Search results for: classification algorithms

Authors: Zhaohan Xie, Yining Yu, Mingliang Chen

Abstract:

As research has shown a convergent tendency for aversion to AI recommendation, it is imperative to find a way to promote AI usage and better harness the technology. In the context of e-commerce, this study has found evidence that people show less avoidance of algorithms when recommending search products compared to experience products. This is due to people’s different attribution of mind to AI versus humans, as suggested by mind perception theory. While people hold the belief that an algorithm owns sufficient capability to think and calculate, which makes it competent to evaluate search product attributes that can be obtained before actual use, they doubt its capability to sense and feel, which is essential for evaluating experience product attributes that must be assessed after experience in person. The result of the behavioral investigation (Study 1, N=112) validated that consumers show low purchase intention to experience products recommended by AI. Further consumer neuroscience study (Study 2, N=26) using Event-related potential (ERP) showed that consumers have a higher level of cognitive conflict when faced with AI recommended experience product as reflected by larger N2 component, while the effect disappears for search product. This research has implications for the effective employment of AI recommenders, and it extends the literature on e-commerce and marketing communication.

Keywords: algorithm recommendation, consumer behavior, e-commerce, event-related potential, experience product, search product

Procedia PDF Downloads 105

Authors: Rajat Mittal, Jung Hee Seo, Jacob Turner, Harshal Raut

Abstract:

The perpetual advancement in computational capabilities, coupled with the continuous evolution of software tools and numerical algorithms, is creating novel avenues for research, exploration, and application at the nexus of computational fluid and structural mechanics. Fish leverage their remarkably flexible bodies and fins to harness energy from vortices, propelling themselves with an elegance and efficiency that captivates engineers. Bats fly with unparalleled agility and speed by using their flexible membrane wings. Wave-assisted propulsion (WAP) systems, utilizing elastically mounted hydrofoils, convert wave energy into thrust. Each of these problems involves a complex and elegant interplay between fluid dynamics and structural mechanics. Historically, investigations into such phenomena were constrained by available tools, but modern computational advancements now facilitate exploration of these multi-physics challenges with an unprecedented level of fidelity, precision, and realism. In this work, the author will discuss projects that harness the capabilities of high-fidelity sharp-interface immersed boundary methods to address a spectrum of engineering and biological challenges involving fluid-structure interaction.

Keywords: immersed boundary methods, CFD, bioflight, fluid structure interaction

Procedia PDF Downloads 28

Authors: P. K. Singhal, R. Naresh, V. Sharma

Abstract:

This paper presents the three optimization models, namely New Binary Artificial Bee Colony (NBABC) algorithm, NBABC with Local Search (NBABC-LS), and NBABC with Genetic Crossover (NBABC-GC) for solving the Wind-Thermal Unit Commitment (WTUC) problem. The uncertain nature of the wind power is incorporated using the Weibull probability density function, which is used to calculate the overestimation and underestimation costs associated with the wind power fluctuation. The NBABC algorithm utilizes a mechanism based on the dissimilarity measure between binary strings for generating the binary solutions in WTUC problem. In NBABC algorithm, an intelligent scout bee phase is proposed that replaces the abandoned solution with the global best solution. The local search operator exploits the neighboring region of the current solutions, whereas the integration of genetic crossover with the NBABC algorithm increases the diversity in the search space and thus avoids the problem of local trappings encountered with the NBABC algorithm. These models are then used to decide the units on/off status, whereas the lambda iteration method is used to dispatch the hourly load demand among the committed units. The effectiveness of the proposed models is validated on an IEEE 10-unit thermal system combined with a wind farm over the planning period of 24 hours.

Keywords: artificial bee colony algorithm, economic dispatch, unit commitment, wind power

Procedia PDF Downloads 351

Authors: Qiang Zhang, Xiaojian Hu

Abstract:

In multi-vehicle tracking, based on feature selection, the tracking system efficiently tracks vehicles in a video with minimal error in combination with color attribution, which focuses on presenting a simple and fast, yet accurate and robust solution to the problem such as inaccurately and untimely responses of statistics-based adaptive traffic control system in the intersection scenario. In this study, a real-time tracking system is proposed for multi-vehicle tracking in the intersection scene. Considering the complexity and application feasibility of the algorithm, in the object detection step, the detection result provided by virtual loops were post-processed and then used as the input for the tracker. For the tracker, lightweight methods were designed to extract and select features and incorporate them into the adaptive color tracking (ACT) framework. And the approbatory online feature selection algorithms are integrated on the mature ACT system with good compatibility. The proposed feature selection methods and multi-vehicle tracking method are evaluated on KITTI datasets and show efficient vehicle tracking performance when compared to the other state-of-the-art approaches in the same category. And the system performs excellently on the video sequences recorded at the intersection. Furthermore, the presented vehicle tracking system is suitable for surveillance applications.

Keywords: real-time, multi-vehicle tracking, feature selection, color attribution

Procedia PDF Downloads 120

Authors: Ashish Jaiswal, Ashwin Ramesh Babu, Mohammad Zaki Zadeh, Fillia Makedon, Glenn Wylie

Abstract:

Functional magnetic resonance imaging (fMRI) is a neuroimaging technique that records neural activations in the brain by capturing the blood oxygen level in different regions based on the task performed by a subject. Given fMRI data, the problem of predicting the state of cognitive fatigue in a person has not been investigated to its full extent. This paper proposes tackling this issue as a multi-class classification problem by dividing the state of cognitive fatigue into six different levels, ranging from no-fatigue to extreme fatigue conditions. We built a spatio-temporal model that uses convolutional neural networks (CNN) for spatial feature extraction and a long short-term memory (LSTM) network for temporal modeling of 4D fMRI scans. We also applied a self-supervised method called MoCo (Momentum Contrast) to pre-train our model on a public dataset BOLD5000 and fine-tuned it on our labeled dataset to predict cognitive fatigue. Our novel dataset contains fMRI scans from Traumatic Brain Injury (TBI) patients and healthy controls (HCs) while performing a series of N-back cognitive tasks. This method establishes a state-of-the-art technique to analyze cognitive fatigue from fMRI data and beats previous approaches to solve this problem.

Keywords: fMRI, brain imaging, deep learning, self-supervised learning, contrastive learning, cognitive fatigue

Procedia PDF Downloads 161

Authors: Jeevan Jyoti Mohindroo, Umesh Kumar Garg

Abstract:

The district of Tarntaran is located25 km south of Amritsar city in Punjab State of Northwestern India. It is 5059 Sq. Km in area. It is surrounded by Amritsar in the North, Kapurthala in the East, and Ferozepur in the South and Pakistan in the West. Patti Town is a municipal council of the Tarntaran district of the Indian state of Punjab, located 45 km from Amritsar its geographical coordinates are 310 16' 51" north to 740 51' 25" East Longitude. The town spreads over an area of 50sq. Km. Moisture content is very less in the air, falling within the semiarid region and frequently facing water scarcity as well as water quality problems. The major sources of employment are agriculture, horticulture and animal husbandry engaging almost 80% of the workforce. Water samples are collected from 400 locations in 20 villages on the Patti –Khem Karan highway with 20 samples from each village, and were subjected to analysis of chemical characteristics. The type of water that predominates in the study area is Ca-Mg-HCO3 type, based on hydro-chemical analysis. Besides, suitability of water for irrigation is evaluated based on the sodium adsorption ratio (SAR), residual sodium carbonate, sodium percent and salinity hazard. Other Physico-chemical parameters such as pH, TDS, conductance, etc. were also determined using a water analysis kit. Analysis of water samples for heavy metal analysis was also carried out in the present study.

Keywords: groundwater, chemical classification, SAR, RSC, USSL diagram

Procedia PDF Downloads 166

Authors: Rabab M. Ramadan, Elaraby A. Elgallad

Abstract:

With extensive application, the performance of unimodal biometrics systems has to face a diversity of problems such as signal and background noise, distortion, and environment differences. Therefore, multimodal biometric systems are proposed to solve the above stated problems. This paper introduces a bimodal biometric recognition system based on the extracted features of the human palm print and iris. Palm print biometric is fairly a new evolving technology that is used to identify people by their palm features. The iris is a strong competitor together with face and fingerprints for presence in multimodal recognition systems. In this research, we introduced an algorithm to the combination of the palm and iris-extracted features using a texture-based descriptor, the Scale Invariant Feature Transform (SIFT). Since the feature sets are non-homogeneous as features of different biometric modalities are used, these features will be concatenated to form a single feature vector. Particle swarm optimization (PSO) is used as a feature selection technique to reduce the dimensionality of the feature. The proposed algorithm will be applied to the Institute of Technology of Delhi (IITD) database and its performance will be compared with various iris recognition algorithms found in the literature.

Keywords: iris recognition, particle swarm optimization, feature extraction, feature selection, palm print, the Scale Invariant Feature Transform (SIFT)

Procedia PDF Downloads 193

Authors: Reza Babajanivalashedi, Stefania Lo Feudo, Jean-Luc Dion

Abstract:

Liquid sloshing is a crucial problem for the dynamic of moving containers in the packaging industries. Sloshing issues have been so far mainly modeled within the framework of fluid dynamics or by using equivalent mechanical models with different kinds of movements and shapes of containers. Nevertheless, these approaches do not allow to determinate the shape of the free surface of the liquid in case of the irregular shape of the moving containers, so that experimental measurements may be required. If there is too much slosh in the moving tank, the liquid can be splashed out on the packages. So, the free surface oscillation must be controlled/reduced to eliminate the splashing. The purpose of this research is to propose an optimization algorithm for finding an optimum command law to reduce surface elevation. In the first step, the free surface of the liquid is simulated based on the separation variable and weak formulation models. Then Genetic and Gradient algorithms are developed for finding the optimum command law. The optimum command law is compared with existing command laws, and the results show that there is a significant difference in surface oscillation between optimum and existing command laws. This algorithm is applicable for different varieties of bottles in case of using the camera for detecting the liquid elevation, and it can produce new command laws for different kinds of tanks to reduce the surface oscillation and remove the splashing phenomenon.

Keywords: sloshing phenomenon, separation variables, weak formulation, optimization algorithm, command law

Procedia PDF Downloads 117

Authors: Yu-Hsiu Lin, Wen-Chun Lin, Yen-Chang Cheng, Chia-Ju Yeh, Yu-Chuan Chen, Tai-You Li

Abstract:

Demand-Side Management (DSM) has the potential to reduce electricity costs and carbon emission, which are associated with electricity used in the modern society. A home Energy Management System (EMS) commonly used by residential consumers in a down-stream sector of a smart grid to monitor, control, and optimize energy efficiency to domestic appliances is a system of computer-aided functionalities as an energy audit for residential DSM. Implementing fault detection and classification to domestic appliances monitored, controlled, and optimized is one of the most important steps to realize preventive maintenance, such as residential air conditioning and heating preventative maintenance in residential/industrial DSM. In this study, a cloud intelligence-based green EMS that comes up with an Internet of Things (IoT) technology stack for residential DSM is developed. In the EMS, Arduino MEGA Ethernet communication-based smart sockets that module a Real Time Clock chip to keep track of current time as timestamps via Network Time Protocol are designed and implemented for readings of load phenomena reflecting on voltage and current signals sensed. Also, a Network-Attached Storage providing data access to a heterogeneous group of IoT clients via Hypertext Transfer Protocol (HTTP) methods is configured to data stores of parsed sensor readings. Lastly, a desktop computer with a WAMP software bundle (the Microsoft® Windows operating system, Apache HTTP Server, MySQL relational database management system, and PHP programming language) serves as a data science analytics engine for dynamic Web APP/REpresentational State Transfer-ful web service of the residential DSM having globally-Advanced Internet of Artificial Intelligence (AI)/Computational Intelligence. Where, an abstract computing machine, Java Virtual Machine, enables the desktop computer to run Java programs, and a mash-up of Java, R language, and Python is well-suited and -configured for AI in this study. Having the ability of sending real-time push notifications to IoT clients, the desktop computer implements Google-maintained Firebase Cloud Messaging to engage IoT clients across Android/iOS devices and provide mobile notification service to residential/industrial DSM. In this study, in order to realize edge intelligence that edge devices avoiding network latency and much-needed connectivity of Internet connections for Internet of Services can support secure access to data stores and provide immediate analytical and real-time actionable insights at the edge of the network, we upgrade the designed and implemented smart sockets to be embedded AI Arduino ones (called embedded AIduino). With the realization of edge analytics by the proposed embedded AIduino for data analytics, an Arduino Ethernet shield WizNet W5100 having a micro SD card connector is conducted and used. The SD library is included for reading parsed data from and writing parsed data to an SD card. And, an Artificial Neural Network library, ArduinoANN, for Arduino MEGA is imported and used for locally-embedded AI implementation. The embedded AIduino in this study can be developed for further applications in manufacturing industry energy management and sustainable energy management, wherein in sustainable energy management rotating machinery diagnostics works to identify energy loss from gross misalignment and unbalance of rotating machines in power plants as an example.

Keywords: demand-side management, edge intelligence, energy management system, fault detection and classification

Procedia PDF Downloads 224

Authors: S. Rasti, M. A. Rajabzadeh

Abstract:

Nickel-bearing laterites occur as two parallel belts along Sedimentary Zagros Orogenic (SZO) and Metamorphic Sanandaj-Sirjan (MSS) petrostructural zones, Fars Province, south Iran. An undisturbed vertical profile of these laterites includes protolith, saprolite, clay, and oxide horizons from base to top. Highly serpentinized harzburgite with relicts of olivine and orthopyroxene is regarded as the source rock. The laterites are unusual in lacking a significant saprolite zone with little development of Ni-silicates. Hematite, saponite, dolomite, smectite and clinochlore increase, while calcite, olivine, lizardite and chrysotile decrease from saprolite to oxide zones. Smectite and clinochlore with minor calcite are the major minerals in clay zone. Contacts of different horizons in laterite profiles are gradual and characterized by a decrease in Mg concentration ranging from 18.1 to 9.3 wt.% in oxide and saprolite, respectively. The maximum Ni concentration is 0.34 wt.% (NiO) in the base of the oxide zone, and goethite is the major Ni-bearing phase. From saprolite to oxide horizons, Al₂O₃, K₂O, TiO₂, and CaO decrease, while SiO₂, MnO, NiO, and Fe₂O₃ increase. Silica content reaches up to 45 wt.% in the upper part of the soil profile. There is a decrease in pH (8.44-8.17) and an increase in organic matter (0.28-0.59 wt.%) from base to top of the soils. The studied laterites are classified in the oxide clans which were derived from ophiolite ultramafic rocks under Mediterranean climate conditions.

Keywords: Iran, laterite, mineralogy, ophiolite

Procedia PDF Downloads 307

Authors: Mohiuddin Sakib, Fatin Nihal, Rabeya Akter, Anisul Haque, Munsur Rahman, Wasif-E-Elahi

Abstract:

Surge generating cyclones are one of the deadliest natural disasters that threaten the life of coastal environment and communities worldwide. Due to the geographic location, ‘low lying alluvial plain, geomorphologic characteristics and 710 kilometers exposed coastline, Bangladesh is considered as one of the greatest vulnerable country for storm surge flooding. Bay of Bengal is possessing the highest potential of creating storm surge inundation to the coastal areas. Bangladesh is the most exposed country to tropical cyclone with an average of four cyclone striking every years. Frequent cyclone landfall made the country one of the worst sufferer within the world for cyclone induced storm surge flooding and casualties. During the years from 1797 to 2009 Bangladesh has been hit by 63 severe cyclones with strengths of different magnitudes. Though detailed studies were done focusing on the specific cyclone like Sidr or Aila, no study was conducted where vulnerable areas of exposed coast were identified based on the strength of cyclones. This study classifies the vulnerable areas of the exposed coast based on storm surge inundation depth and area due to cyclones of varying strengths. Classification of the exposed coast based on hazard induced cyclonic vulnerability will help the decision makers to take appropriate policies for reducing damage and loss.

Keywords: cyclone, landfall, storm surge, exposed coastline, vulnerability

Procedia PDF Downloads 351

Authors: Strahinja Kovačević, Lidija Jevrić, Miloš Kuzmanović, Sanja Podunavac-Kuzmanović

Abstract:

In this paper, various derivatives of benzimidazole have been evaluated against Gram-negative bacteria Escherichia coli. For all investigated compounds the minimum inhibitory concentration (MIC) was determined. Quantitative structure-activity relationships (QSAR) attempts to find consistent relationships between the variations in the values of molecular properties and the biological activity for a series of compounds so that these rules can be used to evaluate new chemical entities. The correlation between MIC and some absorption, distribution, metabolism and excretion (ADME) parameters was investigated, and the mathematical models for predicting the antibacterial activity of this class of compounds were developed. The quality of the multiple linear regression (MLR) models was validated by the leave-one-out (LOO) technique, as well as by the calculation of the statistical parameters for the developed models and the results are discussed on the basis of the statistical data. The results of this study indicate that ADME parameters have a significant effect on the antibacterial activity of this class of compounds. Principal component analysis (PCA) and agglomerative hierarchical clustering algorithms (HCA) confirmed that the investigated molecules can be classified into groups on the basis of the ADME parameters: Madin-Darby Canine Kidney cell permeability (MDCK), Plasma protein binding (PPB%), human intestinal absorption (HIA%) and human colon carcinoma cell permeability (Caco-2).

Keywords: benzimidazoles, QSAR, ADME, in silico

Procedia PDF Downloads 345

Authors: Luljeta Gashi, Naser Ramadani, Zana Deva, Dafina Gexha-Bunjaku

Abstract:

The official HIV/AIDS data in Kosovo are based on HIV case reporting from health-care services, the blood transfusion system and Voluntary Counselling and Testing centres. Between 1986 and 2014, are reported 95 HIV and AIDS cases, of which 49 were AIDS, 46 HIV and 40 deaths. The majority (69%) of cases were men, age group 25 to 34 (37%) and route of transmission is: heterosexual (90%), MSM (7%), vertical transmission (2%) and IDU (1%). Based on existing data and the UNAIDS classification system, Kosovo is currently still categorised as having a low-level HIV epidemic. Even though with a low HIV prevalence, Kosovo faces a number of threatening factors, including increased number of drug users, a stigmatized and discriminated MSM community, high percentage of youth among general population (57% of the population under the age of 25), with changing social norms and especially the sexual ones. Methods: Data collection was done using self administered structured questionnaires amongst 249 high school students. Data were analysed using the Statistical Package for Social Sciences (SPSS). Results: The findings revealed that 68% of students know that HIV transmission can be reduced by having sex with only one uninfected partner who has no other partners, 94% know that the risk of getting HIV can be reduced by using a condom every time they have sex, 68% know that a person cannot get HIV from mosquito bites, 81% know that they cannot get HIV by sharing food with someone who is infected and 46% know that a healthy looking person can have HIV. Conclusions: Seventy one percent of high school students correctly identify ways of preventing the sexual transmission of HIV and who reject the major misconceptions about HIV transmission. The findings of the study indicate a need for more health education and promotion.

Keywords: Kosovo, KPAR, HIV, high school

Procedia PDF Downloads 432

Authors: Umm-E-Hani, Faiza Babar, Hanif Durad

Abstract:

Malware-detecting approaches suffer many limitations, due to which all anti-malware solutions have failed to be reliable enough for detecting zero-day malware. Signature-based solutions depend upon the signatures that can be generated only when malware surfaces at least once in the cyber world. Another approach that works by detecting the anomalies caused in the environment can easily be defeated by diligently and intelligently written malware. Solutions that have been trained to observe the behavior for detecting malicious files have failed to cater to the malware capable of detecting the sandboxed or protected environment. Machine learning and deep learning-based approaches greatly suffer in training their models with either an imbalanced dataset or an inadequate number of samples. AI-based anti-malware solutions that have been trained with enough samples targeted a selected feature vector, thus ignoring the input of leftover features in the maliciousness of malware just to cope with the lack of underlying hardware processing power. Our research focuses on producing an anti-malware solution for detecting malicious PE files by circumventing the earlier-mentioned shortcomings. Our proposed framework, which is based on automated feature engineering through autoencoders, trains the model over a fairly large dataset. It focuses on the visual patterns of malware samples to automatically extract the meaningful part of the visual pattern. Our experiment has successfully produced a state-of-the-art accuracy of 99.54 % over test data.

Keywords: malware, auto encoders, automated feature engineering, classification

Procedia PDF Downloads 46

Authors: Ki-Yeo Kim

Abstract:

Trends in genetics are transforming in order to identify differential coexpressions of correlated gene expression rather than the significant individual gene. Moreover, it is known that a combined biomarker pattern improves the discrimination of a specific cancer. The identification of the combined biomarker is also necessary for the early detection of invasive oral squamous cell carcinoma (OSCC). To identify the combined biomarker that could improve the discrimination of OSCC, we explored an appropriate number of genes in a combined gene set in order to attain the highest level of accuracy. After detecting a significant gene set, including the pre-defined number of genes, a combined expression was identified using the weights of genes in a gene set. We used the Principal Component Analysis (PCA) for the weight calculation. In this process, we used three public microarray datasets. One dataset was used for identifying the combined biomarker, and the other two datasets were used for validation. The discrimination accuracy was measured by the out-of-bag (OOB) error. There was no relation between the significance and the discrimination accuracy in each individual gene. The identified gene set included both significant and insignificant genes. One of the most significant gene sets in the classification of normal and OSCC included MMP1, SOCS3 and ACOX1. Furthermore, in the case of oral dysplasia and OSCC discrimination, two combined biomarkers were identified. The combined genomic expression achieved better performance in the discrimination of different conditions than in a single significant gene. Therefore, it could be expected that accurate diagnosis for cancer could be possible with a combined biomarker.

Keywords: oral squamous cell carcinoma, combined biomarker, microarray dataset, correlated genes

Procedia PDF Downloads 392

Authors: Jorge Rodriguez-Guerra, Carlos Calleja, Aron Pujana, Ana Maria Macarulla

Abstract:

Hydraulic-press commissioning consumes a great amount of man-hours, due to the fact that it takes place several miles away from where it has been designed. This factor became exacerbated due to control designers’ lack of knowledge about which will be the final controller gains before they start working with it. Virtual commissioning has been postulated as an optimal solution to deal with this lack of knowledge. Here, a case study is presented in which a controller is set up against a real-time model based on a hydraulic-press. The press model is designed following manufacturer specifications and it is embedded in a real-time simulator. This methodology ensures that the model achieves similar responses as the real machine that would be placed on the industry. A deterministic communication protocol is in charge of the bidirectional information transmission between the real-time model and the controller. This platform allows the engineer to test and verify the final control responses with exactly the same hardware that is going to be installed in the hydraulic-press, in other words, realize a virtual commissioning of the electro-hydraulic actuator. The Hardware in the Loop (HiL) platform validates in laboratory conditions and harmless for the machine the control algorithms designed, which allows embedding them afterwards in the industrial environment without further modifications.

Keywords: deterministic communication protocol, electro-hydraulic actuator, hardware in the loop, real-time, virtual commissioning

Procedia PDF Downloads 113

Authors: Pirom Thangchitpianpol, Suttipong Jumroonrut

Abstract:

This research investigates the distribution of food demand for animal food and the optimum amount of that food production at minimum cost. The data consist of customer purchase orders for the food of laying hens, price of food for laying hens, cost per unit for the food inventory, cost related to food of laying hens in which the food is out of stock, such as fine, overtime, urgent purchase for material. They were collected from January, 1990 to December, 2013 from a factory in Nakhonratchasima province. The collected data are analyzed in order to explore the distribution of the monthly food demand for the laying hens and to see the rate of inventory per unit. The results are used in a stochastic linear programming model for aggregate planning in which the optimum production or minimum cost could be obtained. Programming algorithms in MATLAB and tools in Linprog software are used to get the solution. The distribution of the food demand for laying hens and the random numbers are used in the model. The study shows that the distribution of monthly food demand for laying has a normal distribution, the monthly average amount (unit: 30 kg) of production from January to December. The minimum total cost average for 12 months is Baht 62,329,181.77. Therefore, the production planning can reduce the cost by 14.64% from real cost.

Keywords: animal food, stochastic linear programming, aggregate planning, production planning, demand uncertainty

Procedia PDF Downloads 353

Authors: Kun Xu, Yuan Xu, Jia Qiao

Abstract:

The document detection plays an important role in optical character recognition and text analysis. Because the traditional detection methods have weak generalization ability, and deep neural network has complex structure and large number of parameters, which cannot be well applied in mobile devices, this paper proposes a lightweight Document Corner Detection Network (DCDNet). DCDNet is a two-stage architecture. The first stage with Encoder-Decoder structure adopts depthwise separable convolution to greatly reduce the network parameters. After introducing the Feature Attention Union (FAU) module, the second stage enhances the feature information of spatial and channel dim and adaptively adjusts the size of receptive field to enhance the feature expression ability of the model. Aiming at solving the problem of the large difference in the number of pixel distribution between corner and non-corner, Weighted Binary Cross Entropy Loss (WBCE Loss) is proposed to define corner detection problem as a classification problem to make the training process more efficient. In order to make up for the lack of Dataset of document corner detection, a Dataset containing 6620 images named Document Corner Detection Dataset (DCDD) is made. Experimental results show that the proposed method can obtain fast, stable and accurate detection results on DCDD.

Keywords: document detection, corner detection, attention mechanism, lightweight

Procedia PDF Downloads 324

Authors: Ghada Badr, Manar Hosny, Nuha Bintayyash, Eman Albilali, Souad Larabi Marie-Sainte

Abstract:

The median problem is significantly applied to derive the most reasonable rearrangement phylogenetic tree for many species. More specifically, the problem is concerned with finding a permutation that minimizes the sum of distances between itself and a set of three signed permutations. Genomes with equal number of genes but different order can be represented as permutations. In this paper, an algorithm, namely BeamGA median, is proposed that combines a heuristic search approach (local beam) as an initialization step to generate a number of solutions, and then a Genetic Algorithm (GA) is applied in order to refine the solutions, aiming to achieve a better median with the smallest possible reversal distance from the three original permutations. In this approach, any genome rearrangement distance can be applied. In this paper, we use the reversal distance. To the best of our knowledge, the proposed approach was not applied before for solving the median problem. Our approach considers true biological evolution scenario by applying the concept of common intervals during the GA optimization process. This allows us to imitate a true biological behavior and enhance genetic approach time convergence. We were able to handle permutations with a large number of genes, within an acceptable time performance and with same or better accuracy as compared to existing algorithms.

Keywords: median problem, phylogenetic tree, permutation, genetic algorithm, beam search, genome rearrangement distance

Procedia PDF Downloads 240

Authors: Gabriela V. Angeles Perez, Jose Castillejos Lopez, Araceli L. Reyes Cabello, Emilio Bravo Grajales, Adriana Perez Espinosa, Jose L. Quiroz Fabian

Abstract:

Road traffic accidents are among the principal causes of traffic congestion, causing human losses, damages to health and the environment, economic losses and material damages. Studies about traditional road traffic accidents in urban zones represents very high inversion of time and money, additionally, the result are not current. However, nowadays in many countries, the crowdsourced GPS based traffic and navigation apps have emerged as an important source of information to low cost to studies of road traffic accidents and urban congestion caused by them. In this article we identified the zones, roads and specific time in the CDMX in which the largest number of road traffic accidents are concentrated during 2016. We built a database compiling information obtained from the social network known as Waze. The methodology employed was Discovery of knowledge in the database (KDD) for the discovery of patterns in the accidents reports. Furthermore, using data mining techniques with the help of Weka. The selected algorithms was the Maximization of Expectations (EM) to obtain the number ideal of clusters for the data and k-means as a grouping method. Finally, the results were visualized with the Geographic Information System QGIS.

Keywords: data mining, k-means, road traffic accidents, Waze, Weka

Procedia PDF Downloads 377

Authors: Jummalla Aashrith, N. L. Shiva Sai, K. Bhavya Sri

Abstract:

The swift progress of web technology has not only amassed a vast reservoir of internet data but also triggered a substantial surge in data generation. The internet has metamorphosed into one of the dynamic hubs for online education, idea dissemination, as well as opinion-sharing. Notably, the widely utilized social networking platform Twitter is experiencing considerable expansion, providing users with the ability to share viewpoints, participate in discussions spanning diverse communities, and broadcast messages on a global scale. The upswing in online engagement has sparked a significant curiosity in subjective analysis, particularly when it comes to Twitter data. This research is committed to delving into sentiment analysis, focusing specifically on the realm of Twitter. It aims to offer valuable insights into deciphering information within tweets, where opinions manifest in a highly unstructured and diverse manner, spanning a spectrum from positivity to negativity, occasionally punctuated by neutrality expressions. Within this document, we offer a comprehensive exploration and comparative assessment of modern approaches to opinion mining. Employing a range of machine learning algorithms such as Naive Bayes and Logistic Regression, our investigation plunges into the domain of Twitter data streams. We delve into overarching challenges and applications inherent in the realm of subjectivity analysis over Twitter.

Keywords: machine learning, sentiment analysis, visualisation, python

Procedia PDF Downloads 24

Authors: A. Bouzekri, H. Benmassaud

Abstract:

Aurès region is one of the arid and semi-arid areas that have suffered climate crises and overexploitation of natural resources they have led to significant land degradation. The use of remote sensing data allowed us to analyze the land and its spatiotemporal changes in the Aurès between 1987 and 2013, for this work, we adopted a method of analysis based on the exploitation of the images satellite Landsat TM 1987 and Landsat OLI 2013, from the supervised classification likelihood coupled with field surveys of the mission of May and September of 2013. Using ENVI EX software by the superposition of the ground cover maps from 1987 and 2013, one can extract a spatial map change of different land cover units. The results show that between 1987 and 2013 vegetation has suffered negative changes are the significant degradation of forests and steppe rangelands, and sandy soils and bare land recorded a considerable increase. The spatial change map land cover units between 1987 and 2013 allows us to understand the extensive or regressive orientation of vegetation and soil, this map shows that dense forests give his place to clear forests and steppe vegetation develops from a degraded forest vegetation and bare, sandy soils earn big steppe surfaces that explain its remarkable extension. The analysis of remote sensing data highlights the profound changes in our environment over time and quantitative monitoring of the risk of desertification.

Keywords: remote sensing, spatiotemporal, land use, Aurès

Procedia PDF Downloads 297

Authors: Ming Liu, Chong Wu, Bingquan Liu, Lei Chen

Abstract:

Internet users have to face the massive amount of textual data every day. Organizing texts into categories can help users dig the useful information from large-scale text collection. Clustering, in fact, is one of the most promising tools for categorizing texts due to its unsupervised characteristic. Unfortunately, most of traditional clustering algorithms lose their high qualities on large-scale text collection. This situation mainly attributes to the high- dimensional vectors generated from texts. To effectively and efficiently cluster large-scale text collection, this paper proposes a vector reconstruction based clustering algorithm. Only the features that can represent the cluster are preserved in cluster’s representative vector. This algorithm alternately repeats two sub-processes until it converges. One process is partial tuning sub-process, where feature’s weight is fine-tuned by iterative process. To accelerate clustering velocity, an intersection based similarity measurement and its corresponding neuron adjustment function are proposed and implemented in this sub-process. The other process is overall tuning sub-process, where the features are reallocated among different clusters. In this sub-process, the features useless to represent the cluster are removed from cluster’s representative vector. Experimental results on the three text collections (including two small-scale and one large-scale text collections) demonstrate that our algorithm obtains high quality on both small-scale and large-scale text collections.

Keywords: vector reconstruction, large-scale text clustering, partial tuning sub-process, overall tuning sub-process

Procedia PDF Downloads 404

Authors: Juliana A. Knocikova

Abstract:

Methods of nonlinear signal analysis are based on finding that random behavior can arise in deterministic nonlinear systems with a few degrees of freedom. Considering the dynamical systems, entropy is usually understood as a rate of information production. Changes in temporal dynamics of physiological data are indicating evolving of system in time, thus a level of new signal pattern generation. During last decades, many algorithms were introduced to assess some patterns of physiological responses to external stimulus. However, the reflex responses are usually characterized by short periods of time. This characteristic represents a great limitation for usual methods of nonlinear analysis. To solve the problems of short recordings, parameter of approximate entropy has been introduced as a measure of system complexity. Low value of this parameter is reflecting regularity and predictability in analyzed time series. On the other side, increasing of this parameter means unpredictability and a random behavior, hence a higher system complexity. Reduced neurophysiological data complexity has been observed repeatedly when analyzing electroneurogram and electromyogram activities during defence reflex responses. Quantitative phrenic neurogram changes are also obvious during severe hypoxia, as well as during airway reflex episodes. Concluding, the approximate entropy parameter serves as a convenient tool for analysis of reflex behavior characterized by short lasting time series.

Keywords: approximate entropy, neurophysiological data, nonlinear dynamics, reflex

Procedia PDF Downloads 278

Authors: Tianqiao Zhang, Ye Tian, Yanliang Yin, Yichao Tian, Suzhai Tian, Weige Sun, Shuhui Gong, Limei Tang, Ruoliang Tang

Abstract:

Introduction: Healthcare workers, especially the nurses all over the world, are highly vulnerable to work-related musculoskeletal disorders (WMSDs), experiencing high rates of neck, shoulder, and low back injuries, due to the unfavorable working conditions. To reduce WMSDs among nursing personnel, many workplace interventions have been developed and implemented. Unfortunately, the ongoing Covid-19 (SARS-CoV-2) pandemic has posed great challenges to the ergonomic practices and interventions in healthcare facilities, particularly the hospitals, since current Covid-19 mitigation measures, such as social distancing and working remotely, has substantially minimized in-person gatherings and trainings. On the other hand, hospitals throughout the world have been short-staffed, resulting in disturbance of shift scheduling and more importantly, the increased job demand among the available caregivers, particularly the doctors and nurses. With the latest development in communication technology, remote intervention measures have been developed as an alternative, without the necessity of in-person meetings. The Omaha System (OS) is a standardized classification system for nursing practices, including a problem classification system, an intervention system, and an outcome evaluation system. This paper describes the development of an OS-based ergonomic intervention program. Methods: First, a comprehensive literature search was performed among worldwide electronic databases, including PubMed, Web of Science, Cochrane Library, China National Knowledge Infrastructure (CNKI), between journal inception to May 2020, resulting in a total of 1,418 scientific articles. After two independent screening processes, the final knowledge pool included eleven randomized controlled trial studies to develop the draft of the intervention program with Omaha intervention subsystem as the framework. After the determination of sample size needed for statistical power and the potential loss to follow-up, a total of 94 nurses from eight clinical departments agreed to provide written, informed consent to participate in the study, which were subsequently assigned into two random groups (i.e., intervention vs. control). A subgroup of twelve nurses were randomly selected to participate in a semi-structured interview, during which their general understanding and awareness of musculoskeletal disorders and potential interventions was assessed. Then, the first draft was modified to reflect the findings from these interviews. Meanwhile, the tentative program schedule was also assessed. Next, two rounds of consultation were conducted among experts in nursing management, occupational health, psychology, and rehabilitation, to further adjust and finalize the intervention program. The control group had access to all the information and exercise modules at baseline, while an interdisciplinary research team was formed and supervised the implementation of the on-line intervention program through multiple social media groups. Outcome measures of this comparative study included biomechanical load assessed by the Quick Exposure Check and stresses due to awkward body postures. Results and Discussion: Modification to the draft included (1) supplementing traditional Chinese medicine practices, (2) adding the use of assistive patient handling equipment, and (3) revising the on-line training method. Information module should be once a week, lasting about 20 to 30 minutes, for a total of 6 weeks, while the exercise module should be 5 times a week, each lasting about 15 to 20 minutes, for a total of 6 weeks.

Keywords: ergonomic interventions, musculoskeletal disorders (MSDs), omaha system, nurses, Covid-19

Procedia PDF Downloads 131

Authors: Loai AbdAllah, Mahmoud Kaiyal

Abstract:

Missing values in real-world datasets are a common problem. Many algorithms were developed to deal with this problem, most of them replace the missing values with a fixed value that was computed based on the observed values. In our work, we used a distance function based on Bhattacharyya distance to measure the distance between objects with missing values. Bhattacharyya distance, which measures the similarity of two probability distributions. The proposed distance distinguishes between known and unknown values. Where the distance between two known values is the Mahalanobis distance. When, on the other hand, one of them is missing the distance is computed based on the distribution of the known values, for the coordinate that contains the missing value. This method was integrated with Wikaya, a digital health company developing a platform that helps to improve prevention of chronic diseases such as diabetes and cancer. In order for Wikaya’s recommendation system to work distance between users need to be measured. Since there are missing values in the collected data, there is a need to develop a distance function distances between incomplete users profiles. To evaluate the accuracy of the proposed distance function in reflecting the actual similarity between different objects, when some of them contain missing values, we integrated it within the framework of k nearest neighbors (kNN) classifier, since its computation is based only on the similarity between objects. To validate this, we ran the algorithm over diabetes and breast cancer datasets, standard benchmark datasets from the UCI repository. Our experiments show that kNN classifier using our proposed distance function outperforms the kNN using other existing methods.

Keywords: missing values, incomplete data, distance, incomplete diabetes data

Procedia PDF Downloads 188

Authors: Raymond Xu, Cindy Jingru Wang

Abstract:

Social media has become a globally connected and influencing platform. Social media data, such as tweets, can help predict the spread of pandemics and provide individuals and healthcare providers early warnings. Public psychological reactions and opinions can be efficiently monitored by AI models on the progression of dominant topics on Twitter. However, statistics show that as the coronavirus spreads, so does an infodemic of misinformation due to pandemic-related factors such as unemployment and lockdowns. Social media algorithms are often biased toward outrage by promoting content that people have an emotional reaction to and are likely to engage with. This can influence users’ attitudes and cause confusion. Therefore, social media is a double-edged sword. Combating fake news and biased content has become one of the essential tasks. This research analyzes the variety of methods used for fake news detection covering random forest, logistic regression, support vector machines, decision tree, naive Bayes, BoW, TF-IDF, LDA, CNN, RNN, LSTM, DeepFake, and hierarchical attention network. The performance of each method is analyzed. Based on these models’ achievements and limitations, a multi-dimensional AI framework is proposed to achieve higher accuracy in infodemic detection, especially pandemic-related news. The model is trained on contextual content, images, and news metadata.

Keywords: artificial intelligence, fake news detection, infodemic detection, image recognition, sentiment analysis

Procedia PDF Downloads 203

Authors: Alvaro Javier Ortega

Abstract:

A large number of companies face the challenge of matching highly-skilled professionals to high-end positions by human resource deployment professionals. However, when the professional list and tasks to be matched are larger than a few dozens, this process result is far from optimal and takes a long time to be made. Therefore, an automated assignment algorithm for this workforce management problem is needed. The majority of companies are divided into several sectors or departments, where trained employees with different experience levels deal with a large number of tasks daily. Also, the execution order of all tasks is of mater consequence, due to some of these tasks just can be run it if the result of another task is provided. Thus, a wrong execution order leads to large waiting times between consecutive tasks. The desired goal is, therefore, creating accurate matches and a near-optimal execution order that maximizes the number of tasks performed and minimizes the idle time of the expensive skilled employees. The problem described before can be model as a mixed-integer non-linear programming (MINLP) as it will be shown in detail through this paper. A large number of MINLP algorithms have been proposed in the literature. Here, genetic algorithm solutions are considered and a comparison between two different mutation approaches is presented. The simulated results considering different complexity levels of assignment decisions show the appropriateness of the proposed model.

Keywords: employees, genetic algorithm, industry management, workforce

Procedia PDF Downloads 128

Authors: Rajvir Kaur, Jeewani Anupama Ginige

Abstract:

With recent trends in Big Data and advancements in Information and Communication Technologies, the healthcare industry is at the stage of its transition from clinician oriented to technology oriented. Many people around the world die of cancer because the diagnosis of disease was not done at an early stage. Nowadays, the computational methods in the form of Machine Learning (ML) are used to develop automated decision support systems that can diagnose cancer with high confidence in a timely manner. This paper aims to carry out the comparative evaluation of a selected set of ML classifiers on two existing datasets: breast cancer and cervical cancer. The ML classifiers compared in this study are Decision Tree (DT), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Logistic Regression, Ensemble (Bagged Tree) and Artificial Neural Networks (ANN). The evaluation is carried out based on standard evaluation metrics Precision (P), Recall (R), F1-score and Accuracy. The experimental results based on the evaluation metrics show that ANN showed the highest-level accuracy (99.4%) when tested with breast cancer dataset. On the other hand, when these ML classifiers are tested with the cervical cancer dataset, Ensemble (Bagged Tree) technique gave better accuracy (93.1%) in comparison to other classifiers.

Keywords: artificial neural networks, breast cancer, classifiers, cervical cancer, f-score, machine learning, precision, recall

Procedia PDF Downloads 248

Authors: Bruce X. B. Yu, Yan Liu, Keith C. C. Chan

Abstract:

We propose to record Activities of Daily Living (ADLs) of elderly people using a vision-based system so as to provide better assistive and personalization technologies. Current ADL-related research is based on data collected with help from non-elderly subjects in laboratory environments and the activities performed are predetermined for the sole purpose of data collection. To obtain more realistic datasets for the application, we recorded ADLs for the elderly with data collected from real-world environment involving real elderly subjects. Motivated by the need to collect data for more effective research related to elderly care, we chose to collect data in the room of an elderly person. Specifically, we installed Kinect, a vision-based sensor on the ceiling, to capture the activities that the elderly subject performs in the morning every day. Based on the data, we identified 12 morning activities that the elderly person performs daily. To recognize these activities, we created a HARELCARE framework to investigate into the effectiveness of existing Human Activity Recognition (HAR) algorithms and propose the use of a transfer learning algorithm for HAR. We compared the performance, in terms of accuracy, and training progress. Although the collected dataset is relatively small, the proposed algorithm has a good potential to be applied to all daily routine activities for healthcare purposes such as evidence-based diagnosis and treatment.

Keywords: daily activity recognition, healthcare, IoT sensors, transfer learning

Procedia PDF Downloads 107