Search results for: categorical datasets

Authors: Pratik Dhabal Deo, Manoj P.

Abstract:

With the increasing number of social media users, the amount of video content available has also significantly increased. Currently, the number of smartphone users is at its peak, and many are increasingly using their smartphones as their main photography and recording devices. There have been a lot of developments in the field of Video Quality Assessment (VQA) and metrics like VMAF, SSIM etc. are said to be some of the best performing metrics, but the evaluation of these metrics is dominantly done on professionally taken video contents using professional tools, lighting conditions etc. No study particularly pinpointing the performance of the metrics on the contents taken by users on very commonly available devices has been done. Datasets that contain a huge number of videos from different high-end devices make it difficult to analyze the performance of the metrics on the content from most used devices even if they contain contents taken in poor lighting conditions using lower-end devices. These devices face a lot of distortions due to various factors since the spectrum of contents recorded on these devices is huge. In this paper, we have presented an analysis of the objective VQA metrics on contents taken only from most used devices and their performance on them, focusing on full-reference metrics. To carry out this research, we created a custom dataset containing a total of 90 videos that have been taken from three most commonly used devices, and android smartphone, an IOS smartphone and a DSLR. On the videos taken on each of these devices, the six most common types of distortions that users face have been applied on addition to already existing H.264 compression based on four reference videos. These six applied distortions have three levels of degradation each. A total of the five most popular VQA metrics have been evaluated on this dataset and the highest values and the lowest values of each of the metrics on the distortions have been recorded. Finally, it is found that blur is the artifact on which most of the metrics didn’t perform well. Thus, in order to understand the results better the amount of blur in the data set has been calculated and an additional evaluation of the metrics was done using HEVC codec, which is the next version of H.264 compression, on the camera that proved to be the sharpest among the devices. The results have shown that as the resolution increases, the performance of the metrics tends to become more accurate and the best performing metric among them is VQM with very few inconsistencies and inaccurate results when the compression applied is H.264, but when the compression is applied is HEVC, SSIM and VMAF have performed significantly better.

Keywords: distortion, metrics, performance, resolution, video quality assessment

Procedia PDF Downloads 203

Authors: Eleni C. Mazarakioti, Anastasios Zotos, Anna-Akrivi Thomatou, Efthimios Kokkotos, Achilleas Kontogeorgos, Athanasios Ladavos, Angelos Patakas

Abstract:

“Gigantes Elefantes” is a particularly dynamic crop of giant beans cultivated in western Macedonia (Greece). This variety of large beans growing in this area and specifically in the regions of Prespes and Kastoria is a protected designation of origin (PDO) species with high nutritional quality. Mislabeling of geographical origin and blending with unidentified samples are common fraudulent practices in Greek food market with financial and possible health consequences. In the last decades, multi-elemental composition analysis has been used in identifying the geographical origin of foods and agricultural products. In an attempt to discriminate the authenticity of Greek beans, multi-elemental analysis (Ag, Al, As, B, Ba, Be, Ca, Cd, Co, Cr, Cs, Cu, Fe, Ga, Ge, K, Li, Mg, Mn, Mo, Na, Nb, Ni, P, Pb, Rb, Re, Se, Sr, Ta, Ti, Tl, U, V, W, Zn, Zr) was performed by inductively coupled plasma mass spectrometry (ICP-MS) on 320 samples of beans, originated from Greece (Prespes and Kastoria), China and Poland. All samples were collected during the autumn of 2021. The obtained data were analysed by principal component analysis (PCA), an unsupervised statistical method, which allows for to reduce of the dimensionality of the enormous datasets. Statistical analysis revealed a clear separation of beans that had been cultivated in Greece compared with those from China and Poland. An adequate discrimination of geographical origin between bean samples originating from the two Greece regions, Prespes and Kastoria, was also evident. Our results suggest that multi-elemental analysis combined with the appropriate multivariate statistical method could be a useful tool for bean’s geographical authentication. Acknowledgment: This research has been financed by the Public Investment Programme/General Secretariat for Research and Innovation, under the call “YPOERGO 3, code 2018SE01300000: project title: ‘Elaboration and implementation of methodology for authenticity and geographical origin assessment of agricultural products.

Keywords: geographical origin, authenticity, multi-elemental analysis, beans, ICP-MS, PCA

Procedia PDF Downloads 78

Authors: Yunbin Deng

Abstract:

Most existing applications of automatic speech recognition relies on cooperative subjects at a short distance to a microphone. Standoff speech recognition using microphone arrays can extend the subject to sensor distance somewhat, but it is still limited to only a few feet. As such, most deployed applications of standoff speech recognitions are limited to indoor use at short range. Moreover, these applications require air passway between the subject and the sensor to achieve reasonable signal to noise ratio. This study reports long range (50 feet) automatic speech recognition experiments using a Laser Doppler Vibrometer (LDV) sensor. This study shows that the LDV sensor modality can extend the speech acquisition standoff distance far beyond microphone arrays to hundreds of feet. In addition, LDV enables 'listening' through the windows for uncooperative subjects. This enables new capabilities in automatic audio and speech intelligence, surveillance, and reconnaissance (ISR) for law enforcement, homeland security and counter terrorism applications. The Polytec LDV model OFV-505 is used in this study. To investigate the impact of different vibrating materials, five parallel LDV speech corpora, each consisting of 630 speakers, are collected from the vibrations of a glass window, a metal plate, a plastic box, a wood slate, and a concrete wall. These are the common materials the application could encounter in a daily life. These data were compared with the microphone counterpart to manifest the impact of various materials on the spectrum of the LDV speech signal. State of the art deep neural network modeling approaches is used to conduct continuous speaker independent speech recognition on these LDV speech datasets. Preliminary phoneme recognition results using time-delay neural network, bi-directional long short term memory, and model fusion shows great promise of using LDV for long range speech recognition. To author’s best knowledge, this is the first time an LDV is reported for long distance speech recognition application.

Keywords: covert speech acquisition, distant speech recognition, DSR, laser Doppler vibrometer, LDV, speech intelligence surveillance and reconnaissance, ISR

Procedia PDF Downloads 179

Authors: Marthin Dody Josias Sumajouw, Bryan Wijaya, Servie O. Dapas, Ronny E. Pandaleke, Banu Handono, Fabian J. Manoppo

Abstract:

Ordinary Portland Cement (OPC) takes a big role as a concrete binder in infrastructure construction purposes, nevertheless, it produces CO2 emissions abundantly. To reduce the CO2 emissions produced by OPC concrete, nowadays, geopolymer material become one of the solutions due to it being a binder made from waste with pozzolan material. In concrete industries, geopolymer concrete has evolved as a more environmentally friendly material than OPC concrete. The geopolymer concrete was created without the usage of OPC known as cementless concrete materials. Geopolymer concrete obtains silicon and aluminum from industrial by-products such as fly ash, ground granulated blast furnace slag, and kaolinite. A highly alkaline solution chemically activates Si and Al, forming a matrix that holds together the loose aggregates as well as additional unreacted components in the mixture. They are then dissolved in alkaline activating solutions, where they polymerize into molecular chains, resulting in rigid binders. This research aims to get an eco-friendly material that can reduce the use of OPC as a binder and be used for infrastructure development end-products such as Curbs, Pavement Bricks, and Wall Bricks. This research was conducted as applied research to develop new products of environmentally friendly materials by utilizing fly ash and employed for infrastructure development, particularly for the production of end products such as Curbs, Pavement Bricks, and Wall Bricks. Three types of end products with various dimensions and mix designs have been made and tested in the laboratory, resulting in quantitative datasets to be used for identifying patterns and relationships among density, compressive strength, flexural strength, and water absorption. The result found that geopolymer binders can be used for the production of curbs, pavement bricks, and wall bricks. Geopolymer curbs have an average compressive strength of 19,36 MPa, which can be determined as K-233 concrete. Geopolymer pavement bricks have an average compressive strength of 20,79 MPa. It can be used in parking areas and determined as the grade B of pavement bricks according to SNI 03-0691-1996. Geopolymer wall bricks have an average compressive strength of 11,24 MPa, which can be determined as the grade I of Wall Bricks according to SNI 03-0349-1989.

Keywords: absorption, compressive strength, curbs, end products, geopolymer, pavement bricks, wall bricks

Procedia PDF Downloads 31

Authors: Hsin Lee, Hsuan Lee

Abstract:

Legal artificial intelligence (LegalAI) has been increasing applications within legal systems, propelled by advancements in natural language processing (NLP). Compared with general documents, legal case documents are typically long text sequences with intrinsic logical structures. Most existing language models have difficulty understanding the long-distance dependencies between different structures. Another unique challenge is that while the Judiciary of Taiwan has released legal judgments from various levels of courts over the years, there remains a significant obstacle in the lack of labeled datasets. This deficiency makes it difficult to train models with strong generalization capabilities, as well as accurately evaluate model performance. To date, models in Taiwan have yet to be specifically trained on judgment data. Given these challenges, this research proposes a Longformer-based pre-trained language model explicitly devised for retrieving similar judgments in Taiwanese legal documents. This model is trained on a self-constructed dataset, which this research has independently labeled to measure judgment similarities, thereby addressing a void left by the lack of an existing labeled dataset for Taiwanese judgments. This research adopts strategies such as early stopping and gradient clipping to prevent overfitting and manage gradient explosion, respectively, thereby enhancing the model's performance. The model in this research is evaluated using both the dataset and the Average Entropy of Offense-charged Clustering (AEOC) metric, which utilizes the notion of similar case scenarios within the same type of legal cases. Our experimental results illustrate our model's significant advancements in handling similarity comparisons within extensive legal judgments. By enabling more efficient retrieval and analysis of legal case documents, our model holds the potential to facilitate legal research, aid legal decision-making, and contribute to the further development of LegalAI in Taiwan.

Keywords: legal artificial intelligence, computation and language, language model, Taiwanese legal cases

Procedia PDF Downloads 72

Authors: Javier Sandoval Bustamante, Pardis Sheikhzadeh, Vijayanarasimha Hindupur Pakka

Abstract:

In the pursuit of achieving net-zero carbon emissions, the integration of low carbon technologies into electricity distribution networks is paramount. This paper delves into the critical assessment of how the integration of low carbon technologies, such as heat pumps, electric vehicle chargers, and photovoltaic systems, impacts the infrastructure and operation of electricity distribution networks. The study employs rigorous methodologies, including power flow analysis and headroom analysis, to evaluate the feasibility and implications of integrating these technologies into existing distribution systems. Furthermore, the research utilizes Local Area Energy Planning (LAEP) methodologies to guide local authorities and distribution network operators in formulating effective plans to meet regional and national decarbonization objectives. Geospatial analysis techniques, coupled with building physics and electric energy systems modeling, are employed to develop geographic datasets aimed at informing the deployment of low carbon technologies at the local level. Drawing upon insights from the Local Energy Net Zero Accelerator (LENZA) project, a comprehensive case study illustrates the practical application of these methodologies in assessing the rollout potential of LCTs. The findings not only shed light on the technical feasibility of integrating low carbon technologies but also provide valuable insights into the broader transition towards a sustainable and electrified energy future. This paper contributes to the advancement of knowledge in power electrical engineering by providing empirical evidence and methodologies to support the integration of low carbon technologies into electricity distribution networks. The insights gained are instrumental for policymakers, utility companies, and stakeholders involved in navigating the complex challenges of energy transition and achieving long-term sustainability goals.

Keywords: energy planning, energy systems, digital twins, power flow analysis, headroom analysis

Procedia PDF Downloads 58

Authors: Shatarupa Thakurta Roy

Abstract:

Along the limelight of mainstream academic practices in Indian art, exist a significant lot of habitual art practices that are mutually susceptible in their contemporary forms. Narrative folk paintings of regional India has successfully dispersed to its audience social messages through pulsating pictures and orations. The paper consists of images from narrative scroll paintings on ‘Ramayana’ theme from various neighboring states as well as districts in India, describing their subtle differences in style of execution, method, and use of material. Despite sharing commonness in the choice of subject matter, habitual and ceremonial Indian folk art in its formative phase thrived within isolated locations to yield in remarkable variety in the art styles. The differences in style took place district wise, cast wise and even gender wise. An open flow is only evident in the contemporary expressions as a result of substantial changes in social structures, mode of communicative devices, cross-cultural exposures and multimedia interactivities. To decipher the complex nature of popular cultural taste of contemporary India it is important to categorically identify its root in vernacular symbolism. The realization of modernity through European primitivism was rather elevated as a perplexed identity in Indian cultural margin in the light of nationalist and postcolonial ideology. To trace the guiding factor that has still managed to obtain ‘Indianness’ in today’s Indian art, researchers need evidences from the past that are yet to be listed in most instances. They are commonly created on ephemeral foundations. The artworks are also found in endangered state and hence, not counted much friendly for frequent handling. The museums are in dearth of proper technological guidelines to preserve them. Even though restoration activities are emerging in the country, the existing withered and damaged artworks are in threat to perish. An immediacy of digital achieving is therefore envisioned as an alternative to save this cultural legacy. The method of this study is, two folded. It primarily justifies the richness of the evidences by conducting categorical aesthetic analysis. The study is supported by comments on the stylistic variants, thematic aspects, and iconographic identities alongside its anthropological and anthropomorphic significance. Further, it explores the possible ways of cultural preservation to ensure cultural sustainability that includes technological intervention in the form of digital transformation as an altered paradigm for better accessibility to the available recourses. The study duly emphasizes on visual description in order to culturally interpret and judge the rare visual evidences following Feldman’s four-stepped method of formal analysis combined with thematic explanation. A habitual design that emerges and thrives within complex social circumstances may experience change placing its principle philosophy at risk by shuffling and altering with time. A tradition that respires in the modern setup struggles to maintain timeless values that operate its creative flow. Thus, the paper hypothesizes the survival and further growth of this practice within the dynamics of time and concludes in realization of the urgency to transform the implicitness of its knowledge into explicit records.

Keywords: aesthetic, identity, implicitness, paradigm

Procedia PDF Downloads 369

Authors: Mohammad Hossein Habibi, Atena Sadat Hosseini

Abstract:

Colorectal cancer is the third leading cause of cancer-related death in the world. Colorectal cancer screening, early detection, and treatment programs could benefit from the most up-to-date information on the disease's burden, given the present worldwide trend of increasing colorectal cancer incidence. Tumor recurrence and resistance are exacerbated by the presence of chemotherapy-resistant cancer stem cells that can generate rapidly proliferating tumor cells. In addition, tumor cells can evolve chemoresistance through adaptation mechanisms. In this work, we used in silico analysis to select suitable GEO datasets. In this study, we compared slow-growing cancer stem cells with high-growth colorectal cancer-derived cancer stem cells. We then evaluated the signal pathways, transcription factors, and kinases associated with these two types of cancer stem cells. A total of 980 upregulated genes and 870 downregulated genes were clustered. MAPK signaling pathway, AGE-RAGE signaling pathway in diabetic complications, Fc gamma R-mediated phagocytosis, and Steroid biosynthesis signaling pathways were observed in upregulated genes. Also, caffeine metabolism, amino sugar and nucleotide sugar metabolism, TNF signaling pathway, and cytosolic DNA-sensing pathway were involved in downregulated genes. In the next step, we evaluated the best transcription factors and kinases in two types of cancer stem cells. In this regard, NR2F2, ZEB2, HEY1, and HDGF as transcription factors and PRDM5, SMAD, CBP, and KDM2B as critical kinases in upregulated genes. On the other hand, IRF1, SPDEF, NCOA1, and STAT1 transcription factors and CTNNB1 and CDH7 kinases were regulated low expression genes. Using bioinformatics analysis in the present study, we conducted an in-depth study of colorectal cancer stem cells at low and high growth rates so that we could take further steps to detect and even target these cells. Naturally, more additional tests are needed in this direction.

Keywords: colorectal cancer, bioinformatics analysis, transcription factor, kinases, cancer stem cells

Procedia PDF Downloads 126

Authors: Pinel Sebastien, Bourrin François, De Madron Du Rieu Xavier, Ludwig Wolfgang, Arnau Pedro

Abstract:

Heavy precipitation constitutes a major meteorological threat in the western Mediterranean. Research has investigated the relationship between the states of the Mediterranean Sea and the atmosphere with the precipitation for short temporal windows. However, at a larger temporal scale, the precursor signals of heavy rainfall in the sea and atmosphere have drawn little attention. Moreover, despite ongoing improvements in numerical weather prediction, the medium-term forecasting of rainfall events remains a difficult task. Here, we aim to investigate the influence of early-spring environmental parameters on the following autumnal heavy precipitations. Hence, we develop a machine learning model to predict extreme autumnal rainfall with a 6-month lead time over the Spanish Catalan coastal area, based on i) the sea pattern (main current-LPC and Sea Surface Temperature-SST) at the mesoscale scale, ii) 4 European weather teleconnection patterns (NAO, WeMo, SCAND, MO) at synoptic scale, and iii) the hydrological regime of the main local river (Rhône River). The accuracy of the developed model classifier is evaluated via statistical analysis based on classification accuracy, logarithmic and confusion matrix by comparing with rainfall estimates from rain gauges and satellite observations (CHIRPS-2.0). Sensitivity tests are carried out by changing the model configuration, such as sea SST, sea LPC, river regime, and synoptic atmosphere configuration. The sensitivity analysis suggests a negligible influence from the hydrological regime, unlike SST, LPC, and specific teleconnection weather patterns. At last, this study illustrates how public datasets can be integrated into a machine learning model for heavy rainfall prediction and can interest local policies for management purposes.

Keywords: extreme hazards, sensitivity analysis, heavy rainfall, machine learning, sea-atmosphere modeling, precipitation forecasting

Procedia PDF Downloads 136

Authors: Joshua W. Edefo, Shafiul Azam, Murray D. Smith

Abstract:

Introduction: In April 2022, the Welsh Government introduced the six goals for urgent and emergency care programs. One of these goals was to provide access to clinically safe alternatives, leading to the establishment of the Same Day Emergency Care (SDEC) program. The SDEC initiative aims to offer viable options that maintain patient safety while avoiding unnecessary hospital stays. The aim of the study is to determine the duration of patient stay in SDEC and compare it with that of Emergency department (ED) stay to ascertain if one of the objectives of SDEC is achieved. Methods: Patient stays and attendance datasets were constructed from Withybush SDEC and ED patient records. These records were provided by Hywel Dda University Health Board Informatics. Some hypothetical pathways were identified, notably SDEC visits involving a single attendance and ED visits then immediately transferred to SDEC. Descriptive statistics were used to summarise the data, and hypothesis tests for mean differences used the student t-test. Propensity scoring was employed to match a set of ED patient stays to SDEC patient stays which were then used to determine the average treatment effect (ATE) to compare durations of stay in SDEC with ED. Regression methods were used to model the natural logarithm of the duration of SDEC attendance, and the level of statistical significance was set to 0.05. Results: SDEC visits involving a single attendance (170 of 384; 44.3%) is the most frequently observed pathway with patient length of stay at 256 minutes (95%CI 237.4 - 275.1). The next most frequently observed pathway of patient stay was SDEC attendance after presenting to ED (80 of 384; 20.8%) and gave the length of stay of 440 minutes (95%CI 351.6 - 529.2). Time spent in this pathway significantly increased by 184 minutes (95%CI 118.0 - 250.2, support for no difference p<0.001) compared to the most seen pathway. When SDEC data were compared with ED, the estimate for the ATE from SDEC single attendance was -272 minutes (95%CI -334.1 - -210.5; p<0.001), while that of ED then SDEC pathway was -50.6 min (95%CI -182.7-81.5; p=0.453). Conclusion: When patients are admitted to SDEC and successfully discharged, their stays are significantly shorter, approximately 4.5 hours, compared to patients who spend their entire stay in the Emergency Department. That difference vanishes when the patient stay includes a period spent previously in ED before transfer to SDEC.

Keywords: attendance, emergency-department, patient-stay, same-day-emergency-care

Procedia PDF Downloads 46

Authors: Rofida Gamal, Mostafa Mohammed, Mariam Adel, Marwa Gamal, Marwa kamal, Ayat Saber, Maha Mamdouh, Amira Emad, Mai Ramadan

Abstract:

Lynch Syndrome is an inherited genetic condition associated with an increased risk of colorectal and other cancers. Detecting Lynch Syndrome in individuals is crucial for early intervention and preventive measures. This study proposes a computational pipeline for Lynch Syndrome detection by integrating alignment, variant calling, and annotation. The pipeline leverages popular tools such as FastQC, Trimmomatic, BWA, bcftools, and ANNOVAR to process the input FASTQ file, perform quality trimming, align reads to the reference genome, call variants, and annotate them. It is believed that the computational pipeline was applied to a dataset of Lynch Syndrome cases, and its performance was evaluated. It is believed that the quality check step ensured the integrity of the sequencing data, while the trimming process is thought to have removed low-quality bases and adaptors. In the alignment step, it is believed that the reads were accurately mapped to the reference genome, and the subsequent variant calling step is believed to have identified potential genetic variants. The annotation step is believed to have provided functional insights into the detected variants, including their effects on known Lynch Syndrome-associated genes. The results obtained from the pipeline revealed Lynch Syndrome-related positions in the genome, providing valuable information for further investigation and clinical decision-making. The pipeline's effectiveness was demonstrated through its ability to streamline the analysis workflow and identify potential genetic markers associated with Lynch Syndrome. It is believed that the computational pipeline presents a comprehensive and efficient approach to Lynch Syndrome detection, contributing to early diagnosis and intervention. The modularity and flexibility of the pipeline are believed to enable customization and adaptation to various datasets and research settings. Further optimization and validation are believed to be necessary to enhance performance and applicability across diverse populations.

Keywords: Lynch Syndrome, computational pipeline, alignment, variant calling, annotation, genetic markers

Procedia PDF Downloads 77

Authors: Migena Mana, Ahmed Khalid Syed, Abdul Malik, Nikhil Cherian

Abstract:

In recent years, advancements in deep learning enabled researchers to tackle the problem of self-driving cars. Car companies use huge datasets to train their deep learning models to make autonomous cars a reality. However, this approach has certain drawbacks in that the state space of possible actions for a car is so huge that there cannot be a dataset for every possible road scenario. To overcome this problem, the concept of reinforcement learning (RL) is being investigated in this research. Since the problem of autonomous driving can be modeled in a simulation, it lends itself naturally to the domain of reinforcement learning. The advantage of this approach is that we can model different and complex road scenarios in a simulation without having to deploy in the real world. The autonomous agent can learn to drive by finding the optimal policy. This learned model can then be easily deployed in a real-world setting. In this project, we focus on three RL algorithms: Q-learning, Deep Deterministic Policy Gradient (DDPG), and Proximal Policy Optimization (PPO). To model the environment, we have used TORCS (The Open Racing Car Simulator), which provides us with a strong foundation to test our model. The inputs to the algorithms are the sensor data provided by the simulator such as velocity, distance from side pavement, etc. The outcome of this research project is a comparative analysis of these algorithms. Based on the comparison, the PPO algorithm gives the best results. When using PPO algorithm, the reward is greater, and the acceleration, steering angle and braking are more stable compared to the other algorithms, which means that the agent learns to drive in a better and more efficient way in this case. Additionally, we have come up with a dataset taken from the training of the agent with DDPG and PPO algorithms. It contains all the steps of the agent during one full training in the form: (all input values, acceleration, steering angle, break, loss, reward). This study can serve as a base for further complex road scenarios. Furthermore, it can be enlarged in the field of computer vision, using the images to find the best policy.

Keywords: autonomous driving, DDPG (deep deterministic policy gradient), PPO (proximal policy optimization), reinforcement learning

Procedia PDF Downloads 149

Authors: Subham Ghosh, Banani Basu, Marami Das

Abstract:

Background: The development of compact, low-power antenna sensors has resulted in hardware restructuring, allowing for wireless ubiquitous sensing. The antenna sensors can create wireless body-area networks (WBAN) by linking various wireless nodes across the human body. WBAN and IoT applications, such as remote health and fitness monitoring and rehabilitation, are becoming increasingly important. In particular, Parkinson’s disease (PD), a common neurodegenerative disorder, presents clinical features that can be easily misdiagnosed. As a mobility disease, it may greatly benefit from the antenna’s nearfield approach with a variety of activities that can use WBAN and IoT technologies to increase diagnosis accuracy and patient monitoring. Methodology: This study investigates the feasibility of leveraging a single patch antenna mounted (using cloth) on the wrist dorsal to differentiate actual Parkinson's disease (PD) from false PD using a small hardware platform. The semi-flexible antenna operates at the 2.4 GHz ISM band and collects reflection coefficient (Γ) data from patients performing five exercises designed for the classification of PD and other disorders such as essential tremor (ET) or those physiological disorders caused by anxiety or stress. The obtained data is normalized and converted into 2-D representations using the Gabor wavelet transform (GWT). Data augmentation is then used to expand the dataset size. A lightweight deep-learning (DL) model is developed to run on the GPU-enabled NVIDIA Jetson Nano platform. The DL model processes the 2-D images for feature extraction and classification. Findings: The DL model was trained and tested on both the original and augmented datasets, thus doubling the dataset size. To ensure robustness, a 5-fold stratified cross-validation (5-FSCV) method was used. The proposed framework, utilizing a DL model with 1.356 million parameters on the NVIDIA Jetson Nano, achieved optimal performance in terms of accuracy of 88.64%, F1-score of 88.54, and recall of 90.46%, with a latency of 33 seconds per epoch.

Keywords: antenna, deep-learning, GPU-hardware, Parkinson’s disease

Procedia PDF Downloads 7

Authors: René A. Sørensen, Søren Skovsen, Peter Christiansen, Henrik Karstoft

Abstract:

Autonomous agricultural machines act in stochastic surroundings and therefore, must be able to perceive the surroundings in real time. This perception can be achieved using image sensors combined with advanced machine learning, in particular Deep Learning. Deep convolutional neural networks excel in labeling and perceiving color images and since the cost of high-quality RGB-cameras is low, the hardware cost of good perception depends heavily on memory and computation power. This paper investigates the possibility of designing lightweight convolutional neural networks for semantic segmentation (pixel wise classification) with reduced hardware requirements, to allow for embedded usage in autonomous agricultural machines. Using compression techniques, a lightweight convolutional neural network is designed to perform real-time semantic segmentation on an embedded platform. The network is trained on two large datasets, ImageNet and Pascal Context, to recognize up to 400 individual classes. The 400 classes are remapped into agricultural superclasses (e.g. human, animal, sky, road, field, shelterbelt and obstacle) and the ability to provide accurate real-time perception of agricultural surroundings is studied. The network is applied to the case of autonomous grass mowing using the NVIDIA Tegra X1 embedded platform. Feeding case-specific images to the network results in a fully segmented map of the superclasses in the image. As the network is still being designed and optimized, only a qualitative analysis of the method is complete at the abstract submission deadline. Proceeding this deadline, the finalized design is quantitatively evaluated on 20 annotated grass mowing images. Lightweight convolutional neural networks for semantic segmentation can be implemented on an embedded platform and show competitive performance with regards to accuracy and speed. It is feasible to provide cost-efficient perceptive capabilities related to semantic segmentation for autonomous agricultural machines.

Keywords: autonomous agricultural machines, deep learning, safety, visual perception

Procedia PDF Downloads 396

Authors: Mehrnoosh Abouzari, Shahrokh Sahraei

Abstract:

Today, with the increase in quantity and quality and variety of crimes, the discussion of crime prevention has faced a serious challenge that human resources alone and with traditional methods will not be effective. One of the developments in the modern world is the presence of artificial intelligence in various fields, including criminal law. In fact, the use of artificial intelligence in criminal investigations and fighting crime is a necessity in today's world. The use of artificial intelligence is far beyond and even separate from other technologies in the struggle against crime. Second, its application in criminal science is different from the discussion of prevention and it comes to the prediction of crime. Crime prevention in terms of the three factors of the offender, the offender and the victim, following a change in the conditions of the three factors, based on the perception of the criminal being wise, and therefore increasing the cost and risk of crime for him in order to desist from delinquency or to make the victim aware of self-care and possibility of exposing him to danger or making it difficult to commit crimes. While the presence of artificial intelligence in the field of combating crime and social damage and dangers, like an all-seeing eye, regardless of time and place, it sees the future and predicts the occurrence of a possible crime, thus prevent the occurrence of crimes. The purpose of this article is to collect and analyze the studies conducted on the use of artificial intelligence in predicting and preventing crime. How capable is this technology in predicting crime and preventing it? The results have shown that the artificial intelligence technologies in use are capable of predicting and preventing crime and can find patterns in the data set. find large ones in a much more efficient way than humans. In crime prediction and prevention, the term artificial intelligence can be used to refer to the increasing use of technologies that apply algorithms to large sets of data to assist or replace police. The use of artificial intelligence in our debate is in predicting and preventing crime, including predicting the time and place of future criminal activities, effective identification of patterns and accurate prediction of future behavior through data mining, machine learning and deep learning, and data analysis, and also the use of neural networks. Because the knowledge of criminologists can provide insight into risk factors for criminal behavior, among other issues, computer scientists can match this knowledge with the datasets that artificial intelligence uses to inform them.

Keywords: artificial intelligence, criminology, crime, prevention, prediction

Procedia PDF Downloads 75

Authors: Sirajdin Olagoke Adeshina, Haidi Ibrahim, Akeem Salawu

Abstract:

large lecture theatres cannot be covered by a single camera but rather by a multicamera setup because of their size, shape, and seating arrangements. Although, classroom capture is achievable through a single camera. Therefore, a design and implementation of a multicamera setup for a large lecture hall were considered. Researchers have shown emphasis on the impact of class attendance taken on the academic performance of students. However, the traditional method of carrying out this exercise is below standard, especially for large lecture theatres, because of the student population, the time required, sophistication, exhaustiveness, and manipulative influence. An automated large classroom attendance system is, therefore, imperative. The common approach in this system is face detection and recognition, where known student faces are captured and stored for recognition purposes. This approach will require constant face database updates due to constant changes in the facial features. Alternatively, face counting can be performed by cropping the localized faces on the video or image into a folder and then count them. This research aims to develop a face localization-based approach to detect student faces in classroom images captured using a multicamera setup. A selected Haar-like feature cascade face detector trained with an asymmetric goal to minimize the False Rejection Rate (FRR) relative to the False Acceptance Rate (FAR) was applied on Raspberry Pi 4B. A relationship between the two factors (FRR and FAR) was established using a constant (λ) as a trade-off between the two factors for automatic adjustment during training. An evaluation of the proposed approach and the conventional AdaBoost on classroom datasets shows an improvement of 8% TPR (output result of low FRR) and 7% minimization of the FRR. The average learning speed of the proposed approach was improved with 1.19s execution time per image compared to 2.38s of the improved AdaBoost. Consequently, the proposed approach achieved 97% TPR with an overhead constraint time of 22.9s compared to 46.7s of the improved Adaboost when evaluated on images obtained from a large lecture hall (DK5) USM.

Keywords: automatic attendance, face detection, haar-like cascade, manual attendance

Procedia PDF Downloads 72

Authors: Simon J. Wilde, David M. Herold, Michael J. Bryant

Abstract:

Social media networks have become the hotbed for advertising activities, due mainly to their increasing consumer/user base, and secondly, owing to the ability of marketers to accurately measure ad exposure and consumer-based insights on such networks. More than half of the world’s population (4.8 billion) now uses social media (60%), with 150 million new users having come online within the last 12 months (to June 2022). As the use of social media networks by users grows, key business strategies used for interacting with these potential customers have matured, especially social media advertising. Unlike other traditional media outlets, social media advertising is highly interactive and digital channel-specific. Social media advertisements are clearly targetable, providing marketers with an extremely powerful marketing tool. Yet despite the measurable benefits afforded to businesses engaged in social media advertising, recent controversies (such as the relationship between Facebook and Cambridge Analytica in 2018) have only heightened the role trust and privacy play within these social media networks. The purpose of this exploratory paper is to investigate the extent to which social media users trust social media advertising. Understanding this relationship will fundamentally assist marketers in better understanding social media interactions and their implications for society. Using a web-based quantitative survey instrument, survey participants were recruited via a reputable online panel survey site. Respondents to the survey represented social media users from all states and territories within Australia. Completed responses were received from a total of 258 social media users. Survey respondents represented all core age demographic groupings, including Gen Z/Millennials (18-45 years = 60.5% of respondents) and Gen X/Boomers (46-66+ years = 39.5% of respondents). An adapted ADTRUST scale, using a 20 item 7-point Likert scale, measured trust in social media advertising. The ADTRUST scale has been shown to be a valid measure of trust in advertising within traditional different media, such as broadcast media and print media, and more recently, the Internet (as a broader platform). The adapted scale was validated through exploratory factor analysis (EFA), resulting in a three-factor solution. These three factors were named reliability, usefulness and affect, and the willingness to rely on. Factor scores (weighted measures) were then calculated for these factors. Factor scores are estimates of the scores survey participants would have received on each of the factors had they been measured directly, with the following results recorded (Reliability = 4.68/7; Usefulness and Affect = 4.53/7; and Willingness to Rely On = 3.94/7). Further statistical analysis (independent samples t-test) determined the difference in factor scores between the factors when age (Gen Z/Millennials vs. Gen X/Boomers) was utilised as the independent, categorical variable. The results showed the difference in mean scores across all three factors to be statistically significant (p<0.05) for these two core age groupings: Gen Z/Millennials Reliability = 4.90/7 vs Gen X/Boomers Reliability = 4.34/7; Gen Z/Millennials Usefulness and Affect = 4.85/7 vs Gen X/Boomers Usefulness and Affect = 4.05/7; and Gen Z/Millennials Willingness to Rely On = 4.53/7 vs Gen X/Boomers Willingness to Rely On = 3.03/7. The results clearly indicate that older social media users lack trust in the quality of information conveyed in social media ads, when compared to younger, more social media-savvy consumers. This is especially evident with respect to Factor 3 (Willingness to Rely On), whose underlying variables reflect one’s behavioural intent to act based on the information conveyed in advertising. These findings can be useful to marketers, advertisers, and brand managers in that the results highlight a critical need to design ‘authentic’ advertisements on social media sites to better connect with these older users, in an attempt to foster positive behavioural responses from within this large demographic group – whose engagement with social media sites continues to increase year on year.

Keywords: social media advertising, trust, older consumers, online

Procedia PDF Downloads 81

Authors: Andrea Gion Saluz, Tal Hertig, Axel Heinrich, Stefan Stevanovic

Abstract:

Higher temperatures, seasonal changes in precipitation, and extreme weather events are increasingly affecting trees. To counteract the increasing challenges of urban trees, strategies are increasingly being sought to preserve existing tree populations on the one hand and to prepare for the coming years on the other. One such strategy lies in strategic climate tree species selection. The search is on for species or varieties that can cope with the new climatic conditions. Many efforts in German-speaking countries deal with this in detail, such as the tree lists of the German Conference of Garden Authorities (GALK), the project Stadtgrün 2021, or the instruments of the Climate Species Matrix by Prof. Dr. Roloff. In this context, different methods for a correct species selection are offered. One possibility is to select certain physiological attributes that indicate the climate resilience of a species. To calculate the dissimilarity of the present climate of different geographic regions in relation to the future climate of any city, a weighted (standardized) Euclidean distance (SED) for seasonal climate values is calculated for each region of the Earth. The calculation was performed in the QGIS geographic information system, using global raster datasets on monthly climate values in the 1981-2010 standard period. Data from a European forest inventory were used to identify tree species growing in the calculated analogue climate regions. The inventory used is the compilation of georeferenced point data at a 1 km grid resolution on the occurrence of tree species in 21 European countries. In this project, the results of the methodological application are shown for the city of Zurich for the year 2060. In the first step, analog climate regions based on projected climate values for the measuring station Kirche Fluntern (ZH) were searched for. In a further step, the methods mentioned above were applied to generate tree species lists for the city of Zurich. These lists were then qualitatively evaluated with respect to the suitability of the different tree species for the Zurich area to generate a cleaned and thus usable list of possible future tree species.

Keywords: climate change, climate region, climate tree, urban tree

Procedia PDF Downloads 108

Authors: Rahmi Kafadar, Levent Genc

Abstract:

In present study, it was aimed to determine potential agricultural lands (PALs) in Gokceada (Imroz) Island of Canakkale province, Turkey. Seven-band Landsat 8 OLI images acquired on July 12 and August 13, 2013, and their 14-band combination image were used to identify current Land Use Land Cover (LULC) status. Principal Component Analysis (PCA) was applied to three Landsat datasets in order to reduce the correlation between the bands. A total of six Original and PCA images were classified using supervised classification method to obtain the LULC maps including 6 main classes (“Forest”, “Agriculture”, “Water Surface”, “Residential Area-Bare Soil”, “Reforestation” and “Other”). Accuracy assessment was performed by checking the accuracy of 120 randomized points for each LULC maps. The best overall accuracy and Kappa statistic values (90.83%, 0.8791% respectively) were found for PCA images which were generated from 14-bands combined images called 3-B/JA. Digital Elevation Model (DEM) with 15 m spatial resolution (ASTER) was used to consider topographical characteristics. Soil properties were obtained by digitizing 1:25000 scaled soil maps of rural services directorate general. Potential Agricultural Lands (PALs) were determined using Geographic information Systems (GIS). Procedure was applied considering that “Other” class of LULC map may be used for agricultural purposes in the future properties. Overlaying analysis was conducted using Slope (S), Land Use Capability Class (LUCC), Other Soil Properties (OSP) and Land Use Capability Sub-Class (SUBC) properties. A total of 901.62 ha areas within “Other” class (15798.2 ha) of LULC map were determined as PALs. These lands were ranked as “Very Suitable”, “Suitable”, “Moderate Suitable” and “Low Suitable”. It was determined that the 8.03 ha were classified as “Very Suitable” while 18.59 ha as suitable and 11.44 ha as “Moderate Suitable” for PALs. In addition, 756.56 ha were found to be “Low Suitable”. The results obtained from this preliminary study can serve as basis for further studies.

Keywords: digital elevation model (DEM), geographic information systems (GIS), gokceada (Imroz), lANDSAT 8 OLI-TIRS, land use land cover (LULC)

Procedia PDF Downloads 353

Authors: Mohammed Al Sulaimani, Hamad Al Manhi

Abstract:

With the development of Remote Sensing technology, the resolution of optical Remote Sensing images has greatly improved, and images have become largely available. Numerous detectors have been developed for detecting different types of objects. In the past few years, Remote Sensing has benefited a lot from deep learning, particularly Deep Convolution Neural Networks (CNNs). Deep learning holds great promise to fulfill the challenging needs of Remote Sensing and solving various problems within different fields and applications. The use of Unmanned Aerial Systems in acquiring Aerial Photos has become highly used and preferred by most organizations to support their activities because of their high resolution and accuracy, which make the identification and detection of very small features much easier than Satellite Images. And this has opened an extreme era of Deep Learning in different applications not only in feature extraction and prediction but also in analysis. This work addresses the capacity of Machine Learning and Deep Learning in detecting and extracting Oil Leaks from Flowlines (Onshore) using High-Resolution Aerial Photos which have been acquired by UAS fixed with RGB Sensor to support early detection of these leaks and prevent the company from the leak’s losses and the most important thing environmental damage. Here, there are two different approaches and different methods of DL have been demonstrated. The first approach focuses on detecting the Oil Leaks from the RAW Aerial Photos (not processed) using a Deep Learning called Single Shoot Detector (SSD). The model draws bounding boxes around the leaks, and the results were extremely good. The second approach focuses on detecting the Oil Leaks from the Ortho-mosaiced Images (Georeferenced Images) by developing three Deep Learning Models using (MaskRCNN, U-Net and PSP-Net Classifier). Then, post-processing is performed to combine the results of these three Deep Learning Models to achieve a better detection result and improved accuracy. Although there is a relatively small amount of datasets available for training purposes, the Trained DL Models have shown good results in extracting the extent of the Oil Leaks and obtaining excellent and accurate detection.

Keywords: GIS, remote sensing, oil leak detection, machine learning, aerial photos, unmanned aerial systems

Procedia PDF Downloads 34

Authors: Philipp Galkin

Abstract:

Government policy is a critical factor in the understanding of energy markets. Regardless, it is rarely approached systematically from a research perspective. Gaining a precise understanding of what policies exist, their intended outcomes, geographical extent, duration, evolution, etc. would enable the research community to answer a variety of questions that, for now, are either oversimplified or ignored. Policy, on its surface, also seems a rather unstructured and qualitative undertaking. There may be quantitative components, but incorporating the concept of policy analysis into quantitative analysis remains a challenge. The KAPSARC Energy Policy Database (KEPD) is intended to address these two energy policy research limitations. Our approach is to represent policies within a quantitative library of the specific policy measures contained within a set of legal documents. Each of these measures is recorded into the database as a single entry characterized by a set of qualitative and quantitative attributes. Initially, we have focused on the major laws at the national level that regulate coal in China. However, KAPSARC is engaged in various efforts to apply this methodology to other energy policy domains. To ensure scalability and sustainability of our project, we are exploring semantic processing using automated computer algorithms. Automated coding can provide a more convenient input data for human coders and serve as a quality control option. Our initial findings suggest that the methodology utilized in KEPD could be applied to any set of energy policies. It also provides a convenient tool to facilitate understanding in the energy policy realm enabling the researcher to quickly identify, summarize, and digest policy documents and specific policy measures. The KEPD captures a wide range of information about each individual policy contained within a single policy document. This enables a variety of analyses, such as structural comparison of policy documents, tracing policy evolution, stakeholder analysis, and exploring interdependencies of policies and their attributes with exogenous datasets using statistical tools. The usability and broad range of research implications suggest a need for the continued expansion of the KEPD to encompass a larger scope of policy documents across geographies and energy sectors.

Keywords: China, energy policy, policy analysis, policy database

Procedia PDF Downloads 323

Authors: A. Chowdhury, P. Egodawatta, J. M. McGree, A. Goonetilleke

Abstract:

Hydrologic models are increasingly used as tools to predict stormwater quantity and quality from urban catchments. However, due to a range of practical issues, most models produce gross errors in simulating complex hydraulic and hydrologic systems. Difficulty in finding a robust approach for model calibration is one of the main issues. Though automatic calibration techniques are available, they are rarely used in common commercial hydraulic and hydrologic modelling software e.g. MIKE URBAN. This is partly due to the need for a large number of parameters and large datasets in the calibration process. To overcome this practical issue, a framework for automatic calibration of a hydrologic model was developed in R platform and presented in this paper. The model was developed based on the time-area conceptualization. Four calibration parameters, including initial loss, reduction factor, time of concentration and time-lag were considered as the primary set of parameters. Using these parameters, automatic calibration was performed using Approximate Bayesian Computation (ABC). ABC is a simulation-based technique for performing Bayesian inference when the likelihood is intractable or computationally expensive to compute. To test the performance and usefulness, the technique was used to simulate three small catchments in Gold Coast. For comparison, simulation outcomes from the same three catchments using commercial modelling software, MIKE URBAN were used. The graphical comparison shows strong agreement of MIKE URBAN result within the upper and lower 95% credible intervals of posterior predictions as obtained via ABC. Statistical validation for posterior predictions of runoff result using coefficient of determination (CD), root mean square error (RMSE) and maximum error (ME) was found reasonable for three study catchments. The main benefit of using ABC over MIKE URBAN is that ABC provides a posterior distribution for runoff flow prediction, and therefore associated uncertainty in predictions can be obtained. In contrast, MIKE URBAN just provides a point estimate. Based on the results of the analysis, it appears as though ABC the developed framework performs well for automatic calibration.

Keywords: automatic calibration framework, approximate bayesian computation, hydrologic and hydraulic modelling, MIKE URBAN software, R platform

Procedia PDF Downloads 309

Authors: Tesfaye Mengistu

Abstract:

Power cables play a crucial role in the transmission and distribution of electrical energy. As the electricity generation, transmission, distribution, and storage systems become smarter, there is a growing emphasis on incorporating intelligent approaches to ensure the reliability of power cables. Various types of electrical cables are employed for transmitting and distributing electrical energy, with cross-linked polyethylene (XLPE) cables being widely utilized due to their exceptional electrical and mechanical properties. However, insulation defects can occur in XLPE cables due to subpar manufacturing techniques during production and cable joint installation. To address this issue, experts have proposed different methods for monitoring XLPE cables. Some suggest the use of interdigital capacitive (IDC) technology for online monitoring, while others propose employing continuous wave (CW) terahertz (THz) imaging systems to detect internal defects in XLPE plates used for power cable insulation. In this study, we have developed models that employ a custom dataset collected locally to classify the physical safety status of individual power cables. Our models aim to replace physical inspections with computer vision and image processing techniques to classify defective power cables from non-defective ones. The implementation of our project utilized the Python programming language along with the TensorFlow package and a convolutional neural network (CNN). The CNN-based algorithm was specifically chosen for power cable defect classification. The results of our project demonstrate the effectiveness of CNNs in accurately classifying power cable defects. We recommend the utilization of similar or additional datasets to further enhance and refine our models. Additionally, we believe that our models could be used to develop methodologies for detecting power cable defects from live video feeds. We firmly believe that our work makes a significant contribution to the field of power cable inspection and maintenance. Our models offer a more efficient and cost-effective approach to detecting power cable defects, thereby improving the reliability and safety of power grids.

Keywords: artificial intelligence, computer vision, defect detection, convolutional neural net

Procedia PDF Downloads 112

Authors: Chow Jeng Hei, Pavel Tkalich, Low Kai Sheng Bryan

Abstract:

Due to the growing demand for sustainability in the maritime industry, there has been a significant increase in focus on alternative fuels such as biofuels, liquefied natural gas (LNG), hydrogen, methanol and ammonia to reduce the carbon footprint of vessels. Alternative fuels offer efficient transportability and significantly reduce carbon dioxide emissions, a critical factor in combating global warming. In an era where the world is determined to tackle climate change, the utilization of methanol is projected to witness a consistent rise in demand, even during downturns in the oil and gas industry. Since 2022, there has been an increase in methanol loading and discharging operations for industrial use in Singapore. These operations were conducted across various storage tank terminals at Jurong Island of varying capacities, which are also used to store alternative fuels for bunkering requirements. The key objective of this research is to support the green shipping industries in the transformation to new fuels such as methanol and ammonia, especially in evolving the capability to inform risk assessment and management of spills. In the unlikely event of accidental spills, a highly reliable forecasting system must be in place to provide mitigation measures and ahead planning. The outcomes of this research would lead to an enhanced metocean prediction capability and, together with advanced sensing, will continuously build up a robust digital twin of the bunkering operating environment. Outputs from the developments will contribute to management strategies for alternative marine fuel spills, including best practices, safety challenges and crisis management. The outputs can also benefit key port operators and the various bunkering, petrochemicals, shipping, protection and indemnity, and emergency response sectors. The forecasted datasets provide a forecast of the expected atmosphere and hydrodynamic conditions prior to bunkering exercises, enabling a better understanding of the metocean conditions ahead and allowing for more refined spill incident management planning

Keywords: clean fuels, hydrodynamics, coastal engineering, impact assessments

Procedia PDF Downloads 70

Authors: Han-Qin Zheng, Yi-Fan Chiang-Hsieh, Chia-Hung Chien, Wen-Chi Chang

Abstract:

As the most important non-vascular plants, algae have many research applications, including high species diversity, biofuel sources, adsorption of heavy metals and, following processing, health supplements. With the increasing availability of next-generation sequencing (NGS) data for algae genomes and transcriptomes, an integrated resource for retrieving gene expression data and metabolic pathway is essential for functional analysis and systems biology in algae. However, gene expression profiles and biological pathways are displayed separately in current resources, and making it impossible to search current databases directly to identify the cellular response mechanisms. Therefore, this work develops a novel AlgaePath database to retrieve gene expression profiles efficiently under various conditions in numerous metabolic pathways. AlgaePath, a web-based database, integrates gene information, biological pathways, and next-generation sequencing (NGS) datasets in Chlamydomonasreinhardtii and Neodesmus sp. UTEX 2219-4. Users can identify gene expression profiles and pathway information by using five query pages (i.e. Gene Search, Pathway Search, Differentially Expressed Genes (DEGs) Search, Gene Group Analysis, and Co-Expression Analysis). The gene expression data of 45 and 4 samples can be obtained directly on pathway maps in C. reinhardtii and Neodesmus sp. UTEX 2219-4, respectively. Genes that are differentially expressed between two conditions can be identified in Folds Search. Furthermore, the Gene Group Analysis of AlgaePath includes pathway enrichment analysis, and can easily compare the gene expression profiles of functionally related genes in a map. Finally, Co-Expression Analysis provides co-expressed transcripts of a target gene. The analysis results provide a valuable reference for designing further experiments and elucidating critical mechanisms from high-throughput data. More than an effective interface to clarify the transcript response mechanisms in different metabolic pathways under various conditions, AlgaePath is also a data mining system to identify critical mechanisms based on high-throughput sequencing.

Keywords: next-generation sequencing (NGS), algae, transcriptome, metabolic pathway, co-expression

Procedia PDF Downloads 407

Authors: Juan Francisco Reinoso Gordo, Francisco Javier Ariza-López, José Rodríguez Avi, Domingo Barrera Rosillo

Abstract:

The evaluation of the quality of a data product is based on the comparison of the product with a reference of greater accuracy. In the case of MDE data products, quality assessment usually focuses on positional accuracy and few studies consider other terrain characteristics, such as slope and orientation. The proposal that is made consists of evaluating the similarity of two DEMs (a product and a reference), through the joint analysis of the distribution functions of the variables of interest, for example, elevations, slopes and orientations. This is a multivariable approach that focuses on distribution functions, not on single parameters such as mean values or dispersions (e.g. root mean squared error or variance). This is considered to be a more holistic approach. The use of the Kolmogorov-Smirnov test is proposed due to its non-parametric nature, since the distributions of the variables of interest cannot always be adequately modeled by parametric models (e.g. the Normal distribution model). In addition, its application to the multivariate case is carried out jointly by means of a single test on the convolution of the distribution functions of the variables considered, which avoids the use of corrections such as Bonferroni when several statistics hypothesis tests are carried out together. In this work, two DEM products have been considered, DEM02 with a resolution of 2x2 meters and DEM05 with a resolution of 5x5 meters, both generated by the National Geographic Institute of Spain. DEM02 is considered as the reference and DEM05 as the product to be evaluated. In addition, the slope and aspect derived models have been calculated by GIS operations on the two DEM datasets. Through sample simulation processes, the adequate behavior of the Kolmogorov-Smirnov statistical test has been verified when the null hypothesis is true, which allows calibrating the value of the statistic for the desired significance value (e.g. 5%). Once the process has been calibrated, the same process can be applied to compare the similarity of different DEM data sets (e.g. the DEM05 versus the DEM02). In summary, an innovative alternative for the comparison of DEM data sets based on a multinomial non-parametric perspective has been proposed by means of a single Kolmogorov-Smirnov test. This new approach could be extended to other DEM features of interest (e.g. curvature, etc.) and to more than three variables

Keywords: data quality, DEM, kolmogorov-smirnov test, multivariate DEM comparison

Procedia PDF Downloads 115

Authors: Luís M. João, Patrício Langa

Abstract:

The article reviews the literature on quality assurance (QA) in African higher education studies (HES) conducted through a bibliometric mapping of published papers between 1999 and 2019. Specifically, the article highlights the nuances of knowledge production in four scientific databases: Scopus, Web of Science (WoS), African Journal Online (AJOL), and Google Scholar. The analysis included 531 papers, of which 127 are from Scopus, 30 are from Web of Science, 85 are from African Journal Online, and 259 are from Google Scholar. In essence, 284 authors wrote these papers from 231 institutions and 69 different countries (i.e., Africa=54 and outside Africa=15). Results indicate the existing knowledge. This analysis allows the readers to understand the growth and development of the field during the two-decade period, identify key contributors, and observe potential trends or gaps in the research. The paper employs bibliometric mapping as its primary analytical lens. By utilizing this method, the study quantitatively assesses the publications related to QA in African HES, helping to identify patterns, collaboration networks, and disparities in research output. The bibliometric approach allows for a systematic and objective analysis of large datasets, offering a comprehensive view of the knowledge production in the field. Furthermore, the study highlights the lack of shared resources available to enhance quality in higher education institutions (HEIs) in Africa. This finding underscores the importance of promoting collaborative research efforts, knowledge exchange, and capacity building within the region to improve the overall quality of higher education. The paper argues that despite the growing quantity of QA research in African higher education, there are challenges related to citation impact and access to high-impact publication avenues for African researchers. It emphasises the need to promote collaborative research and resource-sharing to enhance the quality of HEIs in Africa. The analytical lenses of bibliometric mapping and the examination of publication players' scenarios contribute to a comprehensive understanding of the field and its implications for African higher education.

Keywords: Africa, bibliometric research, higher education studies, quality assurance, scientific database, systematic review

Procedia PDF Downloads 43

Authors: Zhi Hao Chow, Cian Mulligan, Jack Walsh, Antonio Garzon Vico, Dimitar Krastev

Abstract:

Drug development is resource-intensive, time-consuming, and increasingly expensive with each developmental stage. The success rates of drug development are also relatively low, and the resources committed are wasted with each failed candidate. As such, a reliable method of predicting the success of drug development is in demand. The hypothesis was that some examples of failed drug candidates are pushed through developmental pipelines based on false confidence and may possess common linguistic features identifiable through sentiment analysis. Here, the concept of using text analysis to discover such features in research publications and investor reports as predictors of success was explored. R studios were used to perform text mining and lexicon-based sentiment analysis to identify affective phrases and determine their frequency in each document, then using SPSS to determine the relationship between our defined variables and the accuracy of predicting outcomes. A total of 161 publications were collected and categorised into 4 groups: (i) Cancer treatment, (ii) Neurodegenerative disease treatment, (iii) Vaccines, and (iv) Others (containing all other drugs that do not fit into the 3 categories). Text analysis was then performed on each document using 2 separate datasets (BING and AFINN) in R within the category of drugs to determine the frequency of positive or negative phrases in each document. A relative positivity and negativity value were then calculated by dividing the frequency of phrases with the word count of each document. Regression analysis was then performed with SPSS statistical software on each dataset (values from using BING or AFINN dataset during text analysis) using a random selection of 61 documents to construct a model. The remaining documents were then used to determine the predictive power of the models. Model constructed from BING predicts the outcome of drug performance in clinical trials with an overall percentage of 65.3%. AFINN model had a lower accuracy at predicting outcomes compared to the BING model at 62.5% but was not effective at predicting the failure of drugs in clinical trials. Overall, the study did not show significant efficacy of the model at predicting outcomes of drugs in development. Many improvements may need to be made to later iterations of the model to sufficiently increase the accuracy.

Keywords: data analysis, drug development, sentiment analysis, text-mining

Procedia PDF Downloads 158

Authors: Basma Yassa

Abstract:

Evidence on cash transfers’ effectiveness in mitigating macro and idiosyncratic shocks’ impacts has been mixed and is mostly concentrated in Latin America, Sub-Saharan Africa, and South Asia with very limited evidence from the MENA region. Yet conditional cash transfers schemes have been continually used, especially in Egypt, as the main social protection tool in response to the recent socioeconomic crises and macro shocks. We use 2 panel datasets and 1 cross-sectional dataset to estimate the effectiveness of cash transfers as a shock-mitigative mechanism in the Egyptian context. In this paper, the results from the different models (Panel Fixed Effects model and the Regression Discontinuity Design (RDD) model) confirm that micro and macro shocks lead to significant decline in several household-level welfare outcomes and that Takaful cash transfers have a significant positive impact in mitigating the negative shock impacts, especially on households’ debt incidence, debt levels, and asset ownership, but not necessarily on food, and non-food expenditure levels. The results indicate large positive significant effects on decreasing household incidence of debt by up to 12.4 percent and lowered the debt size by approximately 18 percent among Takaful beneficiaries compared to non-beneficiaries’. Similar evidence is found on asset ownership levels, as the RDD model shows significant positive effects on total asset ownership and productive asset ownership, but the model failed to detect positive impacts on per capita food and non-food expenditures. Further extensions are still in progress to compare the models’ results with the DID model results when using a nationally representative ELMPS panel data (2018/2024) rounds. Finally, our initial analysis suggests that conditional cash transfers are effective in buffering the negative shock impacts on certain welfare indicators even after successive macro-economic shocks in 2022 and 2023 in the Egyptian Context.

Keywords: cash transfers, fixed effects, household welfare, household debt, micro shocks, regression discontinuity design

Procedia PDF Downloads 46

Authors: Yanjun Chen, Chuanping Hu, Jie Shao, Lin Mei, Chongyang Zhang

Abstract:

Traditional image classification is based on encoding scheme (e.g. Fisher Vector, Vector of Locally Aggregated Descriptor) with low-level image features (e.g. SIFT, HoG). Compared to these low-level local features, deep convolutional features obtained at the mid-level layer of convolutional neural networks (CNN) have richer information but lack of geometric invariance. For scene classification, there are scattered objects with different size, category, layout, number and so on. It is crucial to find the distinctive objects in scene as well as their co-occurrence relationship. In this paper, we propose a method to take advantage of both deep convolutional features and the traditional encoding scheme while taking object-centric and scene-centric information into consideration. First, to exploit the object-centric and scene-centric information, two CNNs that trained on ImageNet and Places dataset separately are used as the pre-trained models to extract deep convolutional features at multiple scales. This produces dense local activations. By analyzing the performance of different CNNs at multiple scales, it is found that each CNN works better in different scale ranges. A scale-wise CNN adaption is reasonable since objects in scene are at its own specific scale. Second, a fisher kernel is applied to aggregate a global representation at each scale and then to merge into a single vector by using a post-processing method called scale-wise normalization. The essence of Fisher Vector lies on the accumulation of the first and second order differences. Hence, the scale-wise normalization followed by average pooling would balance the influence of each scale since different amount of features are extracted. Third, the Fisher vector representation based on the deep convolutional features is followed by a linear Supported Vector Machine, which is a simple yet efficient way to classify the scene categories. Experimental results show that the scale-specific feature extraction and normalization with CNNs trained on object-centric and scene-centric datasets can boost the results from 74.03% up to 79.43% on MIT Indoor67 when only two scales are used (compared to results at single scale). The result is comparable to state-of-art performance which proves that the representation can be applied to other visual recognition tasks.

Keywords: deep convolutional features, Fisher Vector, multiple scales, scale-specific normalization

Procedia PDF Downloads 331