Search results for: developmental tasks

Authors: Yunyong Guo, Sudhakar Ganti, Bryan Guo

Abstract:

The rapid growth of telehealth Internet of Things (IoT) devices has raised concerns about energy consumption and efficient data processing. This paper presents an energy-efficient model that integrates telehealth IoT devices with a fog and cloud computing-based platform, offering a sustainable and robust solution to overcome these challenges. Our model employs fog computing as a localized data processing layer while leveraging cloud computing for resource-intensive tasks, significantly reducing energy consumption. We incorporate adaptive energy-saving strategies. Simulation analysis validates our approach's effectiveness in enhancing energy efficiency for telehealth IoT systems integrated with localized fog nodes and both private and public cloud infrastructures. Future research will focus on further optimization of the energy-saving model, exploring additional functional enhancements, and assessing its broader applicability in other healthcare and industry sectors.

Keywords: Energy-efficient, fog computing, IoT, telehealth.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 150

Authors: Jean-Alain Grunchec, Jules Hernández-Sánchez, Sara Knott

Abstract:

Some meta-schedulers query the information system of individual supercomputers in order to submit jobs to the least busy supercomputer on a computational Grid. However, this information can become outdated by the time a job starts due to changes in scheduling priorities. The MSR scheme is based on Multiple Simultaneous Requests and can take advantage of opportunities resulting from these priorities changes. This paper presents the SWARM meta-scheduler, which can speed up the execution of large sets of tasks by minimizing the job queuing time through the submission of multiple requests. Performance tests have shown that this new meta-scheduler is faster than an implementation of the MSR scheme and the gLite meta-scheduler. SWARM has been used through the GridQTL project beta-testing portal during the past year. Statistics are provided for this usage and demonstrate its capacity to achieve reliably a substantial reduction of the execution time in production conditions.

Keywords: Grid computing, multiple simultaneous requests, fault tolerance, GridQTL.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1909

Authors: Mohamed R. Mhereeg

Abstract:

The paper discusses the design of a .NET Windows Service based agent system called MACS (Multi-Agent Classification System). MACS is a system aims to accurately classify spreadsheet developers competency over a network. It is designed to automatically and autonomously monitor spreadsheet users and gather their development activities based on the utilization of the software multi-agent technology (MAS). This is accomplished in such a way that makes management capable to efficiently allow for precise tailor training activities for future spreadsheet development. The monitoring agents of MACS are intended to be distributed over the WWW in order to satisfy the monitoring and classification of the multiple developer aspect. The Prometheus methodology is used for the design of the agents of MACS. Prometheus has been used to undertake this phase of the system design because it is developed specifically for specifying and designing agent-oriented systems. Additionally, Prometheus specifies also the communication needed between the agents in order to coordinate to achieve their delegated tasks.

Keywords: Classification, Design, MACS, MAS, Prometheus.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1688

Authors: M. E. Ghobadi, M. Ghobadi, A. Zebarjadi

Abstract:

The effect of flooding can be a serious problem for wheat farmers, even at dry land condition. Amount of flooding damage depends on duration flooding, developmental stage, wheat type and variety. Therefore as a factorial experiment in randomized complete design based on winter bread wheat cultivars (Pishtaz, Marvdasht, Shiraz, Zarin, Shahriar, C-81-4, Sardari, Agosta seed, FGS and Azar2) at stages (Non- flooding stress, flooding at tillering and stem elongation stages for 15 days) carried out in Faculty of Agriculture, Razi University, Kermanshah, Iran. During flooding, soil environment of plant roots were water saturated. Analysis of variance showed that flooding had a significant effect on the number of grains per spike, grain weight per spike and a grain weight. Hence flooding reduces the number of grain per spike between 27.1 to 42.5 percent, grain weight per spike between 34.7 to 54.4 percent and single grain weight between 12.1 to 15.1 percent. Effects of flooding at the tillering stage reduced higher than stem elongation stage on studied traits. The result also showed that flooding at tillering stage delayed spikelet primordial and floret. Between wheat cultivars was significant for traits, but were different reactions. "Shiraz", "Zarin" and "Shahriar" had the most no. grain per spike, but "Zarin" and "Sardari" had the most grain weight per spike and single grain weight, respectively. Also, interaction between start of flooding and cultivar was significant.

Keywords: Flooding, winter wheat, yield components

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2465

Authors: Jie Zhao, Meng Su

Abstract:

Image recognition enables machine-like robotics to understand a scene and plays an important role in computer vision applications. Computer vision platforms as physical infrastructure, supporting Neural Networks for image recognition, are deterministic to leverage the performance of different Neural Networks. In this paper, three different computer vision platforms – edge AI (Jetson Nano, with 4GB), a standalone laptop (with RTX 3000s, using CUDA), and a web-based device (Google Colab, using GPU) are investigated. In the case study, four prominent neural network architectures (including AlexNet, VGG16, GoogleNet, and ResNet (34/50)), are deployed. By using public ImageNets (Cifar-10), our findings provide a nuanced perspective on optimizing image recognition tasks across Edge-AI platforms, offering guidance on selecting appropriate neural network structures to maximize performance under hardware constraints.

Keywords: AlexNet, VGG, GoogleNet, ResNet, ImageNet, Cifar-10, Edge AI, Jetson Nano, CUDA, GPU.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 220

Authors: Othman Maklouf, Abdurazag Ghila, Saleh Gashoot, Ahmed Abdulla

Abstract:

Flight management system (FMS) is a specialized computer system that automates a wide variety of in-flight tasks, reducing the workload on the flight crew to the point that modern aircraft no longer carry flight engineers or navigators. The primary function of FMS is to perform the in-flight management of the flight plan using various sensors (such as GPS and INS often backed up by radio navigation) to determine the aircraft's position. From the cockpit FMS is normally controlled through a Control Display Unit (CDU) which incorporates a small screen and keyboard or touch screen. This paper investigates the performance of GPS/ INS integration techniques in which the data fusion process is done using Kalman filtering. This will include the importance of sensors calibration as well as the alignment of the strap down inertial navigation system. The limitations of the inertial navigation systems are investigated in order to understand why INS sometimes is integrated with other navigation aids and not just operating in standalone mode. Finally, both the loosely coupled and tightly coupled configurations are analyzed for several types of situations and operational conditions.

Keywords: GPS, INS, Kalman Filter.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2494

Authors: H. Iranmanesh, M. Madadi

Abstract:

Work Breakdown Structure (WBS) is one of the most vital planning processes of the project management since it is considered to be the fundamental of other processes like scheduling, controlling, assigning responsibilities, etc. In fact WBS or activity list is the heart of a project and omission of a simple task can lead to an irrecoverable result. There are some tools in order to generate a project WBS. One of the most powerful tools is mind mapping which is the basis of this article. Mind map is a method for thinking together and helps a project manager to stimulate the mind of project team members to generate project WBS. Here we try to generate a WBS of a sample project involving with the building construction using the aid of mind map and the artificial intelligence (AI) programming language. Since mind map structure can not represent data in a computerized way, we convert it to a semantic network which can be used by the computer and then extract the final WBS from the semantic network by the prolog programming language. This method will result a comprehensive WBS and decrease the probability of omitting project tasks.

Keywords: Expert System, Mind map, Semantic network, Work breakdown structure,

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2607

Authors: Zine-Eddine Bouras, Abdelouaheb Talai

Abstract:

The need to merge software artifacts seems inherent to modern software development. Distribution of development over several teams and breaking tasks into smaller, more manageable pieces are an effective means to deal with the kind of complexity. In each case, the separately developed artifacts need to be assembled as efficiently as possible into a consistent whole in which the parts still function as described. In addition, earlier changes are introduced into the life cycle and easier is their management by designers. Interaction-based specifications such as UML sequence diagrams have been found effective in this regard. As a result, sequence diagrams can be used not only for capturing system behaviors but also for merging changes in order to create a new version. The objective of this paper is to suggest a new approach to deal with the problem of software merging at the level of sequence diagrams by using the concept of dependence analysis that captures, formally, all mapping, and differences between elements of sequence diagrams and serves as a key concept to create a new version of sequence diagram.

Keywords: System behaviors, sequence diagram merging, dependence analysis, sequence diagram slicing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1762

Authors: E. Abedi, A. Ahmadi Nadooshan, S. Salehi

Abstract:

Modeling and vibration of a flexible link manipulator with tow flexible links and rigid joints are investigated which can include an arbitrary number of flexible links. Hamilton principle and finite element approach is proposed to model the dynamics of flexible manipulators. The links are assumed to be deflection due to bending. The association between elastic displacements of links is investigated, took into account the coupling effects of elastic motion and rigid motion. Flexible links are treated as Euler-Bernoulli beams and the shear deformation is thus abandoned. The dynamic behavior due to flexibility of links is well demonstrated through numerical simulation. The rigid-body motion and elastic deformations are separated by linearizing the equations of motion around the rigid body reference path. Simulation results are shown on for both position and force trajectory tracking tasks in the presence of varying parameters and unknown dynamics remarkably well. The proposed method can be used in both dynamic simulation and controller design.

Keywords: Flexible manipulator, flexible link, dynamicmodeling, end point.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2479

Authors: Michal Natora, Felix Franke, Klaus Obermayer

Abstract:

Linear convolutive filters are fast in calculation and in application, and thus, often used for real-time processing of continuous data streams. In the case of transient signals, a filter has not only to detect the presence of a specific waveform, but to estimate its arrival time as well. In this study, a measure is presented which indicates the performance of detectors in achieving both of these tasks simultaneously. Furthermore, a new sub-class of linear filters within the class of filters which minimize the quadratic response is proposed. The proposed filters are more flexible than the existing ones, like the adaptive matched filter or the minimum power distortionless response beamformer, and prove to be superior with respect to that measure in certain settings. Simulations of a real-time scenario confirm the advantage of these filters as well as the usefulness of the performance measure.

Keywords: Adaptive matched filter, minimum variance distortionless response, beam forming, Capon beam former, linear filters, performance measure.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1522

Authors: Siyao Zhu, Yifang Xu

Abstract:

After natural and man-made disasters, robots can bypass the danger, expedite the search, and acquire unprecedented situational awareness to design rescue plans. Brain-computer interface is a promising option to overcome the limitations of tedious manual control and operation of robots in the urgent search-and-rescue tasks. This study aims to test the feasibility of using electroencephalography (EEG) signals to decode human intentions and detect the level of consensus on robot-provided information. EEG signals were classified using machine-learning and deep-learning methods to discriminate search intentions and agreement perceptions. The results show that the average classification accuracy for intention recognition and consensus assessment is 67% and 72%, respectively, proving the potential of incorporating recognizable users’ bioelectrical responses into advanced robot-assisted systems for emergency response.

Keywords: Consensus assessment, electroencephalogram, EEG, emergency response, human-robot collaboration, intention recognition, search and rescue.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 344

Authors: Supriya Arya, Sunita Dhingra

Abstract:

Multiprocessor task scheduling problem for dependent and independent tasks is computationally complex problem. Many methods are proposed to achieve optimal running time. As the multiprocessor task scheduling is NP hard in nature, therefore, many heuristics are proposed which have improved the makespan of the problem. But due to problem specific nature, the heuristic method which provide best results for one problem, might not provide good results for another problem. So, Simulated Annealing which is meta heuristic approach is considered. It can be applied on all types of problems. However, due to many runs, meta heuristic approach takes large computation time. Hence, the hybrid approach is proposed by combining the Duplication Scheduling Heuristic and Simulated Annealing (SA) and the makespan results of Simple Simulated Annealing and Hybrid approach are analyzed.

Keywords: Multiprocessor task scheduling Problem, Makespan, Duplication Scheduling Heuristic, Simulated Annealing, Hybrid Approach.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2226

Authors: Naeem Muhammad, Yves Vandewoude, Yolande Berbers, Robert Feldt

Abstract:

The Requirements Abstraction Model (RAM) helps in managing abstraction in requirements by organizing them at four levels (product, feature, function and component). The RAM is adaptable and can be tailored to meet the needs of the various organizations. Because software requirements are an important source of information for developing high-level tests, organizations willing to adopt the RAM model need to know the suitability of the RAM requirements for developing high-level tests. To investigate this suitability, test cases from twenty randomly selected requirements were developed, analyzed and graded. Requirements were selected from the requirements document of a Course Management System, a web based software system that supports teachers and students in performing course related tasks. This paper describes the results of the requirements document analysis. The results show that requirements at lower levels in the RAM are suitable for developing executable tests whereas it is hard to develop from requirements at higher levels.

Keywords: Market-driven requirements engineering, requirements abstraction model, requirements abstraction, system testing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1973

Authors: Nomusa Dlodlo, Ronald Noel Beyers

Abstract:

This paper reports on an effort to address the issue of inequality in girls- and women-s access to science, engineering and technology (SET) education and careers through raising awareness on SET among secondary school girls in South Africa. Girls participated in hands-on high-tech rapid prototyping environment of a fabrication laboratory that was aimed at stimulating creativity and innovation as part of a Fab Kids initiative. The Fab Kids intervention is about creating a SET pipeline as part of the Young Engineers and Scientists of Africa Initiative.The methodology was based on a real world situation and a hands-on approach. In the process, participants acquired a number of skills including computer-aided design, research skills, communication skills, teamwork skills, technical drawing skills, writing skills and problem-solving skills. Exposure to technology enhanced the girls- confidence in being able to handle technology-related tasks.

Keywords: Girls, design engineering, gender, science, women.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2537

Authors: Wilson Chanhemo, Henry. R. Mgombelo, Omar F Hamad, T. Marwala

Abstract:

This paper presents a design of source encoding calculator software which applies the two famous algorithms in the field of information theory- the Shannon-Fano and the Huffman schemes. This design helps to easily realize the algorithms without going into a cumbersome, tedious and prone to error manual mechanism of encoding the signals during the transmission. The work describes the design of the software, how it works, comparison with related works, its efficiency, its usefulness in the field of information technology studies and the future prospects of the software to engineers, students, technicians and alike. The designed “Encodia" software has been developed, tested and found to meet the intended requirements. It is expected that this application will help students and teaching staff in their daily doing of information theory related tasks. The process is ongoing to modify this tool so that it can also be more intensely useful in research activities on source coding.

Keywords: Coding techniques, Coding algorithms, Codingefficiency, Encodia, Encoding software.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3471

Authors: Sharifah Mousli, Sona Taheri, Jiayuan He

Abstract:

Autism spectrum disorder (ASD) is a complex developmental condition involving persistent difficulties with social communication, restricted interests, and repetitive behavior. The challenges associated with ASD can interfere with an affected individual’s ability to function in social, academic, and employment settings. Although there is no effective medication known to treat ASD, to our best knowledge, early intervention can significantly improve an affected individual’s overall development. Hence, an accurate diagnosis of ASD at an early phase is essential. The use of machine learning approaches improves and speeds up the diagnosis of ASD. In this paper, we focus on the application of unsupervised clustering methods in ASD, as a large volume of ASD data generated through hospitals, therapy centers, and mobile applications has no pre-existing labels. We conduct a comparative analysis using seven clustering approaches, such as K-means, agglomerative hierarchical, model-based, fuzzy-C-means, affinity propagation, self organizing maps, linear vector quantisation – as well as the recently developed optimization-based clustering (COMSEP-Clust) approach. We evaluate the performances of the clustering methods extensively on real-world ASD datasets encompassing different age groups: toddlers, children, adolescents, and adults. Our experimental results suggest that the COMSEP-Clust approach outperforms the other seven methods in recognizing ASD with well-separated clusters.

Keywords: Autism spectrum disorder, clustering, optimization, unsupervised machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 415

Authors: Bhekisipho Twala, Mantepu Masetshaba, Ramapulana Nkoana

Abstract:

Multiple classifier systems combine several individual classifiers to deliver a final classification decision. However, an increasingly controversial question is whether such systems can outperform the single best classifier, and if so, what form of multiple classifiers system yields the most significant benefit. Also, multi-target tracking detection using multiple sensors is an important research field in mobile techniques and military applications. In this paper, several multiple classifiers systems are evaluated in terms of their ability to predict a system’s failure or success for multi-sensor target tracking tasks. The Bristol Eden project dataset is utilised for this task. Experimental and simulation results show that the human activity identification system can fulfil requirements of target tracking due to improved sensors classification performances with multiple classifier systems constructed using boosting achieving higher accuracy rates.

Keywords: Single classifier, machine learning, ensemble learning, multi-sensor target tracking.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 598

Authors: Arun Prasad Jaganathan

Abstract:

In today's dynamic industrial world, traditional task allocation methods often fall short in adapting to evolving operational conditions. This paper presents an AI-enabled task assistance and management system designed to overcome the limitations of conventional approaches. By using artificial intelligence (AI) and machine learning (ML), the system intelligently interprets user instructions, analyzes tasks, and allocates resources based on real-time data and environmental factors. Additionally, geolocation tracking enables proactive identification of potential delays, ensuring timely interventions. With its transparent reporting mechanisms, the system provides stakeholders with clear insights into task progress, fostering accountability and informed decision-making. The paper presents a comprehensive overview of the system architecture, algorithm, and implementation, highlighting its potential to revolutionize task management across diverse industries.

Keywords: Artificial intelligence, machine learning, task allocation, operational efficiency, resource optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 74

Authors: Caspar von Seckendorff, Eldar Sultanow

Abstract:

Many studies have shown that parallelization decreases efficiency [1], [2]. There are many reasons for these decrements. This paper investigates those which appear in the context of parallel data integration. Integration processes generally cannot be allocated to packages of identical size (i. e. tasks of identical complexity). The reason for this is unknown heterogeneous input data which result in variable task lengths. Process delay is defined by the slowest processing node. It leads to a detrimental effect on the total processing time. With a real world example, this study will show that while process delay does initially increase with the introduction of more nodes it ultimately decreases again after a certain point. The example will make use of the cloud computing platform Hadoop and be run inside Amazon-s EC2 compute cloud. A stochastic model will be set up which can explain this effect.

Keywords: Process delay, speedup, efficiency, parallel computing, data integration, E-Commerce, Amazon Elastic Compute Cloud (EC2), Hadoop, Nutch.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1628

Authors: Mohamed T. Sorour, Mohamed A. Abdellatif, Ahmed A. Ramadan, Ahmed A. Abo-Ismail

Abstract:

This paper describes the development of an autonomous robot for painting the interior walls of buildings. The robot consists of a painting arm with an end effector roller that scans the walls vertically and a mobile platform to give horizontal feed to paint the whole area of the wall. The painting arm has a planar twolink mechanism with two joints. Joints are driven from a stepping motor through a ball screw-nut mechanism. Four ultrasonic sensors are attached to the mobile platform and used to maintain a certain distance from the facing wall and to avoid collision with side walls. When settled on adjusted distance from the wall, the controller starts the painting process autonomously. Simplicity, relatively low weight and short painting time were considered in our design. Different modules constituting the robot have been separately tested then integrated. Experiments have shown successfulness of the robot in its intended tasks.

Keywords: Automated roller painting, Construction robots, Mobile robots, service robots, two link planar manipulator

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6970

Authors: Ali Sarhadi, Mohammad Reza Meybodi, Ali Yousefi

Abstract:

Resource discovery is one of the chief services of a grid. A new approach to discover the provenances in grid through learning automata has been propounded in this article. The objective of the aforementioned resource-discovery service is to select the resource based upon the user-s applications and the mercantile yardsticks that is to say opting for an originator which can accomplish the user-s tasks in the most economic manner. This novel service is submitted in two phases. We proffered an applicationbased categorization by means of an intelligent nerve-prone plexus. The user in question sets his or her application as the input vector of the nerve-prone nexus. The output vector of the aforesaid network limns the appropriateness of any one of the resource for the presented executive procedure. The most scrimping option out of those put forward in the previous stage which can be coped with to fulfill the task in question is picked out. Te resource choice is carried out by means of the presented algorithm based upon the learning automata.

Keywords: Resource discovery, learning automata, neural network, economic policy

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1452

Authors: A. Bagherzadhalimi, E. Di Maria

Abstract:

The feedbacks obtained regarding the sense of presence from pilot users operating a Mobile Robotic presence (MRP) system to visit a simulated museum are reported in this paper. The aim is to investigate how much the perception of system’s usefulness and ease of use is affected by operators’ sense of social telepresence (presence) in the remote location. Therefore, scenarios of visiting a museum are simulated and the user operators are supposed to perform some regular tasks inside the remote environment including interaction with local users, navigation and visiting the artworks. Participants were divided into two groups, those who had previous experience of operation and interaction with a MRP system and those who never had experience. Based on the results, both groups provided different feedbacks. Moreover, there was a significant association between user’s sense of presence and their perception of system usefulness and ease of use.

Keywords: Mobile Robotic Telepresence, Museum, Social Telepresence, Usability test.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1707

Authors: Kazuki Abe, Myungryun Yoo, Takanori Yokoyama

Abstract:

Tasks of an application program of an embedded system are managed by the scheduler of a real-time operating system (RTOS). Most RTOSs adopt just fixed priority scheduling, which is not optimal in all cases. Some applications require earliest deadline first (EDF) scheduling, which is an optimal scheduling algorithm. In order to develop an efficient real-time embedded system, the scheduling algorithm of the RTOS should be selectable. The paper presents a method to customize the scheduler using aspectoriented programming. We define aspects to replace the fixed priority scheduling mechanism of an OSEK OS with an EDF scheduling mechanism. By using the aspects, we can customize the scheduler without modifying the original source code. We have applied the aspects to an OSEK OS and get a customized operating system with EDF scheduling. The evaluation results show that the overhead of aspect-oriented programming is small enough.

Keywords: aspect-oriented programming, embedded system, operating system, real-time system

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1833

Authors: Ekachai Phaisangittisagul, Rapeepol Chongprachawat

Abstract:

Obtaining labeled data in supervised learning is often difficult and expensive, and thus the trained learning algorithm tends to be overfitting due to small number of training data. As a result, some researchers have focused on using unlabeled data which may not necessary to follow the same generative distribution as the labeled data to construct a high-level feature for improving performance on supervised learning tasks. In this paper, we investigate the impact of the relationship between unlabeled and labeled data for classification performance. Specifically, we will apply difference unlabeled data which have different degrees of relation to the labeled data for handwritten digit classification task based on MNIST dataset. Our experimental results show that the higher the degree of relation between unlabeled and labeled data, the better the classification performance. Although the unlabeled data that is completely from different generative distribution to the labeled data provides the lowest classification performance, we still achieve high classification performance. This leads to expanding the applicability of the supervised learning algorithms using unsupervised learning.

Keywords: Autoencoder, high-level feature, MNIST dataset, selftaught learning, supervised learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1832

Authors: Arnab Bandyopadhyay, Anubhab Pal, Subhajit Debnath

Abstract:

Climate change is a cumulative change in weather patterns over a period of time. Trend analysis using non-parametric Mann-Kendall test may help to determine the existence and magnitude of any statistically significant trend in the climatic data. Another index called Sen slope may be used to quantify the magnitude of such trends. A toolbar extension to ESRI ArcGIS named Arc Trends has been developed in this study for performing the above mentioned tasks. To study the temporal trend of meteorological parameters, 32 years (1971-2002) monthly meteorological data were collected for 133 selected stations over different agro-ecological regions of India. Both the maximum and minimum temperatures were found to be rising. A significant increasing trend in the relative humidity and a consistent significant decreasing trend in the wind speed all over the country were found. However, a general increase in rainfall was not found in recent years.

Keywords: Temporal trend, climate change, ArcGIS, Mann- Kendall test, Sen slope

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3086

Authors: Ghada S. Moussa

Abstract:

With the increase in population along with economic prosperity, an enormous increase in the number and types of vehicles on the roads occurred. This fact brings a growing need for efficiently yet effectively classifying vehicles into their corresponding categories, which play a crucial role in many areas of infrastructure planning and traffic management.

This paper presents two vehicle-type classification approaches; 1) geometric-based and 2) appearance-based. The two classification approaches are used for two tasks: multi-class and intra-class vehicle classifications. For the evaluation purpose of the proposed classification approaches’ performance and the identification of the most effective yet efficient one, 10-fold cross-validation technique is used with a large dataset. The proposed approaches are distinguishable from previous research on vehicle classification in which: i) they consider both geometric and appearance attributes of vehicles, and ii) they perform remarkably well in both multi-class and intra-class vehicle classification. Experimental results exhibit promising potentials implementations of the proposed vehicle classification approaches into real-world applications.

Keywords: Appearance attributes, Geometric attributes, Support vector machine, Vehicle classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4278

Authors: Keqin Li

Abstract:

Given a parallel program to be executed on a heterogeneous computing system, the overall execution time of the program is determined by a schedule. In this paper, we analyze the worst-case performance of the list scheduling algorithm for scheduling tasks of a parallel program in a mixed-machine heterogeneous computing system such that the total execution time of the program is minimized. We prove tight lower and upper bounds for the worst-case performance ratio of the list scheduling algorithm. We also examine the average-case performance of the list scheduling algorithm. Our experimental data reveal that the average-case performance of the list scheduling algorithm is much better than the worst-case performance and is very close to optimal, except for large systems with large heterogeneity. Thus, the list scheduling algorithm is very useful in real applications.

Keywords: Average-case performance, list scheduling algorithm, mixed-machine heterogeneous computing system, worst-case performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1348

Authors: Rozilawati Razali, Paul W. Garratt

Abstract:

Software maintenance, which involves making enhancements, modifications and corrections to existing software systems, consumes more than half of developer time. Specification comprehensibility plays an important role in software maintenance as it permits the understanding of the system properties more easily and quickly. The use of formal notation such as B increases a specification-s precision and consistency. However, the notation is regarded as being difficult to comprehend. Semi-formal notation such as the Unified Modelling Language (UML) is perceived as more accessible but it lacks formality. Perhaps by combining both notations could produce a specification that is not only accurate and consistent but also accessible to users. This paper presents an experiment conducted on a model that integrates the use of both UML and B notations, namely UML-B, versus a B model alone. The objective of the experiment was to evaluate the comprehensibility of a UML-B model compared to a traditional B model. The measurement used in the experiment focused on the efficiency in performing the comprehension tasks. The experiment employed a cross-over design and was conducted on forty-one subjects, including undergraduate and masters students. The results show that the notation used in the UML-B model is more comprehensible than the B model.

Keywords: Model comprehensibility, formal and semi-formal notation, empirical assessment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1597

Authors: Gangmin Li, Fan Yang

Abstract:

Personalized recommendation is crucial for any recommendation system. One of the techniques for personalized recommendation is to identify the intention. Traditional user intention identification uses the user’s selection when facing multiple items. This modeling relies primarily on historical behavior data resulting in challenges such as the cold start, unintended choice, and failure to capture intention when items are new. Motivated by recent advancements in Large Language Models (LLMs) like ChatGPT, we present an approach for user intention identification by embracing LLMs with Chain-of-Thought (CoT) prompting. We use the initial user profile as input to LLMs and design a collection of prompts to align the LLM's response through various recommendation tasks encompassing rating prediction, search and browse history, user clarification, etc. Our tests on real-world datasets demonstrate the improvements in recommendation by explicit user intention identification and, with that intention, merged into a user model.

Keywords: Personalized recommendation, generative user modeling, user intention identification, large language models, chain-of-thought prompting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 87

Authors: Justin Leo Cheang Loong, Khazaimatol S Subari, Muhammad Kamil Abdullah, Nurul Nadia Ahmad, RosliBesar

Abstract:

Heart sound is an acoustic signal and many techniques used nowadays for human recognition tasks borrow speech recognition techniques. One popular choice for feature extraction of accoustic signals is the Mel Frequency Cepstral Coefficients (MFCC) which maps the signal onto a non-linear Mel-Scale that mimics the human hearing. However the Mel-Scale is almost linear in the frequency region of heart sounds and thus should produce similar results with the standard cepstral coefficients (CC). In this paper, MFCC is investigated to see if it produces superior results for PCG based human identification system compared to CC. Results show that the MFCC system is still superior to CC despite linear filter-banks in the lower frequency range, giving up to 95% correct recognition rate for MFCC and 90% for CC. Further experiments show that the high recognition rate is due to the implementation of filter-banks and not from Mel-Scaling.

Keywords: Biometric, Phonocardiogram, Cepstral Coefficients, Mel Frequency

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3551