 Seoul City Master Plan that contains green-link projects to connect critical green areas within the city. However, the plan does not have detailed analyses for green infrastructure to incorporate land-cover information to many structural classes. This study maps green infrastructure networks of Seoul for complementing their green plans with identifying and raking green areas. Hubs and links of main elements of green infrastructure have been identified from incorporating cadastral data of 967,502 parcels to 135 of land use maps using geographic information system. Network analyses were used to rank hubs and links of a green infrastructure map with applying a force-directed algorithm, weighted values, and binary relationships that has metrics of density, distance, and centrality. The results indicate that network analyses using cadastral parcel data can be used as the framework to identify and rank hubs, links, and networks for the green infrastructure planning under a variable scenarios of green areas in cities.

Keywords: cadastral data, green Infrastructure, network analysis, parcel data

Procedia PDF Downloads 176

Authors: Soheila Sadeghi

Abstract:

Accurate cost prediction is essential for effective project management and decision-making in the construction industry. This study aims to develop a cost prediction model for construction projects using Machine Learning techniques and Particle Swarm Optimization (PSO). The research utilizes a comprehensive dataset containing project cost estimates, actual costs, resource details, and project performance metrics from a road reconstruction project. The methodology involves data preprocessing, feature selection, and the development of an Artificial Neural Network (ANN) model optimized using PSO. The study investigates the impact of various input features, including cost estimates, resource allocation, and project progress, on the accuracy of cost predictions. The performance of the optimized ANN model is evaluated using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared. The results demonstrate the effectiveness of the proposed approach in predicting project costs, outperforming traditional benchmark models. The feature selection process identifies the most influential variables contributing to cost variations, providing valuable insights for project managers. However, this study has several limitations. Firstly, the model's performance may be influenced by the quality and quantity of the dataset used. A larger and more diverse dataset covering different types of construction projects would enhance the model's generalizability. Secondly, the study focuses on a specific optimization technique (PSO) and a single Machine Learning algorithm (ANN). Exploring other optimization methods and comparing the performance of various ML algorithms could provide a more comprehensive understanding of the cost prediction problem. Future research should focus on several key areas. Firstly, expanding the dataset to include a wider range of construction projects, such as residential buildings, commercial complexes, and infrastructure projects, would improve the model's applicability. Secondly, investigating the integration of additional data sources, such as economic indicators, weather data, and supplier information, could enhance the predictive power of the model. Thirdly, exploring the potential of ensemble learning techniques, which combine multiple ML algorithms, may further improve cost prediction accuracy. Additionally, developing user-friendly interfaces and tools to facilitate the adoption of the proposed cost prediction model in real-world construction projects would be a valuable contribution to the industry. The findings of this study have significant implications for construction project management, enabling proactive cost estimation, resource allocation, budget planning, and risk assessment, ultimately leading to improved project performance and cost control. This research contributes to the advancement of cost prediction techniques in the construction industry and highlights the potential of Machine Learning and PSO in addressing this critical challenge. However, further research is needed to address the limitations and explore the identified future research directions to fully realize the potential of ML-based cost prediction models in the construction domain.

Keywords: cost prediction, construction projects, machine learning, artificial neural networks, particle swarm optimization, project management, feature selection, road reconstruction

Procedia PDF Downloads 23

Authors: Heba M. Mohamed

Abstract:

Owing to scientific and public concern about health and environment and seeking for a better quality of life; “Green”, “Environmentally” and “Eco” friendly practices have been presented and implemented in different research areas. Subsequently, researchers’ attention is drawn in the direction of greening the analytical methodologies and taking the Green Analytical Chemistry principles (GAC) into consideration. It is of high importance to appraise the environmental impact of each of the implemented green approaches. Compared to the other traditional green metrics (E-factor, Atom economy and the process profile), the eco scale is the optimum choice to assess the environmental impact of the analytical procedures used for pharmaceuticals analysis. For analytical methodologies, Eco-Scale is calculated by allotting penalty points to any factor of the used analytical procedure which disagree and not match with the model green analysis, where the perfect green analysis has its Eco-Scale value of 100. In this work, calculation and comparison of the Eco-Scale for some of the reported green analytical methods was done, to accentuate their greening potentials. Where the different scores can reveal how green the method is, compared to the ideal value. The study emphasizes that greenness measurement is not only about the waste quantity determination but also dictates a holistic scheme, considering all factors.

Keywords: eco scale, green analysis, environmentally friendly, pharmaceuticals analysis

Procedia PDF Downloads 410

Authors: Raja Jarray, Imen Zaghbani, Soufiene Bouallègue

Abstract:

Path planning for Unmanned Aerial Vehicles (UAVs) in dynamic environments poses a significant challenge. Adapting planning algorithms to these complex environments with moving obstacles is a major task in real-world robotics. This article introduces a path-planning strategy based on a Q-learning algorithm, which enables an effective response to avoid moving obstacles while ensuring mission feasibility. A dynamic reward function is introduced, causing the UAV to use the real-time distance between its current position and the destination as training data. The objective of the proposed Q-learning-based path planning algorithm is to guide the drone through an optimal flight itinerary in a dynamic, collision-free environment. The proposed Q-learning-based UAV planner is evaluated considering numerous commonly used performance metrics. Demonstrative results are provided and discussed to show the effectiveness and practicability of such an artificial intelligence-based path planning approach.

Keywords: unmanned aerial vehicles, dynamic path planning, moving obstacles, reinforcement-learning, Q-learning

Procedia PDF Downloads 22

Authors: Mst. Tuhin Akter, Sharun Akter Khushbu, S. M. Shaqib

Abstract:

A real-time system architecture is highly effective for monitoring and detecting various damaged products or fruits that may deteriorate over time or become infected with diseases. Deep learning models have proven to be effective in building such architectures. However, building a deep learning model from scratch is a time-consuming and costly process. A more efficient solution is to utilize deep neural network (DNN) based transfer learning models in the real-time monitoring architecture. This study focuses on using a novel strawberry dataset to develop effective transfer learning models for the proposed real-time monitoring system architecture, specifically for evaluating and detecting strawberry freshness. Several state-of-the-art transfer learning models were employed, and the best performing model was found to be Xception, demonstrating higher performance across evaluation metrics such as accuracy, recall, precision, and F1-score.

Keywords: strawberry freshness evaluation, deep neural network, transfer learning, image augmentation

Procedia PDF Downloads 63

Authors: Abhijith Asok

Abstract:

This paper presents a generalized approach for the simple linear data transformation, Y=bX, through an integration of multidimensional coordinate geometry, vector space theory and polygonal geometry. The scaling is performed by adding an additional ’Dummy Dimension’ to the n-dimensional data, which helps plot two dimensional component-wise straight lines on pairs of dimensions. The end result is a set of scaled extensions of observations in any of the 2n spatial divisions, where n is the total number of applicable dimensions/dataset variables, created by shifting the n-dimensional plane along the ’Dummy Axis’. The derived scaling factor was found to be dependent on the coordinates of the common point of origin for diverging straight lines and the plane of extension, chosen on and perpendicular to the ’Dummy Axis’, respectively. This result indicates the geometrical interpretation of a linear data transformation and hence, opportunities for a more informed choice of the factor ’b’, based on a better choice of these coordinate values. The paper follows on to identify the effect of this transformation on certain popular distance metrics, wherein for many, the distance metric retained the same scaling factor as that of the features.

Keywords: data transformation, dummy dimension, linear transformation, scaling

Procedia PDF Downloads 283

Authors: Devatha Kalyan Kumar, R. Poovarasan

Abstract:

In this paper, we have taken certain important factors and health parameters of diabetes patients especially among children by birth (pediatric congenital) where using the above three metrics methods we are going to assess the importance of each attributes in the dataset and thereby determining the most highly responsible and co-related attribute causing diabetics among young patients. We use cost optimization, control chart and Spearmen methodologies for the real-time application of finding the data efficiency in this diabetes dataset. The Spearmen methodology is the correlation methodologies used in software development process to identify the complexity between the various modules of the software. Identifying the complexity is important because if the complexity is higher, then there is a higher chance of occurrence of the risk in the software. With the use of control; chart mean, variance and standard deviation of data are calculated. With the use of Cost optimization model, we find to optimize the variables. Hence we choose the Spearmen, control chart and cost optimization methods to assess the data efficiency in diabetes datasets.

Keywords: correlation, congenital diabetics, linear relationship, monotonic function, ranking samples, pediatric

Procedia PDF Downloads 241

Authors: Masoud Shahmanzari

Abstract:

The aim of this paper is to present a Variable Neighborhood Search (VNS) with Tabu Search (TS) conditions for the Roaming Salesman Problem (RSP). The RSP is a special case of the well-known traveling salesman problem (TSP) where a set of cities with time-dependent rewards and a set of campaign days are given. Each city can be visited on any day and a subset of cities can be visited multiple times. The goal is to determine an optimal campaign schedule consist of daily open/closed tours that visit some cities and maximizes the total net benefit while respecting daily maximum tour duration constraints and the necessity to return campaign base frequently. This problem arises in several real-life applications and particularly in election logistics where depots are not fixed. We formulate the problem as a mixed integer linear programming (MILP), in which we capture as many real-world aspects of the RSP as possible. We also present a hybrid metaheuristic algorithm based on a VNS with TS conditions. The initial feasible solution is constructed via a new matheuristc approach based on the decomposition of the original problem. Next, this solution is improved in terms of the collected rewards using the proposed local search procedure. We consider a set of 81 cities in Turkey and a campaign of 30 days as our largest instance. Computational results on real-world instances show that the developed algorithm could find near-optimal solutions effectively.

Keywords: optimization, routing, election logistics, heuristics

Procedia PDF Downloads 69

Authors: Boumaraf Malak

Abstract:

The development of intelligent transportation systems (ITS) and artificial intelligence (AI) are spurring us to pave the way for the widespread adoption of autonomous vehicles (AVs). This is open again opportunities for smart roads, smart traffic safety, and mobility comfort. A highly intelligent decision-making system is essential for autonomous driving around dense, dynamic objects. It must be able to handle complex road geometry and topology, as well as complex multiagent interactions, and closely follow higher-level commands such as routing information. Autonomous vehicles have become a very hot research topic in recent years due to their significant ability to reduce traffic accidents and personal injuries. Using new artificial intelligence-based technologies handles important functions in scene understanding, motion planning, decision making, vehicle control, social behavior, and communication for AV. This paper focuses only on deep reinforcement learning-based methods; it does not include traditional (flat) planar techniques, which have been the subject of extensive research in the past because reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments. The DRL algorithm used so far found solutions to the four main problems of autonomous driving; in our paper, we highlight the challenges and point to possible future research directions.

Keywords: deep reinforcement learning, autonomous driving, deep deterministic policy gradient, deep Q-learning

Procedia PDF Downloads 58

Authors: Amar Partap Singh Pharwaha, Balkrishan Jindal

Abstract:

In this paper, a new method is developed for hiding image in a digital image with multilayer security. In the proposed method, the secret image is encrypted in the first instance using a flexible matrix based symmetric key to add first layer of security. Then another layer of security is added to the secret data by encrypting the ciphered data using Pythagorean Theorem method. The ciphered data bits (4 bits) produced after double encryption are then embedded within digital image in the spatial domain using Least Significant Bits (LSBs) substitution. To improve the image quality of the stego-image, an improved form of pixel adjustment process is proposed. To evaluate the effectiveness of the proposed method, image quality metrics including Peak Signal-to-Noise Ratio (PSNR), Mean Square Error (MSE), entropy, correlation, mean value and Universal Image Quality Index (UIQI) are measured. It has been found experimentally that the proposed method provides higher security as well as robustness. In fact, the results of this study are quite promising.

Keywords: Pythagorean theorem, pixel adjustment, ciphered data, image hiding, least significant bit, flexible matrix

Procedia PDF Downloads 318

Authors: Thota Sai Prakash, B. Yaswanth, Jhade Bhuvaneswar, Marreddy Divakar Reddy, Shyam Ji Gupta

Abstract:

Across the globe, there are a lot of chronic diseases, and heart disease stands out as one of the most perilous. Sadly, many lives are lost to this condition, even though early intervention could prevent such tragedies. However, identifying heart disease in its initial stages is not easy. To address this challenge, we propose an automated system aimed at predicting the presence of heart disease using advanced techniques. By doing so, we hope to empower individuals with the knowledge needed to take proactive measures against this potentially fatal illness. Our approach towards this problem involves meticulous data preprocessing and the development of predictive models utilizing classification algorithms such as Support Vector Machines (SVM), Decision Tree, and Random Forest. We assess the efficiency of every model based on metrics like accuracy, ensuring that we select the most reliable option. Additionally, we conduct thorough data analysis to reveal the importance of different attributes. Among the models considered, Random Forest emerges as the standout performer with an accuracy rate of 96.04% in our study.

Keywords: support vector machines, decision tree, random forest

Procedia PDF Downloads 19

Authors: Mallikarjuna Rao Yamarthy, Subramanyam Makam Venkata, Satya Prasad Kodati

Abstract:

The main objective of the proposed work is to reduce the overall network traffic incurred by mobility management, packet delivery cost and to increase the resource utilization. The proposed algorithm, An Efficient Resource Management Algorithm (ERMA) for mobility management in wireless mesh networks, relies on pointer based mobility management scheme. Whenever a mesh client moves from one mesh router to another, the pointer is set up dynamically between the previous mesh router and current mesh router based on the distance constraints. The algorithm evaluated for signaling cost, data delivery cost and total communication cost performance metrics. The proposed algorithm is demonstrated for both internet sessions and intranet sessions. The proposed algorithm yields significantly better performance in terms of signaling cost, data delivery cost, and total communication cost.

Keywords: data delivery cost, mobility management, pointer forwarding, resource management, wireless mesh networks

Procedia PDF Downloads 341

Authors: Allmin Susaiyah, Aki Härmä, Milan Petković

Abstract:

Automatic generation of insights from data using insight mining systems (IMS) is useful in many applications, such as personal health tracking, patient monitoring, and business process management. Existing IMS face challenges in controlling insight extraction, scaling to large databases, and generalising to unseen domains. In this work, we propose a hybrid approach consisting of rule-based and neural components for generating insights from data while overcoming the aforementioned challenges. Firstly, a rule-based data 2CNL component is used to extract statistically significant insights from data and represent them in a controlled natural language (CNL). Secondly, a BERTSum-based CNL2NL component is used to convert these CNLs into natural language texts. We improve the model using task-specific and domain-specific fine-tuning. Our approach has been evaluated using statistical techniques and standard evaluation metrics. We overcame the aforementioned challenges and observed significant improvement with domain-specific fine-tuning.

Keywords: data mining, insight mining, natural language generation, pre-trained language models

Procedia PDF Downloads 88

Authors: Atefeh Heydari, Mohammadali Tavakoli, Zuriati Ismail, Naomie Salim

Abstract:

Seeking and sharing knowledge on online forums have made them popular in recent years. Although online forums are valuable sources of information, due to variety of sources of messages, retrieving reliable threads with high quality content is an issue. Majority of the existing information retrieval systems ignore the quality of retrieved documents, particularly, in the field of thread retrieval. In this research, we present an approach that employs various quality features in order to investigate the quality of retrieved threads. Different aspects of content quality, including completeness, comprehensiveness, and politeness, are assessed using these features, which lead to finding not only textual, but also conceptual relevant threads for a user query within a forum. To analyse the influence of the features, we used an adopted version of voting model thread search as a retrieval system. We equipped it with each feature solely and also various combinations of features in turn during multiple runs. The results show that incorporating the quality features enhances the effectiveness of the utilised retrieval system significantly.

Keywords: content quality, forum search, thread retrieval, voting techniques

Procedia PDF Downloads 190

Authors: Hanlin Liu, Hua Li, Yintan AI

Abstract:

Network performance prediction (NPP) is essential for the management and optimization of software-defined networking (SDN) and contributes to improving the quality of service (QoS) in SDN to meet the requirements of users. Although current deep learning-based methods can achieve high effectiveness, they still suffer from some problems, such as difficulty in capturing global information of the network, inefficiency in modeling end-to-end network performance, and inadequate graph feature extraction. To cope with these issues, our proposed Graphormer-based architecture for NPP leverages the powerful graph representation ability of Graphormer to effectively model the graph structure data, and a node-edge transformation algorithm is designed to transfer the feature extraction object from nodes to edges, thereby effectively extracting the end-to-end performance characteristics of the network. Moreover, routing oriented centrality measure coefficient for nodes and edges is proposed respectively to assess their importance and influence within the graph. Based on this coefficient, an enhanced feature extraction method and an advanced centrality encoding strategy are derived to fully extract the structural information of the graph. Experimental results on three public datasets demonstrate that the proposed GraphNPP architecture can achieve state-of-the-art results compared to current NPP methods.

Keywords: software-defined networking, network performance prediction, Graphormer, graph neural network

Procedia PDF Downloads 19