Search results for: deep q-network

Authors: Amin Nezarat, Naeime Seifadini

Abstract:

Trip mode selection is a behavioral characteristic of passengers with immense importance for travel demand analysis, transportation planning, and traffic management. Identification of trip mode distribution will allow transportation authorities to adopt appropriate strategies to reduce travel time, traffic and air pollution. The majority of existing trip mode inference models operate based on human selected features and traditional machine learning algorithms. However, human selected features are sensitive to changes in traffic and environmental conditions and susceptible to personal biases, which can make them inefficient. One way to overcome these problems is to use neural networks capable of extracting high-level features from raw input. In this study, the convolutional neural network (CNN) architecture is used to predict the trip mode distribution based on raw GPS trajectory data. The key innovation of this paper is the design of the layout of the input layer of CNN as well as normalization operation, in a way that is not only compatible with the CNN architecture but can also represent the fundamental features of motion including speed, acceleration, jerk, and Bearing rate. The highest prediction accuracy achieved with the proposed configuration for the convolutional neural network with batch normalization is 85.26%.

Keywords: predicting, deep learning, neural network, urban trip

Procedia PDF Downloads 138

Authors: Subham Ghosh, Arnab Nandi

Abstract:

Background: The proliferation of Wireless Body Area Networks (WBAN) and Internet of Things (IoT) applications demonstrates the potential for continuous monitoring of physical changes in the body. These technologies are vital for health monitoring tasks, such as identifying coughing and breathing activities, which are necessary for disease diagnosis and management. Monitoring activities such as coughing and deep breathing can provide valuable insights into a variety of medical issues. Wearable radio-based antenna sensors, which are lightweight and easy to incorporate into clothing or portable goods, provide continuous monitoring. This mobility gives it a substantial advantage over stationary environmental sensors like as cameras and radar, which are constrained to certain places. Furthermore, using compressive techniques provides benefits such as reduced data transmission speeds and memory needs. These wearable sensors offer more advanced and diverse health monitoring capabilities. Methodology: This study analyzes the feasibility of using a semi-flexible antenna operating at 2.4 GHz (ISM band) and positioned around the neck and near the mouth to identify three activities: coughing, deep breathing, and idleness. Vector network analyzer (VNA) is used to collect time-varying complex reflection coefficient data from perturbed antenna nearfield. The reflection coefficient (S11) conveys nuanced information caused by simultaneous variations in the nearfield radiation of three activities across time. The signatures are sparsely represented with gaussian windowed Gabor spectrograms. The Gabor spectrogram is used as a sparse representation approach, which reassigns the ridges of the spectrogram images to improve their resolution and focus on essential components. The antenna is biocompatible in terms of specific absorption rate (SAR). The sparsely represented Gabor spectrogram pictures are fed into a lightweight deep learning (DL) model for feature extraction and classification. Two antenna locations are investigated in order to determine the most effective localization for three different activities. Findings: Cross-validation techniques were used on data from both locations. Due to the complex form of the recorded S11, separate analyzes and assessments were performed on the magnitude, phase, and their combination. The combination of magnitude and phase fared better than the separate analyses. Various sliding window sizes, ranging from 1 to 5 seconds, were tested to find the best window for activity classification. It was discovered that a neck-mounted design was effective at detecting the three unique behaviors.

Keywords: activity recognition, antenna, deep-learning, time-frequency

Procedia PDF Downloads 10

Authors: Auwal Abubakar, Shazril Imran Shaukat, Noor Khairiah A. Karim, Mohammed Zakir Kassim, Gokula Kumar Appalanaido, Hafiz Mohd Zin

Abstract:

Background: Voluntary deep inspiration breath-hold radiotherapy (vDIBH-RT) is an effective cardiac dose reduction technique during left breast radiotherapy. This study aimed to assess the accuracy of the implementation of the vDIBH technique among left breast cancer patients without the use of a special device such as a surface-guided imaging system. Methods: The vDIBH-RT technique was implemented among thirteen (13) left breast cancer patients at the Advanced Medical and Dental Institute (AMDI), Universiti Sains Malaysia. Breath-hold monitoring was performed based on breath-hold skin marks and laser light congruence observed on zoomed CCTV images from the control console during each delivery. The initial setup was verified using cone beam computed tomography (CBCT) during breath-hold. Each field was delivered using multiple beam segments to allow a delivery time of 20 seconds, which can be tolerated by patients in breath-hold. The data were analysed using an in-house developed MATLAB algorithm. PTV margin was computed based on van Herk's margin recipe. Results: The setup error analysed from CBCT shows that the population systematic error in lateral (x), longitudinal (y), and vertical (z) axes was 2.28 mm, 3.35 mm, and 3.10 mm, respectively. Based on the CBCT image guidance, the Planning target volume (PTV) margin that would be required for vDIBH-RT using CCTV/Laser monitoring technique is 7.77 mm, 10.85 mm, and 10.93 mm in x, y, and z axes, respectively. Conclusion: It is feasible to safely implement vDIBH-RT among left breast cancer patients without special equipment. The breath-hold monitoring technique is cost-effective, radiation-free, easy to implement, and allows real-time breath-hold monitoring.

Keywords: vDIBH, cone beam computed tomography, radiotherapy, left breast cancer

Procedia PDF Downloads 57

Authors: Srinivasan Chandrasekaran, R. Nagavinothini

Abstract:

Offshore platforms for ultra-deep waters are form-dominant by design; hybrid systems with large flexibility in horizontal plane and high rigidity in vertical plane are preferred due to functional complexities. Offshore triceratops is relatively a new-generation offshore platform, whose deck is partially isolated from the supporting buoyant legs by ball joints. They allow transfer of partial displacements of buoyant legs to the deck but restrain transfer of rotational response. Buoyant legs are in turn taut-moored to the sea bed using pre-tension tethers. Present study will discuss detailed dynamic analysis and preliminary design of the chosen geometric, which is necessary as a proof of validation for such design applications. A detailed numeric analysis of triceratops at 2400 m water depth under random waves is presented. Preliminary design confirms member-level design requirements under various modes of failure. Tether configuration, proposed in the study confirms no pull-out of tethers as stress variation is comparatively lesser than the yield value. Presented study shall aid offshore engineers and contractors to understand suitability of triceratops, in terms of design and dynamic response behaviour.

Keywords: offshore structures, triceratops, random waves, buoyant legs, preliminary design, dynamic analysis

Procedia PDF Downloads 206

Authors: Surajit Chakrabarty, Piyush Chauhan, Subhasis Panda, Sujoy Bhattacharya

Abstract:

A large proportion of roads in India are not well maintained as per the laid down public safety guidelines leading to loss of direction control and fatal accidents. We propose a technique to detect speed breakers and potholes using mobile sensor data captured from multiple vehicles and provide a profile of the road. This would, in turn, help in monitoring roads and revolutionize digital maps. Incorporating randomness in the model formulation for detection of speed breakers and potholes is crucial due to substantial heterogeneity observed in data obtained using a mobile application from multiple vehicles driven by different drivers. This is accomplished with Hidden Markov Models, whose hidden state sequence is found for each time step given the observables sequence, and are then fed as input to LSTM network with peephole connections. A precision score of 0.96 and 0.63 is obtained for classifying bumps and potholes, respectively, a significant improvement from the machine learning based models. Further visualization of bumps/potholes is done by converting time series to images using Markov Transition Fields where a significant demarcation among bump/potholes is observed.

Keywords: deep learning, hidden Markov model, pothole, speed breaker

Procedia PDF Downloads 144

Authors: Morteza Karami, Soheila Dayani

Abstract:

Deep Soil Mixing (DSM) is a soil improvement technique that involves mechanically mixing the soil with a binder material to improve its strength, stiffness, and durability. This technique is typically used in geotechnical engineering applications where weak or unstable soil conditions exist, such as in building foundations, embankment support, or ground improvement projects. In this study, the settlement of the foundation on the improved soil using the wet DSM technique has been analyzed for a case study. Before DSM production, the initial soil mixture has been determined based on the laboratory tests and then, the proper mix designs have been optimized based on the pilot scale tests. The results show that the spacing and depth of the DSM columns depend on the soil properties, the intended loading conditions, and other factors such as the available space and equipment limitations. Moreover, monitoring instruments installed in the pilot area verify that the settlement of the foundation has been placed in an acceptable range to ensure that the soil mixture is providing the required strength and stiffness to support the structure or load. As an important result, if the DSM columns touch or penetrate into the stiff soil layer, the settlement of the foundation can be significantly decreased. Furthermore, the DSM columns should be allowed to cure sufficiently before placing any significant loads on the structure to prevent excessive deformation or settlement.

Keywords: deep soil mixing, soil mixture, settlement, instrumentation, curing age

Procedia PDF Downloads 85

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: Rita Phillips, Mark Burgess, Maga Berlinski

Abstract:

Although the positive impact of religiosity on well-being, health, and life-coping abilities is well known, up to date research has failed to provide scientific evidence for the relationship reasons. Therefore the present study took a qualitative approach by examining how religiosity interacts in coping with emotionally distressful situations, for which wedding preparations are an example. Wedding preparations, related to the experience of ambiguous emotions, can be the reason for phases of high distress. Although being per-se religious ceremonies, they are also socially-scripted and characterized by people’s striving for personally meaningful celebrations. The negotiation of these many influences can evoke conflicts. To reveal components of religiosity which contribute to stress-resolution, eight biographic-narrative interviews with recently married spouses were conducted. Participants were from different nationalities and Catholic deep-belief communities in order to determine factors independent from national-culture and social-subgroup. The audio-tape recorded, transcribed and translated interviews were analyzed by Interpretative Phenomenological Analysis. Opposing previous research on wedding-related conflicts but in-line with the quantitative account on the relation between stress-resilience and religiosity, the present study found participants reporting very low levels of distress and ambiguity. Although similar areas of potential conflicts were revealed, deep-belief Christians seemed to handle them in a different way. Participants freed themselves from own and others’ rigor mundane expectations by their spiritual preparation and the focus on a divine instance. This evoked a feeling of perceived closeness to God and of unconditional love, resulting in acceptance of oneself and others. Through relativizing mundane goods, participants perceived absolute freedom. Thus belief did not supplement coping strategies, previously defined in the literature, but substituted them. The paper implies that in explaining the connection between stress-resilience and religiosity, one’s perception and experience of unconditional love might outweigh other social or personal factors. However, further qualitative investigations are needed to fully explain the phenomenon.

Keywords: deep-belief, religiosity, resilience, wedding

Procedia PDF Downloads 245

Authors: Marcos Silva Tavares, Jamile Raquel Regazzo, Edson José de Souza Sardinha, Murilo Mesquita Baesso

Abstract:

Common beans are a widely cultivated and consumed legume globally, serving as a staple food for humans, especially in developing countries, due to their nutritional characteristics. Nitrogen (N) is the most limiting nutrient for productivity, and foliar analysis is crucial to ensure balanced nitrogen fertilization. Excessive N applications can cause, either isolated or cumulatively, soil and water contamination, plant toxicity, and increase their susceptibility to diseases and pests. However, the quantification of N using conventional methods is time-consuming and costly, demanding new technologies to optimize the adequate supply of N to plants. Thus, it becomes necessary to establish constant monitoring of the foliar content of this macronutrient in plants, mainly at the V4 stage, aiming at precision management of nitrogen fertilization. In this work, the objective was to evaluate the performance of a deep learning model, Resnet-50, in the classification of foliar nitrogen in common beans using RGB images. The BRS Estilo cultivar was sown in a greenhouse in a completely randomized design with four nitrogen doses (T1 = 0 kg N ha-1, T2 = 25 kg N ha-1, T3 = 75 kg N ha-1, and T4 = 100 kg N ha-1) and 12 replications. Pots with 5L capacity were used with a substrate composed of 43% soil (Neossolo Quartzarênico), 28.5% crushed sugarcane bagasse, and 28.5% cured bovine manure. The water supply of the plants was done with 5mm of water per day. The application of urea (45% N) and the acquisition of images occurred 14 and 32 days after sowing, respectively. A code developed in Matlab© R2022b was used to cut the original images into smaller blocks, originating an image bank composed of 4 folders representing the four classes and labeled as T1, T2, T3, and T4, each containing 500 images of 224x224 pixels obtained from plants cultivated under different N doses. The Matlab© R2022b software was used for the implementation and performance analysis of the model. The evaluation of the efficiency was done by a set of metrics, including accuracy (AC), F1-score (F1), specificity (SP), area under the curve (AUC), and precision (P). The ResNet-50 showed high performance in the classification of foliar N levels in common beans, with AC values of 85.6%. The F1 for classes T1, T2, T3, and T4 was 76, 72, 74, and 77%, respectively. This study revealed that the use of RGB images combined with deep learning can be a promising alternative to slow laboratory analyses, capable of optimizing the estimation of foliar N. This can allow rapid intervention by the producer to achieve higher productivity and less fertilizer waste. Future approaches are encouraged to develop mobile devices capable of handling images using deep learning for the classification of the nutritional status of plants in situ.

Keywords: convolutional neural network, residual network 50, nutritional status, artificial intelligence

Procedia PDF Downloads 19

Authors: Mojtaba Heydarizad

Abstract:

Andarokh basin is one of the main karstic regions in Khorasan Razavi province NE Iran. This basin is part of Kopeh-Dagh mega zone extending from Caspian Sea in the east to northern Afghanistan in the west. This basin is covered by Mozdooran Formation, Ngr evaporative formation and quaternary alluvium deposits in descending order of age. Mozdooran carbonate formation is notably karstified. The main surface karstic features in Mozdooran formation are Groove karren, Cleft karren, Rain pit, Rill karren, Tritt karren, Kamintza, Domes, and Table karren. In addition to surface features, deep karstic feature Andarokh Cave also exists in the region. Studying Ca, Mg, Mn, Sr, Fe concentration and Sr/Mn ratio in Mozdooran formation samples with distance to main faults and joints system using PCA analyses demonstrates intense meteoric digenesis role in controlling carbonate rock geochemistry. The karst evaluation in Andarokh basin varies from early stages 'deep seated karst' in Mesozoic to mature karstic system 'Exhumed karst' in quaternary period. Andarokh cave (the main cave in Andarokh basin) is rudimentary branch work consists of three passages of A, B and C and two entrances Andarokh and Sky.

Keywords: Andarokh basin, Andarokh cave, geochemical analyses, karst evaluation

Procedia PDF Downloads 154

Authors: Tanmay Bisen, Aastha Shayla

Abstract:

This study introduces an advanced approach to tree canopy detection in urban environments and a regional analysis of Northern and Central Kolkata that delves into the intricate relationship between urban development and environmental conservation. Leveraging high-resolution drone imagery from diverse urban green spaces in Kolkata, we fine-tuned the deep forest model to enhance its precision and accuracy. Our results, characterized by an impressive Intersection over Union (IoU) score of 0.90 and a mean average precision (mAP) of 0.87, underscore the model's robustness in detecting and classifying tree crowns amidst the complexities of aerial imagery. This research not only emphasizes the importance of model customization for specific datasets but also highlights the potential of drone-based remote sensing in urban forestry studies. The study investigates the spatial distribution, density, and environmental impact of trees in Northern and Central Kolkata. The findings underscore the significance of urban green spaces in met-ropolitan cities, emphasizing the need for sustainable urban planning that integrates green infrastructure for ecological balance and human well-being.

Keywords: urban greenery, advanced spatial distribution analysis, drone imagery, deep learning, tree detection

Procedia PDF Downloads 56

Authors: Yao-Hong Tsai

Abstract:

Due to the sensor technology, video surveillance has become the main way for security control in every big city in the world. Surveillance is usually used by governments for intelligence gathering, the prevention of crime, the protection of a process, person, group or object, or the investigation of crime. Many surveillance systems based on computer vision technology have been developed in recent years. Moving target tracking is the most common task for Unmanned Aerial Vehicle (UAV) to find and track objects of interest in mobile aerial surveillance for civilian applications. The paper is focused on vision-based collision avoidance for UAVs by recurrent neural networks. First, images from cameras on UAV were fused based on deep convolutional neural network. Then, a recurrent neural network was constructed to obtain high-level image features for object tracking and extracting low-level image features for noise reducing. The system distributed the calculation of the whole system to local and cloud platform to efficiently perform object detection, tracking and collision avoidance based on multiple UAVs. The experiments on several challenging datasets showed that the proposed algorithm outperforms the state-of-the-art methods.

Keywords: unmanned aerial vehicle, object tracking, deep learning, collision avoidance

Procedia PDF Downloads 160

Authors: K. Shaji Mon, P. R. John Sreenidhi

Abstract:

In deep-submicrometer CMOS processes, time-domain resolution of a digital signal is becoming higher than voltage resolution of analog signals. This claim is nowadays pushing toward a new circuit design paradigm in which the traditional analog signal processing is expected to be progressively substituted by the processing of times in the digital domain. Within this novel paradigm, digitally controlled delay lines (DCDL) should play the role of digital-to-analog converters in traditional, analog-intensive, circuits. Digital delay locked loops are highly prevalent in integrated systems.The proposed paper addresses the glitches present in delay circuits along with area,power dissipation and signal integrity.The digitally controlled delay lines(DCDL) under study have been designed in a 90 nm CMOS technology 6 layer metal Copper Strained SiGe Low K Dielectric. Simulation and synthesis results show that the novel circuits exhibit no glitches for dual output coarse DCDL with less power dissipation and consumes less area compared to the glitch free NAND based DCDL.

Keywords: glitch free, NAND-based DCDL, CMOS, deep-submicrometer

Procedia PDF Downloads 245

Authors: Majid Habib Khan, Jinwei Zhao, Xinhong Hei, Liu Jiedong, Rana Shahzad Noor, Muhammad Imran

Abstract:

Deep learning is increasingly employed in image classification, yet the scarcity and high cost of labeled data for training remain a challenge. Limited samples often lead to overfitting due to biased sample distribution. This paper introduces a dynamic distribution calibration method for few-shot learning. Initially, base and new class samples undergo normalization to mitigate disparate feature magnitudes. A pre-trained model then extracts feature vectors from both classes. The method dynamically selects distribution characteristics from base classes (both adjacent and remote) in the embedding space, using a threshold value approach for new class samples. Given the propensity of similar classes to share feature distributions like mean and variance, this research assumes a Gaussian distribution for feature vectors. Subsequently, distributional features of new class samples are calibrated using a corrected hyperparameter, derived from the distribution features of both adjacent and distant base classes. This calibration augments the new class sample set. The technique demonstrates significant improvements, with up to 4% accuracy gains in few-shot classification challenges, as evidenced by tests on miniImagenet and CUB datasets.

Keywords: deep learning, computer vision, image classification, few-shot learning, threshold

Procedia PDF Downloads 67

Authors: Skyler Kim

Abstract:

An early diagnosis of leukemia has always been a challenge to doctors and hematologists. On a worldwide basis, it was reported that there were approximately 350,000 new cases in 2012, and diagnosing leukemia was time-consuming and inefficient because of an endemic shortage of flow cytometry equipment in current clinical practice. As the number of medical diagnosis tools increased and a large volume of high-quality data was produced, there was an urgent need for more advanced data analysis methods. One of these methods was the AI approach. This approach has become a major trend in recent years, and several research groups have been working on developing these diagnostic models. However, designing and implementing a leukemia diagnostic system in real clinical environments based on a deep learning approach with larger sets remains complex. Leukemia is a major hematological malignancy that results in mortality and morbidity throughout different ages. We decided to select acute lymphocytic leukemia to develop our diagnostic system since acute lymphocytic leukemia is the most common type of leukemia, accounting for 74% of all children diagnosed with leukemia. The results from this development work can be applied to all other types of leukemia. To develop our model, the Kaggle dataset was used, which consists of 15135 total images, 8491 of these are images of abnormal cells, and 5398 images are normal. In this paper, we design and implement a leukemia diagnostic system in a real clinical environment based on deep learning approaches with larger sets. The proposed diagnostic system has the function of detecting and classifying leukemia. Different from other AI approaches, we explore hybrid architectures to improve the current performance. First, we developed two independent convolutional neural network models: VGG19 and ResNet50. Then, using both VGG19 and ResNet50, we developed a hybrid deep learning architecture employing transfer learning techniques to extract features from each input image. In our approach, fusing the features from specific abstraction layers can be deemed as auxiliary features and lead to further improvement of the classification accuracy. In this approach, features extracted from the lower levels are combined into higher dimension feature maps to help improve the discriminative capability of intermediate features and also overcome the problem of network gradient vanishing or exploding. By comparing VGG19 and ResNet50 and the proposed hybrid model, we concluded that the hybrid model had a significant advantage in accuracy. The detailed results of each model’s performance and their pros and cons will be presented in the conference.

Keywords: acute lymphoblastic leukemia, hybrid model, leukemia diagnostic system, machine learning

Procedia PDF Downloads 187

Authors: M. Draman, S. Z. Muhamad Yassin, M. S. Alias, Z. Lambak, M. I. Zulkifli, S. N. Padhi, K. N. Baharim, F. Maskuriy, A. I. A. Rahim

Abstract:

The performance of Malay automatic speech recognition (ASR) system for the call centre environment is presented. The system utilizes Kaldi toolkit as the platform to the entire library and algorithm used in performing the ASR task. The acoustic model implemented in this system uses a deep neural network (DNN) method to model the acoustic signal and the standard (n-gram) model for language modelling. With 80 hours of training data from the call centre recordings, the ASR system can achieve 72% of accuracy that corresponds to 28% of word error rate (WER). The testing was done using 20 hours of audio data. Despite the implementation of DNN, the system shows a low accuracy owing to the varieties of noises, accent and dialect that typically occurs in Malaysian call centre environment. This significant variation of speakers is reflected by the large standard deviation of the average word error rate (WERav) (i.e., ~ 10%). It is observed that the lowest WER (13.8%) was obtained from recording sample with a standard Malay dialect (central Malaysia) of native speaker as compared to 49% of the sample with the highest WER that contains conversation of the speaker that uses non-standard Malay dialect.

Keywords: conversational speech recognition, deep neural network, Malay language, speech recognition

Procedia PDF Downloads 322

Authors: Khansa Hayat

Abstract:

Organizational stress is one of the vital phenomena which is having its roots deep down in has deep roots in management, psychology, and organizational behavior research. In the meanwhile, keeping its focus on the positive strength of humans rather than the traditional negativity oriented research, positive psychology has emerged as a separate branch of organizational behavior. The current study investigates the interactive effects of Challenge and hindrance stressors and core Self Evaluations (CSE’s) of the individual on job performances including the in-role performance and extra role performances. The study also aims to investigate the supporting/buffering role of the human dispositions (i.e., self esteem, self efficacy, locus of control and emotional stability). The results show that Challenge stressors have a significant positive effect on in role performance and extra role performance of the individual. The findings of the study indicate that Core Self evaluations strengthen the relationship between challenge stressors and in role performance of the individual. In case of Hindrance Stressors the Core self Evaluations lessen the negative impact of Hindrance stressors and they let the individual perform at a better and normal position even when the Hindrance stressors are high. The relationship and implication of conservation of resource theory are also discussed. The limitations, future research directions and implications of the study are also discussed.

Keywords: challenge-hindrance stressors, core self evaluations, in-role performance, extra-role performance

Procedia PDF Downloads 277

Authors: Victor Breux, Jérôme Boutet, Alain Goret, Viviane Cattin

Abstract:

Early detection of anomalies in data centers is important to reduce downtimes and the costs of periodic maintenance. However, there is little research on this topic and even fewer on the fusion of sensor data for the detection of abnormal events. The goal of this paper is to propose a method for anomaly detection in data centers by combining sensor data (temperature, humidity, power) and deep learning models. The model described in the paper uses one autoencoder per sensor to reconstruct the inputs. The auto-encoders contain Long-Short Term Memory (LSTM) layers and are trained using the normal samples of the relevant sensors selected by correlation analysis. The difference signal between the input and its reconstruction is then used to classify the samples using feature extraction and a random forest classifier. The data measured by the sensors of a data center between January 2019 and May 2020 are used to train the model, while the data between June 2020 and May 2021 are used to assess it. Performances of the model are assessed a posteriori through F1-score by comparing detected anomalies with the data center’s history. The proposed model outperforms the state-of-the-art reconstruction method, which uses only one autoencoder taking multivariate sequences and detects an anomaly with a threshold on the reconstruction error, with an F1-score of 83.60% compared to 24.16%.

Keywords: anomaly detection, autoencoder, data centers, deep learning

Procedia PDF Downloads 194

Authors: Fatima Zohra Ibn Majdoub Hassani, Ivan Lavandera, Joseph Kreit

Abstract:

This study explored the effects of different organic solvents, temperature, and the amount of glycerol on the alcohol dehydrogenase (ADH)-catalysed stereoselective reduction of different ketones. These conversions were then analyzed by gas chromatography. It was found that when the amount of deep eutectic solvents (DES) increases, it can improve the stereoselectivity of the enzyme although reducing its ability to convert the substrate into the corresponding alcohol. Moreover, glycerol was found to have a strong stabilizing effect on the ADH from Ralstonia sp. (E. coli/ RasADH). In the case of organic solvents, it was observed that the best conversions into the alcohols were achieved with DMSO and hexane. It was also observed that temperature decreased the ability of the enzyme to convert the substrates into the products and also affected the selectivity. In addition to that, the recycling of DES up to three times gave good conversions and enantiomeric excess results and glycerol showed a positive effect in the stability of various ADHs. Using RasADH, a good conversion and enantiomeric excess into the S-alcohol were obtained. It was found that an enhancement of the temperature disabled the stabilizing effect of glycerol and decreased the stereoselectivity of the enzyme. However, for other ADHs a temperature increase had an opposite positive effect, especially with ADH-T from Thermoanaerobium sp. One of the objectives of this study was to see the effect of cofactors such as NAD(P) on the biocatlysis activities of ADHs.

Keywords: alcohol dehydrogenases, DES, gas chromatography, RasADH

Procedia PDF Downloads 193

Authors: Aragorn Joaquin Pineda Dela Cruz

Abstract:

Road traffic congestion is continually deteriorating in Hong Kong. The largest contributing factor is the increase in vehicle fleet size, resulting in higher competition over the utilisation of road space. This study proposes a project that can process closed-circuit television images and videos to provide real-time traffic detection and prediction capabilities. Specifically, a deep-learning model involving computer vision techniques for video and image-based vehicle counting, then a separate model to detect and predict traffic congestion levels based on said data. State-of-the-art object detection models such as You Only Look Once and Faster Region-based Convolutional Neural Networks are tested and compared on closed-circuit television data from various major roads in Hong Kong. It is then used for training in long short-term memory networks to be able to predict traffic conditions in the near future, in an effort to provide more precise and quicker overviews of current and future traffic conditions relative to current solutions such as navigation apps.

Keywords: intelligent transportation system, vehicle detection, traffic analysis, deep learning, machine learning, computer vision, traffic prediction

Procedia PDF Downloads 102

Authors: Mehrdad Shafiei Dizaji, Hoda Azari

Abstract:

The research explores the pioneering integration of Physics-Informed Neural Networks (PINNs) into the domain of Ground-Penetrating Radar (GPR) data prediction, akin to advancements in medical imaging for tracking tumor progression in the human body. This research presents a detailed development framework for a specialized PINN model proficient at interpreting and forecasting GPR data, much like how medical imaging models predict tumor behavior. By harnessing the synergy between deep learning algorithms and the physical laws governing subsurface structures—or, in medical terms, human tissues—the model effectively embeds the physics of electromagnetic wave propagation into its architecture. This ensures that predictions not only align with fundamental physical principles but also mirror the precision needed in medical diagnostics for detecting and monitoring tumors. The suggested deep learning structure comprises three components: a CNN, a spatial feature channel attention (SFCA) mechanism, and ConvLSTM, along with temporal feature frame attention (TFFA) modules. The attention mechanism computes channel attention and temporal attention weights using self-adaptation, thereby fine-tuning the visual and temporal feature responses to extract the most pertinent and significant visual and temporal features. By integrating physics directly into the neural network, our model has shown enhanced accuracy in forecasting GPR data. This improvement is vital for conducting effective assessments of bridge deck conditions and other evaluations related to civil infrastructure. The use of Physics-Informed Neural Networks (PINNs) has demonstrated the potential to transform the field of Non-Destructive Evaluation (NDE) by enhancing the precision of infrastructure deterioration predictions. Moreover, it offers a deeper insight into the fundamental mechanisms of deterioration, viewed through the prism of physics-based models.

Keywords: physics-informed neural networks, deep learning, ground-penetrating radar (GPR), NDE, ConvLSTM, physics, data driven

Procedia PDF Downloads 40

Authors: Madhawa Basnayaka, Jouni Paltakari

Abstract:

Fully passive backscattering chipless RFID tags are an emerging wireless technology with low cost, higher reading distance, and fast automatic identification without human interference, unlike already available technologies like optical barcodes. The design optimization of chipless RFID tags is crucial as it requires replacing integrated chips found in conventional RFID tags with printed geometric designs. These designs enable data encoding and decoding through backscattered electromagnetic (EM) signatures. The applications of chipless RFID tags have been limited due to the constraints of data encoding capacity and the ability to design accurate yet efficient configurations. The traditional approach to accomplishing design parameters for a desired EM response involves iterative adjustment of design parameters and simulating until the desired EM spectrum is achieved. However, traditional numerical simulation methods encounter limitations in optimizing design parameters efficiently due to the speed and resource consumption. In this work, a deep learning neural network (DNN) is utilized to establish a correlation between the EM spectrum and the dimensional parameters of nested centric rings, specifically square and octagonal. The proposed bi-directional DNN has two simultaneously running neural networks, namely spectrum prediction and design parameters prediction. First, spectrum prediction DNN was trained to minimize mean square error (MSE). After the training process was completed, the spectrum prediction DNN was able to accurately predict the EM spectrum according to the input design parameters within a few seconds. Then, the trained spectrum prediction DNN was connected to the design parameters prediction DNN and trained two networks simultaneously. For the first time in chipless tag design, design parameters were predicted accurately after training bi-directional DNN for a desired EM spectrum. The model was evaluated using a randomly generated spectrum and the tag was manufactured using the predicted geometrical parameters. The manufactured tags were successfully tested in the laboratory. The amount of iterative computer simulations has been significantly decreased by this approach. Therefore, highly efficient but ultrafast bi-directional DNN models allow rapid and complicated chipless RFID tag designs.

Keywords: artificial intelligence, chipless RFID, deep learning, machine learning

Procedia PDF Downloads 50

Authors: M. Solairaju, Nithin J. Thomas, S. Ganesan

Abstract:

Each and every rotating part of a machine element consists of bearings within its structure. In particular, the rolling element bearings such as cylindrical roller bearing and deep groove ball bearings are frequently used. Improper handling, excessive loading, improper lubrication and sealing cause bearing damage. Hence health monitoring of bearings is an important aspect for radiation pattern of bearing vibration is computed using the dipole model. Sound pressure level for defect-free and race defect the prolonged life of machinery and auto motives. This paper presents modeling and analysis of Acoustic response of deep groove ball bearing with localized race defects. Most of the ball bearings, especially in machine tool spindles and high-speed applications are pre-loaded along an axial direction. The present study is carried out with axial preload. Based on the vibration response, the orbit motion of the inner race is studied, and it was found that the oscillation takes place predominantly in the axial direction. Simplified acoustic is estimated. Acoustic response shows a better indication in identifying the defective bearing. The computed sound signal is visualized in diagrammatic representation using Symmetrised Dot Pattern (SDP). SDP gives better visual distinction between the defective and defect-free bearing

Keywords: bearing, dipole, noise, sound

Procedia PDF Downloads 294

Authors: Rujia Chen, Ajit Narayanan

Abstract:

Convolutional neural networks (CNN), as typically applied in deep learning, use layer-wise backpropagation (BP) to construct filters and kernels for feature extraction. Such filters are 2D or 3D groups of weights for constructing feature maps at subsequent layers of the CNN and are shared across the entire input. BP as a gradient descent algorithm has well-known problems of getting stuck at local optima. The use of genetic algorithms (GAs) for evolving weights between layers of standard artificial neural networks (ANNs) is a well-established area of neuroevolution. In particular, the use of crossover techniques when optimizing weights can help to overcome problems of local optima. However, the application of GAs for evolving the weights of filters and kernels in CNNs is not yet an established area of neuroevolution. In this paper, a GA-based filter development algorithm is proposed. The results of the proof-of-concept experiments described in this paper show the proposed GA algorithm can find filter weights through evolutionary techniques rather than BP learning. For some simple classification tasks like geometric shape recognition, the proposed algorithm can achieve 100% accuracy. The results for MNIST classification, while not as good as possible through standard filter learning through BP, show that filter and kernel evolution warrants further investigation as a new subarea of neuroevolution for deep architectures.

Keywords: neuroevolution, convolutional neural network, genetic algorithm, filters, kernels

Procedia PDF Downloads 186

Authors: Tsega Asresa Mengistu, Getahun Tigistu

Abstract:

Computer vision is an artificial intelligence subfield that allows computers and systems to retrieve meaning from digital images. It is applied in various fields of study self-driving cars, video surveillance, agriculture, Quality control, Health care, construction, military, and everyday life. Aromatic and medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, and other natural health products for therapeutic and Aromatic culinary purposes. Herbal industries depend on these special plants. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs, and going to export not only industrial raw materials but also valuable foreign exchange. There is a lack of technologies for the classification and identification of Aromatic and medicinal plants in Ethiopia. The manual identification system of plants is a tedious, time-consuming, labor, and lengthy process. For farmers, industry personnel, academics, and pharmacists, it is still difficult to identify parts and usage of plants before ingredient extraction. In order to solve this problem, the researcher uses a deep learning approach for the efficient identification of aromatic and medicinal plants by using a convolutional neural network. The objective of the proposed study is to identify the aromatic and medicinal plant Parts and usages using computer vision technology. Therefore, this research initiated a model for the automatic classification of aromatic and medicinal plants by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides the root, flower and fruit, latex, and barks. The study was conducted on aromatic and medicinal plants available in the Ethiopian Institute of Agricultural Research center. An experimental research design is proposed for this study. This is conducted in Convolutional neural networks and Transfer learning. The Researcher employs sigmoid Activation as the last layer and Rectifier liner unit in the hidden layers. Finally, the researcher got a classification accuracy of 66.4 in convolutional neural networks and 67.3 in mobile networks, and 64 in the Visual Geometry Group.

Keywords: aromatic and medicinal plants, computer vision, deep convolutional neural network

Procedia PDF Downloads 438

Authors: Zhuang Hou, Xiaolei Cao

Abstract:

The general public and medical professionals recognized the importance of accurately measuring and storing blood oxygen levels and heart rate during the COVID-19 pandemic. The demand for accurate contactless devices was motivated by the need for cross-infection reduction and the shortage of conventional oximeters, partially due to the global supply chain issue. This paper evaluated a contactless mini program HealthyPai’s heart rate (HR) and oxygen saturation (SpO2) measurements compared with other wearable devices. In the HR study of 185 samples (81 in the laboratory environment, 104 in the real-life environment), the mean absolute error (MAE) ± standard deviation was 1.4827 ± 1.7452 in the lab, 6.9231 ± 5.6426 in the real-life setting. In the SpO2 study of 24 samples, the MAE ± standard deviation of the measurement was 1.0375 ± 0.7745. Our results validated that HealthyPai utilizing the Integrated Image Deep Learning Solution (IIDLS) framework, can accurately measure HR and SpO2, providing the test quality at least comparable to other FDA-approved wearable devices in the market and surpassing the consumer-grade and research-grade wearable standards.

Keywords: remote photoplethysmography, heart rate, oxygen saturation, contactless measurement, mini program

Procedia PDF Downloads 135

Authors: John Paul Q. Tomas, Mark Wilson L. de los Reyes, Kirsten Joyce P. Vasquez

Abstract:

The most frequent type of fracture is a wrist fracture, which often makes it difficult for medical professionals to find and locate. In this study, fractures in wrist x-ray pictures were located and identified using deep learning and computer vision. The researchers used image filtering, masking, morphological operations, and data augmentation for the image preprocessing and trained the RetinaNet and Faster R-CNN models with ResNet50 backbones and Adam optimizers separately for each image filtering technique and projection. The RetinaNet model with Anisotropic Diffusion Smoothing filter trained with 50 epochs has obtained the greatest accuracy of 99.14%, precision of 100%, sensitivity/recall of 98.41%, specificity of 100%, and an IoU score of 56.44% for the Posteroanterior projection utilizing augmented data. For the Lateral projection using augmented data, the RetinaNet model with an Anisotropic Diffusion filter trained with 50 epochs has produced the highest accuracy of 98.40%, precision of 98.36%, sensitivity/recall of 98.36%, specificity of 98.43%, and an IoU score of 58.69%. When comparing the test results of the different individual projections, models, and image filtering techniques, the Anisotropic Diffusion filter trained with 50 epochs has produced the best classification and regression scores for both projections.

Keywords: Artificial Intelligence, Computer Vision, Wrist Fracture, Deep Learning

Procedia PDF Downloads 73

Authors: Zehra Aytac, Nurdilek Gulmezoglu

Abstract:

Safflower has been grown for centuries for many purposes worldwide. Especially it is important for the orange-red dye from its petal and for its high-quality oil obtained from the seeds. The crop is high adaptable to areas with insufficient rainfall and poor soil conditions. The plant has a deep taproot that can draw moisture and plant nutrients from deep to the subsoil. The research was carried out to study the nitrogen (N) uptake of different safflower cultivars and lines at different stages of growth and different plant parts in the experimental field of Faculty of Agriculture, Eskişehir Osmangazi University under semi-arid conditions. Different safflower cultivars and lines of varied origins were used as the material. The cultivars and lines were planted in a Randomized Complete Block Design with three replications. Two different growth stages (flowering and harvest) and three different plant parts (head, stem+leaf and seed) were determined. The nitrogen concentration of different plant parts was determined by the Kjeldahl method. Statistical analysis were performed by analysis of variance for each growth stage and plant parts taking a level of p < 0.05 and p < 0.01 as significant according to the LSD test. As a result, N concentration showed significant differences among different plant parts and different growth stages for different safflower genotypes of varied origins.

Keywords: Carthamus tinctorius L., growth stages, head N, leaf N, N uptake, seed N, Safflower

Procedia PDF Downloads 224

Authors: Sanjida Akter, Ambali Alade Odebowale, Andrey E. Miroshnichenko, Haroldo T. Hattori

Abstract:

Photodetectors (PDs) play a pivotal role in optoelectronics and optical devices, serving as fundamental components that convert light signals into electrical signals. As the field progresses, the integration of advanced materials with unique optical properties has become a focal point, paving the way for the innovation of novel PDs. This study delves into the exploration of a cutting-edge photodetector designed for deep and near ultraviolet (UV) applications. The photodetector is constructed with a composite of Zirconium Boride (ZrB2) and Chromium (Cr) alloy, deposited onto a 6H nitrogen-doped silicon carbide substrate. The determination of the optimal alloy thickness is achieved through Finite-Difference Time-Domain (FDTD) simulation, and the synthesis of the alloy is accomplished using radio frequency (RF) sputtering. Remarkably, the resulting photodetector exhibits an exceptional responsivity of 3.5 A/W under an applied voltage of -2 V, at wavelengths of 405 nm and 280 nm. This heterostructure not only exemplifies high performance but also provides a versatile platform for the development of near UV photodetectors capable of operating effectively in challenging conditions, such as environments characterized by high power and elevated temperatures. This study contributes to the expanding landscape of photodetector technology, offering a promising avenue for the advancement of optoelectronic devices in demanding applications.

Keywords: responsivity, silicon carbide, ultraviolet photodetector, zirconium boride

Procedia PDF Downloads 66