Search results for: supervised decision tree

Authors: Jessica M. Black

Abstract:

Although much of natural and social science research aims to enhance human flourishing and address social problems, the training within the two fields is significantly different across theory, methodology, and implementation of results. Social scientists are trained in social, psychological, and to the extent that it is relevant to their discipline, spiritual development, theory, and accompanying methodologies. They tend not to receive training or learn about accompanying methodology related to interrogating human development and social problems from a biological perspective. On the other hand, those in the natural sciences, and for the purpose of this work, human biological sciences specifically – biology, neuroscience, genetics, epigenetics, and physiology – are often trained first to consider cellular development and related methodologies, and may not have opportunity to receive formal training in many of the foundational principles that guide human development, such as systems theory or person-in-environment framework, methodology related to tapping both proximal and distal psycho-social-spiritual influences on human development, and foundational principles of equity, justice and inclusion in research design. There is a need for disciplines heretofore siloed to know one another, to receive streamlined, easy to access training in theory and methods from one another and to learn how to build interdisciplinary teams that can speak and act upon a shared research language. Team science is more essential than ever, as are transdisciplinary approaches to training and research design. This study explores the use of a methodological toolbox that natural and social scientists can use by employing a decision-making tree regarding project aims, costs, and participants, among other important study variables. The decision tree begins with a decision about whether the researcher wants to learn more about social sciences approaches or biological approaches to study design. The toolbox and platform are flexible, such that users could also choose among modules, for instance, reviewing epigenetics or community-based participatory research even if those are aspects already a part of their home field. To start, both natural and social scientists would receive training on systems science, team science, transdisciplinary approaches, and translational science. Next, social scientists would receive training on grounding biological theory and the following methodological approaches and tools: physiology, (epi)genetics, non-invasive neuroimaging, invasive neuroimaging, endocrinology, and the gut-brain connection. Natural scientists would receive training on grounding social science theory, and measurement including variables, assessment and surveys on human development as related to the developing person (e.g., temperament and identity), microsystems (e.g., systems that directly interact with the person such as family and peers), mesosystems (e.g., systems that interact with one another but do not directly interact with the individual person, such as parent and teacher relationships with one another), exosystems (e.g., spaces and settings that may come back to affect the individual person, such as a parent’s work environment, but within which the individual does not directly interact, macrosystems (e.g., wider culture and policy), and the chronosystem (e.g., historical time, such as the generational impact of trauma). Participants will be able to engage with the toolbox and one another to foster increased transdisciplinary work

Keywords: methodology, natural science, social science, transdisciplinary

Procedia PDF Downloads 115

Authors: Tanmay Bisen, Aastha Shayla

Abstract:

This study introduces an advanced approach to tree canopy detection in urban environments and a regional analysis of Northern and Central Kolkata that delves into the intricate relationship between urban development and environmental conservation. Leveraging high-resolution drone imagery from diverse urban green spaces in Kolkata, we fine-tuned the deep forest model to enhance its precision and accuracy. Our results, characterized by an impressive Intersection over Union (IoU) score of 0.90 and a mean average precision (mAP) of 0.87, underscore the model's robustness in detecting and classifying tree crowns amidst the complexities of aerial imagery. This research not only emphasizes the importance of model customization for specific datasets but also highlights the potential of drone-based remote sensing in urban forestry studies. The study investigates the spatial distribution, density, and environmental impact of trees in Northern and Central Kolkata. The findings underscore the significance of urban green spaces in met-ropolitan cities, emphasizing the need for sustainable urban planning that integrates green infrastructure for ecological balance and human well-being.

Keywords: urban greenery, advanced spatial distribution analysis, drone imagery, deep learning, tree detection

Procedia PDF Downloads 55

Authors: Gizelle K. Vianna, Gustavo S. Oliveira, Gabriel V. Cunha

Abstract:

The use of decision support systems in agriculture may help monitoring large fields of crops by automatically detecting the symptoms of foliage diseases. In our work, we designed and implemented a decision support system for small tomatoes producers. This work investigates ways to recognize the late blight disease from the analysis of digital images of tomatoes, using a pair of multilayer perceptron neural networks. The networks outputs are used to generate repainted tomato images in which the injuries on the plant are highlighted, and to calculate the damage level of each plant. Those levels are then used to construct a situation map of a farm where a cellular automata simulates the outbreak evolution over the fields. The simulator can test different pesticides actions, helping in the decision on when to start the spraying and in the analysis of losses and gains of each choice of action.

Keywords: artificial neural networks, cellular automata, decision support system, pattern recognition

Procedia PDF Downloads 455

Authors: Zahra Ramezanpanah, Joachim Carvallo, Aurelien Rodriguez

Abstract:

This paper aims to detect anomalies in streaming data using machine learning algorithms. In this regard, we designed two separate pipelines and evaluated the effectiveness of each separately. The first pipeline, based on supervised machine learning methods, consists of two phases. In the first phase, we trained several supervised models using the UNSW-NB15 data-set. We measured the efficiency of each using different performance metrics and selected the best model for the second phase. At the beginning of the second phase, we first, using Argus Server, sniffed a local area network. Several types of attacks were simulated and then sent the sniffed data to a running algorithm at short intervals. This algorithm can display the results of each packet of received data in real-time using the trained model. The second pipeline presented in this paper is based on unsupervised algorithms, in which a Temporal Graph Network (TGN) is used to monitor a local network. The TGN is trained to predict the probability of future states of the network based on its past behavior. Our contribution in this section is introducing an indicator to identify anomalies from these predicted probabilities.

Keywords: temporal graph network, anomaly detection, cyber security, IDS

Procedia PDF Downloads 103

Authors: Muhammad Shoaib, Hassan M Al-Swaidan

Abstract:

Saudi Arabia is the major date producer in the world. In order to maximize the production from date tree, pruning of the date trees is required annually. Large amount of this agriculture waste material (palm tree fronds) is available in Saudi Arabia and considered as an ideal source as a precursor for production of activated carbon (AC). The single step procedure for the preparation of micro porous activated carbon (AC) from Saudi date tree fronds using mixture of gases (N2 and CO2) is carried out at carbonization/activation temperature at 850°C and at different ramp rates of 10, 20 and 30 degree per minute. Alloy 330 horizontal reactor is used for tube furnace. Flow rate of nitrogen and carbon dioxide gases are kept at 150 ml/min and 50 ml/min respectively during the preparation. Characterization results reveal that the BET surface area, pore volume, and average pore diameter of the resulting activated carbon generally decreases with the increase in ramp rate. The activated carbon prepared at a ramp rate of 10 degrees/minute attains larger surface area and can offer higher potential to produce activated carbon of greater adsorption capacity from agriculture wastes such as date fronds. The BET surface areas of the activated carbons prepared at a ramp rate of 10, 20 and 30 degree/minute after 30 minutes activation time are 1094, 1020 and 515 m2/g, respectively. Scanning electron microscopy (SEM) for surface morphology, and FTIR for functional groups was carried out that also verified the same trend. Moreover, by increasing the ramp rate from 10 and 20 degrees/min the yield remains same, i.e. 18%, whereas at a ramp rate of 30 degrees/min the yield increases from 18 to 20%. Thus, it is feasible to produce high-quality micro porous activated carbon from date frond agro waste using N2 carbonization followed by physical activation with CO2 and N2 mixture. This micro porous activated carbon can be used as adsorbent of heavy metals from wastewater, NOx SOx emission adsorption from ambient air and electricity generation plants, purification of gases, sewage treatment and many other applications.

Keywords: activated carbon, date tree fronds, agricultural waste, applied chemistry

Procedia PDF Downloads 278

Authors: Onur Özdemir, M.Erhan ORHAN

Abstract:

Knowledge Development (KD) is just one of the important phases of Knowledge Management (KM). KD is the phase in which intelligence is used to see the big picture. In order to understand whether information is important or not, we have to use the intelligence cycle that includes four main steps: aiming, collecting data, processing and utilizing. KD also needs these steps. To make a precise decision, the decision maker has to be aware of his subordinates’ ideas. If the decision maker ignores the ideas of his subordinates or participants of the organization, it is not possible for him to get the target. KD is a way of using wisdom to accumulate the puzzle. If the decision maker does not bring together the puzzle pieces, he cannot get the big picture, and this shows its effects on the battlefield. In order to understand the battlefield, the decision maker has to use the intelligence cycle. To convert information to knowledge, KD is the main means for the intelligence cycle. On the other hand, the “Z Generation” born after the millennium are really the game changers. They have different attitudes from their elders. Their understanding of life is different - the definition of freedom and independence have different meanings to them than others. Decision makers have to consider these factors and rethink their decisions accordingly. This article tries to explain the relation between KD and Generation Z. KD is the main method of target managing. But if leaders neglect their people, the world will be seeing much more movements like the Arab Spring and other insurgencies.

Keywords: knowledge development, knowledge management, generation Z, intelligence cycle

Procedia PDF Downloads 517

Authors: Ling Qi, Matloob Khushi, Josiah Poon

Abstract:

This paper introduces a pre-trained Masked Candlestick Model (MCM) for trading time-series data. The pre-trained model is based on three core designs. First, we convert trading price data at each data point as a set of normalized elements and produce embeddings of each element. Second, we generate a masked sequence of such embedded elements as inputs for self-supervised learning. Third, we use the encoder mechanism from the transformer to train the inputs. The masked model learns the contextual relations among the sequence of embedded elements, which can aid downstream classification tasks. To evaluate the performance of the pre-trained model, we fine-tune MCM for three different downstream classification tasks to predict future price trends. The fine-tuned models achieved better accuracy rates for all three tasks than the baseline models. To better analyze the effectiveness of MCM, we test the same architecture for three currency pairs, namely EUR/GBP, AUD/USD, and EUR/JPY. The experimentation results demonstrate MCM’s effectiveness on all three currency pairs and indicate the MCM’s capability for signal extraction from trading data.

Keywords: masked language model, transformer, time series prediction, trading prediction, embedding, transfer learning, self-supervised learning

Procedia PDF Downloads 125

Authors: Sally Heyeon Hwang

Abstract:

Within decision theory, there are normative principles that dictate how one should act in addition to empirical theories of actual behavior. As a normative guide to one’s actual behavior, evidential or causal decision-theoretic equations allow one to identify outcomes with maximal utility values. The choice that each person makes, however, will, of course, differ according to varying assignments of weight and probability values. Regarding these different choices, it remains a subject of considerable philosophical controversy whether individual subjects have the capacity to exercise free will with respect to the assignment of probabilities, or whether instead the assignment is in some way constrained. A version of this question is given a precise form in Richard Jeffrey’s assumption that free will is necessary for Newcomb’s paradox to count as a decision problem. This paper will argue, against Jeffrey, that decision theory does not require the assumption of libertarian freedom. One of the hallmarks of decision-making is its application across a wide variety of contexts; the implications of a background assumption of free will is similarly varied. One constant across the contexts of decision is that there are always at least two levels of choice for a given agent, depending on the degree of prior constraint. Within the context of Newcomb’s problem, when the predictor is attempting to guess the choice the agent will make, he or she is analyzing the determined aspects of the agent such as past characteristics, experiences, and knowledge. On the other hand, as David Lewis’ backtracking argument concerning the relationship between past and present events brings to light, there are similarly varied ways in which the past can actually be dependent on the present. One implication of this argument is that even in deterministic settings, an agent can have more free will than it may seem. This paper will thus argue against the view that a stable background assumption of free will or determinism in decision theory is necessary, arguing instead for a compatibilist decision theory yielding a novel treatment of Newcomb’s problem.

Keywords: decision theory, compatibilism, free will, Newcomb’s problem

Procedia PDF Downloads 321

Authors: Xudong Guan, Ainong Li, Gaohuan Liu, Chong Huang, Wei Zhao

Abstract:

Due to the low spatial resolution of MODIS data, the accuracy of small-area plaque extraction with a high degree of landscape fragmentation is greatly limited. To this end, the study combines Landsat data with higher spatial resolution and MODIS data with higher temporal resolution for decision-level fusion. Considering the importance of the land heterogeneity factor in the fusion process, it is superimposed with the weighting factor, which is to linearly weight the Landsat classification result and the MOIDS classification result. Three levels were used to complete the process of data fusion, that is the pixel of MODIS data, the pixel of Landsat data, and objects level that connect between these two levels. The multilevel decision fusion scheme was tested in two sites of the lower Mekong basin. We put forth a comparison test, and it was proved that the classification accuracy was improved compared with the single data source classification results in terms of the overall accuracy. The method was also compared with the two-level combination results and a weighted sum decision rule-based approach. The decision fusion scheme is extensible to other multi-resolution data decision fusion applications.

Keywords: image classification, decision fusion, multi-temporal, remote sensing

Procedia PDF Downloads 124

Authors: Mohamed El-Shikh

Abstract:

Phaseolus vulgaris L. is the world’s second most important bean after soybeans; used for human food and animal feed. It has generally been linked to reduced risk of cardiovascular disease, diabetes mellitus, obesity, cancer and diseases of digestive tract. The effectiveness of ISSR in achievement of the genetic diversity among 60 common bean accessions; represent various germplasms around the world was investigated. In general, the studied Phaseolus vulgaris accessions were divided into 2 major groups. All of the South-American accessions were separated into the second major group. These accessions may have different genetic features that are distinct from the rest of the accessions clustered in the major group. Asia and Europe accessions (1-20) seem to be more genetically similar (99%) to each other as they clustered in the same sub-group. The American and African varieties showed similarities as well and clustered in the same sub-tree group. In contrast, Asian and American accessions No. 22 and 23 showed a high level of genetic similarities, although these were isolated from different regions. The phylogenetic tree showed that all the Asian accessions (along with Australian No. 59 and 60) were similar except Indian and Yemen accessions No. 9 and 20. Only Netherlands accession No. 3 was different from the rest of European accessions. Morocco accession No. 52 was genetically different from the rest of the African accessions. Canadian accession No. 44 seems to be different from the other North American accessions including Guatemala, Mexico and USA.

Keywords: phylogenetic tree, Phaseolus vulgaris, ISSR technique, genetics

Procedia PDF Downloads 408

Authors: Shaowei Sun

Abstract:

Let G be a graph with vertex set V(G)={v_1,v_2,...,v_n} and edge set E(G). For any vertex v belong to V(G), let d_v denote the degree of v. The normalized Laplacian matrix of the graph G is the matrix where the non-diagonal (i,j)-th entry is -1/(d_id_j) when vertex i is adjacent to vertex j and 0 when they are not adjacent, and the diagonal (i,i)-th entry is the di. In this paper, we discuss some bounds on the largest and the second smallest normalized Laplacian eigenvalue of trees and graphs. As following, we found some new bounds on the second smallest normalized Laplacian eigenvalue of tree T in terms of graph parameters. Moreover, we use Sage to give some conjectures on the second largest and the third smallest normalized eigenvalues of graph.

Keywords: graph, normalized Laplacian eigenvalues, normalized Laplacian matrix, tree

Procedia PDF Downloads 328

Authors: Yuliya Lipshits-Braziler

Abstract:

For many young adults, career decision making is a difficult and complex process that may lead to indecision. Indecision is frequently associated with great psychological distress and low levels of well-being. One important resource for dealing with indecision is career decision self-efficacy (CDSE), which refers to people’s beliefs about their ability to successfully accomplish certain tasks involved in career choice. Drawing from Social Cognitive Theory, it has been hypothesized that CDSE correlates with (a) people’s likelihood to engage in or avoid career decision making tasks, (b) the amount of effort put into the decision making process, (c) the people’s persistence in decision making efforts when faced with difficulties, and (d) the eventual success in arriving at career decisions. Based on these assumptions, the present study examines the associations between the CDSE and 14 strategies for coping with career indecision among young adults. Using the structural equation modeling (SEM), the results showed that CDSE is positively associated with the use of productive coping strategies, such as information-seeking, problem-solving, positive thinking, and self-regulation. In addition, CDSE was negatively associated with nonproductive coping strategies, such as avoidance, isolation, ruminative thinking, and blaming others. Contrary to our expectations, CDSE was not significantly correlated with instrumental help-seeking, while it was negatively correlated with emotional help-seeking. The results of this study can be used to facilitate the development of interventions aiming to reinforce young adults’ career decision making self-efficacy, which may provide them with a basis for overcoming career indecision more effectively.

Keywords: career decision self-efficacy, career indecision, coping strategies, career counseling

Procedia PDF Downloads 256

Authors: Dhanuj M. Gandikota

Abstract:

Sensor-derived three-dimensional (3D) point clouds of trees are invaluable in remote sensing analysis for the accurate measurement of key structural metrics, bio-inventory values, spatial planning/visualization, and ecological modeling. Machine learning (ML) holds the potential in addressing the restrictive tradeoffs in cost, spatial coverage, resolution, and information gain that exist in current point cloud sensing methods. Terrestrial laser scanning (TLS) remains the highest fidelity source of both canopy and below-canopy structural features, but usage is limited in both coverage and cost, requiring manual deployment to map out large, forested areas. While aerial laser scanning (ALS) remains a reliable avenue of LIDAR active remote sensing, ALS is also cost-restrictive in deployment methods. Space-borne photogrammetry from high-resolution satellite constellations is an avenue of passive remote sensing with promising viability in research for the accurate construction of vegetation 3-D point clouds. It provides both the lowest comparative cost and the largest spatial coverage across remote sensing methods. However, both space-borne photogrammetry and ALS demonstrate technical limitations in the capture of valuable below-canopy point cloud data. Looking to minimize these tradeoffs, we explored a class of powerful ML algorithms called Deep Learning (DL) that show promise in recent research on 3-D point cloud reconstruction and interpolation. Our research details the efficacy of applying these DL techniques to reconstruct accurate below-canopy point clouds from space-borne and aerial remote sensing through learned patterns of tree species fractal symmetry properties and the supplementation of locally sourced bio-inventory metrics. From our dataset, consisting of tree point clouds obtained from TLS, we deconstructed the point clouds of each tree into those that would be obtained through ALS and satellite photogrammetry of varying resolutions. We fed this ALS/satellite point cloud dataset, along with the simulated local bio-inventory metrics, into the DL point cloud reconstruction architectures to generate the full 3-D tree point clouds (the truth values are denoted by the full TLS tree point clouds containing the below-canopy information). Point cloud reconstruction accuracy was validated both through the measurement of error from the original TLS point clouds as well as the error of extraction of key structural metrics, such as crown base height, diameter above root crown, and leaf/wood volume. The results of this research additionally demonstrate the supplemental performance gain of using minimum locally sourced bio-inventory metric information as an input in ML systems to reach specified accuracy thresholds of tree point cloud reconstruction. This research provides insight into methods for the rapid, cost-effective, and accurate construction of below-canopy tree 3-D point clouds, as well as the supported potential of ML and DL to learn complex, unmodeled patterns of fractal tree growth symmetry.

Keywords: deep learning, machine learning, satellite, photogrammetry, aerial laser scanning, terrestrial laser scanning, point cloud, fractal symmetry

Procedia PDF Downloads 102

Authors: Muhammad Zaheer Awan, Adnan Qadir, Zeeshan Anjum

Abstract:

Housefly, Musca domestica Linnaeus is ubiquitous and hazardous for Homo sapiens and livestock in sundry venerations. Musca domestica cart 100 different pathogens, such as typhoid, salmonella, bacillary dysentery, tuberculosis, anthrax and parasitic worms. The flies in rural areas usually carry more pathogens. Houseflies feed on liquid or semi-liquid substances besides solid materials which are softened by saliva. Neem botanically known as Azadirachta indica belongs to the family Meliaceae and is an indigenous tree to Pakistan. The neem tree is also one such tree which has been revered by the Pakistanis and Kashmiris for its medicinal properties. Present study showed neem seed extract has potentially toxic ability that affect Total Haemocyte Count (THC) and Differential Haemocytes Count (DHC) in insect’s blood cells, of the housefly. A significant variation in haemolymph density was observed just after application, 30 minutes and 60 minutes post treatment in term of THC and DHC in comparison with novastar. The study strappingly acclaim use of neem seed extract as insecticide as compare to artificial insecticides.

Keywords: neem, Azadirachta indica, Musca domestica, differential haemocyte count (DHC), total haemocytes count (DHC), novastar

Procedia PDF Downloads 205

Authors: Syed Talib Abbas Raza, Tahseen Ahmed Jilani, Saleem Abdullah

Abstract:

This paper presents interval-valued intuitionistic fuzzy soft sets based TOPSIS method for group decision making. The interval-valued intuitionistic fuzzy soft set is a mutation of an interval-valued intuitionistic fuzzy set and soft set. In group decision making problems IVIFSS makes the process much more algebraically elegant. We have used weighted arithmetic averaging operator for aggregating the information and define a new Hybrid Score Function as metric tool for comparison between interval-valued intuitionistic fuzzy values. In an illustrative example we have applied the developed method to a criminological problem. We have developed a group decision making model for integrating the imprecise and hesitant evaluations of multiple law enforcement agencies working on target killing cases in the country.

Keywords: group decision making, interval-valued intuitionistic fuzzy soft set, TOPSIS, score function, criminology

Procedia PDF Downloads 603

Authors: Gladys Maame Akua Setordzie

Abstract:

Decision on one’s future career is said to have both beneficial and detrimental effects on one’s mental health, social and economic standing later in life, making it an important developmental problem for young people. In this light, the study’s overarching goal was to assess how different personality traits serve as a determinant of career decision-making difficulties experienced by university students in Ghana. Specifically, for the purpose of shaping the future of individualized career counselling support, the study investigated whether the “Big Five” personality traits influenced the difficulties students at the University of Ghana encounter while making career decisions. Cross-sectional survey design using a stratified random sampling technique, sampled 494 undergraduate students from the University of Ghana, who completed the Big Five Questionnaire and the Career Decision-making Difficulties Questionnaire. Hierarchical multiple regression analyses indicated that neuroticism, consciousness, and openness, accounted for a significant proportion of the variance in career decision-making difficulties. This study provides empirical evidence to support the idea that neuroticism is not necessarily a negative emotion when it comes to career decisionmaking, as has been suggested in previous studies, but rather it allows students to perform better in career decision-making. These results suggests that personality traits play a significant role in the career decision-making process of students of the University of Ghana. Therefore, a better understanding of how different personal and interpersonal factors impact career indecision in students could help career counsellors develop more focused vocational and career guidance interventions.

Keywords: career decision-making difficulties, dysfunctional career beliefs, personality traits, young people

Procedia PDF Downloads 101

Authors: Oluwatobi Emmanuel Olaniyi, Babafemi George Ogunjemite

Abstract:

The high rate of infrastructural development in Ikogosi warm spring towards harnessing her great ecotourism potentials calls for a serious concern, as more forest areas are been opened up for public access and the landscape is modified. On this note, we investigated the implication of ecotourism development on the floristic composition and forest structure in Ikogosi. The study aimed at identifying the past and present status of infrastructural development, assessing and comparing the floristic composition and structure of the built- up/ recreational areas and undisturbed forested areas, to infer on the impact of ecotourism development on the study site. We conducted stakeholder interview and field observation to identify the past and present status of infrastructural development respectively. A total of ten quadrants were employed in the vegetation assessment to characterize the woody tree species composition, diameter at breast height and height, to obtain mean indices characterizing each part of the site. These indices were compared using T – test analysis. A total of 49 different woody tree species distributed in 21 families were identified in the built-in/ recreational areas while 67 different woody tree species belonging to 25 families were recorded in the undeveloped forested areas. Although, the latter has a higher mean diameter at breast height of woody trees, it was not significantly different from the former (T-test = -0.74, p = 0.46). On the contrary, the built-up area had a higher mean trees height than the undeveloped areas, but the difference was not statistically significant (T-test= 1.04, p = 0.30). Despite these, the slight reduction in richness and diversity of the woody tree species in the built- up/ recreational areas implies mitigating the negative effects of infrastructural development on the warm spring's vegetation.

Keywords: ecosystem services, forest structure, vegetation assessment, warm-spring

Procedia PDF Downloads 509

Authors: K. Bresilla, L. Manfrini, B. Morandi, A. Boini, G. Perulli, L. C. Grappadelli

Abstract:

Image/video processing for fruit in the tree using hard-coded feature extraction algorithms have shown high accuracy during recent years. While accurate, these approaches even with high-end hardware are computationally intensive and too slow for real-time systems. This paper details the use of deep convolution neural networks (CNNs), specifically an algorithm (YOLO - You Only Look Once) with 24+2 convolution layers. Using deep-learning techniques eliminated the need for hard-code specific features for specific fruit shapes, color and/or other attributes. This CNN is trained on more than 5000 images of apple and pear fruits on 960 cores GPU (Graphical Processing Unit). Testing set showed an accuracy of 90%. After this, trained data were transferred to an embedded device (Raspberry Pi gen.3) with camera for more portability. Based on correlation between number of visible fruits or detected fruits on one frame and the real number of fruits on one tree, a model was created to accommodate this error rate. Speed of processing and detection of the whole platform was higher than 40 frames per second. This speed is fast enough for any grasping/harvesting robotic arm or other real-time applications.

Keywords: artificial intelligence, computer vision, deep learning, fruit recognition, harvesting robot, precision agriculture

Procedia PDF Downloads 420

Authors: Farzane Sadatnia, Bahram Fathi

Abstract:

Today, all public and private organizations have found that the management of the world for key information related to the activities of a staff and its main essence and philosophy, though they constitute the management information systems are very helpful in this respect the right to apply systems can save a lot in terms of economic organizations including reducing the time decision - making, improve the quality of decision making, and cost savings to bring information systems is a backup system that can never be instead of logic and human reasoning, which can be used in the series is spreading, providing resources, and provide the necessary facilities, provide better services for users, balanced budget allocation, determine strengths and weaknesses and previous plans to review the current decisions and especially the decision . Hence; in this study attempts to the effect of an information system on a review of the organization.

Keywords: information system, planning, organization, coordination, control

Procedia PDF Downloads 475

Authors: Tomáš Vyčítal

Abstract:

In a simulation model of a railway system it is important, besides other crucial algorithms, to have correct behaviour of train overtaking in stochastic conditions. This problem is being addressed in many simulation tools focused on railway traffic, however these are not very human-realistic. The goal of this paper is to create a more human-realistic overtaking decision support system for the use in railway traffic simulations. A fuzzy system has been chosen for this task as fuzzy systems are well-suited for human-like decision making. The fuzzy system designed takes into account timetables, train positions, delays and buffer times as inputs and provides an instruction to overtake or not overtake.

Keywords: decision-making support, fuzzy systems, simulation, railway, transport

Procedia PDF Downloads 139

Authors: Neelu Raina, Parvez Singh Slathia, Deepali Bhagat, Preeti Sharma

Abstract:

Pretreatment of lignocellulosic biomass for generating suitable substrates (starch/ sugars) for conversion to bioethanol is the most crucial step. In present study waste from furniture industry i.e sawdust from softwood Cedrus deodara (deodar) and hardwood Shorea robusta (sal) was used as lignocellulosic biomass. Thermochemical pretreatment was given by autoclaving at 121°C temperature and 15 psi pressure. Acids (H2SO4,HCl,HNO3,H3PO4), alkali (NaOH,NH4OH,KOH,Ca(OH)2) and organic acids (C6H8O7,C2H2O4,C4H4O4) were used at 0.1%, 0.5% and 1% concentration without giving any residence time. 1% HCl gave maximum sugar yield of 3.6587g/L in deodar and 6.1539 g/L in sal. For biological pretreatment a fungi isolated from decaying wood was used , sawdust from deodar tree species was used as a lignocellulosic substrate and before thermochemical pretreatment sawdust was treated with fungal culture at 37°C under submerged conditions with a residence time of one week followed by a thermochemical pretreatment methodology. Higher sugar yields were obtained with sal tree species followed by deodar tree species, i.e., 6.0334g/L in deodar and 8.3605g/L in sal was obtained by a combined biological and thermochemical pretreatment. Use of acids along with biological pretreatment is a favourable factor for breaking the lignin seal and thus increasing the sugar yield. Sugar estimation was done using Dinitrosalicyclic assay method. Result validation is being done by statistical analysis.

Keywords: lignocellulosic biomass, bioethanol, pretreatment, sawdust

Procedia PDF Downloads 413

Authors: Jacob Nortey

Abstract:

Introduction: In recent years, there has been an enormous success in discoveries of scientific knowledge in medicine coupled with the advancement of technology. Despite all these successes, diagnoses and treatment of diseases have become complex. According to the Ibero – American Study of Adverse Effects (IBEAS), about 10% of hospital patients suffer from secondary damage during the care process, and approximately 2% die from this process. Many clinical decision support systems have been developed to help mitigate some healthcare medical errors. Method: Relevant databases were searched, including ones that were peculiar to the clinical decision support system (that is, using google scholar, Pub Med and general google searches). The articles were then screened for a comprehensive overview of the functionality, consultative style and statistical usage of Dxplain Clinical decision support systems. Results: Inferences drawn from the articles showed high usage of Dxplain clinical decision support system for problem-based learning among students in developed countries as against little or no usage among students in Low – and Middle – income Countries. The results also indicated high usage among general practitioners. Conclusion: Despite the challenges Dxplain presents, the benefits of its usage to clinicians and students are enormous.

Keywords: dxplain, clinical decision support sytem, diagnosis, support systems

Procedia PDF Downloads 79

Authors: Symbat Moldabekova

Abstract:

This research explores the practice of decision-making in commercial banks in Kazakhstan. It focuses on recent technologies, such as contactless payments and QR code, and uses interviews with bank executives and industry practitioners to gain an understanding of how decisions are made and the role of financial assessment methods. The aim of the research is (1) to study the importance of financial techniques to evaluate IT investments; (2) to understand the role of different expert groups; (3) to explore how market trends and industry features affect decisions on IT; (4) to build a model that defines the real practice of decision-making on IT in commercial banks in Kazakhstan. The theoretical framework suggests that decision-making on IT is a socially constructed process, where actor groups with different background interact and negotiate with each other to develop a shared understanding of IT and to make more effective decisions. Theory and observations suggest that the more parties involved in the process of decision-making, the higher the possibility of disagreements between them. As each actor group has their views on the rational decision on an IT project, it is worth exploring how the final decision is made in practice. Initial findings show that the financial assessment methods are used as a guideline and do not play a big role in the final decision. The commercial banks of Kazakhstan tend to study experience of neighboring countries before adopting innovation. Implementing contactless payments is widely regarded as pinnacle success factor due to increasing competition in the market. First-to-market innovations are considered as priorities therefore, such decisions can be made with exemption of some certain actor groups from the process. Customers play significant role and they participate in testing demo versions of the products before bringing innovation to the market. The study will identify the viewpoints of actors in the banking sector on a rational decision, and the ways decision-makers from a variety of disciplines interact with each other in order to make a decision on IT in retail banks.

Keywords: actor groups, decision making, technology investment, retail banks

Procedia PDF Downloads 122

Authors: Mane Darbinyan, Lusine Hayrapetyan, Elen Matevosyan

Abstract:

Artificial Intelligence in Education (AIED) has been created to help students get ready for the workforce, and over the past 25 years, it has grown significantly, offering a variety of technologies to support academic, institutional, and administrative services. However, this is still challenging, especially considering the labor market's rapid change. While choosing a career, people face various obstacles because they do not take into consideration their own preferences, which might lead to many other problems like shifting jobs, work stress, occupational infirmity, reduced productivity, and manual error. Besides preferences, people should properly evaluate their technical and non-technical skills, as well as their personalities. Professional counseling has become a difficult undertaking for counselors due to the wide range of career choices brought on by changing technological trends. It is necessary to close this gap by utilizing technology that makes sophisticated predictions about a person's career goals based on their personality. Hence, there is a need to create an automated model that would help in decision-making based on user inputs. Improving career guidance can be achieved by embedding machine learning into the career consulting ecosystem. There are various systems of career guidance that work based on the same logic, such as the classification of applicants, matching applications with appropriate departments or jobs, making predictions, and providing suitable recommendations. Methodologies like KNN, Neural Networks, K-means clustering, D-Tree, and many other advanced algorithms are applied in the fields of data and compute some data, which is helpful to predict the right careers. Besides helping users with their career choice, these systems provide numerous opportunities which are very useful while making this hard decision. They help the candidate to recognize where he/she specifically lacks sufficient skills so that the candidate can improve those skills. They are also capable to offer an e-learning platform, taking into account the user's lack of knowledge. Furthermore, users can be provided with details on a particular job, such as the abilities required to excel in that industry.

Keywords: career guidance system, machine learning, career prediction, predictive decision, data mining, technical and non-technical skills

Procedia PDF Downloads 80

Authors: Xinghang Lv, Tao Peng, Jia Chen, Junping Liu, Xinrong Hu, Ruhan He, Minghua Jiang, Wenli Cao

Abstract:

As one of the most dangerous vulnerabilities, effective detection of buffer overflow vulnerabilities is extremely necessary. Traditional detection methods are not accurate enough and consume more resources to meet complex and enormous code environment at present. In order to resolve the above problems, we propose the method for Buffer overflow detection based on Abstract syntax tree, Control flow graph, and Data dependency graph (BodeACD) in C/C++ programs with source code. Firstly, BodeACD constructs the function samples of buffer overflow that are available on Github, then represents them as code representation sequences, which fuse control flow, data dependency, and syntax structure of source code to reduce information loss during code representation. Finally, BodeACD learns vulnerability patterns for vulnerability detection through deep learning. The results of the experiments show that BodeACD has increased the precision and recall by 6.3% and 8.5% respectively compared with the latest methods, which can effectively improve vulnerability detection and reduce False-positive rate and False-negative rate.

Keywords: vulnerability detection, abstract syntax tree, control flow graph, data dependency graph, code representation, deep learning

Procedia PDF Downloads 170

Authors: Denise Hexom, Judith Menoher

Abstract:

Teachers and administrators across America are being asked to use data and hard evidence to inform practice as they begin the task of implementing Common Core State Standards. Yet, the courses they are taking in schools of education are not preparing teachers or principals to understand the data-driven decision making (DDDM) process nor to utilize data in a much more sophisticated fashion. DDDM has been around for quite some time, however, it has only recently become systematically and consistently applied in the field of education. This paper discusses the theoretical framework of DDDM; empirical evidence supporting the effectiveness of DDDM; a process a department in a school of education has utilized to implement DDDM; and recommendations to other schools of education who attempt to implement DDDM in their decision-making processes and in their students’ coursework.

Keywords: data-driven decision making, institute of higher education, special education, continuous improvement

Procedia PDF Downloads 387

Authors: S. S. Patil, Sachidanand Kini

Abstract:

Classification of land use patterns is compelling in complexity and variability of remote sensing imageries data. An imperative research in remote sensing application exploited to mine some of the significant spatially variable factors as land cover and land use from satellite images for remote arid areas in Karnataka State, India. The diverse classification techniques, unsupervised and supervised consisting of maximum likelihood, Mahalanobis distance, and minimum distance are applied in Bellary District in Karnataka State, India for the classification of the raw satellite images. The accuracy evaluations of results are compared visually with the standard maps with ground-truths. We initiated with the maximum likelihood technique that gave the finest results and both minimum distance and Mahalanobis distance methods over valued agriculture land areas. In meanness of mislaid few irrelevant features due to the low resolution of the satellite images, high-quality accord between parameters extracted automatically from the developed maps and field observations was found.

Keywords: Mahalanobis distance, minimum distance, supervised, unsupervised, user classification accuracy, producer's classification accuracy, maximum likelihood, kappa coefficient

Procedia PDF Downloads 183

Authors: Mane Darbinyan, Lusine Hayrapetyan, Elen Matevosyan

Abstract:

Artificial Intelligence in Education (AIED) has been created to help students get ready for the workforce, and over the past 25 years, it has grown significantly, offering a variety of technologies to support academic, institutional, and administrative services. However, this is still challenging, especially considering the labor market's rapid change. While choosing a career, people face various obstacles because they do not take into consideration their own preferences, which might lead to many other problems like shifting jobs, work stress, occupational infirmity, reduced productivity, and manual error. Besides preferences, people should evaluate properly their technical and non-technical skills, as well as their personalities. Professional counseling has become a difficult undertaking for counselors due to the wide range of career choices brought on by changing technological trends. It is necessary to close this gap by utilizing technology that makes sophisticated predictions about a person's career goals based on their personality. Hence, there is a need to create an automated model that would help in decision-making based on user inputs. Improving career guidance can be achieved by embedding machine learning into the career consulting ecosystem. There are various systems of career guidance that work based on the same logic, such as the classification of applicants, matching applications with appropriate departments or jobs, making predictions, and providing suitable recommendations. Methodologies like KNN, neural networks, K-means clustering, D-Tree, and many other advanced algorithms are applied in the fields of data and compute some data, which is helpful to predict the right careers. Besides helping users with their career choice, these systems provide numerous opportunities which are very useful while making this hard decision. They help the candidate to recognize where he/she specifically lacks sufficient skills so that the candidate can improve those skills. They are also capable of offering an e-learning platform, taking into account the user's lack of knowledge. Furthermore, users can be provided with details on a particular job, such as the abilities required to excel in that industry.

Keywords: career guidance system, machine learning, career prediction, predictive decision, data mining, technical and non-technical skills

Procedia PDF Downloads 70

Authors: Rohini Hariharan, Yazhini R., Blessy Maria Mathew

Abstract:

The task of detecting email spam is a very important one in the era of digital technology that needs effective ways of curbing unwanted messages. This paper presents an approach aimed at making email spam categorization algorithms transparent, reliable and more trustworthy by incorporating Local Interpretable Model-agnostic Explanations (LIME). Our technique assists in providing interpretable explanations for specific classifications of emails to help users understand the decision-making process by the model. In this study, we developed a complete pipeline that incorporates LIME into the spam classification framework and allows creating simplified, interpretable models tailored to individual emails. LIME identifies influential terms, pointing out key elements that drive classification results, thus reducing opacity inherent in conventional machine learning models. Additionally, we suggest a visualization scheme for displaying keywords that will improve understanding of categorization decisions by users. We test our method on a diverse email dataset and compare its performance with various baseline models, such as Gaussian Naive Bayes, Multinomial Naive Bayes, Bernoulli Naive Bayes, Support Vector Classifier, K-Nearest Neighbors, Decision Tree, and Logistic Regression. Our testing results show that our model surpasses all other models, achieving an accuracy of 96.59% and a precision of 99.12%.

Keywords: text classification, LIME (local interpretable model-agnostic explanations), stemming, tokenization, logistic regression.

Procedia PDF Downloads 47

Authors: Tushar K. Routh

Abstract:

If inputs are engineered in certain manners, they can influence deep neural networks’ (DNN) performances by facilitating misclassifications, a phenomenon well-known as adversarial attacks that question networks’ vulnerability. Recent studies have unfolded the relationship between vulnerability of such networks with their complexity. In this paper, the distinctive influence of additional convolutional layers at the decision boundaries of several DNN architectures was investigated. Here, to engineer inputs from widely known image datasets like MNIST, Fashion MNIST, and Cifar 10, we have exercised One Step Spectral Attack (OSSA) and Fast Gradient Method (FGM) techniques. The aftermaths of adding layers to the robustness of the architectures have been analyzed. For reasoning, separation width from linear class partitions and local geometry (curvature) near the decision boundary have been examined. The result reveals that model complexity has significant roles in adjusting relative distances from margins, as well as the local features of decision boundaries, which impact robustness.

Keywords: DNN robustness, decision boundary, local curvature, network complexity

Procedia PDF Downloads 75