Search results for: multi sensor image fusion

Authors: Andrey Yatsun, Andrei Malchikov

Abstract:

Exoskeletons are used to support and compensate for the load on the human musculoskeletal system. Elastomers are an important component of exoskeletons, providing additional support and compensating for the load. The algorithm of the active elastomer tension system provides the required auxiliary force depending on the angle of rotation and the tilt speed of the operator's torso. Feedback for the drive is provided by a force sensor integrated into the attachment of the exoskeleton vest. The use of direct force measurement ensures the required accuracy in all settings of the man-machine system. Non-adjustable elastic elements make it difficult to move without load, tilt forward and walk. A strategy for the organization of the auxiliary forces management system is proposed based on the allocation of 4 operating modes of the human-machine system.

Keywords: soft exoskeleton, mathematical modeling, pre-tension elastomer, human-machine interaction

Procedia PDF Downloads 67

Authors: Ashkan Ebadi, Adam Krzyzak

Abstract:

Recommender systems, also known as recommender engines, have become an important research area and are now being applied in various fields. In addition, the techniques behind the recommender systems have been improved over the time. In general, such systems help users to find their required products or services (e.g. books, music) through analyzing and aggregating other users’ activities and behavior, mainly in form of reviews, and making the best recommendations. The recommendations can facilitate user’s decision making process. Despite the wide literature on the topic, using multiple data sources of different types as the input has not been widely studied. Recommender systems can benefit from the high availability of digital data to collect the input data of different types which implicitly or explicitly help the system to improve its accuracy. Moreover, most of the existing research in this area is based on single rating measures in which a single rating is used to link users to items. This paper proposes a highly accurate hotel recommender system, implemented in various layers. Using multi-aspect rating system and benefitting from large-scale data of different types, the recommender system suggests hotels that are personalized and tailored for the given user. The system employs natural language processing and topic modelling techniques to assess the sentiment of the users’ reviews and extract implicit features. The entire recommender engine contains multiple sub-systems, namely users clustering, matrix factorization module, and hybrid recommender system. Each sub-system contributes to the final composite set of recommendations through covering a specific aspect of the problem. The accuracy of the proposed recommender system has been tested intensively where the results confirm the high performance of the system.

Keywords: tourism, hotel recommender system, hybrid, implicit features

Procedia PDF Downloads 273

Authors: Shafqat Ullah Khan, Ammar Nasir

Abstract:

Using planar antenna array (PAA) in radars, Broadcasting, satellite antennas, and sonar for the detection of targets, Helps provide instant beam pattern control. High flexibility and Adaptability are achieved by multiple beam steering by using a Planar array and are particularly needed in real-life Sanrio’s where the need arises for several high-directivity beams. Faulty sensors in planar arrays generate asymmetry, which leads to service degradation, radiation pattern distortion, and increased levels of sidelobe. The POA, a nature-inspired optimization algorithm, accurately determines faulty sensors within an array, enhancing the reliability and performance of planar array antennas through extensive simulations and experiments. The analysis was done for different types of faults in 7 x 7 and 8 x 8 planar arrays in MATLAB.

Keywords: Planar antenna array, , Pelican optimisation Algorithm, , Faculty sensor, Antenna arrays

Procedia PDF Downloads 81

Authors: Aliyu Shitu Said

Abstract:

One of the major setbacks of every society is the proliferation of crimes that results in the inducement of fear, destruction of properties and loss of lives of people. The rising incidence of crime and general insecurity rate in the society and the inability of the policing agencies to curtail the menace necessitated the introduction of community policing in order to have a collaborative effort with community members in addressing the problem of crime. Thus, this study assessed the impact of community policing in crime prevention and control in Fagge Local Government area, Kano State, Nigeria. The study also examined the elements, roles, and challenges of community policing in crime prevention and control in the study area. The study adopted Broken Window and Routine Activity theories as frame of analysis. Mixed methods of data collection (quantitative and qualitative) were utilized for the study. Multi stage and purposive sampling techniques were adopted in selection of the study population. A total of 308 respondents were sampled for the study. These include 300 members of the public who were sampled through a multi stage sampling for questionnaire administration and 8 other respondents who were purposively sampled for in-depth interview. Findings of the study revealed that community policing has significant impact on crime prevention and control in the study area. Findings of the study further revealed that the elements and roles of community policing are effective and fully utilized, and there is cordial relationship between the police and the community members in the study area. This study therefore recommends that government should provide adequate support to community policing programmes and give more awareness to public, so as to boost the morale of the community in having a collaborative effort with the police in crime prevention and control.

Keywords: community, policing, crime, prevention, control

Procedia PDF Downloads 76

Authors: Bade-Afuye Toyin Beatrice

Abstract:

Nigeria, as a multi-cultural nation, boasts of many festivals, many of which are found in the six geo-political zones of the country. One of the major festivals that bring together the Nigerian citizens as one entity is the National Festival of Arts and Culture (NAFEST), organized by the National Council for Arts and Culture (NCAC). The festival is celebrated yearly in ways that are unique to Nigerians and culture enthusiasts locally and abroad. The festival has equally boosted the Nigerian economy through tourism promotion and culture preservation. This study shall adopt the cultural identity theory. The theory will be used to examine the festival as a platform that showcases culture, which represents the totality of the ways and lives of the Nigerian people. To achieve this, the researcher shall gather data as a participant-observer during the festival, which featured elements such as costume, make-up, dance, drama, children's theatre, fashion parade, local cuisines, local games, music, props, acrobatic displays, trade fair among others. These elements are the cultural aesthetics of the festival, thereby creating spectacles and colours in unique styles by each of the 36 states of the federation and the FCT Abuja. The study particularly examines the 2021 edition of NAFEST hosted by the Ekiti State Government. The study reveals that the festival is a unique multi-ethnic event that brings together Nigerians and their kinsmen in the diaspora. NAFEST has equally provided a good opportunity to showcase the rich cultural heritage of the Ekiti people and the economic values of their products and materials. The paper, therefore, concludes that the National Festival of Arts and Culture has over the years promoted national unity and social integration among Nigerians.

Keywords: colours, culture, spectacle, NAFEST

Procedia PDF Downloads 106

Authors: Svitlana Panchenko

Abstract:

Tourism in Ukraine is an underdeveloped branch of the economy, religious tourism is in its infancy. New challenges of the time, the Covid-19 pandemic and the war are making adjustments, and religious tourism is now in a difficult situation. Although, as scientists describe, it was religious tourism during the pandemic that proved to be a sustainable form of tourism, surviving due to the stability of faith of believers. Tourism in Germany is quite developed and profitable industry, so its interesting for studing such places of pilgrimage in Bavaria as: Passau, Regensburg, Munich, these cities are rich in their shrines and sacred places. In Germany, religious tourism is a well-developed economic sector, so it is necessary to study this issue from the point of view of attracting foreign tourists to Ukrainian lands to visit the shrines. For example, the city of Trier received a large part of the relics of Saint Matthew the Apostle, the relics of the Saint have remained a place of world Christian pilgrimage for centuries. This is the only city in Germany where there are relics of the apostle. Basically, all the relics of the holy apostles are kept in Italy, some in Spain and France. It is important to study different confessional groups, their psychology, the purpose of the pilgrimage, description of shrines. The subject of the study is religious tourism in the cities and villages of Transcarpathia and Bavaria, taking into account the psychological characteristics of pilgrims from a multi-confessional point of view. The article used the culturological, phenomenological, religious studies methods, which allows to analyze the problems of religious tourism from this point of view, taking into account the specifics of this sphere. The results of the research consist in the study of multi-confessional shrines on the example of Ukrainian and German towns to study the importance of cultural heritage and pilgrimage routes, taking into account the psychological factors of pilgrims.

Keywords: communications, cultural heritage, pilgrimage, religious tourism

Procedia PDF Downloads 82

Authors: Mauricio George Miguel Jardini, Jose Antonio Jardini

Abstract:

Transmission power utilities participate with kilometers of circuits, many with particularities in terms of vegetation growth. To control these rights-of-way, maintenance teams perform ground, and air inspections, and the identification method is subjective (indirect). On a ground inspection, when identifying an irregularity, for example, high vegetation threatening contact with the conductor cable, pruning or suppression is performed immediately. In an aerial inspection, the suppression team is mobilized to the identified point. This work investigates the use of 3D modeling of a transmission line segment using RGB (red, blue, and green) images and LiDAR (Light Detection and Ranging) sensor data. Both sensors are coupled to unmanned aerial vehicle. The goal is the accurate and timely detection of vegetation along the right-of-way that can cause shutdowns.

Keywords: 3D modeling, LiDAR, right-of-way, transmission lines, vegetation

Procedia PDF Downloads 131

Authors: Ora Geiger

Abstract:

Reading is a cognitive process of deciphering visual signs to produce meaning. During the reading process, written information of symbols and signs is received in the person’s eye and processed in the brain. This definition is relevant to both the reading of letters and the reading of musical notation. But while the letters of the alphabet are signs determined arbitrarily, notes are recorded systematically on a staff, with the location of each note on the staff indicating its relative pitch. In this paper, the researcher specifies the characteristics of alphabet reading in comparison to musical notation reading, and discusses the question whether a person diagnosed with dyslexia will necessarily have difficulty in reading musical notes. Dyslexia is a learning disorder that makes it difficult to acquire alphabet-reading skills due to difficulties expressed in the identification of letters, spelling, and other language deciphering skills. In order to read, one must be able to connect a symbol with a sound and to join the sounds into words. A person who has dyslexia finds it difficult to translate a graphic symbol into the sound that it represents. When teaching reading to children diagnosed with dyslexia, the multi-sensory approach, supporting the activation and involvement of most of the senses in the learning process, has been found to be particularly effective. According to this approach, when most senses participate in the reading learning process, it becomes more effective. During years of experience, the researcher, who is a music specialist, has been following the music reading learning process of elementary school age students, some of them diagnosed with Dyslexia, while studying to play soprano (descant) recorder. She argues that learning music reading while studying to play a musical instrument is a multi-sensory experience by its nature. The senses involved are: sight, hearing, touch, and the kinesthetic sense (motion), which provides the brain with information on the relative positions of the body. In this way, the learner experiences simultaneously visual, auditory, tactile, and kinesthetic impressions. The researcher concludes that there should be no contra-indication for teaching standard music reading to children with dyslexia if an appropriate process is offered. This conclusion is based on two main characteristics of music reading: (1) musical notation system is a systematic, logical, relative set of symbols written on a staff; and (2) music reading learning connected with playing a musical instrument is by its nature a multi-sensory activity since it combines sight, hearing, touch, and movement. This paper describes music reading teaching procedures and provides unique teaching methods that have been found to be effective for students who were diagnosed with Dyslexia. It provides theoretical explanations in addition to guidelines for music education practices.

Keywords: alphabet reading, dyslexia, multisensory teaching method, music reading, recorder playing

Procedia PDF Downloads 365

Authors: Mayuva Youngsabanant-Areekijseree, Chanikarn Srinark, S. Sengsai, Mayuree Pumipaiboon

Abstract:

Our project was aimed at morphology of oocytes, follicle cells and follicular fluid proteins study of Large White pig (at local slaughter house in Nakhon Pathom Province). The porcine oocytes and follicular fluid of healthy small follicles (1-2 mm), medium follicles (3-6 mm in diameters) and large follicles (7-8 mm and 10 mm in diameter) were aspirated and collected from the ovary by sterile technique. Then, the oocytes and the follicle cells were separated from the fluid. The oocytes were round shape and surrounded by zona pellucida with numerous layers of cumulus cells. Based on the number of cumulus cell layers surrounding oocytes, the oocytes were classified into 5 types, which were intact-, multi-, partial-cumulus layer oocyte, completely denuded oocyte and degenerative oocyte. The collected oocytes showed high percentages of intact- and multi- cumulus cell layers in the small follicles (53.48%) medium follicles (56.94%) and large follicles (56.52%) which have high potential to develop into mature oocytes in vitro. Proteins from follicular fluid of 3 size follicles were separated by SDS-PAGE and LC/MS/MS. The molecular weight of follicular fluid proteins from the small follicles were 24, 60-65, 79, 110, 140, 160, and > 220 kDa. Meanwhile, the follicular fluid protein from medium and large follicle contained 52, 65, 79, 90, 110, 120, 160, 190 and > 220 kDa. Almost all proteins played important roles in promoting and regulating growth and development of oocytes and ovulation. This finding was an initial tool for in vitro testing and applied biotechnology research. Acknowledgements: The project was funded by a grant from Silpakorn University Research & Development Institute (SURDI) and Faculty of Science, Silpakorn University, Thailand.

Keywords: follicular fluid protein, LC/MS/MS, porcine oocyte, SDS-PAGE, reproductive biology

Procedia PDF Downloads 235

Authors: Tsega Asresa, Getahun Tigistu, Melaku Bayih

Abstract:

Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type 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 roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.

Keywords: aromatic medicinal plant, computer vision, convolutional neural network, deep learning, plant classification, residual neural network

Procedia PDF Downloads 187

Authors: Arjmand Khaliq, Pemra Sohaib

Abstract:

In this paper smart grid technologies which converts conventional grid into smart grid has been discussed. Integration of advanced technologies including two way communication, advanced control system, sensors, smart metering system and other provide opportunity to make conventional grid a intelligent and automatic system which is named as smart grid. This paper gives the concept of smart grid and functional characteristics of smart grid technology, summed up the research progress in Pakistan and abroad and the significance of developing smart grid. Based on the analysis of the smart grid, smart grid technologies will result a reliable and energy efficient power system in the future. On the other hand smart grid technologies have been reviewed in this paper highlighting the key technologies of smart grid, and points out the problems and challenges in the realization of smart grid.

Keywords: energy, power system reliability, power system monitoring and control, sensor, smart grid, two-way communication

Procedia PDF Downloads 396

Authors: Ben Haines, Li Bai

Abstract:

Patch based reconstruction methods have been and still are one of the top performing approaches to 3D reconstruction to date. Their local approach to refining the position and orientation of a patch, free of global minimisation and independent of surface smoothness, make patch based methods extremely powerful in recovering fine grained detail of an objects surface. However, patch based approaches still fail to faithfully reconstruct textureless or highly occluded surface regions thus though performing well under lab conditions, deteriorate in industrial or real world situations. They are also computationally expensive. Current patch based methods generate point clouds with holes in texturesless or occluded regions that require expensive energy minimisation techniques to fill and interpolate a high fidelity reconstruction. Such shortcomings hinder the adaptation of the methods for industrial applications where object surfaces are often highly textureless and the speed of reconstruction is an important factor. This paper presents on-going work towards a multi-resolution approach to address the problems, utilizing particle swarm optimisation to reconstruct high fidelity geometry, and increasing robustness to textureless features through an adapted approach to the normalised cross correlation. The work also aims to speed up the reconstruction using advances in GPU technologies and remove the need for costly initialization and expansion. Through the combination of these enhancements, it is the intention of this work to create denser patch clouds even in textureless regions within a reasonable time. Initial results show the potential of such an approach to construct denser point clouds with a comparable accuracy to that of the current top-performing algorithms.

Keywords: 3D reconstruction, multiview stereo, particle swarm optimisation, photo consistency

Procedia PDF Downloads 204

Authors: Christoph Ramsauer, Jaydeep Karandikar, Tony Schmitz, Friedrich Bleicher

Abstract:

Machining stability is an important limitation to discrete part machining. In this work, a networked implementation of milling stability optimization with Bayesian learning is presented. The milling process was monitored with a wireless sensory tool holder instrumented with an accelerometer at the Vienna University of Technology, Vienna, Austria. The recorded data from a milling test cut is used to classify the cut as stable or unstable based on the frequency analysis. The test cut result is fed to a Bayesian stability learning algorithm at the University of Tennessee, Knoxville, Tennessee, USA. The algorithm calculates the probability of stability as a function of axial depth of cut and spindle speed and recommends the parameters for the next test cut. The iterative process between two transatlantic locations repeats until convergence to a stable optimal process parameter set is achieved.

Keywords: machining stability, machine learning, sensor, optimization

Procedia PDF Downloads 206

Authors: Victor A. Okenyi, Kehinde A. Alawode

Abstract:

Corrosion of reinforcement in concrete structures remains a durability issue in structural engineering with the increasing cost of repair and maintenance. The mechanism and factors influencing reinforcement corrosion in concrete with various electrochemical monitoring techniques including non-destructive, destructive techniques and the roles of sensors have been reviewed with the aim of determining the monitoring technique that proved most effective in determining corrosion parameters and more practicable for the assessment of concrete durability. Electrochemical impedance spectroscopy (EIS) and linear polarization resistance (LPR) techniques showed great performance in evaluating corrosion kinetics and corrosion rate, respectively, while the gravimetric weight loss (GWL) technique provided accurate measurements. However, no single monitoring technique showed to be the ultimate technique, and this calls for more research work in the development of more dynamic monitoring tools capable of considering all possible corrosion factors in the corrosion monitoring process.

Keywords: corrosion, concrete structures, durability, non-destructive technique, sensor

Procedia PDF Downloads 182

Authors: Seyed-Yaser Nabavi-Chashmi, Davood Asadi, Karim Ahmadi, Eren Demir

Abstract:

The landing phase of a UAV is very critical as there are many uncertainties in this phase, which can easily entail a hard landing or even a crash. In this paper, the estimation of relative distance and velocity to the ground, as one of the most important processes during the landing phase, is studied. Using accurate measurement sensors as an alternative approach can be very expensive for sensors like LIDAR, or with a limited operational range, for sensors like ultrasonic sensors. Additionally, absolute positioning systems like GPS or IMU cannot provide distance to the ground independently. The focus of this paper is to determine whether we can measure the relative distance and velocity of UAV and ground in the landing phase using just low-resolution images taken by a monocular camera. The Lucas-Konda feature detection technique is employed to extract the most suitable feature in a series of images taken during the UAV landing. Two different approaches based on Extended Kalman Filters (EKF) have been proposed, and their performance in estimation of the relative distance and velocity are compared. The first approach uses the kinematics of the UAV as the process and the calculated optical flow as the measurement; On the other hand, the second approach uses the feature’s projection on the camera plane (pixel position) as the measurement while employing both the kinematics of the UAV and the dynamics of variation of projected point as the process to estimate both relative distance and relative velocity. To verify the results, a sequence of low-quality images taken by a camera that is moving on a specifically developed testbed has been used to compare the performance of the proposed algorithm. The case studies show that the quality of images results in considerable noise, which reduces the performance of the first approach. On the other hand, using the projected feature position is much less sensitive to the noise and estimates the distance and velocity with relatively high accuracy. This approach also can be used to predict the future projected feature position, which can drastically decrease the computational workload, as an important criterion for real-time applications.

Keywords: altitude estimation, drone, image processing, trajectory planning

Procedia PDF Downloads 113

Authors: Hiroshi Nakayama, Yuji Ito

Abstract:

Synthetic cannabinoids have attracted much public attention recently in Japan. 1-pentyl-3-(1-naphthoyl)-indole (JWH-018), 1-pentyl-2-methyl-3-(1-naphthoyl) indole (JWH-015), 1-(5-fluoropentyl)-3- (1-(2,2,3,3- tetramethylcyclopropyl)) indole (XLR-11) and 1-methyl-3- (1-admantyl) indole (JWH-018 adamantyl analog) are known as synthetic cannabinoids and are also considered dangerous illegal drugs in Japan. It has become necessary to develop sensitive and useful methods for detection of synthetic cannabinoids. We produced two monoclonal antibodies (MAb) against synthetic cannabinoids, named NT1 (IgG1) and NT2 (IgG1), using Hybridoma technology. The cross-reactivity of these produced MAbs was evaluated using a competitive enzyme-linked immunosorbent assay (ELISA). In the results, we found both of these antibodies recognize many kinds of synthetic cannabinoids analog. However, neither of these antibodies recognizes naphtoic acid, 1-methyl-indole and indole known as a raw material of synthetic cannabinoid. Thus, the MAbs produced in this study could be a useful tool for the detection of synthetic cannabinoids.

Keywords: ELISA, monoclonal antibody, sensor, synthetic cannabinoid

Procedia PDF Downloads 355

Authors: T. Nagata, S. Xaphakdy, P. Souvannavong, P. Chanthamaly, K. Sithavong, C. H. Lee, S. Phommathat, V. Srithilat, P. Sengdala, B. Phetarnousone, B. Siharath, X. Chemcheng, T. Yamaguchi, A. Suenaga, S. Kashima

Abstract:

National University of Laos (NUOL) requested Japan International Cooperation Agency (JICA) volunteers to begin a physics experiments class using multi media. However, there are issues. NUOL had no physics experiment class, no space for physics experiments, experiment materials were not used for many years and were scattered in various places, and there is no projector and laptop computer in the unit. This raised the question: How do authors begin the physics experiments class using multimedia? To solve this problem, the JICA took some steps, took stock of what was available and reviewed the syllabus. The JICA then revised the experiment materials to assess what was available and then developed textbooks for experiments using them; however, the question remained, what about the multimedia component of the course? Next, the JICA reviewed Physics teacher Pavy Souvannavong’s YouTube channel, where he and his students upload video reports of their physics classes at NUOL using their smartphones. While they use multi-media, almost all the videos recorded were of class presentations. To improve the multimedia style, authors edited the videos in the style of another YouTube channel, “Science for Lao,” which is a science education group made up of Japan Overseas Cooperation Volunteers (JOCV) in Laos. They created the channel to enhance science education in Laos, and hold regular monthly meetings in the capital, Vientiane, and at teacher training colleges in the country. They edit the video clips in three parts, which are the materials and procedures part including pictures, practice footage of the experiment part, and then the result and conclusion part. Then students perform experiments and prepare for presentation by following the videos. The revised experiment presentation reports use PowerPoint presentations, material pictures and experiment video clips. As for providing textbooks and submitting reports, the students use the e-Learning system of “Moodle” of the Information Technology Center in Dongdok campus of NUOL. The Korean International Cooperation Agency (KOICA) donated those facilities. The authors have passed the process of the revised materials, developed textbooks, the PowerPoint slides presented by students, downloaded textbooks and uploaded reports, to begin the physics experiments class using multimedia. This is the practice research report for beginning a physics experiments class using multimedia in the physics unit at the Department of Natural Science, Faculty of Education, at the NUOL.

Keywords: NUOL, JICA, KOICA, physics experiment materials, smartphone, Moodle, IT center, Science for Lao

Procedia PDF Downloads 353

Authors: M. S. Sukumar

Abstract:

Our objective is to develop a full-fledged system for exploring and studying nature of fossils and to extend this to underwater archaeology and mineral mapping. This includes aerial surveying, imaging techniques, artefact extraction and spectrum analysing techniques. These techniques help in regular monitoring of fossils and also the sensing system. The ROV was designed to complete several tasks which simulate collecting data and samples. Given the time constraints, the ROV was engineered for efficiency and speed in performing tasks. Its other major design consideration was modularity, allowing the team to distribute the building process, to easily test systems as they were completed and troubleshoot and replace systems as necessary. Our design itself had several challenges of on-board waterproofed sensor mounting, waterproofing of motors, ROV stability criteria, camera mounting and hydrophone sound acquisition.

Keywords: remotely operated vehicle (ROV) dragonair, underwater archaeology, full-fledged system, aerial imaging and detection

Procedia PDF Downloads 237

Authors: Manuel Alves, Angelica Reis, Armindo Lobo, Valdemar Leiras

Abstract:

In industry 4.0, it is common to have a lot of sensor data. In this deluge of data, hints of possible problems are difficult to spot. The digital twin concept aims to help answer this problem, but it is mainly used as a monitoring tool to handle the visualisation of data. Failure detection is of paramount importance in any industry, and it consumes a lot of resources. Any improvement in this regard is of tangible value to the organisation. The aim of this paper is to add the ability to forecast test failures, curtailing detection times. To achieve this, several anomaly detection algorithms were compared with a symbolic regression approach. To this end, Isolation Forest, One-Class SVM and an auto-encoder have been explored. For the symbolic regression PySR library was used. The first results show that this approach is valid and can be added to the tools available in this context as a low resource anomaly detection method since, after training, the only requirement is the calculation of a polynomial, a useful feature in the digital twin context.

Keywords: anomaly detection, digital twin, industry 4.0, symbolic regression

Procedia PDF Downloads 120

Authors: N. N. Mosola, S. J. Molete, L. S. Masoebe, M. Letsae

Abstract:

Hand gesture recognition is a technique used to locate, detect, and recognize a hand gesture. Detection and recognition are concepts of Artificial Intelligence (AI). AI concepts are applicable in Human Computer Interaction (HCI), Expert systems (ES), etc. Hand gesture recognition can be used in sign language interpretation. Sign language is a visual communication tool. This tool is used mostly by deaf societies and those with speech disorder. Communication barriers exist when societies with speech disorder interact with others. This research aims to build a hand recognition system for Lesotho’s Sesotho and English language interpretation. The system will help to bridge the communication problems encountered by the mentioned societies. The system has various processing modules. The modules consist of a hand detection engine, image processing engine, feature extraction, and sign recognition. Detection is a process of identifying an object. The proposed system uses Canny pruning Haar and Haarcascade detection algorithms. Canny pruning implements the Canny edge detection. This is an optimal image processing algorithm. It is used to detect edges of an object. The system employs a skin detection algorithm. The skin detection performs background subtraction, computes the convex hull, and the centroid to assist in the detection process. Recognition is a process of gesture classification. Template matching classifies each hand gesture in real-time. The system was tested using various experiments. The results obtained show that time, distance, and light are factors that affect the rate of detection and ultimately recognition. Detection rate is directly proportional to the distance of the hand from the camera. Different lighting conditions were considered. The more the light intensity, the faster the detection rate. Based on the results obtained from this research, the applied methodologies are efficient and provide a plausible solution towards a light-weight, inexpensive system which can be used for sign language interpretation.

Keywords: canny pruning, hand recognition, machine learning, skin tracking

Procedia PDF Downloads 185

Authors: Nishant Rodrigues, Nicole Spanedda, Chilukuri K. Mohan, Arindam Chakraborty

Abstract:

A crucial objective in quantum chemistry is the computation of the energy levels of chemical systems. This task requires electron-repulsion integrals as inputs, and the steep computational cost of evaluating these integrals poses a major numerical challenge in efficient implementation of quantum chemical software. This work presents a moment-based machine-learning approach for the efficient evaluation of electron-repulsion integrals. These integrals were approximated using linear combinations of a small number of moments. Machine learning algorithms were applied to estimate the coefficients in the linear combination. A random forest approach was used to identify promising features using a recursive feature elimination approach, which performed best for learning the sign of each coefficient but not the magnitude. A neural network with two hidden layers were then used to learn the coefficient magnitudes along with an iterative feature masking approach to perform input vector compression, identifying a small subset of orbitals whose coefficients are sufficient for the quantum state energy computation. Finally, a small ensemble of neural networks (with a median rule for decision fusion) was shown to improve results when compared to a single network.

Keywords: quantum energy calculations, atomic orbitals, electron-repulsion integrals, ensemble machine learning, random forests, neural networks, feature extraction

Procedia PDF Downloads 114

Authors: D. Madhushanka, Y. Liu, H. C. Fernando

Abstract:

Fires are one of the foremost factors of land surface disturbance in diverse ecosystems, causing soil erosion and land-cover changes and atmospheric effects affecting people's lives and properties. Generally, the severity of the fire is calculated as the Normalized Burn Ratio (NBR) index. This is performed manually by comparing two images obtained afterward. Then by using the bitemporal difference of the preprocessed satellite images, the dNBR is calculated. The burnt area is then classified as either unburnt (dNBR<0.1) or burnt (dNBR>= 0.1). Furthermore, Wildfire Severity Assessment (WSA) classifies burnt areas and unburnt areas using classification levels proposed by USGS and comprises seven classes. This procedure generates a burn severity report for the area chosen by the user manually. This study is carried out with the objective of producing an automated tool for the above-mentioned process, namely the World Wildfire Severity Assessment Tool (WWSAT). It is implemented in Google Earth Engine (GEE), which is a free cloud-computing platform for satellite data processing, with several data catalogs at different resolutions (notably Landsat, Sentinel-2, and MODIS) and planetary-scale analysis capabilities. Sentinel-2 MSI is chosen to obtain regular processes related to burnt area severity mapping using a medium spatial resolution sensor (15m). This tool uses machine learning classification techniques to identify burnt areas using NBR and to classify their severity over the user-selected extent and period automatically. Cloud coverage is one of the biggest concerns when fire severity mapping is performed. In WWSAT based on GEE, we present a fully automatic workflow to aggregate cloud-free Sentinel-2 images for both pre-fire and post-fire image compositing. The parallel processing capabilities and preloaded geospatial datasets of GEE facilitated the production of this tool. This tool consists of a Graphical User Interface (GUI) to make it user-friendly. The advantage of this tool is the ability to obtain burn area severity over a large extent and more extended temporal periods. Two case studies were carried out to demonstrate the performance of this tool. The Blue Mountain national park forest affected by the Australian fire season between 2019 and 2020 is used to describe the workflow of the WWSAT. This site detected more than 7809 km2, using Sentinel-2 data, giving an error below 6.5% when compared with the area detected on the field. Furthermore, 86.77% of the detected area was recognized as fully burnt out, of which high severity (17.29%), moderate-high severity (19.63%), moderate-low severity (22.35%), and low severity (27.51%). The Arapaho and Roosevelt National Forest Park, California, the USA, which is affected by the Cameron peak fire in 2020, is chosen for the second case study. It was found that around 983 km2 had burned out, of which high severity (2.73%), moderate-high severity (1.57%), moderate-low severity (1.18%), and low severity (5.45%). These spots also can be detected through the visual inspection made possible by cloud-free images generated by WWSAT. This tool is cost-effective in calculating the burnt area since satellite images are free and the cost of field surveys is avoided.

Keywords: burnt area, burnt severity, fires, google earth engine (GEE), sentinel-2

Procedia PDF Downloads 235

Authors: Gaurav Prabhudesai, Shaurya Kaushal, Pulkit Dubey, B. D. Pant

Abstract:

The current race of miniaturization of circuits, systems, modules and networks has resulted in portable and mobile wireless systems having tremendous capabilities with small volume and weight. The power drivers or the power pack, electrically driving these modules have also reduced in proportion. Normally, the power packs in these mobile or fixed systems are batteries, rechargeable or non-rechargeable, which need regular replacement or recharging. Another approach to power these modules is to utilize the ambient energy available for electrical driving to make the system self-sustained. The current paper presents an overview of the different MEMS (Micro-Electro-Mechanical Systems) based techniques used for the harvesting of vibration energy to electrically drive a WSN (wireless sensor network) or a mobile module. This kind of system would have enormous applications, the most significant one, may be in cell phones.

Keywords: energy harvesting, WSN, MEMS, piezoelectrics

Procedia PDF Downloads 500

Authors: Leila Chebaiki-Adli, Naima Chabbi-Chemrouk

Abstract:

In the Algiers context, the historical city (the old medina) was in the middle age surrounded by several residencies and gardens. They were built in the aim to spend hot days of the year. Among these later, the residences of AbdelTif and the gardens of the dey (which exist always), benefit from important criteria which increase interior comfort. Their know-how is today in trend and can give us several considerations to the architectural design and to the landscape architecture. Their particularity is seen in the built-garden interactions and the design solutions. These later let the user live with vegetation, sky and water through maximum of places in the constructions. On the basis on an aesthetic-tectonic approach, which make in evidence the architectural criteria of the two quoted cases studies (the AbdelTif residence and the gardens of the dey), we will explain in the proposed paper, some important characteristics and design solutions, which contribute strongly to the concretisation and the materialisation of a landscape architecture, and which can be used in all the Mediterranean area. The proposed aesthetic-tectonic approach is based on the fusion between interior and exterior, in the aim to distinguish syntactic criteria. The syntactic criteria correspond to: The composition and the articulation between interior and exterior spaces, the employed materials in the quoted spaces, the manifestation processes. The major finding of this study is the identification of paradigmatic processes related to the architectural design. These later reveal more figurative (direct) than expressive (no direct) way of design and creativeness. While the figurative way benefits from a high level of manifestation, the expressive one benefits from more composed and articulated materials.

Keywords: aesthetic/tectonic approach, Algiers context, design, landscape architecture

Procedia PDF Downloads 405

Authors: Yuriko Takayama, Norihiro Kato

Abstract:

Quorum sensing (QS) is a cell-to-cell communication system in bacteria to regulate expression of target genes. In gram-negative bacteria, activation on QS is controlled by a concentration increase of N-acylhomoserine lactone (AHL), which can diffuse in and out of the cell. Effective control of QS is expected to avoid virulence factor production in infectious pathogens, biofilm formation, and antibiotic production because various cell functions in gram-negative bacteria are controlled by AHL-mediated QS. In this research, we applied cyclodextrins (CDs) as artificial hosts for the AHL signal to reduce the AHL concentration in the culture broth below its threshold for QS activation. The AHL-receptor complex induced under the high AHL concentration activates transcription of the QS-target gene. Accordingly, artificial reduction of the AHL concentration is one of the effective strategies to inhibit the QS. A hydrophobic cavity of the CD can interact with the acyl-chain of the AHL due to hydrophobic interaction in aqueous media. We studied N-hexanoylhomoserine lactone (C6HSL)-mediated QS in Serratia marcescens; accumulation of C6HSL is responsible for regulation of the expression of pig cluster. Inhibitory effects of added CDs on QS were demonstrated by determination of prodigiosin amount inside cells after reaching stationary phase, because production of prodigiosin depends on the C6HSL-mediated QS. By adding approximately 6 wt% hydroxypropyl-β-CD (HP-β-CD) in Luria-Bertani (LB) medium prior to inoculation of S. maecescens AS-1, the intracellularly accumulated prodigiosin was drastically reduced to 7-10%, which was determined after the extraction of prodigiosin in acidified ethanol. The AHL retention ability of HP-β-CD was also demonstrated by Chromobacterium violacuem CV026 bioassay. The CV026 strain is an AHL-synthase defective mutant that activates QS solely by adding AHLs from outside of cells. A purple pigment violacein is induced by activation of the AHL-mediated QS. We demonstrated that the violacein production was effectively suppressed when the C6HSL standard solution was spotted on a LB agar plate dispersing CV026 cells and HP-β-CD. Physico-chemical analysis was performed to study the affinity between the immobilized CD and added C6HSL using a quartz crystal microbalance (QCM) sensor. The COOH-terminated self-assembled monolayer was prepared on a gold electrode of 27-MHz AT-cut quartz crystal. Mono(6-deoxy-6-N, N-diethylamino)-β-CD was immobilized on the electrode using water-soluble carbodiimide. The C6HSL interaction with the β-CD cavity was studied by injecting the C6HSL solution to a cup-type sensor cell filled with buffer solution. A decrement of resonant frequency (ΔFs) clearly showed the effective C6HSL complexation with immobilized β-CD and its stability constant for MBP-SpnR-C6HSL complex was on the order of 102 M-1. The CD has high potential for engineered control of QS because it is safe for human use.

Keywords: acylhomoserine lactone, cyclodextrin, intracellular signaling, quorum sensing

Procedia PDF Downloads 239

Authors: Raunak Munjal, Mohammad Akif Ali, Prithiv Raj

Abstract:

This study investigates the relative effectiveness of various flight controllers for drone obstacle avoidance. To assess ultrasonic sensors' performance in real-time obstacle detection, they are integrated with ESP32 and Arduino Nano controllers. The study determines which controller is most effective for this particular application by analyzing important parameters such as accuracy (mean absolute error), standard deviation, and mean distance range. Furthermore, the study explores the possibility of incorporating state-driven algorithms into the Arduino Nano configuration to potentially improve obstacle detection performance. The results offer significant perspectives for enhancing sensor integration, choosing the best flight controller for obstacle avoidance, and maybe enhancing drones' general environmental navigation ability.

Keywords: ultrasonic distance measurement, accuracy and consistency, flight controller comparisons, ESP32 vs arduino nano

Procedia PDF Downloads 58

Authors: Hira Lal Gope, Hidekazu Fukai

Abstract:

The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.

Keywords: convolutional neural networks, coffee bean, peaberry, sorting, support vector machine

Procedia PDF Downloads 144

Authors: Mahdi Ghasemi-Varnamkhasti, Ayat Mohammad-Razdari, Seyedeh-Hoda Yoosefian

Abstract:

Taste is an important sensory property governing acceptance of products for administration through mouth. The advent of artificial sensorial systems as non-destructive tools able to mimic chemical senses such as those known as electronic tongue (ET) has open a variety of practical applications and new possibilities in many fields where the presence of taste is the phenomenon under control. In recent years, electronic tongue technology opened the possibility to exploit information on taste attributes of fruits providing real time information about quality and ripeness. Electronic tongue systems have received considerable attention in the field of sensor technology during the last two decade because of numerous applications in diverse fields of applied sciences. This paper deals with some facets of this technology in the quality monitoring of fruits along with more recent its applications.

Keywords: fruit, electronic tongue, non-destructive, taste machine, horticultural

Procedia PDF Downloads 257

Authors: Nkechinyere Joy Olawuyi, Babajide Samuel Afolabi, Bola Ibitoye

Abstract:

This study collected a preprocessed dataset of chest radiographs and formulated a deep neural network model for detecting abnormalities. It also evaluated the performance of the formulated model and implemented a prototype of the formulated model. This was with the view to developing a deep neural network model to automatically classify abnormalities in chest radiographs. In order to achieve the overall purpose of this research, a large set of chest x-ray images were sourced for and collected from the CheXpert dataset, which is an online repository of annotated chest radiographs compiled by the Machine Learning Research Group, Stanford University. The chest radiographs were preprocessed into a format that can be fed into a deep neural network. The preprocessing techniques used were standardization and normalization. The classification problem was formulated as a multi-label binary classification model, which used convolutional neural network architecture to make a decision on whether an abnormality was present or not in the chest radiographs. The classification model was evaluated using specificity, sensitivity, and Area Under Curve (AUC) score as the parameter. A prototype of the classification model was implemented using Keras Open source deep learning framework in Python Programming Language. The AUC ROC curve of the model was able to classify Atelestasis, Support devices, Pleural effusion, Pneumonia, A normal CXR (no finding), Pneumothorax, and Consolidation. However, Lung opacity and Cardiomegaly had a probability of less than 0.5 and thus were classified as absent. Precision, recall, and F1 score values were 0.78; this implies that the number of False Positive and False Negative is the same, revealing some measure of label imbalance in the dataset. The study concluded that the developed model is sufficient to classify abnormalities present in chest radiographs into present or absent.

Keywords: transfer learning, convolutional neural network, radiograph, classification, multi-label

Procedia PDF Downloads 129

Authors: A. J. Cobley, L. Krishnan

Abstract:

The demand for multi-functional lightweight materials in sectors such as automotive, aerospace, electronics is growing, and for this reason fibre-reinforced, epoxy polymer composites are being widely utilized. The fibre reinforcing material is mainly responsible for the strength and stiffness of the composites whilst the main role of the epoxy polymer matrix is to enhance the load distribution applied on the fibres as well as to protect the fibres from the effect of harmful environmental conditions. The superior properties of the fibre-reinforced composites are achieved by the best properties of both of the constituents. Although factors such as the chemical nature of the epoxy and how it is cured will have a strong influence on the properties of the epoxy matrix, the method of mixing and degassing of the resin can also have a significant impact. The production of a fibre-reinforced epoxy polymer composite will usually begin with the mixing of the epoxy pre-polymer with a hardener and accelerator. Mechanical methods of mixing are often employed for this stage but such processes naturally introduce air into the mixture, which, if it becomes entrapped, will lead to voids in the subsequent cured polymer. Therefore, degassing is normally utilised after mixing and this is often achieved by placing the epoxy resin mixture in a vacuum chamber. Although this is reasonably effective, it is another process stage and if a method of mixing could be found that, at the same time, degassed the resin mixture this would lead to shorter production times, more effective degassing and less voids in the final polymer. In this study the effect of four different methods for mixing and degassing of the pre-polymer with hardener and accelerator were investigated. The first two methods were manual stirring and magnetic stirring which were both followed by vacuum degassing. The other two techniques were ultrasonic mixing/degassing using a 40 kHz ultrasonic bath and a 20 kHz ultrasonic probe. The cured cast resin samples were examined under scanning electron microscope (SEM), optical microscope, and Image J analysis software to study morphological changes, void content and void distribution. Three point bending test and differential scanning calorimetry (DSC) were also performed to determine the thermal and mechanical properties of the cured resin. It was found that the use of the 20 kHz ultrasonic probe for mixing/degassing gave the lowest percentage voids of all the mixing methods in the study. In addition, the percentage voids found when employing a 40 kHz ultrasonic bath to mix/degas the epoxy polymer mixture was only slightly higher than when magnetic stirrer mixing followed by vacuum degassing was utilized. The effect of ultrasonic mixing/degassing on the thermal and mechanical properties of the cured resin will also be reported. The results suggest that low frequency ultrasound is an effective means of mixing/degassing a pre-polymer mixture and could enable a significant reduction in production times.

Keywords: degassing, low frequency ultrasound, polymer composites, voids

Procedia PDF Downloads 296