Search results for: intention recognition

Authors: Weifeng Wang, Guoqing Huang, Xianwei Zeng

Abstract:

The nearly 21-year-old Jiujiang Bridge, which is suffering from uneven line shape, constant great downwarping of the main beam and cracking of the box girder, needs reinforcement and cable adjustment. It has undergone cable adjustment for twice with incomplete data. Therefore, the initial internal force state of the Jiujiang Bridge is identified as the key for the cable adjustment project. Based on parameter identification by means of static force test data, this paper suggests determining the initial internal force state of the cable-stayed bridge according to the cable force-displacement relationship parameter identification method. That is, upon measuring the displacement and the change in cable forces for twice, one can identify the parameters concerned by means of optimization. This method is applied to the cable adjustment, replacement and reinforcement project for the Jiujiang Bridge as a guidance for the cable adjustment and reinforcement project of the bridge.

Keywords: Cable-stayed bridge, cable force-displacement, parameter identification, internal force state

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1540

Authors: G. Türkmen, Ö. Tekin, K. Kurtuluş, Y. Y. Yurtseven, M. Baran

Abstract:

A scanning electron microscope (SEM) is a type of electron microscope mainly used in nanoscience and nanotechnology areas. Automatic image recognition and classification are among the general areas of application concerning SEM. In line with these usages, the present paper proposes a deep learning algorithm that classifies SEM images into nine categories by means of an online application to simplify the process. The NFFA-EUROPE - 100% SEM data set, containing approximately 21,000 images, was used to train and test the algorithm at 80% and 20%, respectively. Validation was carried out using a separate data set obtained from the Middle East Technical University (METU) in Turkey. To increase the accuracy in the results, the Inception ResNet-V2 model was used in view of the Fine-Tuning approach. By using a confusion matrix, it was observed that the coated-surface category has a negative effect on the accuracy of the results since it contains other categories in the data set, thereby confusing the model when detecting category-specific patterns. For this reason, the coated-surface category was removed from the train data set, hence increasing accuracy by up to 96.5%.

Keywords: Convolutional Neural Networks, deep learning, image classification, scanning electron microscope.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 197

Authors: Pei-Ti Hsu, I-Ju Chen, Jeu-Jung Chen, Cheng-Fen Chang, Shiu-Yan Yang

Abstract:

Background: Taiwan now is an aging society. Research on the elderly should not be confined to caring for seniors, but should also be focused on ways to improve health and the quality of life. Senior citizens who participate in volunteer services could become less lonely, have new growth opportunities, and regain a sense of accomplishment. Thus, the question of how to get the elderly to participate in volunteer service is worth exploring. Objective: Apply the Transtheoretical Model to understand stages of change in regular volunteer service and voluntary service behaviour among the seniors. Methods: 1525 adults over the age of 65 from the Renai district of Keelung City were interviewed. The research tool was a self-constructed questionnaire, and individual interviews were conducted to collect data. Then the data was processed and analyzed using the IBM SPSS Statistics 20 (Windows version) statistical software program. Results: In the past six months, research subjects averaged 9.92 days of volunteer services. A majority of these elderly individuals had no intention to change their regular volunteer services. We discovered that during the maintenance stage, the self-efficacy for volunteer services was higher than during all other stages, but self-perceived barriers were less during the preparation stage and action stage. Self-perceived benefits were found to have an important predictive power for those with regular volunteer service behaviors in the previous stage, and self-efficacy was found to have an important predictive power for those with regular volunteer service behaviors in later stages. Conclusions/Implications for Practice: The research results support the conclusion that community nursing staff should group elders based on their regular volunteer services change stages and design appropriate behavioral change strategies.

Keywords: Seniors, stages of change in regular volunteer services, volunteer service behavior, self-efficacy, self-perceived benefits.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1958

Authors: Hamed Alqahtani, Manolya Kavakli-Thorne

Abstract:

The large pose discrepancy is one of the critical challenges in face recognition during video surveillance. Due to the entanglement of pose attributes with identity information, the conventional approaches for pose-independent representation lack in providing quality results in recognizing largely posed faces. In this paper, we propose a practical approach to disentangle the pose attribute from the identity information followed by synthesis of a face using a classifier network in latent space. The proposed approach employs a modified generative adversarial network framework consisting of an encoder-decoder structure embedded with a classifier in manifold space for carrying out factorization on the latent encoding. It can be further generalized to other face and non-face attributes for real-life video frames containing faces with significant attribute variations. Experimental results and comparison with state of the art in the field prove that the learned representation of the proposed approach synthesizes more compelling perceptual images through a combination of adversarial and classification losses.

Keywords: Video surveillance, disentanglement, face detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 606

Authors: Yuan Zheng

Abstract:

3D model-based vehicle matching provides a new way for vehicle recognition, localization and tracking. Its key is to construct an evaluation function, also called fitness function, to measure the degree of vehicle matching. The existing fitness functions often poorly perform when the clutter and occlusion exist in traffic scenarios. In this paper, we present a practical and efficient fitness function. Unlike the existing evaluation functions, the proposed fitness function is to study the vehicle matching problem from both local and global perspectives, which exploits the pixel gradient information as well as the silhouette information. In view of the discrepancy between 3D vehicle model and real vehicle, a weighting strategy is introduced to differently treat the fitting of the model’s wireframes. Additionally, a normalization operation for the model’s projection is performed to improve the accuracy of the matching. Experimental results on real traffic videos reveal that the proposed fitness function is efficient and robust to the cluttered background and partial occlusion.

Keywords: 3D-2D matching, fitness function, 3D vehicle model, local image gradient, silhouette information.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1633

Authors: Feifei Lee, Qiu Chen, Koji Kotani, Tadahiro Ohmi

Abstract:

In this paper, we propose a novel fast search algorithm for short MPEG video clips from video database. This algorithm is based on the adjacent pixel intensity difference quantization (APIDQ) algorithm, which had been reliably applied to human face recognition previously. An APIDQ histogram is utilized as the feature vector of the frame image. Instead of fully decompressed video frames, partially decoded data, namely DC images are utilized. Combined with active search [4], a temporal pruning algorithm, fast and robust video search can be realized. The proposed search algorithm has been evaluated by 6 hours of video to search for given 200 MPEG video clips which each length is 15 seconds. Experimental results show the proposed algorithm can detect the similar video clip in merely 80ms, and Equal Error Rate (ERR) of 3 % is achieved, which is more accurately and robust than conventional fast video search algorithm.

Keywords: Fast search, adjacent pixel intensity difference quantization (APIDQ), DC image, histogram feature.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1578

Authors: Talbi Mourad, Salhi Lotfi, Chérif Adnen

Abstract:

In this work, we are interested in developing a speech denoising tool by using a discrete wavelet packet transform (DWPT). This speech denoising tool will be employed for applications of recognition, coding and synthesis. For noise reduction, instead of applying the classical thresholding technique, some wavelet packet nodes are set to zero and the others are thresholded. To estimate the non stationary noise level, we employ the spectral entropy. A comparison of our proposed technique to classical denoising methods based on thresholding and spectral subtraction is made in order to evaluate our approach. The experimental implementation uses speech signals corrupted by two sorts of noise, white and Volvo noises. The obtained results from listening tests show that our proposed technique is better than spectral subtraction. The obtained results from SNR computation show the superiority of our technique when compared to the classical thresholding method using the modified hard thresholding function based on u-law algorithm.

Keywords: Enhancement, spectral subtraction, SNR, discrete wavelet packet transform, spectral entropy Histogram

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1990

Authors: I. Ludviga, A. Kalvina

Abstract:

This paper aims to link together the concepts of job satisfaction, work engagement, trust, job meaningfulness and loyalty to the organisation focusing on specific type of employment – academic jobs. The research investigates the relationships between job satisfaction, work engagement and loyalty as well as the impact of trust and job meaningfulness on the work engagement and loyalty. The survey was conducted in one of the largest Latvian higher education institutions and the sample was drawn from academic staff (n=326). Structured questionnaire with 44 reflective type questions was developed to measure the constructs. Data was analysed using SPSS and Smart-PLS software. Variance based structural equation modelling (PLS-SEM) technique was used to test the model and to predict the most important factors relevant to employee engagement and loyalty. The first order model included two endogenous constructs (loyalty and intention to stay and recommend to work in this organisation, and employee engagement), as well as six exogenous constructs (feeling of fair treatment and trust in management; career growth opportunities; compensation, pay and benefits; management; colleagues and teamwork; and finally job meaningfulness). Job satisfaction was developed as second order construct and both: first and second order models were designed for data analysis. It was found that academics are more engaged than satisfied with their work and main reason for that was found to be job meaningfulness, which is significant predictor for work engagement, but not for job satisfaction. Compensation is not significantly related to work engagement, but only to job satisfaction. Trust was not significantly related neither to engagement, nor to satisfaction, however, it appeared to be significant predictor of loyalty and intentions to stay with the University. Paper revealed academic jobs as specific kind of employment where employees can be more engaged than satisfied and highlighted the specific role of job meaningfulness in the University settings.

Keywords: Job satisfaction, job meaningfulness, higher education, work engagement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2922

Authors: Marcell S. A. Martins, Benedito S. R. Neto, Gerson L. Serejo, Carlos G. R. Santos

Abstract:

Indoor positioning systems use sensors such as Bluetooth, ZigBee, and Wi-Fi, as well as cameras for image capture, which can be fixed or mobile. These computer vision-based positioning approaches are low-cost to implement, mainly when it uses a mobile camera. The present study aims to create a design of a fiducial marker for a low-cost indoor localization system. The marker is tape-shaped to perform a continuous reading employing two detection algorithms, one for greater distances and another for smaller distances. Therefore, the location service is always operational, even with variations in capture distance. A minimal localization and reading algorithm was implemented for the proposed marker design, aiming to validate it. The accuracy tests consider readings varying the capture distance between [0.5, 10] meters, comparing the proposed marker with others. The tests showed that the proposed marker has a broader capture range than the ArUco and QRCode, maintaining the same size. Therefore, reducing the visual pollution and maximizing the tracking since the ambient can be covered entirely.

Keywords: Multiscale recognition, indoor localization, tape-shaped marker, Fiducial Marker.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 173

Authors: Yongsuk Jang Kim, Sun-Tae Chung, Boogyun Kim, Seongwon Cho

Abstract:

Realistic 3D face model is more precise in representing pose, illumination, and expression of face than 2D face model so that it can be utilized usefully in various applications such as face recognition, games, avatars, animations, and etc. In this paper, we propose a 3D face modeling method based on 3D dense morphable shape model. The proposed 3D modeling method first constructs a 3D dense morphable shape model from 3D face scan data obtained using a 3D scanner. Next, the proposed method extracts and matches facial landmarks from 2D image sequence containing a face to be modeled, and then reconstructs 3D vertices coordinates of the landmarks using a factorization-based SfM technique. Then, the proposed method obtains a 3D dense shape model of the face to be modeled by fitting the constructed 3D dense morphable shape model into the reconstructed 3D vertices. Also, the proposed method makes a cylindrical texture map using 2D face image sequence. Finally, the proposed method generates a 3D face model by rendering the 3D dense face shape model using the cylindrical texture map. Through building processes of 3D face model by the proposed method, it is shown that the proposed method is relatively easy, fast and precise.

Keywords: 3D Face Modeling, 3D Morphable Shape Model, 3DReconstruction, 3D Correspondence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2426

Authors: B. Sabayan, A. Alidadi, S. Ebrahimi, N. M. Bakhshani

Abstract:

Neuropsychological problems are more common in hemodialysis (HD) patients than in healthy individuals. The aim of this study was to investigate the effect of long term HD on memory types of HD patients. To assess the different type of memory, we used memory parts of the Persian Papers and Pencil Cognitive assessment package (PCAP) and Addenbrooke's Cognitive Examination (ACE-R). Our study included 80 HD patients of whom 39 had less than six months of HD and 41 patients and another group which had a history of HD more than six months. The population had a mean age of 51.60 years old and 27.5% of them were female. The scores of patients who have been hemodialyzed for a long time (median time of HD was up to 4 years) had lower score in anterograde, explicit, visual, recall and recognition memory (5.44±1.07, 9.49±3.472, 22.805±6.6913, 5.59±10.435, 11.02±3.190 score) than the HD patients who underwent HD for a shorter term, where the median time was 3 to 5 months (P<0.01). The regression result shows that, by increasing the HD duration, all memory types are reduced (R2=0.600, P<0.01). The present study demonstrated that HD patients who were under HD for a long time had significantly lower scores in the different types of memory. However, additional researches are needed in this area.

Keywords: Hemodialysis patients, duration of hemodialysis, memory types, Zahedan.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1304

Authors: Pogula Rakesh, T. Kishore Kumar

Abstract:

Speech enhancement is a long standing problem with numerous applications like teleconferencing, VoIP, hearing aids and speech recognition. The motivation behind this research work is to obtain a clean speech signal of higher quality by applying the optimal noise cancellation technique. Real-time adaptive filtering algorithms seem to be the best candidate among all categories of the speech enhancement methods. In this paper, we propose a speech enhancement method based on Recursive Least Squares (RLS) adaptive filter of speech signals. Experiments were performed on noisy data which was prepared by adding AWGN, Babble and Pink noise to clean speech samples at -5dB, 0dB, 5dB and 10dB SNR levels. We then compare the noise cancellation performance of proposed RLS algorithm with existing NLMS algorithm in terms of Mean Squared Error (MSE), Signal to Noise ratio (SNR) and SNR Loss. Based on the performance evaluation, the proposed RLS algorithm was found to be a better optimal noise cancellation technique for speech signals.

Keywords: Adaptive filter, Adaptive Noise Canceller, Mean Squared Error, Noise reduction, NLMS, RLS, SNR, SNR Loss.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3182

Authors: Ollie Hall, Salma ElSayed

Abstract:

Affective adaptation is a creative way for game designers to add an extra layer of engagement to their productions. When player’s emotions are an explicit factor in mechanics design, endless possibilities for imaginative gameplay emerge. Whilst gaining popularity, existing affective game research mostly runs controlled experiments in restrictive settings and rely on one or more specialist devices for measuring player’s emotional state. These conditions albeit effective, are not necessarily realistic. Moreover, the simplified narrative and intrusive wearables may not be suitable for players. This exploratory study investigates delivering an immersive affective experience in the wild with minimal requirements, in an attempt for the average developer to reach the average player. A puzzle game is created with rich narrative and creative mechanics. It employs both explicit and implicit adaptation and only requires a web camera. Participants played the game on their own machines in various settings. Whilst it was rated feasible, very engaging and enjoyable, it remains questionable whether a fully immersive experience was delivered due to the limited sample size.

Keywords: affective games, dynamic adaptation, emotion recognition, game design

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 844

Authors: R. Biondi, G. Dys, G. Ferone, T. Renard, M. Zysman

Abstract:

This paper describes an automated implementable system for impulsive signals detection and recognition. The system uses a Digital Signal Processing device for the detection and identification process. Here the system analyses the signals in real time in order to produce a particular response if needed. The system analyses the signals in real time in order to produce a specific output if needed. Detection is achieved through normalizing the inputs and comparing the read signals to a dynamic threshold and thus avoiding detections linked to loud or fluctuating environing noise. Identification is done through neuronal network algorithms. As a setup our system can receive signals to “learn” certain patterns. Through “learning” the system can recognize signals faster, inducing flexibility to new patterns similar to those known. Sound is captured through a simple jack input, and could be changed for an enhanced recording surface such as a wide-area recorder. Furthermore a communication module can be added to the apparatus to send alerts to another interface if needed.

Keywords: Sound Detection, Impulsive Signal, Background Noise, Neural Network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2333

Authors: Thomas Schalow

Abstract:

This paper posits the need to take a cross-cultural approach to communication with non-human cultures and intelligences in order to meet the following three imminent contingencies: communicating with sentient biological intelligences, communicating with extraterrestrial intelligences, and communicating with artificial super-intelligences. The paper begins with a discussion of how intelligence emerges. It disputes some common assumptions we maintain about consciousness, intention, and language. The paper next explores cross-cultural communication among humans, including non-sapiens species. The next argument made is that we need to become much more serious about communicating with the non-human, intelligent life forms that already exist around us here on Earth. There is an urgent need to broaden our definition of communication and reach out to the other sentient life forms that inhabit our world. The paper next examines the science and philosophy behind CETI (communication with extraterrestrial intelligences) and how it has proven useful, even in the absence of contact with alien life. However, CETI’s assumptions and methodology need to be revised and based on the cross-cultural approach to communication proposed in this paper if we are truly serious about finding and communicating with life beyond Earth. The final theme explored in this paper is communication with non-biological super-intelligences using a cross-cultural communication approach. This will present a serious challenge for humanity, as we have never been truly compelled to converse with other species, and our failure to seriously consider such intercourse has left us largely unprepared to deal with communication in a future that will be mediated and controlled by computer algorithms. Fortunately, our experience dealing with other human cultures can provide us with a framework for this communication. The basic assumptions behind intercultural communication can be applied to the many types of communication envisioned in this paper if we are willing to recognize that we are in fact dealing with other cultures when we interact with other species, alien life, and artificial super-intelligence. The ideas considered in this paper will require a new mindset for humanity, but a new disposition will prepare us to face the challenges posed by a future dominated by artificial intelligence.

Keywords: Artificial intelligence, CETI, communication, culture, language.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 984

Authors: Hyun-Koo Kim, Sagong Kuk, MinKwan Kim, Ho-Youl Jung

Abstract:

This paper presents an effective method for detecting vehicles in front of the camera-assisted car during nighttime driving. The proposed method detects vehicles based on detecting vehicle headlights and taillights using techniques of image segmentation and clustering. First, to effectively extract spotlight of interest, a segmentation process based on automatic multi-level threshold method is applied on the road-scene images. Second, to spatial clustering vehicle of detecting lamps, a grouping process based on light tracking and locating vehicle lighting patterns. For simulation, we are implemented through Da-vinci 7437 DSP board with near infrared mono-camera and tested it in the urban and rural roads. Through the test, classification performances are above 97% of true positive rate evaluated on real-time environment. Our method also has good performance in the case of clear, fog and rain weather.

Keywords: Assistance Driving System, Multi-level Threshold Method, Near Infrared Mono Camera, Nighttime Vehicle Detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2937

Authors: Ali Alzaabi, Georges Alquié, Hussain Tassadaq, Ali Seba

Abstract:

This article presents the developments of efficient algorithms for tablet copies comparison. Image recognition has specialized use in digital systems such as medical imaging, computer vision, defense, communication etc. Comparison between two images that look indistinguishable is a formidable task. Two images taken from different sources might look identical but due to different digitizing properties they are not. Whereas small variation in image information such as cropping, rotation, and slight photometric alteration are unsuitable for based matching techniques. In this paper we introduce different matching algorithms designed to facilitate, for art centers, identifying real painting images from fake ones. Different vision algorithms for local image features are implemented using MATLAB. In this framework a Table Comparison Computer Tool “TCCT" is designed to facilitate our research. The TCCT is a Graphical Unit Interface (GUI) tool used to identify images by its shapes and objects. Parameter of vision system is fully accessible to user through this graphical unit interface. And then for matching, it applies different description technique that can identify exact figures of objects.

Keywords: Harris Extraction and SIFT Matching

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1733

Authors: I. Gupta, B. Karmakar

Abstract:

Bengal has a long history (8^th century A.D. onwards) of decorating the wall of brick-built temples with curved terracotta plaques on a diverse range of subjects. These could be considered as one of the most significant visual archives to understand the various facets of the then contemporary societies. The temples under focus include Char-bangla temple complex (circa 1755 A.D.), Bhavanishvara temple (circa 1755 A.D.) and the Gangeshvara Shiva Jor-bangla temple (circa 1753 A.D.), located within a part of the river Bhagirathi basin in Baranagar, Murshidabad, West Bengal, India. Though, a diverse range of subjects have been intricately carved mainly on the front façades of the Baranagar temple cluster, the study specifically concentrates on depictions related to religious and non-religious acts performed by practitioners of various religious sects of late medieval Bengal with the intention to acquire knowledge about the various facets of their life. Apart from this, the paper also mapped the spatial location of these religious performers on the temples’ façades to examine if any systematic plan or arrangement had been employed for connoting a particular idea. Further, an attempt is made to provide a commentary on the attire worn by followers of various religious sects of late medieval Bengal. The primary materials for the study comprise the depictions which denote religious activities carved on the terracotta plaques. The secondary material has been collected from published and unpublished theses, journals and books. These data have been further supplemented with photographic documentation, some useful line-drawings and descriptions in table format to get a clear understanding of the concerned issues.

Keywords: Attire, scheme of allocation, terracotta temple, various religious sect.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 775

Authors: Rujijan Vichivanives, Kittiya Poonsilp, Canasanan Wanavijit

Abstract:

This research aims to create mobile tools to analyze rice disease quickly and easily. The principle of object-oriented software engineering and objective-C language were used for software development methodology and the principle of decision tree technique was used for analysis method. Application users can select the features of rice disease or the color appears on the rice leaves for recognition analysis results on iOS mobile screen. After completing the software development, unit testing and integrating testing method were used to check for program validity. In addition, three plant experts and forty farmers have been assessed for usability and benefit of this system. The overall of users’ satisfaction was found in a good level, 57%. The plant experts give a comment on the addition of various disease symptoms in the database for more precise results of the analysis. For further research, it is suggested that image processing system should be developed as a tool that allows users search and analyze for rice diseases more convenient with great accuracy.

Keywords: Rice disease, analysis system, mobile application, iOS operating system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1291

Authors: Omer Nebil Yaveroglu, Tolga Can

Abstract:

In this study, a high accuracy protein-protein interaction prediction method is developed. The importance of the proposed method is that it only uses sequence information of proteins while predicting interaction. The method extracts phylogenetic profiles of proteins by using their sequence information. Combining the phylogenetic profiles of two proteins by checking existence of homologs in different species and fitting this combined profile into a statistical model, it is possible to make predictions about the interaction status of two proteins. For this purpose, we apply a collection of pattern recognition techniques on the dataset of combined phylogenetic profiles of protein pairs. Support Vector Machines, Feature Extraction using ReliefF, Naive Bayes Classification, K-Nearest Neighborhood Classification, Decision Trees, and Random Forest Classification are the methods we applied for finding the classification method that best predicts the interaction status of protein pairs. Random Forest Classification outperformed all other methods with a prediction accuracy of 76.93%

Keywords: Protein Interaction Prediction, Phylogenetic Profile, SVM , ReliefF, Decision Trees, Random Forest Classification

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1612

Authors: Yasaswi Palagummi, Sareh Rowlands

Abstract:

Generalised Zero-Shot Learning, often known as GZSL, is an advanced variant of zero-shot learning in which the samples in the unseen category may be either seen or unseen. GZSL methods typically have a bias towards the seen classes because they learn a model to perform recognition for both the seen and unseen classes using data samples from the seen classes. This frequently leads to the misclassification of data from the unseen classes into the seen classes, making the task of GZSL more challenging. In this work, we propose an approach leveraging the Shifted Window based Self-Attention in the Swin Transformer (Swin-GZSL) to work in the inductive GZSL problem setting. We run experiments on three popular benchmark datasets: CUB, SUN, and AWA2, which are specifically used for ZSL and its other variants. The results show that our model based on Swin Transformer has achieved state-of-the-art harmonic mean for two datasets - AWA2 and SUN and near-state-of-the-art for the other dataset - CUB. More importantly, this technique has a linear computational complexity, which reduces training time significantly. We have also observed less bias than most of the existing GZSL models.

Keywords: Generalised Zero-shot Learning, Inductive Learning, Shifted-Window Attention, Swin Transformer, Vision Transformer.

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

Authors: Mathew Wakefield, Matthew Mitchell, Lisa Wise, Christopher McCarthy

Abstract:

This paper aims to provide an interpretation of artificial neural networks (ANNs) and explore some of its implications. The interpretation views ANNs as a memory which encodes instances of experience. An experiment explores the behavior of encoding and retrieval of instances from memory. A localised representation ANN is created that allows control over encoding and retrieved memory sample size and is experimented with using the MNIST digits dataset. The relationship between input familiarity, conflict within retrieved samples, and error rates is described and demonstrated to be an effective driver for memory encoding. Results indicate that selective encoding and retrieval samples that allow detection of memory conflicts produce optimal performance, and that error rates are normally distributed with input familiarity and conflict. By using input familiarity and sample consistency to guide memory encoding, the number of encoding trials on the dataset were reduced to 18.33% of the training data while maintaining good recognition performance on the test data.

Keywords: Artificial Neural Networks, ANNs, representation, memory, conflict monitoring, confidence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 504

Authors: Trien V. Do, Jong-Weon Lee

Abstract:

This paper describes a 3D modeling system in Augmented Reality environment, named 3DARModeler. It can be considered a simple version of 3D Studio Max with necessary functions for a modeling system such as creating objects, applying texture, adding animation, estimating real light sources and casting shadows. The 3DARModeler introduces convenient, and effective human-computer interaction to build 3D models by combining both the traditional input method (mouse/keyboard) and the tangible input method (markers). It has the ability to align a new virtual object with the existing parts of a model. The 3DARModeler targets nontechnical users. As such, they do not need much knowledge of computer graphics and modeling techniques. All they have to do is select basic objects, customize their attributes, and put them together to build a 3D model in a simple and intuitive way as if they were doing in the real world. Using the hierarchical modeling technique, the users are able to group several basic objects to manage them as a unified, complex object. The system can also connect with other 3D systems by importing and exporting VRML/3Ds Max files. A module of speech recognition is included in the system to provide flexible user interfaces.

Keywords: 3D Modeling, Augmented Reality, GeometricModeling, Virtual Reality

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2640

Authors: K.Manimala, Dr.K.Selvi, R.Ahila

Abstract:

Artificial Intelligence (AI) methods are increasingly being used for problem solving. This paper concerns using AI-type learning machines for power quality problem, which is a problem of general interest to power system to provide quality power to all appliances. Electrical power of good quality is essential for proper operation of electronic equipments such as computers and PLCs. Malfunction of such equipment may lead to loss of production or disruption of critical services resulting in huge financial and other losses. It is therefore necessary that critical loads be supplied with electricity of acceptable quality. Recognition of the presence of any disturbance and classifying any existing disturbance into a particular type is the first step in combating the problem. In this work two classes of AI methods for Power quality data mining are studied: Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs). We show that SVMs are superior to ANNs in two critical respects: SVMs train and run an order of magnitude faster; and SVMs give higher classification accuracy.

Keywords: back propagation network, power quality, probabilistic neural network, radial basis function support vector machine

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1555

Authors: Hyun-Woo Cho

Abstract:

Real-time or in-line process monitoring frameworks are designed to give early warnings for a fault along with meaningful identification of its assignable causes. In artificial intelligence and machine learning fields of pattern recognition various promising approaches have been proposed such as kernel-based nonlinear machine learning techniques. This work presents a kernel-based empirical monitoring scheme for batch type production processes with small sample size problem of partially unbalanced data. Measurement data of normal operations are easy to collect whilst special events or faults data are difficult to collect. In such situations, noise filtering techniques can be helpful in enhancing process monitoring performance. Furthermore, preprocessing of raw process data is used to get rid of unwanted variation of data. The performance of the monitoring scheme was demonstrated using three-dimensional batch data. The results showed that the monitoring performance was improved significantly in terms of detection success rate of process fault.

Keywords: Process Monitoring, kernel methods, multivariate filtering, data-driven techniques, quality improvement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1745

Authors: Nadia Masood Khan, Muhammad Salman Khan, Gul Muhammad Khan

Abstract:

Cardiologists perform cardiac auscultation to detect abnormalities in heart sounds. Since accurate auscultation is a crucial first step in screening patients with heart diseases, there is a need to develop computer-aided detection/diagnosis (CAD) systems to assist cardiologists in interpreting heart sounds and provide second opinions. In this paper different algorithms are implemented for automated heart sound classification using unsegmented phonocardiogram (PCG) signals. Support vector machine (SVM), artificial neural network (ANN) and cartesian genetic programming evolved artificial neural network (CGPANN) without the application of any segmentation algorithm has been explored in this study. The signals are first pre-processed to remove any unwanted frequencies. Both time and frequency domain features are then extracted for training the different models. The different algorithms are tested in multiple scenarios and their strengths and weaknesses are discussed. Results indicate that SVM outperforms the rest with an accuracy of 73.64%.

Keywords: Pattern recognition, machine learning, computer aided diagnosis, heart sound classification, and feature extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1280

Authors: Hadeer R. M. Tawfik, Rania A. K. Birry, Amani A. Saad

Abstract:

Eyes are considered to be the most sensitive and important organ for human being. Thus, any eye disorder will affect the patient in all aspects of life. Cataract is one of those eye disorders that lead to blindness if not treated correctly and quickly. This paper demonstrates a model for automatic detection, classification, and grading of cataracts based on image processing techniques and artificial intelligence. The proposed system is developed to ease the cataract diagnosis process for both ophthalmologists and patients. The wavelet transform combined with 2D Log Gabor Wavelet transform was used as feature extraction techniques for a dataset of 120 eye images followed by a classification process that classified the image set into three classes; normal, early, and advanced stage. A comparison between the two used classifiers, the support vector machine SVM and the artificial neural network ANN were done for the same dataset of 120 eye images. It was concluded that SVM gave better results than ANN. SVM success rate result was 96.8% accuracy where ANN success rate result was 92.3% accuracy.

Keywords: Cataract, classification, detection, feature extraction, grading, log-gabor, neural networks, support vector machines, wavelet.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 993

Authors: Sriranjani Srinivasan

Abstract:

To appreciate Indian art and architecture by studying it in India alone will only lead to partial understanding of the whole story and the variety of the statement has been amply proved by subsequent decades of patient research. The results of the work of the Archaeological Survey of India forms only one half of the picture, the other half emerges with the studies of the archaeology and art of the Far East that progressed almost simultaneously under the Archaeological Survey of the Dutch East Indies, the École française d'Extrême-Orient (EFEO), or French School of Asian Studies, and allied institutions. The conclusions arrived at have only rendered the assertion that India produced her ultimate master pieces only through foreign influences and in foreign lands (the South-Eastern peninsular and archipelagic regions) almost axiomatic. Angkor in Cambodia and Borobudur in Java, undoubtedly the two greatest architectural marvels of Indian genius, for in content and spirit these (and other monuments of varying magnitudes), are purely Indian, would well illustrate the statement mentioned earlier. Stimulated research followed the discoveries and among the many studies and publications of such pioneers like Coedes, Parmentier, Coomaraswamy and many others in Dutch, French and English made growing contributions to the subject. This paper will discuss in detail the impact of India on the architecture of South East Asia by detailed comparison of architectural styles, elements, and construction materials of a few specific architectural master pieces, in both India and South East Asian countries. It will also analyze the reasoning behind the influence of India on South East Asian countries in spite of them being exposed to the equally culturally rich and civilized kingdoms of China. The intention of this paper is to understand that, conquest by war is not always the only reason for architectural influences and impacts.

Keywords: Architectural influence, Buddhist architecture, Indian architecture, Southeast Asian architecture.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1313

Authors: Zaharani Ahmad, Nor Hashimah Jalaluddin

Abstract:

The aim of this paper is to examine and identify the issue of linguistic redundancy in two competing grammars of Malay, namely the school grammar and the corpus grammar. The former is a normative grammar which is formally and prescriptively taught in the classroom, whereas the latter is a descriptive grammar that is informally acquired and mastered by the students as native speakers of the language outside the classroom. Corpus grammar is depicted based on its actual used in natural occurring texts, as attested in the corpus. It is observed that the grammar taught in schools is incompatible with the grammar used in the corpus. For instance, a noun phrase containing nominal reduplicated form which denotes plurality (i.e. murid-murid ‘students’ which is derived from murid ‘student’) and a modifier categorized as quantifiers (i.e. semua ‘all’, seluruh ‘entire’, and kebanyakan ‘most’) is not acceptable in the school grammar because the formation (i.e. semua murid-murid ‘all the students’ kebanyakan pelajar-pelajar ‘most of the students’) is claimed to be redundant, and redundancy is prohibited in the grammar. Redundancy is generally construed as the property of speech and language by which more information is provided than is precisely required for the message to be understood, so that, if some information is omitted, the remaining information will still be sufficient for the message to be comprehended. Thus, the correct construction to be used is strictly the reduplicated form (i.e. murid-murid ‘students’) or the quantifier plus the root (i.e. semua murid ‘all the students’) with the intention that the grammatical meaning of plural is not repeated. Nevertheless, the so-called redundant form (i.e. kebanyakan pelajar-pelajar ‘most of the students’) is frequently used in the corpus grammar. This study shows that there are a number of redundant forms occur in the morphology of the language, particularly in affixation, reduplication and combination of both. Apparently, the so-called redundancy has grammatical and socio-cultural functions in communication that is to give emphasis and to stress the importance of the information delivered by the speakers or writers.

Keywords: Corpus grammar, morphology, redundancy, school grammar.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1790

Authors: E. Izsó, M. Bartalné-Berceli, Sz. Gergely, A. Salgó

Abstract:

The aim of this investigation is to elaborate nearinfrared methods for testing and recognition of chemical components and quality in “Pannon wheat” allied (i.e. true to variety or variety identified) milling fractions as well as to develop spectroscopic methods following the milling processes and evaluate the stability of the milling technology by different types of milling products and according to sampling times, respectively. These wheat categories produced under industrial conditions where samples were collected versus sampling time and maximum or minimum yields. The changes of the main chemical components (such as starch, protein, lipid) and physical properties of fractions (particle size) were analysed by dispersive spectrophotometers using visible (VIS) and near-infrared (NIR) regions of the electromagnetic radiation. Close correlation were obtained between the data of spectroscopic measurement techniques processed by various chemometric methods (e.g. principal component analysis [PCA], cluster analysis [CA]) and operation condition of milling technology. It is obvious that NIR methods are able to detect the deviation of the yield parameters and differences of the sampling times by a wide variety of fractions, respectively. NIR technology can be used in the sensitive monitoring of milling technology.

Keywords: Allied wheat fractions, CA, milling process, nearinfrared spectroscopy, PCA.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1689