Search results for: computer processing of large databases

Authors: Devatha Kalyan Kumar, Aravindraj D., Sadathulla A.

Abstract:

Big data are now rapidly expanding in all engineering and science and many other domains. The potential of large or massive data is undoubtedly significant, make sense to require new ways of thinking and learning techniques to address the various big data challenges. Machine learning is continuously unleashing its power in a wide range of applications. In this paper, the latest advances and advancements in the researches on machine learning for big data processing. First, the machine learning techniques methods in recent studies, such as deep learning, representation learning, transfer learning, active learning and distributed and parallel learning. Then focus on the challenges and possible solutions of machine learning for big data.

Keywords: active learning, big data, deep learning, machine learning

Procedia PDF Downloads 446

Authors: Jinyan Li, Simon Fong, Raymond Wong, Mohammed Sabah, Fiaidhi Jinan

Abstract:

Clinical data analysis and forecasting have make great contributions to disease control, prevention and detection. However, such data usually suffer from highly unbalanced samples in class distributions. In this paper, we target at the binary imbalanced dataset, where the positive samples take up only the minority. We investigate two different meta-heuristic algorithms, particle swarm optimization and bat-inspired algorithm, and combine both of them with the synthetic minority over-sampling technique (SMOTE) for processing the datasets. One approach is to process the full dataset as a whole. The other is to split up the dataset and adaptively process it one segment at a time. The experimental results reveal that while the performance improvements obtained by the former methods are not scalable to larger data scales, the later one, which we call Adaptive Swarm Balancing Algorithms, leads to significant efficiency and effectiveness improvements on large datasets. We also find it more consistent with the practice of the typical large imbalanced medical datasets. We further use the meta-heuristic algorithms to optimize two key parameters of SMOTE. Leading to more credible performances of the classifier, and shortening the running time compared with the brute-force method.

Keywords: Imbalanced dataset, meta-heuristic algorithm, SMOTE, big data

Procedia PDF Downloads 441

Authors: Belbahi Ahlam

Abstract:

With the phenomenal growth in the Internet, network security has become an integral part of computer and information security. In order to come up with measures that make networks more secure, it is important to learn about the vulnerabilities that could exist in a computer network and then have an understanding of the typical attacks that have been carried out in such networks. The first half of this paper will expose the readers to the classical network attacks that have exploited the typical vulnerabilities of computer networks in the past and solutions that have been adopted since then to prevent or reduce the chances of some of these attacks. The second half of the paper will expose the readers to the different network security controls including the network architecture, protocols, standards and software/ hardware tools that have been adopted in modern day computer networks.

Keywords: network security, attacks and controls, computer and information, solutions

Procedia PDF Downloads 455

Authors: Pan Rui, Ma Jun, Zhao Caiqi, Wang Guangda

Abstract:

With the development of the tourism and religion,more and more large statue structures are adopted to build all over the world.For instance,the GuanYin statue with three plane reaches 108 meters high in HaiNan province in China.These statue structures belong to typical high-rise Building. However,the geometry sculpt of statues are complicated .The irregular shape makes these structures more complicated in force analysis than those normal standard tall buildings.In this paper,the Liu Bang Statue which is located at XuZhou in China.

Keywords: large statue structure, special-shaped steel, GuanYin statue, China

Procedia PDF Downloads 395

Authors: Mohamed Amine Ferhat, Mohamed Nadjib Bouhatem, Farid Chemat

Abstract:

One of the principal aims of sustainable and green processing development remains the dissemination and teaching of green chemistry to both developed and developing nations. This paper describes one attempt to show that “north-south” collaborations yield innovative sustainable and green technologies which give major benefits for both nations. In this paper we present early results from a solvent free microwave extraction (SFME) of essential oils using fresh orange peel, a byproduct in the production of orange juice. SFME is performed at atmospheric pressure without added any solvent or water. SFME increases essential oil yield and eliminate wastewater treatment. The procedure is appropriate for the teaching laboratory, and allows the students to learn extraction, chromatographic and spectroscopic analysis skills, and are expose to dramatic visual example of rapid, sustainable and green extraction of essential oil, and are introduced to commercially successful sustainable and green chemical processing with microwave energy.

Keywords: essential oil, extraction, green processing, microwave

Procedia PDF Downloads 544

Authors: G. Yakubova, A. Kavetskiy, S. A. Prior, H. A. Torbert

Abstract:

In-situ soil carbon determination over large soil surface areas (several hectares) is required in regard to carbon sequestration and carbon credit issues. This capability is important for optimizing modern agricultural practices and enhancing soil science knowledge. Collecting and processing representative field soil cores for traditional laboratory chemical analysis is labor-intensive and time-consuming. The neutron-stimulated gamma analysis method can be used for in-situ measurements of primary elements in agricultural soils (e.g., Si, Al, O, C, Fe, and H). This non-destructive method can assess several elements in large soil volumes with no need for sample preparation. Neutron-gamma soil elemental analysis utilizes gamma rays issued from different neutron-nuclei interactions. This process has become possible due to the availability of commercial portable pulse neutron generators, high-efficiency gamma detectors, reliable electronics, and measurement/data processing software complimented by advances in state-of-the-art nuclear physics methods. In Pulsed Fast Thermal Neutron Analysis (PFTNA), soil irradiation is accomplished using a pulsed neutron flux, and gamma spectra acquisition occurs both during and between pulses. This method allows the inelastic neutron scattering (INS) gamma spectrum to be separated from the thermal neutron capture (TNC) spectrum. Based on PFTNA, a mobile system for field-scale soil elemental determinations (primarily carbon) was developed and constructed. Our scanning methodology acquires data that can be directly used for creating soil elemental distribution maps (based on ArcGIS software) in a reasonable timeframe (~20-30 hectares per working day). Created maps are suitable for both agricultural purposes and carbon sequestration estimates. The measurement system design, spectra acquisition process, strategy for acquiring field-scale carbon content data, and mapping of agricultural fields will be discussed.

Keywords: neutron gamma analysis, soil elemental content, carbon sequestration, carbon credit, soil gamma spectroscopy, portable neutron generators, ArcMap mapping

Procedia PDF Downloads 90

Authors: Huan Ting Liao

Abstract:

In a typical manufacturing environment, computer numerical control (CNC) machining is essential for automating production through precise computer-controlled tool operations, significantly enhancing efficiency and ensuring consistent product quality. However, traditional CNC production lines often rely on manual loading and unloading, limiting operational efficiency and scalability. Although automated loading systems have been developed, they frequently lack sufficient intelligence and configuration efficiency, requiring extensive setup adjustments for different products and impacting overall productivity. This research addresses the job shop scheduling problem (JSSP) in CNC machining environments, aiming to minimize total completion time (makespan) and maximize CNC machine utilization. We propose a novel approach using reinforcement learning (RL), specifically the Q-learning algorithm, to optimize scheduling decisions. The study simulates the JSSP, incorporating robotic arm operations, machine processing times, and work order demand allocation to determine optimal processing sequences. The Q-learning algorithm enhances machine utilization by dynamically balancing workloads across CNC machines, adapting to varying job demands and machine states. This approach offers robust solutions for complex manufacturing environments by automating decision-making processes for job assignments. Additionally, we evaluate various layout configurations to identify the most efficient setup. By integrating RL-based scheduling optimization with layout analysis, this research aims to provide a comprehensive solution for improving manufacturing efficiency and productivity in CNC-based job shops. The proposed method's adaptability and automation potential promise significant advancements in tackling dynamic manufacturing challenges.

Keywords: job shop scheduling problem, reinforcement learning, operations sequence, layout optimization, q-learning

Procedia PDF Downloads 24

Authors: Mannan Malik Muhammad Naeem, Jeong Myung Yung

Abstract:

Functional near infrared spectroscopy (fNIRS) has a favorable position in non-invasive brain imaging techniques. The concentration change of oxygenated hemoglobin and de-oxygenated hemoglobin during particular cognitive activity is the basis for this neuro-imaging modality. Two wavelengths of near-infrared light can be used with modified Beer-Lambert law to explain the indirect status of neuronal activity inside brain. The temporal resolution of fNIRS is very good for real-time brain computer-interface applications. The portability, low cost and an acceptable temporal resolution of fNIRS put it on a better position in neuro-imaging modalities. In this study, an optimization model for impulse response function has been used to estimate/predict initial dip using fNIRS data. In addition, the activity strength parameter related to motor based cognitive task has been analyzed. We found an initial dip that remains around 200-300 millisecond and better localize neural activity.

Keywords: fNIRS, brain-computer interface, optimization algorithm, adaptive signal processing

Procedia PDF Downloads 226

Authors: Saad Alkahtani

Abstract:

This study aims to identify the extent to which the faculty members who teach Arabic to speakers of other languages in Arabic language institutes at Saudi universities use computer technologies such as language laboratories, websites, software programs, and learning management system (LMS). It also seeks to identify critical difficulties that hinder the use of these technologies by faculty members. The population of the study consisted of 103 faculty members in four Arabic language institutes at Saudi universities. The results of the study showed a disparity in the use of computer technologies in teaching Arabic to non-native speakers. The means of degree of use ranged from 1.20 through 2.83. The study also identified difficulties limiting the use of computer technology in teaching Arabic. And the means of averages of difficulty of use ranged from 1.50 to 2.89. The differences were not statistically significant among the institutes (at 0.05).

Keywords: Arabic language programs, computer technology, using technology in teaching Arabic language, Arabic as a second language, computer skills

Procedia PDF Downloads 462

Authors: Han Xiao, Ruan Qi, Zhang Lei, Qi Yan

Abstract:

Space environment simulator is a facility used to conduct thermal test for spacecraft, and vacuum vessel is the main body of it. According to the requirements for thermal tests of the spacecraft and its solar array panels, the primary vessel and the side vessels are designed to be a combinative structure connected with aperture, which ratio reaches 0.7. Since the vacuum vessel suffers 0.1MPa external pressure during the process of thermal test, in order to ensure the simulator’s reliability and safety, it’s necessary to calculate the vacuum vessel’s intensity and stability. Based on the impact of large openings to vacuum vessel structure, this paper explored the reinforce design and analytical way of vacuum vessel with large openings, using a large space environment simulator’s vacuum vessel design as an example. Tests showed that the reinforce structure is effective to fulfill the requirements of external pressure and the gravity. This ensured the reliability of the space environment simulator, providing a guarantee for developing the spacecraft.

Keywords: vacuum vessel, large opening, space environment simulator, structure design

Procedia PDF Downloads 535

Authors: Mohammad Hossein Ahmadi, Vahid Haghighatdoost

Abstract:

Spatial databases have been an active area of research over years. In this paper, we study how to answer the General Time-Dependent Sequenced Route queries. Given the origin and destination of a user over a time-dependent road network graph, an ordered list of categories of interests and a departure time interval, our goal is to find the minimum travel time path along with the best departure time that minimizes the total travel time from the source location to the given destination passing through a sequence of points of interests belonging to each of the specified categories of interest. The challenge of this problem is the added complexity to the optimal sequenced route queries, where we assume that first the road network is time dependent, and secondly the user defines a departure time interval instead of one single departure time instance. For processing general time-dependent sequenced route queries, we propose two solutions as Discrete-Time and Continuous-Time Sequenced Route approaches, finding approximate and exact solutions, respectively. Our proposed approaches traverse the road network based on A*-search paradigm equipped with an efficient heuristic function, for shrinking the search space. Extensive experiments are conducted to verify the efficiency of our proposed approaches.

Keywords: trip planning, time dependent, sequenced route query, road networks

Procedia PDF Downloads 321

Authors: Shubhangi Salokhe

Abstract:

Agriculture encompasses crop and livestock production, forestry, and fisheries for food and non-food products. Farmers combine land, water, commercial inputs, labor, and their management skills into practices and systems that produce food and fibre. Harvesting of agricultural produce is either followed by the processing of fresh produce or storage for later consumption. All these activities result in a vast generation of waste in terms of crop residue or food waste. So, a large amount of agricultural waste is produced every year. Waste arising from food and agricultural sectors has the potential for vast applications. So, agricultural waste management is an essential component of sustainable agriculture. The major portion of the waste comes from the residues of crops on farms, food processing, livestock, aquaculture, and agro-industry waste. Therefore, management of these agricultural wastes is an important task, and it requires robust strategic planning. It can contribute to three pillars of sustainable agriculture development. It protects the environment (environmental pillar), enhances the livelihoods of farmers (economic pillar), and can contribute to increasing the sustainability of the agricultural sector (social pillar). This paper addresses the essential technological aspects, possible solutions, and sound policy concerns to accomplish long-term way out of agriculture waste management and to minimize the negative impact of waste on the environment. The author has developed a sustainable agriculture waste management model for improving the sustainability of agriculture.

Keywords: agriculture, development, management, waste

Procedia PDF Downloads 50

Authors: Johanes Mandowa

Abstract:

The study evaluated the status of Occupational Safety and Health Management Systems’ (OSHMSs) implementation by Mutare urban timber processing factories. A descriptive cross sectional survey method was utilized in the study. Questionnaires, interviews and direct observations were the techniques employed to extract primary data from the respondents. Secondary data was acquired from OSH encyclopedia, OSH journals, newspaper articles, internet, past research papers, African Newsletter on OSH and NSSA On-guard magazines among others. Analysis of data collected was conducted using statistical and descriptive methods. Results revealed an unpleasant low uptake rate (16%) of OSH Management Systems by Mutare urban timber processing factories. On a comparative basis, low implementation levels were more pronounced in small timber processing factories than in large factories. The low uptake rate of OSH Management Systems revealed by the study validates the Government of Zimbabwe and its social partners’ observation that the dismal Zimbabwe OSH performance was largely due to non implementation of safety systems at most workplaces. The results exhibited a relationship between availability of a SHE practitioner in Mutare urban timber processing factories and OSHMS implementation. All respondents and interviewees’ agreed that OSH Management Systems are handy in curbing occupational injuries and diseases. It emerged from the study that the top barriers to implementation of safety systems are lack of adequate financial resources, lack of top management commitment and lack of OSHMS implementation expertise. Key motivators for OSHMSs establishment were cited as provision of adequate resources (76%), strong employee involvement (64%) and strong senior management commitment and involvement (60%). Study results demonstrated that both OSHMSs implementation barriers and motivators affect all Mutare urban timber processing factories irrespective of size. The study recommends enactment of a law by Ministry of Public Service, Labour and Social Welfare in consultation with NSSA to make availability of an OSHMS and qualified SHE practitioner mandatory at every workplace. More so, the enacted law should prescribe minimum educational qualification required for one to practice as a SHE practitioner. Ministry of Public Service, Labour and Social Welfare and NSSA should also devise incentives such as reduced WCIF premiums for good OSH performance to cushion Mutare urban timber processing factories from OSHMS implementation costs. The study recommends the incorporation of an OSH module in the academic curriculums of all programmes offered at tertiary institutions so as to ensure that graduates who later end up assuming influential management positions in Mutare urban timber processing factories are abreast with the necessity of OSHMSs in preventing occupational injuries and diseases. In the quest to further boost management’s awareness on the importance of OSHMSs, NSSA and SAZ are urged by the study to conduct OSHMSs awareness breakfast meetings targeting executive management on a periodic basis. The Government of Zimbabwe through the Ministry of Public Service, Labour and Social Welfare should also engage ILO Country Office for Zimbabwe to solicit for ILO’s technical assistance so as to enhance the effectiveness of NSSA’s and SAZ’s OSHMSs promotional programmes.

Keywords: occupational safety health management system, national social security authority, standard association of Zimbabwe, Mutare urban timber processing factories, ministry of public service, labour and social welfare

Procedia PDF Downloads 336

Authors: Igor Faulmann, Arnaud Saj, Roland Maurer

Abstract:

Spatial cognition consists in a plethora of high level cognitive abilities: among them, the ability to learn and to navigate in large scale environments is probably one of the most complex skills. Navigation is thought to rely on the ability to read a cognitive map, defined as an allocentric representation of ones environment. Those representations are of course intimately related to the two geometrical primitives of the environment: distance and direction. Also, many recent studies point to a predominant hippocampal and para-hippocampal role in spatial cognition, as well as in the more specific cluster of navigational skills. In a previous study in humans, we used a newly validated test assessing cognitive map processing by evaluating the ability to judge relative distances and directions: the CMRT (Cognitive Map Recall Test). This study identified in topographically disorientated patients (1) behavioral differences between the evaluation of distances and of directions, and (2) distinct causality patterns assessed via VLSM (i.e., distinct cerebral lesions cause distinct response patterns depending on the modality (distance vs direction questions). Thus, we hypothesized that: (1) if the CMRT really taps into the same resources as real navigation, there would be hippocampal, parahippocampal, and parietal activation, and (2) there exists underlying neuroanatomical and functional differences between the processing of this two modalities. Aiming toward a better understanding of the neuroanatomical correlates of the CMRT in humans, and more generally toward a better understanding of how the brain processes the cognitive map, we adapted the CMRT as an fMRI procedure. 23 healthy subjects (11 women, 12 men), all living in Geneva for at least 2 years, underwent the CMRT in fMRI. Results show, for distance and direction taken together, than the most active brain regions are the parietal, frontal and cerebellar parts. Additionally, and as expected, patterns of brain activation differ when comparing the two modalities. Furthermore, distance processing seems to rely more on parietal regions (compared to other brain regions in the same modality and also to direction). It is interesting to notice that no significant activity was observed in the hippocampal or parahippocampal areas. Direction processing seems to tap more into frontal and cerebellar brain regions (compared to other brain regions in the same modality and also to distance). Significant hippocampal and parahippocampal activity has been shown only in this modality. This results demonstrated a complex interaction of structures which are compatible with response patterns observed in other navigational tasks, thus showing that the CMRT taps at least partially into the same brain resources as real navigation. Additionally, differences between the processing of distances and directions leads to the conclusion that the human brain processes each modality distinctly. Further research should focus on the dynamics of this processing, allowing a clearer understanding between the two sub-processes.

Keywords: cognitive map, navigation, fMRI, spatial cognition

Procedia PDF Downloads 294

Authors: Ali E. Abbas

Abstract:

This paper summarizes some of the discussions that occurred in a workshop in West Virginia, U.S.A which was sponsored by the National Science Foundation (NSF) in February 2016. The goal of the workshop was to explore the opportunities and challenges for applying systems engineering in large enterprises, and some of the issues that still persist. The main topics of the discussion included challenges with elaboration and abstraction in large systems, interfacing physical and social systems, and the need for axiomatic frameworks for large enterprises. We summarize these main points of discussion drawing parallels with decision making in organizations to instigate research in these discussion areas.

Keywords: decision analysis, systems engineering, framing, value creation

Procedia PDF Downloads 329

Authors: Jali Octariady, Ida Herliningsih, Ade K. Mulyana, Annisa Fitria, Diaz C. K. Yuwana

Abstract:

Awareness of the importance large-scale maps for development of a country is growing in all walks of life, especially for governments in Indonesia. Various parties, especially local governments throughout Indonesia demanded for immediate availability the large-scale maps of 1:5000 for regional development. But in fact, the large-scale maps of 1:5000 is only available less than 5% of the entire territory of Indonesia. Unavailability precise GCP at the entire territory of Indonesia is one of causes of slow availability the large scale maps of 1:5000. This research was conducted to find an alternative solution to this problem. This study was conducted to assess the accuracy of ArcGIS base maps coordinate when it shall be used as GCP for creating a map scale of 1:5000. The study was conducted by comparing the GCP coordinate from Field survey using GPS Geodetic than the coordinate from ArcGIS basemaps in various locations in Indonesia. Some areas are used as a study area are Lombok Island, Kupang City, Surabaya City and Kediri District. The differences value of the coordinates serve as the basis for assessing the accuracy of ArcGIS basemaps coordinates. The results of the study at various study area show the variation of the amount of the coordinates value given. Differences coordinate value in the range of millimeters (mm) to meters (m) in the entire study area. This is shown the inconsistency quality of ArcGIS base maps coordinates. This inconsistency shows that the coordinate value from ArcGIS Basemaps is careless. The Careless coordinate from ArcGIS Basemaps indicates that its cannot be used as GCP for large-scale mapping on the entire territory of Indonesia.

Keywords: accuracy, ArcGIS base maps, GCP, large scale maps

Procedia PDF Downloads 373

Authors: Yayun Hsu, Henry Horng-Shing Lu

Abstract:

In this paper, a new method is proposed to extending the method of connected component labeling from processing binary images to multi-scale modeling of images. By using the adaptive threshold of multi-scale attributes, this approach minimizes the possibility of missing those important components with weak intensities. In addition, the computational cost of this approach remains similar to that of the typical approach of component labeling. Then, this methodology is applied to grain boundary detection and Drosophila Brain-bow neuron segmentation. These demonstrate the feasibility of the proposed approach in the analysis of challenging microscopy images for scientific discovery.

Keywords: microscopic image processing, scientific data mining, multi-scale modeling, data mining

Procedia PDF Downloads 434

Authors: Liang Fang

Abstract:

The development of the large suburban residential area is a product of the leap development during the rapid urbanization process in China. On the process of the large-scale development of large settlements in a short time, various problems arose in the suburban residential area, such as spatial layout being disorder, basic facilities construction lagging behind and being unreasonable, residential neighborhood space and street culture missing. Aimed at the contradictions mentioned above, exploring a way is imminent to construct appropriate residential area. We select a typical Liangzhu Culture Village in Hangzhou and put forward functional composite residential area of fine development strategy, along which business promotes and assists community autonomy and then a good community culture is constructed. All in all, the development and construction mode, contributing to an all-people and full-time participation, is beneficial to create a harmonious community of sustainable development, which gives good implication to a single enterprise development city real estate projects.

Keywords: community autonomy, development and construction mode, functional composite, suburban large residential area

Procedia PDF Downloads 358

Authors: Neringa Bagdonaite

Abstract:

Study Aims: The current study aimed to systematically analyse various research done in the area of female post-traumatic stress disorder (PTSD) and alcohol abuse, and to critically review these results on the basis of theoretical models as well as answer following questions: (I) What is the reciprocal relationship between PTSD and problem alcohol use among females; (II) What are the moderating/mediating factors of this relationship? Methods: The computer bibliographic databases Ebsco, Scopus, Springer, Web of Science, Medline, Science Direct were used to search for scientific articles. Systematic analyses sample consisted of peer-reviewed, English written articles addressing mixed gender and female PTSD and alcohol abuse issues from Jan 2012 to May 2017. Results: Total of 1011 articles were found in scientific databases related to searched keywords of which 29 met the selection criteria and were analysed. The results of longitudinal studies indicate that (I) various trauma, especially interpersonal trauma exposure in childhood is linked with increased risk of revictimization in later life and problem alcohol use; (II) revictimization in adolescence or adulthood, rather than victimization in childhood has a greater impact on the onset and progression of problematic alcohol use in adulthood. Cross-sectional and epidemiological studies also support significant relationships between female PTSD and problem alcohol use. Regards to the negative impact of alcohol use on PTSD symptoms results are yet controversial; some evidence suggests that alcohol does not exacerbate symptoms of PTSD over time, while others argue that problem alcohol use worsens PTSD symptoms and is linked to chronicity of both disorders, especially among women with previous alcohol use problems. Analysis of moderating/mediating factors of PTSD and problem alcohol use revealed, that higher motives/expectancies, specifically distress coping motives for alcohol use significantly moderates the relationship between PTSD and problematic alcohol use. Whereas negative affective states mediate relationship between symptoms of PTSD and alcohol use, but only among woman with alcohol use problems already developed. Conclusions: Interpersonal trauma experience, especially in childhood and its reappearance in lifetime is linked with PTSD symptoms and problem drinking among women. Moreover, problem alcohol use can be both a cause and a consequence of trauma and PTSD, and if used for coping it, increases the likelihood of chronicity of both disorders. In order to effectively treat both disorders, it’s worthwhile taking into account this dynamic interplay of women's PTSD symptoms and problem drinking.

Keywords: female, trauma, post-traumatic stress disorder, problem alcohol use, systemic analysis

Procedia PDF Downloads 183

Authors: Sergei Aleinik, Yuri Matveev

Abstract:

In this paper a novel method for the detection of clipping in speech signals is described. It is shown that the new method has better performance than known clipping detection methods, is easy to implement, and is robust to changes in signal amplitude, size of data, etc. Statistical simulation results are presented.

Keywords: clipping, clipped signal, speech signal processing, digital signal processing

Procedia PDF Downloads 392

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 289

Authors: Kanika Sood, Sijie Shang

Abstract:

A fundamental goal of education includes preparing students to become a part of the global workforce by making beneficial contributions to society. In this paper, we analyze student performance for multiple courses that involve different teaching pedagogies: a cooperative learning technique and an inquiry-based learning strategy. Student performance includes student engagement, grades, and attendance records. We perform this study in the Computer Science department for online and in-person courses for 450 students. We will perform correlation analysis to study the relationship between student scores and other parameters such as gender, mode of learning. We use natural language processing and machine learning to analyze student feedback data and performance data. We assess the learning outcomes of two teaching pedagogies for undergraduate and graduate courses to showcase the impact of pedagogical adoption and learning outcome as determinants of academic achievement. Early findings suggest that when using the specified pedagogies, students become experts on their topics and illustrate enhanced engagement with peers.

Keywords: bag-of-words, cooperative learning, education, inquiry-based learning, in-person learning, natural language processing, online learning, sentiment analysis, teaching pedagogy

Procedia PDF Downloads 77

Authors: Farina Riaz, Shahab Abdulla, Srinjoy Ganguly, Hajime Suzuki, Ravinesh C. Deo, Susan Hopkins

Abstract:

Recently, quantum machine learning has received significant attention. For various types of data, including text and images, numerous quantum machine learning (QML) models have been created and are being tested. Images are exceedingly complex data components that demand more processing power. Despite being mature, classical machine learning still has difficulties with big data applications. Furthermore, quantum technology has revolutionized how machine learning is thought of, by employing quantum features to address optimization issues. Since quantum hardware is currently extremely noisy, it is not practicable to run machine learning algorithms on it without risking the production of inaccurate results. To discover the advantages of quantum versus classical approaches, this research has concentrated on colored image data. Deep learning classification models are currently being created on Quantum platforms, but they are still in a very early stage. Black and white benchmark image datasets like MNIST and Fashion MINIST have been used in recent research. MNIST and CIFAR-10 were compared for binary classification, but the comparison showed that MNIST performed more accurately than colored CIFAR-10. This research will evaluate the performance of the QML algorithm on the colored benchmark dataset CIFAR-10 to advance QML's real-time applicability. However, deep learning classification models have not been developed to compare colored images like Quantum Convolutional Neural Network (QCNN) to determine how much it is better to classical. Only a few models, such as quantum variational circuits, take colored images. The methodology adopted in this research is a hybrid approach by using penny lane as a simulator. To process the 10 classes of CIFAR-10, the image data has been translated into grey scale and the 28 × 28-pixel image containing 10,000 test and 50,000 training images were used. The objective of this work is to determine how much the quantum approach can outperform a classical approach for a comprehensive dataset of color images. After pre-processing 50,000 images from a classical computer, the QCNN model adopted a hybrid method and encoded the images into a quantum simulator for feature extraction using quantum gate rotations. The measurements were carried out on the classical computer after the rotations were applied. According to the results, we note that the QCNN approach is ~12% more effective than the traditional classical CNN approaches and it is possible that applying data augmentation may increase the accuracy. This study has demonstrated that quantum machine and deep learning models can be relatively superior to the classical machine learning approaches in terms of their processing speed and accuracy when used to perform classification on colored classes.

Keywords: CIFAR-10, quantum convolutional neural networks, quantum deep learning, quantum machine learning

Procedia PDF Downloads 129

Authors: Virender Singh, Mathew Rees, Simon Hampton, Sivaram Annadurai

Abstract:

Plant identification is a challenging task that aims to identify the family, genus, and species according to plant morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users narrow down the possibilities. However, numerous morphological similarities between and within species render correct classification difficult. In this paper, we tested custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88,000 provided by the Royal Horticultural Society (RHS) and a smaller dataset of 16,000 images from the PlantClef 2015 dataset for classifying plants at genus and species levels, respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420 and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. For classifying plants at the species level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success. In conclusion, these results could help end users, professionals and the general public alike in identifying plants quicker and with improved accuracy.

Keywords: plant identification, CNN, image processing, vision transformer, classification

Procedia PDF Downloads 103

Authors: Y. Venturini, C. Tintori

Abstract:

Given the continuous demand for improved readout performances in particle and dark matter physics, CAEN SpA is pushing on the development of advanced technologies for detector readout. We present the Digitizers 2.0, the result of the success of the previous Digitizers generation, combined with expanded capabilities and a renovation of the user experience introducing the open FPGA. The first product of the family is the VX2740 (64 ch, 125 MS/s, 16 bit) for advanced waveform recording and Digital Pulse Processing, fitting with the special requirements of Dark Matter and Neutrino experiments. In parallel, CAEN is developing the FERS-5200 platform, a Front-End Readout System designed to read out large multi-detector arrays, such as SiPMs, multi-anode PMTs, silicon strip detectors, wire chambers, GEM, gas tubes, and others. This is a highly-scalable distributed platform, based on small Front-End cards synchronized and read out by a concentrator board, allowing to build extremely large experimental setup. We plan to develop a complete family of cost-effective Front-End cards tailored to specific detectors and applications. The first one available is the A5202, a 64-channel unit for SiPM readout based on CITIROC ASIC by Weeroc.

Keywords: dark matter, digitizers, front-end electronics, open FPGA, SiPM

Procedia PDF Downloads 128

Authors: Brian J. Kozak, Joshua D. Shipman, Peng Hao Wang, Blake Shipp

Abstract:

The unmanned aerial system (UAS) industry is growing at a rapid pace. This growth has increased the demand for low cost, custom made and high strength unmanned aerial vehicles (UAV). The area of most growth is in the area of 25 kg to 200 kg vehicles. Vehicles this size are beyond the size and scope of simple wood and fabric designs commonly found in hobbyist aircraft. These high end vehicles require stronger materials to complete their mission. Traditional aircraft construction materials such as aluminum are difficult to use without machining or advanced computer controlled tooling. However, by using general aviation composite aircraft homebuilding techniques and materials, a large scale UAV can be constructed cheaply and easily. Furthermore, these techniques could be used to easily manufacture cost made composite shapes and airfoils that would be cost prohibitive when using metals. These homebuilt aircraft techniques are being demonstrated by the researchers in the construction of a 75 kg aircraft.

Keywords: composite aircraft, homebuilding, unmanned aerial system industry, UAS, unmanned aerial vehicles, UAV

Procedia PDF Downloads 138

Authors: Jaspreet Singh, Gurvinder Singh, Prabhsimran Singh, Rajinder Singh, Prithvipal Singh, Karanjeet Singh Kahlon, Ravinder Singh Sawhney

Abstract:

Morphological evaluation of Indian languages is one of the burgeoning fields in the area of Natural Language Processing (NLP). The evaluation of a language is an eminent task in the era of information retrieval and text mining. The extraction and classification of knowledge from text can be exploited for sentiment analysis and morphological evaluation. This study coalesce morphological evaluation and sentiment analysis for the task of classification of farmer suicide cases reported in Punjab state of India. The pre-processing of Punjabi text involves morphological evaluation and normalization of Punjabi word tokens followed by the training of proposed model using deep learning classification on Punjabi language text extracted from online Punjabi news reports. The class-wise accuracies of sentiment prediction for four negatively oriented classes of farmer suicide cases are 93.85%, 88.53%, 83.3%, and 95.45% respectively. The overall accuracy of sentiment classification obtained using proposed framework on 275 Punjabi text documents is found to be 90.29%.

Keywords: deep neural network, farmer suicides, morphological processing, punjabi text, sentiment analysis

Procedia PDF Downloads 326

Authors: Lindani Mbatha, Suvendi Rimer, Mpho Gololo

Abstract:

Image segmentation is the process of dividing an image into several sections, such as the object's background and the foreground. It is a critical technique in both image-processing tasks and computer vision. Most of the image segmentation algorithms have been developed for gray-scale images and little research and algorithms have been developed for the color images. Most image segmentation algorithms or techniques vary based on the input data and the application. Nearly all of the techniques are not suitable for noisy environments. Most of the work that has been done uses the Markov Random Field (MRF), which involves the computations and is said to be robust to noise. In the past recent years' image segmentation has been brought to tackle problems such as easy processing of an image, interpretation of the contents of an image, and easy analysing of an image. This article reviews and summarizes some of the image segmentation techniques and algorithms that have been developed in the past years. The techniques include neural networks (CNN), edge-based techniques, region growing, clustering, and thresholding techniques and so on. The advantages and disadvantages of medical ultrasound image segmentation techniques are also discussed. The article also addresses the applications and potential future developments that can be done around image segmentation. This review article concludes with the fact that no technique is perfectly suitable for the segmentation of all different types of images, but the use of hybrid techniques yields more accurate and efficient results.

Keywords: clustering-based, convolution-network, edge-based, region-growing

Procedia PDF Downloads 96

Authors: Eugene Y. J. Aw, J. W. Koh, S. H. Chew, K. E. Chua, Lionel L. J. Ang, Algernon C. S. Hong, Danette S. E. Tan, Grace H. B. Foo, K. Q. Hong, L. M. Cheng, M. L. Leong

Abstract:

This paper presents a novel rapid soil classification technique that combines computer vision with four-probe soil electrical resistivity method and cone penetration test (CPT), to improve the accuracy and productivity of on-site classification of excavated soil. In Singapore, excavated soils from local construction projects are transported to Staging Grounds (SGs) to be reused as fill material for land reclamation. Excavated soils are mainly categorized into two groups (“Good Earth” and “Soft Clay”) based on particle size distribution (PSD) and water content (w) from soil investigation reports and on-site visual survey, such that proper treatment and usage can be exercised. However, this process is time-consuming and labour-intensive. Thus, a rapid classification method is needed at the SGs. Computer vision, four-probe soil electrical resistivity and CPT were combined into an innovative non-destructive and instantaneous classification method for this purpose. The computer vision technique comprises soil image acquisition using industrial grade camera; image processing and analysis via calculation of Grey Level Co-occurrence Matrix (GLCM) textural parameters; and decision-making using an Artificial Neural Network (ANN). Complementing the computer vision technique, the apparent electrical resistivity of soil (ρ) is measured using a set of four probes arranged in Wenner’s array. It was found from the previous study that the ANN model coupled with ρ can classify soils into “Good Earth” and “Soft Clay” in less than a minute, with an accuracy of 85% based on selected representative soil images. To further improve the technique, the soil strength is measured using a modified mini cone penetrometer, and w is measured using a set of time-domain reflectometry (TDR) probes. Laboratory proof-of-concept was conducted through a series of seven tests with three types of soils – “Good Earth”, “Soft Clay” and an even mix of the two. Validation was performed against the PSD and w of each soil type obtained from conventional laboratory tests. The results show that ρ, w and CPT measurements can be collectively analyzed to classify soils into “Good Earth” or “Soft Clay”. It is also found that these parameters can be integrated with the computer vision technique on-site to complete the rapid soil classification in less than three minutes.

Keywords: Computer vision technique, cone penetration test, electrical resistivity, rapid and non-destructive, soil classification

Procedia PDF Downloads 218

Authors: Hee-Choul Kwon, Heeyong Kwon

Abstract:

Image rotation is one of main pre-processing steps for image processing or image pattern recognition. It is implemented with a rotation matrix multiplication. It requires a lot of floating point arithmetic operations and trigonometric calculations, so it takes a long time to execute. Therefore, there has been a need for a high speed image rotation algorithm without two major time-consuming operations. However, the rotated image has a drawback, i.e. distortions. We solved the problem using an augmented two-step shear transform. We compare the presented algorithm with the conventional rotation with images of various sizes. Experimental results show that the presented algorithm is superior to the conventional rotation one.

Keywords: high-speed rotation operation, image rotation, transform matrix, image processing, pattern recognition

Procedia PDF Downloads 277