Search results for: artificial intellogence

Authors: ChunYi Peng, Wei Hsuan CHeng, Shyh Kuang Ueng

Abstract:

This study focuses on the application of self-organizing maps (SOM) technology in analyzing credit card transaction data, aiming to enhance the accuracy and efficiency of fraud detection. Som, as an artificial neural network, is particularly suited for pattern recognition and data classification, making it highly effective for the complex and variable nature of credit card transaction data. By analyzing transaction characteristics with SOM, the research identifies abnormal transaction patterns that could indicate potentially fraudulent activities. Moreover, this study has developed a specialized visualization tool to intuitively present the relationships between SOM analysis outcomes and transaction data, aiding financial institution personnel in quickly identifying and responding to potential fraud, thereby reducing financial losses. Additionally, the research explores the integration of SOM technology with composite intelligent system technologies (including finite state machines, fuzzy logic, and decision trees) to further improve fraud detection accuracy. This multimodal approach provides a comprehensive perspective for identifying and understanding various types of fraud within credit card transactions. In summary, by integrating SOM technology with visualization tools and composite intelligent system technologies, this research offers a more effective method of fraud detection for the financial industry, not only enhancing detection accuracy but also deepening the overall understanding of fraudulent activities.

Keywords: self-organizing map technology, fraud detection, information visualization, data analysis, composite intelligent system technologies, decision support technologies

Procedia PDF Downloads 57

Authors: E. A. Babiker, S. A. Makawi

Abstract:

The influence of the season (autumn, winter, and summer) on semen production in Nubian and Saanen bucks was studied. Seven mature bucks (4 Nubian and 3 Saanen) were used in this study to prepare semen samples which were collected with an artificial vagina. The samples were extended in Tris-egg yolk-glycerol-glucose extender, frozen, and stored in liquid nitrogen at –196 0C for 48 hours. Straws were thawed in water at –37 0C for 15 seconds before sperm evaluation (post-thaw sperm motility). There was a significant seasonal variation in both semen quantity (volume, concentration, and the total number of spermatozoa per ejaculate) and quality (percentage of sperm motility, percentage of post-thaw sperm motility, and dead spermatozoa). Greater ejaculate volumes were observed during summer and autumn in comparison to winter. Higher values of sperms concentration were observed during autumn, while the lowest sperm concentration values were observed during summer. Higher values of sperm motility were observed during autumn in comparison to summer. Lower values of dead spermatozoa were recorded during autumn, while the highest percentages of dead spermatozoa were observed during summer for the two breeds of bucks. The influence of season on post-thaw sperm motility was significant. Semen frozen during autumn and winter had the highest values, while during summer, lower mean values were observed. The best semen was produced during autumn and winter, while during summer, poor semen quality was recorded.

Keywords: season, Nubian, Saanen, semen production, Sudan

Procedia PDF Downloads 112

Authors: Praveen Chandramenon, Andrew Gascoyne, Fideline Tchuenbou-Magaia

Abstract:

Aquaponics offers a simple conclusive solution to the food and environmental crisis of the world. This approach combines the idea of Aquaculture (growing fish) to Hydroponics (growing vegetables and plants in a soilless method). Smart Aquaponics explores the use of smart technology including artificial intelligence and IoT, to assist farmers with better decision making and online monitoring and control of the system. Identification of different growth stages of Swiss Chard plants and predicting its harvest time is found to be important in Aquaponic yield management. This paper brings out the comparative analysis of a standard Aquaponics with a Vermiponics (Aquaponics with worms), which was grown in the controlled environment, by implementing IoT and deep learning-based growth stage segregation and harvest time prediction of Swiss Chards before and after applying an optimal freshwater replenishment. Data collection, Growth stage classification and Harvest Time prediction has been performed with and without water replenishment. The paper discusses the experimental design, IoT and sensor communication with architecture, data collection process, image segmentation, various regression and classification models and error estimation used in the project. The paper concludes with the results comparison, including best models that performs growth stage segregation and harvest time prediction of the Aquaponic and Vermiponic testbed with and without freshwater replenishment.

Keywords: aquaponics, deep learning, internet of things, vermiponics

Procedia PDF Downloads 71

Authors: Remon Karam Zakry Kelada

Abstract:

This survey research ambitions to examine the usual of carrier quality of meals and beverage provider staffs in lodge business by way of studying the carrier fashionable of 3 pattern inns, Siam Kempinski lodge Bangkok, four Seasons lodge Chiang Mai, and Banyan Tree Phuket. as a way to locate the international provider general of food and beverage provider, triangular research, i.e. quantitative, qualitative, and survey were hired. on this research, questionnaires and in-depth interview have been used for getting the statistics on the sequences and method of services. There had been three components of modified questionnaires to degree carrier pleasant and visitor’s satisfaction inclusive of carrier facilities, attentiveness, obligation, reliability, and circumspection. This observe used pattern random sampling to derive topics with the go back fee of the questionnaires changed into 70% or 280. information have been analyzed via SPSS to find mathematics mean, SD, percent, and comparison by using t-take a look at and One-manner ANOVA. The outcomes revealed that the service first-rate of the three lodges have been in the worldwide stage that could create excessive pride to the international clients. hints for studies implementations have been to hold the area of precise carrier satisfactory, and to enhance some dimensions of service fine together with reliability. training in service fashionable, product expertise, and new generation for employees must be provided. furthermore, for you to develop the provider pleasant of the enterprise, training collaboration among inn corporation and academic institutions in food and beverage carrier should be considered.

Keywords: food and beverage staff, food poisoning, food production, hygiene knowledge BPA, health, regulations, toxicity service standard, food and beverage department, sequence of service, service method

Procedia PDF Downloads 34

Authors: Peng Chun-Yi, Chen Wei-Hsuan, Ueng Shyh-Kuang

Abstract:

This study focuses on the application of self-organizing maps (SOM) technology in analyzing credit card transaction data, aiming to enhance the accuracy and efficiency of fraud detection. Som, as an artificial neural network, is particularly suited for pattern recognition and data classification, making it highly effective for the complex and variable nature of credit card transaction data. By analyzing transaction characteristics with SOM, the research identifies abnormal transaction patterns that could indicate potentially fraudulent activities. Moreover, this study has developed a specialized visualization tool to intuitively present the relationships between SOM analysis outcomes and transaction data, aiding financial institution personnel in quickly identifying and responding to potential fraud, thereby reducing financial losses. Additionally, the research explores the integration of SOM technology with composite intelligent system technologies (including finite state machines, fuzzy logic, and decision trees) to further improve fraud detection accuracy. This multimodal approach provides a comprehensive perspective for identifying and understanding various types of fraud within credit card transactions. In summary, by integrating SOM technology with visualization tools and composite intelligent system technologies, this research offers a more effective method of fraud detection for the financial industry, not only enhancing detection accuracy but also deepening the overall understanding of fraudulent activities.

Keywords: self-organizing map technology, fraud detection, information visualization, data analysis, composite intelligent system technologies, decision support technologies

Procedia PDF Downloads 59

Authors: Jana Atteah, Wid Jan, Yara AlHibshi, Rahaf AlRougi

Abstract:

Anyword is an AI copywriting tool that helps marketers create effective campaigns for specific audiences. It offers a wide range of templates for various platforms, brand voice guidelines, and valuable analytics insights. Anyword is used by top global companies and has been recognized as one of the "Fastest Growing Products" in the 2023 software awards. A recent study examined the utilization and impact of AI-powered writing tools, specifically focusing on the adoption of AI in writing pursuits and the use of the Anyword platform. The results indicate that a majority of respondents (52.17%) had not previously used Anyword, but those who had were generally satisfied with the platform. Notable productivity improvements were observed among 13% of the participants, while an additional 34.8% reported a slight increase in productivity. A majority (47.8%) maintained a neutral stance, suggesting that their productivity remained unaffected. Only a minimal percentage (4.3%) claimed that their productivity did not improve with the usage of Anyword AI. In terms of the quality of written content generated, the participants responded positively. Approximately 91% of participants gave Anyword AI a score of 5 or higher, with roughly 17% giving it a perfect score. A small percentage (approximately 9%) gave a low score between 0-2. The mode result was a score of 7, indicating a generally positive perception of the quality of content generated using Anyword AI. These findings suggest that AI can contribute to increased productivity and positively influence the quality of written content. Further research and exploration of AI tools in writing pursuits are warranted to fully understand their potential and limitations.

Keywords: artificial intelligence, marketing platforms, productivity, user interface

Procedia PDF Downloads 63

Authors: Prashansa Singh, Rohit Bajaj, Manjot Kaur

Abstract:

In the modern agricultural landscape, precision farming has emerged as a pivotal strategy for enhancing crop yield and optimizing resource utilization. This paper introduces an innovative Crop Recommendation System (CRS) that leverages the Internet of Things (IoT) technology and the Message Queuing Telemetry Transport (MQTT) protocol to collect critical environmental and soil data via sensors deployed across agricultural fields. The system is designed to address the challenges of real-time data acquisition, efficient data transmission, and dynamic crop recommendation through the application of advanced Artificial Intelligence (AI) and Machine Learning (ML) models. The CRS architecture encompasses a network of sensors that continuously monitor environmental parameters such as temperature, humidity, soil moisture, and nutrient levels. This sensor data is then transmitted to a central MQTT server, ensuring reliable and low-latency communication even in bandwidth-constrained scenarios typical of rural agricultural settings. Upon reaching the server, the data is processed and analyzed by AI/ML models trained to correlate specific environmental conditions with optimal crop choices and cultivation practices. These models consider historical crop performance data, current agricultural research, and real-time field conditions to generate tailored crop recommendations. This implementation gets 99% accuracy.

Keywords: Iot, MQTT protocol, machine learning, sensor, publish, subscriber, agriculture, humidity

Procedia PDF Downloads 68

Authors: Fangyan Li, Lin Min Lee, Hui Zhu Peh, Shoet Harn Chan

Abstract:

Advantame, a derivative of aspartame, is the latest addition to a family of low caloric and high potent dipeptide sweeteners which include aspartame, neotame and alitame. The use of advantame as a high-intensity sweetener in food was first accepted by Food Standards Australia New Zealand in 2011 and subsequently by US and EU food authorities in 2014, with the results from toxicity and exposure studies showing advantame poses no safety concern to the public at regulated levels. To our knowledge, currently there is barely any detailed information on the analytical method of advantame in food matrix, except for one report published in Japanese, stating a high performance liquid chromatography (HPLC) and liquid chromatography/ mass spectrometry (LC-MS) method with a detection limit at ppm level. However, the use of acid in sample preparation and instrumental analysis in the report raised doubt over the reliability of the method, as there is indication that stability of advantame is compromised under acidic conditions. Besides, the method may not be suitable for analyzing food matrices containing advantame at low ppm or sub-ppm level. In this presentation, a simple, specific and sensitive method for the determination of advantame in food is described. The method involved extraction with water and clean-up via solid phase extraction (SPE) followed by detection using liquid chromatography tandem mass spectrometry (LC-MS/MS) in negative electrospray ionization mode. No acid was used in the entire procedure. Single laboratory validation of the method was performed in terms of linearity, precision and accuracy. A low detection limit at ppb level was achieved. Satisfactory recoveries were obtained using spiked samples at three different concentration levels. This validated method could be used in the routine inspection of the advantame level in food.

Keywords: advantame, food, LC-MS/MS, sweetener

Procedia PDF Downloads 475

Authors: Ying Li, Zaisheng Hong, Weihong Wang

Abstract:

With the rapid enlargement of the size of Chinese universities, newly built campuses are springing up everywhere in recent years. It is urged to build eco-green campus because the role of higher education institutions in the transition to a more sustainable society has been highlighted for almost three decades. On condition that a new campus is usually built on an undeveloped site, where the basic infrastructure is not completed, finding proper strategies in planning and design of the campus becomes a primary concern. Low Impact Development (LID) options have been proposed as an alternative approach to make better use of rainwater in planning and design of an undeveloped site. On the basis of analyzing the natural circumstance, geographic condition, and other relative information, four main LID approaches are coordinated in this study of Hebei Union University, which are ‘Storage’, ‘Retaining’, ‘Infiltration’ and ‘Purification’. ‘Storage’ refers to a big central lake in the campus for rainwater harvesting. ‘Retaining’ means rainwater gardens scattered in the campus, also being known as bioretention areas which mimic the naturally created pools of water, to decrease surface flow runoff. ‘Infiltration’ is designed of grassed swales, which also play a part of floodway channel. ‘Purification’ is known as either natural or artificial wetland to reduce pollutants such as nitrogen and phosphorous in the waterbody. With above mentioned measures dealing with the synthetic use of rainwater in the acid & alkali area in the coastal district, an eco-green campus construction and an ecological sustainability will be realized, which will give us more enlightenment and reference.

Keywords: newly built campus, low impact development, planning design, rainwater reuse

Procedia PDF Downloads 248

Authors: Jin-Hui Lee, Myung-Min Oh

Abstract:

The application of temporary abiotic stresses before crop harvest is a potential strategy to enhance phytochemical content. The objective of this study was to determine the effect of various UV-A LED lights on the growth and content of bioactive compounds in kale (Brassica oleracea var. acephala). Fourteen-day-old kale seedlings were cultivated in a plant factory with artificial lighting (air temperature of 20℃, relative humidity of 60%, photosynthesis photon flux density (PPFD) of 125 µmol·m⁻²·s⁻¹) for 3 weeks. Kale plants were irradiated by four types of UV-A LEDs (peak wavelength; 365, 375, 385, and 395 nm) with 30 W/m² for 7 days. As a result, image chlorophyll fluorescence (Fv/Fm) value of kale leaves was lower as the UV-A LEDs peak wavelength was shorter. Fresh and dry weights of shoots and roots of kale plants were significantly higher in the plants under UV-A than the control at 7 days of treatment. In particular, the growth was significantly increased with a longer peak wavelength of the UV-A LEDs. The results of leaf area and specific leaf weight showed a similar pattern with those of growth characteristics. Chlorophyll content was highest in kale leaves subjected to UV-A LEDs with the peak wavelength of 395 nm at 3 days of treatment compared with the control. Total phenolic contents of UV-A LEDs with the peak wavelength of 395 nm at 5 and 6 days of treatment were 44% and 47% higher than those of the control, respectively. Antioxidant capacity showed almost the same pattern as the results of total phenol content. The activity of phenylalanine ammonia-lyase was approximately 11% and 8% higher in the UV-A LEDs with the peak wavelength of 395 nm compared to the control at 5 and 6 days of treatment, respectively. Our results imply that the UV-A LEDs with relative longer peak wavelength were effective to improve growth as well as the content of bioactive compounds of kale plants.

Keywords: bioactive compounds, growth, Kale, UV-A LEDs

Procedia PDF Downloads 142

Authors: Temesgen Kassa Getahun, Gezahegn Mamo, Beksisa Urge

Abstract:

A cross-sectional study was conducted from December 2019 to May 2020 with the aim of determining the seroprevalence of brucellosis in dairy cows and their owners in the central highland of Oromia, Ethiopia. A total of 352 blood samples from dairy cattle, 149 from animal owners, and 17 from farm workers were collected and initially screened using the Rose Bengal Plate test and confirmed by the Complement Fixation test. Overall seroprevalence was 0.6% (95% CI: 0.0016–0.0209) in bovines and 1.2% (95% CI: 0.0032–0.0427) in humans. Market-based stock replacement (OR=16.55, p=0.002), breeding by artificial insemination (OR=7.58, p=0.05), and parturition pen (OR = 11.511, p=0.027) were found to be significantly associated with the seropositivity for Brucella infection in dairy cattle. Human housing (OR=1.8, p=0.002), contact with an aborted fetus (OR=21.19, p=0.017), drinking raw milk from non-aborted (OR=24.99, p=0.012), aborted (OR=5.72, p=0.019) and retained fetal membrane (OR=4.22, p=0.029) cows had a significant influence on human brucellosis. A structured interview question was administered to 284 respondents. Accordingly, most respondents had no knowledge of brucellosis (93.3%), and in contrast, 90% of them consumed raw milk. In conclusion, the present seroprevalence study revealed that brucellosis was low among dairy cattle and exposed individuals in the study areas. However, since there were no control strategies implemented in the study areas, there is a potential risk of transmission of brucellosis in dairy cattle and the exposed human population in the study areas. Implementation of a test and slaughter strategy with compensation to farmers is recommended, while in the case of human brucellosis, continuous social training and implementing one health approach framework must be applied.

Keywords: abortion, bovine brucellosis, human brucellosis, risk factors, seroprevalence

Procedia PDF Downloads 105

Authors: Joseph George, Anne Kotteswara Roa

Abstract:

Skin disease is one of the most common and popular kinds of health issues faced by people nowadays. Skin cancer (SC) is one among them, and its detection relies on the skin biopsy outputs and the expertise of the doctors, but it consumes more time and some inaccurate results. At the early stage, skin cancer detection is a challenging task, and it easily spreads to the whole body and leads to an increase in the mortality rate. Skin cancer is curable when it is detected at an early stage. In order to classify correct and accurate skin cancer, the critical task is skin cancer identification and classification, and it is more based on the cancer disease features such as shape, size, color, symmetry and etc. More similar characteristics are present in many skin diseases; hence it makes it a challenging issue to select important features from a skin cancer dataset images. Hence, the skin cancer diagnostic accuracy is improved by requiring an automated skin cancer detection and classification framework; thereby, the human expert’s scarcity is handled. Recently, the deep learning techniques like Convolutional neural network (CNN), Deep belief neural network (DBN), Artificial neural network (ANN), Recurrent neural network (RNN), and Long and short term memory (LSTM) have been widely used for the identification and classification of skin cancers. This survey reviews different DL techniques for skin cancer identification and classification. The performance metrics such as precision, recall, accuracy, sensitivity, specificity, and F-measures are used to evaluate the effectiveness of SC identification using DL techniques. By using these DL techniques, the classification accuracy increases along with the mitigation of computational complexities and time consumption.

Keywords: skin cancer, deep learning, performance measures, accuracy, datasets

Procedia PDF Downloads 128

Authors: Blessing Ojeme, Frederick Quinn, Russell Karls, Shannon Quinn

Abstract:

The detection and segmentation of mitochondria from fluorescence microscopy are crucial for understanding the complex structure of the nervous system. However, the constant fission and fusion of mitochondria and image distortion in the background make the task of detection and segmentation challenging. In the literature, a number of open-source software tools and artificial intelligence (AI) methods have been described for analyzing mitochondrial images, achieving remarkable classification and quantitation results. However, the availability of combined expertise in the medical field and AI required to utilize these tools poses a challenge to its full adoption and use in clinical settings. Motivated by the advantages of automated methods in terms of good performance, minimum detection time, ease of implementation, and cross-platform compatibility, this study proposes a fully automated framework for the detection and segmentation of mitochondria using both image shape information and descriptive statistics. Using the low-cost, open-source python and openCV library, the algorithms are implemented in three stages: pre-processing, image binarization, and coarse-to-fine segmentation. The proposed model is validated using the mitochondrial fluorescence dataset. Ground truth labels generated using a Lab kit were also used to evaluate the performance of our detection and segmentation model. The study produces good detection and segmentation results and reports the challenges encountered during the image analysis of mitochondrial morphology from the fluorescence mitochondrial dataset. A discussion on the methods and future perspectives of fully automated frameworks conclude the paper.

Keywords: 2D, binarization, CLAHE, detection, fluorescence microscopy, mitochondria, segmentation

Procedia PDF Downloads 357

Authors: Chakraborty Sudipta, A. R. Kambekar, Sarma Arnab

Abstract:

Sea-level rise being one of the most important impacts of anthropogenic induced climate change resulting from global warming and melting of icebergs at Arctic and Antarctic, the investigations done by various researchers both on Indian Coast and elsewhere during the last decade has been reviewed in this paper. The paper aims to ascertain the propensity of consistency of different suggested methods to predict the near-accurate future sea level rise along the coast of Mumbai. Case studies at East Coast, Southern Tip and West and South West coast of India have been reviewed. Coastal Vulnerability Index of several important international places has been compared, which matched with Intergovernmental Panel on Climate Change forecasts. The application of Geographic Information System mapping, use of remote sensing technology, both Multi Spectral Scanner and Thematic Mapping data from Landsat classified through Iterative Self-Organizing Data Analysis Technique for arriving at high, moderate and low Coastal Vulnerability Index at various important coastal cities have been observed. Instead of data driven, hindcast based forecast for Significant Wave Height, additional impact of sea level rise has been suggested. Efficacy and limitations of numerical methods vis-à-vis Artificial Neural Network has been assessed, importance of Root Mean Square error on numerical results is mentioned. Comparing between various computerized methods on forecast results obtained from MIKE 21 has been opined to be more reliable than Delft 3D model.

Keywords: climate change, Coastal Vulnerability Index, global warming, sea level rise

Procedia PDF Downloads 132

Authors: Andrea Treviño Gavito, Diego Klabjan, Sanjiv J. Shah

Abstract:

Echocardiograms serve as pivotal resources for clinicians in diagnosing cardiac conditions, offering non-invasive insights into a heart’s structure and function. When echocardiographic studies are conducted, no standardized labeling of the acquired views is performed. Employing machine learning algorithms for automated echocardiogram view detection has emerged as a promising solution to enhance efficiency in echocardiogram use for diagnosis. However, existing approaches predominantly rely on supervised learning, necessitating labor-intensive expert labeling. In this paper, we introduce a fully unsupervised echocardiographic view detection framework that leverages convolutional autoencoders to obtain lower dimensional representations and the K-means algorithm for clustering them into view-related groups. Our approach focuses on discriminative patches from echocardiographic frames. Additionally, we propose a trainable inverse average layer to optimize decoding of average operations. By integrating both public and proprietary datasets, we obtain a marked improvement in model performance when compared to utilizing a proprietary dataset alone. Our experiments show boosts of 15.5% in accuracy and 9.0% in the F-1 score for frame-based clustering, and 25.9% in accuracy and 19.8% in the F-1 score for view-based clustering. Our research highlights the potential of unsupervised learning methodologies and the utilization of open-sourced data in addressing the complexities of echocardiogram interpretation, paving the way for more accurate and efficient cardiac diagnoses.

Keywords: artificial intelligence, echocardiographic view detection, echocardiography, machine learning, self-supervised representation learning, unsupervised learning

Procedia PDF Downloads 32

Authors: Noriyuki Suyama

Abstract:

The progress and spread of digitalization have led to the provision of a variety of new services. The recent progress in digitization can be attributed to rapid developments in science and technology. First, the research and diffusion of artificial intelligence (AI) has made dramatic progress. Around 2000, the third wave of AI research, which had been underway for about 50 years, arrived. Specifically, machine learning and deep learning were made possible in AI, and the ability of AI to acquire knowledge, define the knowledge, and update its own knowledge in a quantitative manner made the use of big data practical even for commercial PCs. On the other hand, with the spread of social media, information exchange has become more common in our daily lives, and the lending and borrowing of goods and services, in other words, the sharing economy, has become widespread. The scope of this trend is not limited to any industry, and its momentum is growing as the SDGs take root. In addition, the Social Network Service (SNS), a part of social media, has brought about the evolution of the retail business. In the past few years, social network services (SNS) involving users or companies have especially flourished. The People's Republic of China (hereinafter referred to as "China") is a country that is stimulating enormous consumption through its own unique SNS, which is different from the SNS used in developed countries around the world. This paper focuses on the effectiveness and challenges of influencer marketing by focusing on the influence of influencers on users' behavior and satisfaction with Chinese SNSs. Specifically, Conducted was the quantitative survey of Tik Tok users living in China, with the aim of gaining new insights from the analysis and discussions. As a result, we found several important findings and knowledge.

Keywords: customer satisfaction, social networking services, influencer marketing, Chinese consumers’ behavior

Procedia PDF Downloads 89

Authors: Min Jindong, Wang Mingxia

Abstract:

With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.

Keywords: object detection, knowledge distillation, convolutional network, model compression

Procedia PDF Downloads 278

Authors: Raghava Dhanya, Shashank S.

Abstract:

This paper delves into the intersection of chess and computer science, specifically focusing on the efficient representation of chess game states. We propose two methods: the Static Method and the Dynamic Method, each offering unique advantages in terms of space efficiency and computational complexity. The Static Method aims to represent the game state using a fixedlength encoding, allocating 192 bits to capture the positions of all pieces on the board. This method introduces a protocol for ordering and encoding piece positions, ensuring efficient storage and retrieval. However, it faces challenges in representing pieces no longer in play. In contrast, the Dynamic Method adapts to the evolving game state by dynamically adjusting the encoding length based on the number of pieces in play. By incorporating Alive Bits for each piece kind, this method achieves greater flexibility and space efficiency. Additionally, it includes provisions for encoding additional game state information such as castling rights and en passant squares. Our findings demonstrate that the Dynamic Method offers superior space efficiency compared to traditional Forsyth-Edwards Notation (FEN), particularly as the game progresses and pieces are captured. However, it comes with increased complexity in encoding and decoding processes. In conclusion, this study provides insights into optimizing the representation of chess game states, offering potential applications in chess engines, game databases, and artificial intelligence research. The proposed methods offer a balance between space efficiency and computational overhead, paving the way for further advancements in the field.

Keywords: chess, optimisation, encoding, bit manipulation

Procedia PDF Downloads 50

Authors: Suvarna Kumar Gogula, Sandhya Devi Gogula, P. Chanakya

Abstract:

Augmented reality is defined as the collection of the digital (or) computer generated information like images, audio, video, 3d models, etc. and overlay them over the real time environment. Augmented reality can be thought as a blend between completely synthetic and completely real. Augmented reality provides scope in a wide range of industries like manufacturing, retail, gaming, advertisement, tourism, etc. and brings out new dimensions in the modern digital world. As it overlays the content, it makes the users enhance the knowledge by providing the content blended with real world. In this application, we integrated augmented reality with data analytics and integrated with cloud so the virtual content will be generated on the basis of the data present in the database and we used marker based augmented reality where every marker will be stored in the database with corresponding unique ID. This application can be used in wide range of industries for different business processes, but in this paper, we mainly focus on the marketing industry which helps the customer in gaining the knowledge about the products in the market which mainly focus on their prices, customer feedback, quality, and other benefits. This application also focuses on providing better market strategy information for marketing managers who obtain the data about the stocks, sales, customer response about the product, etc. In this paper, we also included the reports from the feedback got from different people after the demonstration, and finally, we presented the future scope of Augmented Reality in different business processes by integrating with new technologies like cloud, big data, artificial intelligence, etc.

Keywords: augmented reality, data analytics, catch room, marketing and sales

Procedia PDF Downloads 237

Authors: Bliss Singhal

Abstract:

Machine learning (ML) is a branch of Artificial Intelligence (AI) where computers analyze data and find patterns in the data. The study focuses on the detection of metastatic cancer using ML. Metastatic cancer is the stage where cancer has spread to other parts of the body and is the cause of approximately 90% of cancer-related deaths. Normally, pathologists spend hours each day to manually classifying whether tumors are benign or malignant. This tedious task contributes to mislabeling metastasis being over 60% of the time and emphasizes the importance of being aware of human error and other inefficiencies. ML is a good candidate to improve the correct identification of metastatic cancer, saving thousands of lives and can also improve the speed and efficiency of the process, thereby taking fewer resources and time. So far, the deep learning methodology of AI has been used in research to detect cancer. This study is a novel approach to determining the potential of using preprocessing algorithms combined with classification algorithms in detecting metastatic cancer. The study used two preprocessing algorithms: principal component analysis (PCA) and the genetic algorithm, to reduce the dimensionality of the dataset and then used three classification algorithms: logistic regression, decision tree classifier, and k-nearest neighbors to detect metastatic cancer in the pathology scans. The highest accuracy of 71.14% was produced by the ML pipeline comprising of PCA, the genetic algorithm, and the k-nearest neighbor algorithm, suggesting that preprocessing and classification algorithms have great potential for detecting metastatic cancer.

Keywords: breast cancer, principal component analysis, genetic algorithm, k-nearest neighbors, decision tree classifier, logistic regression

Procedia PDF Downloads 81

Authors: Alisher Ibragimov, Sofya Senotrusova, Aleksandra Beliaeva, Egor Ushakov, Yuri Markin

Abstract:

Mammography plays a critical role in screening for breast cancer in women, and artificial intelligence has enabled the automatic detection of diseases in medical images. Many of the current techniques used for mammogram analysis focus on a single view (mediolateral or craniocaudal view), while in clinical practice, radiologists consider multiple views of mammograms from both breasts to make a correct decision. Consequently, computer-aided diagnosis (CAD) systems could benefit from incorporating information gathered from multiple views. In this study, the introduce a method based on a Siamese neural network (SNN) model that simultaneously analyzes mammographic images from tri-view: bilateral and ipsilateral. In this way, when a decision is made on a single image of one breast, attention is also paid to two other images – a view of the same breast in a different projection and an image of the other breast as well. Consequently, the algorithm closely mimics the radiologist's practice of paying attention to the entire examination of a patient rather than to a single image. Additionally, to the best of our knowledge, this research represents the first experiments conducted using the recently released Vietnamese dataset of digital mammography (VinDr-Mammo). On an independent test set of images from this dataset, the best model achieved an AUC of 0.87 per image. Therefore, this suggests that there is a valuable automated second opinion in the interpretation of mammograms and breast cancer diagnosis, which in the future may help to alleviate the burden on radiologists and serve as an additional layer of verification.

Keywords: breast cancer, computer-aided diagnosis, deep learning, multi-view mammogram, siamese neural network

Procedia PDF Downloads 137

Authors: A. Shirazibeheshti, T. Radwan, A. Ettefaghian, G. Wilson, C. Luca, Farbod Khanizadeh

Abstract:

Anticholinergic medication has been associated with events such as falls, delirium, and cognitive impairment in older patients. To further assess this, anticholinergic burden scores have been developed to quantify risk. A risk model based on clustering was deployed in a healthcare management system to cluster patients into multiple risk groups according to anticholinergic burden scores of multiple medicines prescribed to patients to facilitate clinical decision-making. To do so, anticholinergic burden scores of drugs were extracted from the literature, which categorizes the risk on a scale of 1 to 3. Given the patients’ prescription data on the healthcare database, a weighted anticholinergic risk score was derived per patient based on the prescription of multiple anticholinergic drugs. This study was conducted on over 300,000 records of patients currently registered with a major regional UK-based healthcare provider. The weighted risk scores were used as inputs to an unsupervised learning algorithm (mean-shift clustering) that groups patients into clusters that represent different levels of anticholinergic risk. To further evaluate the performance of the model, any association between the average risk score within each group and other factors such as socioeconomic status (i.e., Index of Multiple Deprivation) and an index of health and disability were investigated. The clustering identifies a group of 15 patients at the highest risk from multiple anticholinergic medication. Our findings also show that this group of patients is located within more deprived areas of London compared to the population of other risk groups. Furthermore, the prescription of anticholinergic medicines is more skewed to female than male patients, indicating that females are more at risk from this kind of multiple medications. The risk may be monitored and controlled in well artificial intelligence-equipped healthcare management systems.

Keywords: anticholinergic medicines, clustering, deprivation, socioeconomic status

Procedia PDF Downloads 211

Authors: Namwinwelbere Dabire, Eugene C. Ezin, Adandedji M. Firmin

Abstract:

The prediction of hydrological flows (rainfall-depth or rainfall-discharge) is becoming increasingly important in the management of hydrological risks such as floods. In this study, the Long Short-Term Memory (LSTM) network, a state-of-the-art algorithm dedicated to time series, is applied to predict the daily water level of Nokoue Lake in Benin. This paper aims to provide an effective and reliable method enable of reproducing the future daily water level of Nokoue Lake, which is influenced by a combination of two phenomena: rainfall and river flow (runoff from the Ouémé River, the Sô River, the Porto-Novo lagoon, and the Atlantic Ocean). Performance analysis based on the forecasting horizon indicates that LSTM can predict the water level of Nokoué Lake up to a forecast horizon of t+10 days. Performance metrics such as Root Mean Square Error (RMSE), coefficient of correlation (R²), Nash-Sutcliffe Efficiency (NSE), and Mean Absolute Error (MAE) agree on a forecast horizon of up to t+3 days. The values of these metrics remain stable for forecast horizons of t+1 days, t+2 days, and t+3 days. The values of R² and NSE are greater than 0.97 during the training and testing phases in the Nokoué Lake basin. Based on the evaluation indices used to assess the model's performance for the appropriate forecast horizon of water level in the Nokoué Lake basin, the forecast horizon of t+3 days is chosen for predicting future daily water levels.

Keywords: forecasting, long short-term memory cell, recurrent artificial neural network, Nokoué lake

Procedia PDF Downloads 64

Authors: L. Krpalkova, N. O' Mahony, A. Carvalho, S. Campbell, G. Corkery, E. Broderick, J. Walsh

Abstract:

Farm management and operations will drastically change due to access to real-time data, real-time forecasting, and tracking of physical items in combination with Internet of Things developments to further automate farm operations. Dairy farms have embraced technological innovations and procured vast amounts of permanent data streams during the past decade; however, the integration of this information to improve the whole farm-based management and decision-making does not exist. It is now imperative to develop a system that can collect, integrate, manage, and analyse on-farm and off-farm data in real-time for practical and relevant environmental and economic actions. The developed systems, based on machine learning and artificial intelligence, need to be connected for useful output, a better understanding of the whole farming issue, and environmental impact. Evolutionary computing can be very effective in finding the optimal combination of sets of some objects and, finally, in strategy determination. The system of the future should be able to manage the dairy farm as well as an experienced dairy farm manager with a team of the best agricultural advisors. All these changes should bring resilience and sustainability to dairy farming as well as improving and maintaining good animal welfare and the quality of dairy products. This review aims to provide an insight into the state-of-the-art of big data applications and evolutionary computing in relation to smart dairy farming and identify the most important research and development challenges to be addressed in the future. Smart dairy farming influences every area of management, and its uptake has become a continuing trend.

Keywords: big data, evolutionary computing, cloud, precision technologies

Procedia PDF Downloads 189

Authors: Leila Karshenas, Hamid Reza Khodaei, Behnaz Mahdavi

Abstract:

We know that nitric oxide (NO) plays an important role in all sexual activities of animals. It is made in body from NO synthase enzyme and L-arginin molecule. NO can bound with sulfur-iron complexes and because production of steroid sexual hormones is related to enzymes which have this complex, NO can change the activity of these enzymes. NO affects many cells including endothelial cells of veins, macrophages and mast cells. These cells are found in testis leydig cells and therefore are important source of NO in testis tissue. Minimizing damages to sperm at the time of sperm freezing and thawing is really important. The goal of this study was to determine the function of NO before freezing and its effects on quality and viability of sperms after thawing and incubation. 4 Holstein bulls were selected from the age of 4, and artificial insemination was done for 3 weeks (2 times a week). Treatments were 0, 10, 50 and 100 nm of sodium nitroprusside (SNP). Data analysis was performed by SAS98 program. Also, mean comparison was done using Duncan's multiple ranges test (P<0.05). Concentrations used was found to increase motility and viability of spermatozoa at 1, 2 and 3 hours after thawing significantly (P<0.05), but there was no significant difference at zero time. SNP levels reduced the amount of lipid peroxidation in sperm membrane, increased acrosome health and improved sample membranes especially in 50 and 100 nm treatments. According to results, adding SNP to semen diluents increases motility and viability of spermatozoa. Also, it reduces lipid peroxidation in sperm membrane and improves sperm function.

Keywords: sperm motility, nitric oxide, lipid peroxidation, spermatozoa

Procedia PDF Downloads 359

Authors: Oscar Covarrubias, Diane Ghanem, Christopher Murdock, Babar Shafiq

Abstract:

Introduction: ChatGPT is an advanced language AI tool designed to understand and generate human-like text. The aim of this study is to assess the ability of ChatGPT-4 to re-write orthopaedic trauma patient education materials at the recommended 6th-grade level. Methods: Two independent reviewers accessed ChatGPT-4 (chat.openai.com) and gave identical instructions to simplify the readability of provided text to a 6th-grade level. All trauma-related articles by the Orthopaedic Trauma Association (OTA) and American Academy of Orthopaedic Surgeons (AAOS) were sequentially provided. The academic grade level was determined using the Flesh-Kincaid Grade Level (FKGL) and Flesch Reading Ease (FRE). Paired t-tests and Wilcox-rank sum tests were used to compare the FKGL and FRE between the ChatGPT-4 revised and original text. Inter-rater correlation coefficient (ICC) was used to assess variability in ChatGPT-4 generated text between the two reviewers. Results: ChatGPT-4 significantly reduced FKGL and increased FRE scores in the OTA (FKGL: 5.7±0.5 compared to the original 8.2±1.1, FRE: 76.4±5.7 compared to the original 65.5±6.6, p < 0.001) and AAOS articles (FKGL: 5.8±0.8 compared to the original 8.9±0.8, FRE: 76±5.5 compared to the original 56.7±5.9, p < 0.001). On average, 14.6% of OTA and 28.6% of AAOS articles required at least two revisions by ChatGPT-4 to achieve a 6th-grade reading level. ICC demonstrated poor reliability for FKGL (OTA 0.24, AAOS 0.45) and moderate reliability for FRE (OTA 0.61, AAOS 0.73). Conclusion: This study provides a novel, simple and efficient method using language AI to optimize the readability of patient education content which may only require the surgeon’s final proofreading. This method would likely be as effective for other medical specialties.

Keywords: artificial intelligence, AI, chatGPT, patient education, readability, trauma education

Procedia PDF Downloads 72

Authors: Sareh Enjavi

Abstract:

In recent years, the field of visual communication design has seen a significant shift in the way that art is created and consumed, with the advent of new technologies like virtual reality, augmented reality, and artificial intelligence. This paper explores the ways in which technology is changing the landscape of visual communication design, and how designers are incorporating new technological tools into their artistic practices. The primary objective of this research paper is to investigate the ways in which technology is influencing the creative process of designers and artists in the field of visual communication design. The paper also aims to examine the challenges and limitations that arise from the intersection of art and technology in visual communication design, and to identify strategies for overcoming these challenges. Drawing on examples from a range of fields, including advertising, fine art, and digital media, this paper highlights the exciting innovations that are emerging as artists and designers use technology to push the boundaries of traditional artistic expression. The paper argues that embracing technological innovation is essential for the continued evolution of visual communication design. By exploring the intersection of art and technology, designers can create new and exciting visual experiences that engage and inspire audiences in new ways. The research also contributes to the theoretical and methodological understanding of the intersection of art and technology, a topic that has gained significant attention in recent years. Ultimately, this paper emphasizes the importance of embracing innovation and experimentation in the field of visual communication design, and highlights the exciting innovations that are emerging as a result of the intersection of art and technology, and emphasizes the importance of embracing innovation and experimentation in the field of visual communication design.

Keywords: visual communication design, art and technology, virtual reality, interactive art, creative process

Procedia PDF Downloads 118

Authors: Ali Asgary, Haopeng Zhou, Ghassem Tofighi

Abstract:

Use of virtual (VR), augmented reality (AR), and extended reality technologies for training and education has increased in recent years as more hardware and software tools have become available and accessible to larger groups of users. Similarly, the applications of these technologies in earthquake related training and education are on the rise. Several studies have reported promising results for the use of VR and AR for evacuation behaviour and training under earthquake situations. They simulate the impacts that earthquake has on buildings, buildings’ contents, and how building occupants and users can find safe spots or open paths to outside. Considering that considerable number of earthquake injuries and fatalities are linked to the behaviour, our goal is to use these technologies to reduce the impacts of building contents on people. Building on our artificial intelligence (AI) based indoor earthquake risk assessment application that enables users to use their mobile device to assess the risks associated with building contents during earthquakes, we develop a virtual reality application to demonstrate the behavior of different building contents during earthquakes, their associate moving, spreading, falling, and collapsing risks, and their risk mitigation methods. We integrate realistic seismic models, building contents behavior with and without risk mitigation measures in virtual reality environment. The application can be used for training of architects, interior design experts, and building users to enhance indoor safety of the buildings that can sustain earthquakes. This paper describes and demonstrates the application development background, structure, components, and usage.

Keywords: virtual reality, earthquake damage, building content, indoor risks, earthquake risk mitigation, interior design, unity game engine, oculus

Procedia PDF Downloads 105

Authors: Fatin Khalida Abdul Khadir, Husna Takaijudin

Abstract:

Bioretention system is one of the alternatives to approach the conventional stormwater management, low impact development (LID) strategy for best management practices (BMPs). Incorporating both filtration and infiltration, initial research on bioretention systems has shown that this practice extensively decreases runoff volumes and peak flows. The LID-BMP treatment train is one of the latest LID-BMPs for stormwater treatments in urbanized watersheds. The treatment train is developed to overcome the drawbacks that arise from conventional LID-BMPs and aims to enhance the performance of the existing practices. In addition, it is also used to improve treatments in both water quality and water quantity controls as well as maintaining the natural hydrology of an area despite the current massive developments. The objective of this paper is to review the effectiveness of the conventional LID-BMPS on hydrologic and hydraulic performances through column studies in different configurations. The previous studies on the applications of LID-BMP treatment train that were developed to overcome the drawbacks of conventional LID-BMPs are reviewed and use as the guidelines for implementing this system in Universiti Teknologi Petronas (UTP) and elsewhere. The reviews on the analysis conducted for hydrologic and hydraulic performances using the artificial neural network (ANN) model are done in order to be utilized in this study. In this study, the role of the LID-BMP treatment train is tested by arranging bioretention cells in series in order to be implemented for controlling floods that occurred currently and in the future when the construction of the new buildings in UTP completed. A summary of the research findings on the performances of the system is provided which includes the proposed modifications on the designs.

Keywords: bioretention system, LID-BMP treatment train, hydrological and hydraulic performance, ANN analysis

Procedia PDF Downloads 118

Authors: S. Potgieter-Vermaak, N. Bain, A. Brown, K. Shaw

Abstract:

It is well-known from public news media that air pollution is a health hazard and is responsible for early deaths. The quantification of the relationship between air quality and health is a probing question not easily answered. It is known that airborne particulate matter (APM) <2.5µm deposits in the tracheal and alveoli zones and our research probes the possibility of quantifying pulmonary injury by linking reactive oxygen species (ROS) in these particles to DNA damage. Currently, APM mass concentration is linked to early deaths and limited studies probe the influence of other properties on human health. To predict the full extent and type of impact, particles need to be characterised for chemical composition and structure. APMs are routinely analysed for their bulk composition, but of late analysis on a micro level probing single particle character, using micro-analytical techniques, are considered. The latter, single particle analysis (SPA), permits one to obtain detailed information on chemical character from nano- to micron-sized particles. This paper aims to provide a snapshot of studies using data obtained from chemical characterisation and its link with in-vitro studies to inform on personal health risks. For this purpose, two studies will be compared, namely, the bioaccessibility of the inhalable fraction of urban road dust versus total suspended solids (TSP) collected in the same urban environment. The significant influence of metals such as Cu and Fe in TSP on DNA damage is illustrated. The speciation of Hg (determined by SPA) in different urban environments proved to dictate its bioaccessibility in artificial lung fluids rather than its concentration.

Keywords: air pollution, human health, in-vitro studies, particulate matter

Procedia PDF Downloads 225