Search results for: Kernel Mapping Recommender Systems

Authors: Amir Hajian, Sepehr Damavandinejadmonfared

Abstract:

In this paper the issue of dimensionality reduction is investigated in finger vein recognition systems using kernel Principal Component Analysis (KPCA). One aspect of KPCA is to find the most appropriate kernel function on finger vein recognition as there are several kernel functions which can be used within PCA-based algorithms. In this paper, however, another side of PCA-based algorithms -particularly KPCA- is investigated. The aspect of dimension of feature vector in PCA-based algorithms is of importance especially when it comes to the real-world applications and usage of such algorithms. It means that a fixed dimension of feature vector has to be set to reduce the dimension of the input and output data and extract the features from them. Then a classifier is performed to classify the data and make the final decision. We analyze KPCA (Polynomial, Gaussian, and Laplacian) in details in this paper and investigate the optimal feature extraction dimension in finger vein recognition using KPCA.

Keywords: biometrics, finger vein recognition, principal component analysis (PCA), kernel principal component analysis (KPCA)

Procedia PDF Downloads 363

Authors: Yan Li

Abstract:

Purpose: There is a lack of suitable recommendation systems to assist engineering teaching. The existing traditional engineering pedagogies lack learning interests for postgraduate students. The knowledge graph-based recommender system aims to enhance postgraduate students’ programming skills, with a focus on programming courses. Design/methodology/approach: The case study will be used as a major research method, and the two case studies will be taken in both two teaching styles of the universities (Zhejiang University and the University of Nottingham Ningbo China), followed by the interviews. Quantitative and qualitative research methods will be combined in this study. Research limitations/implications: The case studies were only focused on two teaching styles universities, which is not comprehensive enough. The subject was limited to postgraduate students. Originality/value: The study collected and analyzed the data from two teaching styles of universities’ perspectives. It explored the challenges of Engineering education and tried to seek potential enhancement.

Keywords: knowledge graph and recommender system, engineering pedagogy, programming skills, postgraduate students

Procedia PDF Downloads 71

Authors: Hoyeon Park, Yunhwan Keon, Kyoung-Jae Kim

Abstract:

Location Based Social Network services (LBSNs) is a new term that combines location based service and social network service (SNS). Unlike traditional SNS, LBSNs emphasizes empirical elements in the user's actual physical location. Point-of-Interest (POI) is the most important factor to implement LBSNs recommendation system. POI information is the most popular spot in the area. In this study, we would like to recommend POI to users in a specific area through recommendation system using collaborative filtering. The process is as follows: first, we will use different data sets based on Seoul and New York to find interesting results on human behavior. Secondly, based on the location-based activity information obtained from the personalized LBSNs, we have devised a new rating that defines the user's preference for the area. Finally, we have developed an automated rating algorithm from massive raw data using distributed systems to reduce advertising costs of LBSNs.

Keywords: location-based social network services, point-of-interest, recommender systems, business analytics

Procedia PDF Downloads 228

Authors: Aziz Sezgin

Abstract:

We consider the problem of stabilization of an unstable heat equation in a 2-D, 3-D and generally n-D domain by deriving a generalized backstepping boundary control design methodology. To stabilize the systems, we design boundary backstepping controllers inspired by the 1-D unstable heat equation stabilization procedure. We assume that one side of the boundary is hinged and the other side is controlled for each direction of the domain. Thus, controllers act on two boundaries for 2-D domain, three boundaries for 3-D domain and ”n” boundaries for n-D domain. The main idea of the design is to derive ”n” controllers for each of the dimensions by using ”n” kernel functions. Thus, we obtain ”n” controllers for the ”n” dimensional case. We use a transformation to change the system into an exponentially stable ”n” dimensional heat equation. The transformation used in this paper is a generalized Volterra/Fredholm type with ”n” kernel functions for n-D domain instead of the one kernel function of 1-D design.

Keywords: backstepping, boundary control, 2-D, 3-D, n-D heat equation, distributed parameter systems

Procedia PDF Downloads 402

Authors: Patik Joslin Kenfack, Polyakov Vladimir Mikhailovich

Abstract:

Machine Learning (ML) systems are trained using human generated data that could be biased by implicitly containing racist, sexist, or discriminating data. ML models learn those biases or even amplify them. Recent research in work on has begun to consider issues of fairness. The concept of fairness is extended to recommendation. A recommender system will be considered fair if it doesn’t under rank items of protected group (gender, race, demographic...). Several metrics for evaluating fairness concerns in recommendation systems have been proposed, which take pairs of items as ‘instances’ in fairness evaluation. It doesn’t take in account the fact that the fairness should be evaluated across a list of items. The paper explores a probabilistic approach that generalize pairwise metric by using a list k (listwise) of items as ‘instances’ in fairness evaluation, parametrized by k. We also explore new regularization method based on this metric to improve fairness ranking during model training.

Keywords: Fairness, Recommender System, Ranking, Listwise Approach

Procedia PDF Downloads 147

Authors: Kai Chen, Shuguang Cui, Feng Yin

Abstract:

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

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

Procedia PDF Downloads 193

Authors: Ho Yeon Park, Kyoung-Jae Kim

Abstract:

Recently, user’s interests for location-based social network service increases according to the advances of social web and location-based technologies. It may be easy to recommend preferred items if we can use user’s preference, context and social network information simultaneously. In this study, we propose context-aware POI (point-of-interests) recommender systems using location-based network analysis and sentiment analysis which consider context, social network information and implicit user’s preference score. We propose a context-aware POI recommendation system consisting of three sub-modules and an integrated recommendation system of them. First, we will develop a recommendation module based on network analysis. This module combines social network analysis and cluster-indexing collaboration filtering. Next, this study develops a recommendation module using social singular value decomposition (SVD) and implicit SVD. In this research, we will develop a recommendation module that can recommend preference scores based on the frequency of POI visits of user in POI recommendation process by using social and implicit SVD which can reflect implicit feedback in collaborative filtering. We also develop a recommendation module using them that can estimate preference scores based on the recommendation. Finally, this study will propose a recommendation module using opinion mining and emotional analysis using data such as reviews of POIs extracted from location-based social networks. Finally, we will develop an integration algorithm that combines the results of the three recommendation modules proposed in this research. Experimental results show the usefulness of the proposed model in relation to the recommended performance.

Keywords: sentiment analysis, network analysis, recommender systems, point-of-interests, business analytics

Procedia PDF Downloads 248

Authors: Jacob Livingston Slosser, Naja Holten Moller, Thomas Troels Hildebrandt, Henrik Palmer Olsen

Abstract:

In this paper, we propose a model for human-AI interaction in public administration that involves legal decision-making. Inspired by Alan Turing’s test for machine intelligence, we propose a way of institutionalizing a continuous working relationship between man and machine that aims at ensuring both good legal quality and higher efficiency in decision-making processes in public administration. We also suggest that our model enhances the legitimacy of using AI in public legal decision-making. We suggest that case loads in public administration could be divided between a manual and an automated decision track. The automated decision track will be an algorithmic recommender system trained on former cases. To avoid unwanted feedback loops and biases, part of the case load will be dealt with by both a human case worker and the automated recommender system. In those cases an experienced human case worker will have the role of an evaluator, choosing between the two decisions. This model will ensure that the algorithmic recommender system is not compromising the quality of the legal decision making in the institution. It also enhances the legitimacy of using algorithmic decision support because it provides justification for its use by being seen as superior to human decisions when the algorithmic recommendations are preferred by experienced case workers. The paper outlines in some detail the process through which such a model could be implemented. It also addresses the important issue that legal decision making is subject to legislative and judicial changes and that legal interpretation is context sensitive. Both of these issues requires continuous supervision and adjustments to algorithmic recommender systems when used for legal decision making purposes.

Keywords: administrative law, algorithmic decision-making, decision support, public law

Procedia PDF Downloads 216

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

Abstract:

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

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

Procedia PDF Downloads 294

Authors: Yousuf Alkhezi

Abstract:

Since most of the literature on algebra does not make much deal with the special case of mapping cone. This paper is an alternative way to examine the special tensor product and mapping cone. Also, we show that the isomorphism that implies the mapping cone commutes with the tensor product for the ordinary tensor product no longer holds for the pinched tensor product. However, we show there is a morphism. We will introduce an alternative way of mapping cone. We are looking for more properties which is our future project. Also, we want to apply these new properties in some application. Many results and examples with classical algorithms will be provided.

Keywords: complex, tensor product, pinched tensore product, mapping cone

Procedia PDF Downloads 128

Authors: Behnam Tavakkol

Abstract:

Uncertain data mining algorithms use different ways to consider uncertainty in data such as by representing a data object as a sample of points or a probability distribution. Fuzzy methods have long been used for clustering traditional (certain) data objects. They are used to produce non-crisp cluster labels. For uncertain data, however, besides some uncertain fuzzy k-medoids algorithms, not many other fuzzy clustering methods have been developed. In this work, we develop a fuzzy kernel k-medoids algorithm for clustering uncertain data objects. The developed fuzzy kernel k-medoids algorithm is superior to existing fuzzy k-medoids algorithms in clustering data sets with non-linearly separable clusters.

Keywords: clustering algorithm, fuzzy methods, kernel k-medoids, uncertain data

Procedia PDF Downloads 215

Authors: Patel Darshan Shaileshkumar, M. G. Vanza

Abstract:

Black cotton soil is problematic soil for any construction work. Black cotton soil contains montmorillonite in its structure. Due to this mineral, black cotton soil will attain maximum swelling and shrinkage. Due to these volume changes, it is necessary to stabilize black cotton soil before the construction of the road. For soil stabilization use of pozzolanic waste is found to be a good solution by some researchers. The palm kernel shell ash (PKSA) is a pozzolanic material that can be used for soil stabilization. Basically, PKSA is a waste material, and it is available at a cheap cost. Palm kernel shell is a waste material generated in palm oil mills. Then palm kernel shell is used in industries instead of coal for power generation. After the burning of a palm kernel shell, ash is formed; the ash is called palm kernel shell ash (PKSA). The PKSA contains a free lime content that will react chemically with the silicate and aluminate of black cotton soil and forms a C-S-H and C-A-H gel which will bines soil particles together and reduce the plasticity of the soil. In this study, the PKSA is added to the soil. It was found that with the addition of PKSA content in the soil, the liquid limit of the soil is decreased, the plastic limit of the soil is increased, and the plasticity of the soil is decreased. The group index value of the soil is evaluated, and it was found that with the addition of PKSA GI value of the soil is decreased, which indicates the strength of the soil is improved.

Keywords: palm kernel shell ash, black cotton soil, liquid limit, group index, plastic limit, plasticity index

Procedia PDF Downloads 108

Authors: Robert Höttger, Lukas Krawczyk, Burkhard Igel

Abstract:

This paper introduces novel approaches to partitioning and mapping in terms of model-based embedded multicore system engineering and further discusses benefits, industrial relevance and features in common with existing approaches. In order to assess and evaluate results, both approaches have been applied to a real industrial application as well as to various prototypical demonstrative applications, that have been developed and implemented for different purposes. Evaluations show, that such applications improve significantly according to performance, energy efficiency, meeting timing constraints and covering maintaining issues by using the AMALTHEA platform and the implemented approaches. Further- more, the model-based design provides an open, expandable, platform independent and scalable exchange format between OEMs, suppliers and developers on different levels. Our proposed mechanisms provide meaningful multicore system utilization since load balancing by means of partitioning and mapping is effectively performed with regard to the modeled systems including hardware, software, operating system, scheduling, constraints, configuration and more data.

Keywords: partitioning, mapping, distributed systems, scheduling, embedded multicore systems, model-based, system analysis

Procedia PDF Downloads 619

Authors: Denis Özdemir, Max Senges

Abstract:

There are many examples of AI-supported apps for better health and wellbeing. Generally, these applications help people to achieve their goals based on scientific research and input data. Still, they do not always explain how those three are related, e.g. by making implicit assumptions about goals that hold for many but not for all. We present a seven-step method for designing health and wellbeing AIs considering goal setting, measurable results, real-time indicators, analytics, visual representations, communication, and feedback. It can help engineers as guidance in developing apps, recommendation algorithms, and interfaces that support humans in their decision-making without patronization. To illustrate the method, we create a recommender AI for tiny wellbeing habits and run a small case study, including a survey. From the results, we infer how people perceive the relationship between them and the AI and to what extent it helps them to achieve their goals. We review our seven-step engineering method and suggest modifications for the next iteration.

Keywords: recommender systems, natural language processing, health apps, engineering methods

Procedia PDF Downloads 164

Authors: Guillermo Manuel Flores Figueroa, Juan Alejandro Vazquez Feijoo, Jose Navarro Antonio

Abstract:

A continuous nonlinear system response may be obtained by an infinite sum of the so-called Volterra operators. Each operator is obtained from multidimensional convolution of nth-order between the nth-order Volterra kernel and the system input. These operators can also be obtained from the Associated Linear Equations (ALEs) that are linear models of subsystems which inputs and outputs are of the same nth-order. Each ALEs produces a particular nth-Volterra operator. As linear models a unitary impulse response can be obtained from them. This work shows the relationship between this unitary impulse responses and the corresponding order Volterra kernel.

Keywords: Volterra series, frequency response functions FRF, associated linear equations ALEs, unitary response function, Voterra kernel

Procedia PDF Downloads 667

Authors: Mirnawati, Gita Ciptaan, Ferawati

Abstract:

Background and Objective: Palm kernel cake (PKC) is a waste of the palm oil industry. Indonesia, as the largest palm oil producer in the world, produced 45-46% palm kernel cake. Palm kernel cake can potentially be used as animal ration but its utilization for poultry is limited. Thus, fermentation process was done in order to increase the utilization PKC in poultry ration. An experiment was conducted to study the effect between Inoculum Doses with Bacillus subtilis and fermentation time to improve the quality and nutrient content of fermented Palm Kernel Cake. Material and Methods: 1) Palm kernel cake derived from Palm Kernel Processing Manufacture of Andalas Agro Industry in Pasaman, West Sumatra. 2) Bacillus subtilis obtained from The Research Center of Applied Chemistry LIPI, Bogor. 3) Preparations nutrient agar medium (NA) produced by Difoo - Becton Dickinson. 4) Rice bran 5) Aquades and mineral standard. The experiment used completely randomize design (CRD) with 3 x 3 factorial and 3 replications. The first factors were three doses of inoculum Bacillus subtilis: (3%), (5%), and (7%). The second factor was fermentation time: (1) 2 day, (2) 4 day, and (3) 6 day. The parameters were crude protein, crude fiber, nitrogen retention, and crude fiber digestibility of fermented palm kernel cake (FPKC). Results: The result of the study showed that there was significant interaction (P<0.01) between factor A and factor B and each factor A and B also showed significant effect (P<0.01) on crude protein, crude fiber, nitrogen retention, and crude fiber digestibility. Conclusion: From this study, it can be concluded that fermented PKC with 7% doses of Bacillus subtilis and 6 days fermentation time provides the best result as seen from 24.65% crude protein, 17.35% crude fiber, 68.47% nitrogen retention, 53.25% crude fiber digestibility of fermented palm kernel cake (FPKC).

Keywords: fermentation, Bacillus Subtilis, inoculum, palm kernel cake, quality, nutrient

Procedia PDF Downloads 213

Authors: Mostafa Gamal, Hoda K. Mohamed, Islam El-Maddah, Ali Hamdi

Abstract:

In recent years, many digital documents on the web have been created due to the rapid growth of ’social applications’ communities or ’Data-intensive applications’. The evolution of online-based multimedia data poses new challenges in storing and querying large amounts of data for online recommender systems. Graph data models have been shown to be more efficient than relational data models for processing complex data. This paper will explain the key differences between graph and relational databases, their strengths and weaknesses, and why using graph databases is the best technology for building a realtime recommendation system. Also, The paper will discuss several similarity metrics algorithms that can be used to compute a similarity score of pairs of nodes based on their neighbourhoods or their properties. Finally, the paper will discover how NLP strategies offer the premise to improve the accuracy and coverage of realtime recommendations by extracting the information from the stored unstructured knowledge, which makes up the bulk of the world’s data to enrich the graph database with this information. As the size and number of data items are increasing rapidly, the proposed system should meet current and future needs.

Keywords: graph databases, NLP, recommendation systems, similarity metrics

Procedia PDF Downloads 103

Authors: Cassandra A. Skinner, Linda R. Chamberlain

Abstract:

The nonprofit and public sectors are increasingly turning to Geographic Information Systems for data visualizations which can better inform programmatic and policy decisions. Additionally, the private and nonprofit sectors are turning to systems mapping to better understand the ecosystems within which they operate. This study explores the potential which combining these data visualization methods—a method which is called geographic systems mapping—to create an exhaustive and comprehensive understanding of a social problem’s ecosystem may have in social innovation efforts. Researchers with Grand Valley State University collaborated with Talent 2025 of West Michigan to conduct a mixed-methods research study to paint a comprehensive picture of the workforce development ecosystem in West Michigan. Using semi-structured interviewing, observation, secondary research, and quantitative analysis, data were compiled on workforce development organizations’ locations, programming, metrics for success, partnerships, funding sources, and service language. To best visualize and disseminate the data, a geographic system map was created which identifies programmatic, operational, and geographic gaps in workforce development services of West Michigan. By combining geographic and systems mapping methods, the geographic system map provides insight into the cross-sector relationships, collaboration, and competition which exists among and between workforce development organizations. These insights identify opportunities for and constraints around cross-sectoral social innovation in the West Michigan workforce development ecosystem. This paper will discuss the process utilized to prepare the geographic systems map, explain the results and outcomes, and demonstrate how geographic systems mapping illuminated the needs of the community and opportunities for social innovation. As complicated social problems like unemployment often require cross-sectoral and multi-stakeholder solutions, there is potential for geographic systems mapping to be a tool which informs, enables, and inspires these solutions.

Keywords: cross-sector collaboration, data visualization, geographic systems mapping, social innovation, workforce development

Procedia PDF Downloads 295

Authors: M. K. Benhaoua, A. K. Singh, A. E. H. Benyamina, A. Kumar, P. Boulet

Abstract:

In this paper, we propose a new packing strategy to find free resources for run-time mapping of application tasks on NoC-based Heterogeneous MPSoCs. The proposed strategy minimizes the task mapping time in addition to placing the communicating tasks close to each other. To evaluate our approach, a comparative study is carried out. Experiments show that our strategy provides better results when compared to latest dynamic mapping strategies reported in the literature.

Keywords: heterogeneous MPSoCs, NoC, dynamic mapping, routing

Procedia PDF Downloads 524

Authors: Hung-Sheng Lin, Cheng-Hsuan Li

Abstract:

Over the past few years, kernel-based algorithms have been widely used to extend some linear feature extraction methods such as principal component analysis (PCA), linear discriminate analysis (LDA), and nonparametric weighted feature extraction (NWFE) to their nonlinear versions, kernel principal component analysis (KPCA), generalized discriminate analysis (GDA), and kernel nonparametric weighted feature extraction (KNWFE), respectively. These nonlinear feature extraction methods can detect nonlinear directions with the largest nonlinear variance or the largest class separability based on the given kernel function. Moreover, they have been applied to improve the target detection or the image classification of hyperspectral images. The double nearest proportion feature extraction (DNP) can effectively reduce the overlap effect and have good performance in hyperspectral image classification. The DNP structure is an extension of the k-nearest neighbor technique. For each sample, there are two corresponding nearest proportions of samples, the self-class nearest proportion and the other-class nearest proportion. The term “nearest proportion” used here consider both the local information and other more global information. With these settings, the effect of the overlap between the sample distributions can be reduced. Usually, the maximum likelihood estimator and the related unbiased estimator are not ideal estimators in high dimensional inference problems, particularly in small data-size situation. Hence, an improved estimator by shrinkage estimation (regularization) is proposed. Based on the DNP structure, LDA is included as a special case. In this paper, the kernel method is applied to extend DNP to kernel-based DNP (KDNP). In addition to the advantages of DNP, KDNP surpasses DNP in the experimental results. According to the experiments on the real hyperspectral image data sets, the classification performance of KDNP is better than that of PCA, LDA, NWFE, and their kernel versions, KPCA, GDA, and KNWFE.

Keywords: feature extraction, kernel method, double nearest proportion feature extraction, kernel double nearest feature extraction

Procedia PDF Downloads 341

Authors: Vijaya Subramaniam, Loh Soh Kheang, Astimar Abdul Aziz

Abstract:

Water footprint (WFP) has gained importance due to the increase in water scarcity in the world. This study analyses the WFP for an agriculture sector, i.e., the oil palm supply chain, which produces oil palm fresh fruit bunch (FFB), crude palm oil, palm kernel, and crude palm kernel oil. The water accounting and vulnerability evaluation (WAVE) method was used. This method analyses the water depletion index (WDI) based on the local blue water scarcity. The main contribution towards the WFP at the plantation was the production of FFB from the crop itself at 0.23m³/tonne FFB. At the mill, the burden shifts to the water added during the process, which consists of the boiler and process water, which accounted for 6.91m³/tonne crude palm oil. There was a 33% reduction in the WFP when there was no dilution or water addition after the screw press at the mill. When allocation was performed, the WFP reduced by 42% as the burden was shared with the palm kernel and palm kernel shell. At the kernel crushing plant (KCP), the main contributor towards the WFP 4.96 m³/tonne crude palm kernel oil which came from the palm kernel which carried the burden from upstream followed by electricity, 0.33 m³/tonne crude palm kernel oil used for the process and 0.08 m³/tonne crude palm kernel oil for transportation of the palm kernel. A comparison was carried out for mills with biogas capture versus no biogas capture, and the WFP had no difference for both scenarios. The comparison when the KCPs operate in the proximity of mills as compared to those operating in the proximity of ports only gave a reduction of 6% for the WFP. Both these scenarios showed no difference and insignificant difference, which differed from previous life cycle assessment studies on the carbon footprint, which showed significant differences. This shows that findings change when only certain impact categories are focused on. It can be concluded that the impact from the water used by the oil palm tree is low due to the practice of no irrigation at the plantations and the high availability of water from rainfall in Malaysia. This reiterates the importance of planting oil palm trees in regions with high rainfall all year long, like the tropics. The milling stage had the most significant impact on the WFP. Mills should avoid dilution to reduce this impact.

Keywords: life cycle assessment, water footprint, crude palm oil, crude palm kernel oil, WAVE method

Procedia PDF Downloads 173

Authors: Olatundun Bukola Ezekiel, Adejumo Olusoji

Abstract:

A feeding trial was conducted with 100 two-weeks old broiler chicken to evaluate the influence of inclusion in broiler diets at 0, 2.5, 5, 7.5 and 10% neem kernel (used to replace equal quantity of maize) on their performance, organ weight and gut morphometry. The birds were randomly allotted to five dietary treatments, each treatment having four replicates consisting of five broilers in a completely randomized design. The diets were formulated to be iso-nitrogenous (23% CP). Weekly feed intake and changes in body weight were calculated and feed efficiency determined. At the end of the 28-day feeding trial, four broilers per treatment were selected and sacrificed for carcass evaluation. Results were subjected to statistical analysis using the analysis of variance procedures of Statistical Analysis Software The treatment means were presented with group standard errors of means and where significant, were compared using the Duncan multiple range test of the same software. The results showed that broilers fed 2.5% neem kernel inclusion diets had growth performance statistically comparable to those fed the control diet. Birds on 5, 7.5 and 10% neem kernel diets showed significant (P<0.05) increase in relative weight of liver. The absolute weight of spleen also increased significantly (P<0.05) in birds on 10 % neem kernel diet. More than 5 % neem kernel diets gave significant (P<0.05) increase in the relative weight of the kidney. The length of the small intestine significantly increased in birds fed 7.5 and 10% neem kernel diets. Significant differences (P<0.05) did not occur in the length of the large intestine, right and left caeca. It is recommended that neem kernel can be included up to 2.5% in broiler chicken diet without any deleterious effects on the performance and physiological status of the birds.

Keywords: broiler chicken, growth performance, gut morphometry, neem kernel, organ weight

Procedia PDF Downloads 759

Authors: A. Schirru, A. Irimescu, S. Merola, A. d’Adamo, S. Fontanesi

Abstract:

One of the aspects that are usually neglected during the design phase of an engine is the effect of the spark plug on the flow field inside the combustion chamber. Because of the difficulties in the experimental investigation of the mutual interaction between flow alteration and early flame kernel convection effect inside the engine combustion chamber, CFD-3D simulation is usually exploited in such cases. Experimentally speaking, a particular type of engine has to be used in order to directly observe the flame propagation process. In this study, a double electrode spark plug was fitted into an optically accessible engine and a high-speed camera was used to capture the initial stages of the combustion process. Both the arc and the kernel phases were observed. Then, a morphologic analysis was carried out and the position of the center of mass of the flame, relative to the spark plug position, was calculated. The crossflow orientation was chosen for the spark plug and the kernel growth process was observed for different air-fuel ratios. It was observed that during a normal cycle the flow field between the electrodes tends to transport the arc deforming it. Because of that, the kernel growth phase takes place away from the electrodes and the flame propagates with a preferential direction dictated by the flow field.

Keywords: Combustion, Optically Accessible Engine, Spark-Ignition Engine, Sparl Orientation, Kernel Growth

Procedia PDF Downloads 140

Authors: Baba Mbaye

Abstract:

In collaborative filtering recommendation systems, a user receives suggested items based on the opinions and evaluations of a community of users. This type of recommendation system uses only the information (notes in numerical values) contained in a usage matrix as input data. This matrix can be constructed based on users' behaviors or by offering users to declare their opinions on the items they know. The cold start problem leads to very poor performance for new users. It is a phenomenon that occurs at the beginning of use, in the situation where the system lacks data to make recommendations. There are three types of cold start problems: cold start for a new item, a new system, and a new user. We are interested in this article at the cold start for a new user. When the system welcomes a new user, the profile exists but does not have enough data, and its communities with other users profiles are still unknown. This leads to recommendations not adapted to the profile of the new user. In this paper, we propose an approach that improves cold start by using the notions of similarity and semantic proximity between users profiles during cold start. We will use the cold-metadata available (metadata extracted from the new user's data) useful in positioning the new user within a community. The aim is to look for similarities and semantic proximities with the old and current user profiles of the system. Proximity is represented by close concepts considered to belong to the same group, while similarity groups together elements that appear similar. Similarity and proximity are two close but not similar concepts. This similarity leads us to the construction of similarity which is based on: a) the concepts (properties, terms, instances) independent of ontology structure and, b) the simultaneous representation of the two concepts (relations, presence of terms in a document, simultaneous presence of the authorities). We propose an ontology, OIVCSRS (Ontology of Improvement Visitor Cold Start in Recommender Systems), in order to structure the terms and concepts representing the meaning of an information field, whether by the metadata of a namespace, or the elements of a knowledge domain. This approach allows us to automatically attach the new user to a user community, partially compensate for the data that was not initially provided and ultimately to associate a better first profile with the cold start. Thus, the aim of this paper is to propose an approach to improving cold start using semantic technologies.

Keywords: visitor cold start, recommender systems, collaborative filtering, semantic filtering

Procedia PDF Downloads 217

Authors: Shahin Mirshekari, Mohammadreza Moradi, Hossein Jafari, Mehdi Jafari, Mohammad Ensaf

Abstract:

This research employs Gaussian Process Regression (GPR) with an ensemble kernel, integrating Exponential Squared, Revised Matern, and Rational Quadratic kernels to analyze pharmaceutical sales data. Bayesian optimization was used to identify optimal kernel weights: 0.76 for Exponential Squared, 0.21 for Revised Matern, and 0.13 for Rational Quadratic. The ensemble kernel demonstrated superior performance in predictive accuracy, achieving an R² score near 1.0, and significantly lower values in MSE, MAE, and RMSE. These findings highlight the efficacy of ensemble kernels in GPR for predictive analytics in complex pharmaceutical sales datasets.

Keywords: Gaussian process regression, ensemble kernels, bayesian optimization, pharmaceutical sales analysis, time series forecasting, data analysis

Procedia PDF Downloads 68

Authors: Medjadj Tarek, Ghribi Hayet

Abstract:

This study aims to develop a flood sensitivity assessment tool using machine learning (ML) techniques and geographic information system (GIS). The importance of this study is integrating the geographic information systems (GIS) and machine learning (ML) techniques for mapping flood risks, which help decision-makers to identify the most vulnerable areas and take the necessary precautions to face this type of natural disaster. To reach this goal, we will study the case of the city of M'sila, which is among the areas most vulnerable to floods. This study drew a map of flood-prone areas based on the methodology where we have made a comparison between 3 machine learning algorithms: the xGboost model, the Random Forest algorithm and the K Nearest Neighbour algorithm. Each of them gave an accuracy respectively of 97.92 - 95 - 93.75. In the process of mapping flood-prone areas, the first model was relied upon, which gave the greatest accuracy (xGboost).

Keywords: Geographic information systems (GIS), machine learning (ML), emergency mapping, flood disaster management

Procedia PDF Downloads 93

Authors: Chien-Hung Chen, Yan-Chun Hsing, Yung-Chun Chang

Abstract:

The Internet has grown into a powerful medium for information dispersion and social interaction that leads to a rapid growth of social media which allows users to easily post their emotions and perspectives regarding certain topics online. Our research aims at using natural language processing and text mining techniques to explore the public emotions expressed on Twitter by analyzing the sentiment behind tweets. In this paper, we propose a composite kernel method that integrates tree kernel with the linear kernel to simultaneously exploit both the tree representation and the distributed emotion keyword representation to analyze the syntactic and content information in tweets. The experiment results demonstrate that our method can effectively detect public emotion of tweets while outperforming the other compared methods.

Keywords: emotion recognition, natural language processing, composite kernel, sentiment analysis, text mining

Procedia PDF Downloads 216

Authors: Kazeem K. Adewole, Ismail A. Yahya

Abstract:

In the published literature, Palm Kernel Shell (PKS), an agricultural waste has largely been used as a large aggregate in PKS concrete production. In this paper, the development of Crushed Palm Kernel Shell Fine Aggregate Concrete (CPKSFAC) with crushed PKS (CPKS) as the fine aggregate and granite as the coarse aggregate is presented. 100mm x 100mm x 100mm 1:11/2:3 and 1:2:4 CPKSFAC and River Sand Fine Aggregate Concrete (RSFAC) cubes were molded, cured for 28 days and subjected to a compressive strength test. The average wet densities of the 1:11/2:3 and 1:2:4 CPKSFAC cubes are 2240kg/m3 and 2335kg/m3 respectively. The average wet densities of the 1:11/2:3 and 1:2:4 RSFAC cubes are 2606kg/m3 and 2553kg/m3 respectively. The average compressive strengths of the 1:11/2:3 and 1:2:4 CPKSFAC cubes are 15.40MPa and 14.30MPa respectively. This study demonstrates that CPKSFA is suitable for the production of non-structural C8/10 and C12/15 concrete specified in BS EN 206-1:2000.

Keywords: crushed palm kernel shell, fine aggregate, lightweight concrete, non-structural concrete

Procedia PDF Downloads 424

Authors: Jurijs Salijevs, Katrina Bolocko

Abstract:

The integration of artificial intelligence and neural networks has significantly changed full-body imaging and high-resolution 3D mapping systems, and this paper reviews research in these areas. With an emphasis on their use in the early identification of melanoma and other disorders, the goal is to give a wide perspective on the current status and potential future of these medical imaging technologies. Authors also examine methodologies such as machine learning and deep learning, seeking to identify efficient procedures that enhance diagnostic capabilities through the analysis of 3D body scans. This work aims to encourage further research and technological development to harness the full potential of AI in disease diagnosis.

Keywords: artificial intelligence, neural networks, 3D scan, body scan, 3D mapping system, healthcare

Procedia PDF Downloads 103

Authors: Alper Taner, Yesim Benal Oztekin, Huseyin Duran

Abstract:

In this study, an Artificial Neural Network (ANN) was developed in order to classify barley varieties. For this purpose, physical properties of barley varieties were determined and ANN techniques were used. The physical properties of 8 barley varieties grown in Turkey, namely thousand kernel weight, geometric mean diameter, sphericity, kernel volume, surface area, bulk density, true density, porosity and colour parameters of grain, were determined and it was found that these properties were statistically significant with respect to varieties. As ANN model, three models, N-l, N-2 and N-3 were constructed. The performances of these models were compared. It was determined that the best-fit model was N-1. In the N-1 model, the structure of the model was designed to be 11 input layers, 2 hidden layers and 1 output layer. Thousand kernel weight, geometric mean diameter, sphericity, kernel volume, surface area, bulk density, true density, porosity and colour parameters of grain were used as input parameter; and varieties as output parameter. R2, Root Mean Square Error and Mean Error for the N-l model were found as 99.99%, 0.00074 and 0.009%, respectively. All results obtained by the N-l model were observed to have been quite consistent with real data. By this model, it would be possible to construct automation systems for classification and cleaning in flourmills.

Keywords: physical properties, artificial neural networks, barley, classification

Procedia PDF Downloads 178