Search results for: deep sub micron

Authors: Beata Bilska, Marzena Tomaszewska, Danuta Kolozyn-Krajewska

Abstract:

Food loss and food waste are a global problem of the modern economy. The research undertaken aimed to analyze how food is handled in catering establishments when it comes to food waste and to demonstrate the main ways of management with foods/dishes not served to consumers. A survey study was conducted from January to June 2019. The selection of catering establishments participating in the study was deliberate. The study included establishments located only in Mazowieckie Voivodeship (Poland). Forty-two completed questionnaires were collected. In some questions, answers were based on a 5-point scale of 1 to 5 (from "always" / "every day" to "never"). The survey also included closed questions with a suggested cafeteria of answers. The respondents stated that in their workplaces, dishes served cold and hot ready meals are discarded every day or almost every day (23.7% and 20.5% of answers respectively). A procedure most frequently used for dealing with dishes not served to consumers on a given day is their storage at a cool temperature until the following day. In the research, 1/5 of respondents admitted that consumers "always" or "usually" leave uneaten meals on their plates, and over 41% "sometimes" do so. It was found additionally that food not used in the foodservice sector is most often thrown into a public container for rubbish. Most often thrown into the public container (with communal trash) were: expired products (80.0%), plate waste (80.0%) and inedible products (fruit and vegetable peels, eggshells) (77.5%). Most frequently into the container dedicated only to food waste were thrown out used deep-frying oil (62.5%). 10% of respondents indicated that inedible products in their workplaces are allocated for animal feeds. Food waste in the foodservice sector remains an insufficiently studied issue, as owners of these objects are often unwilling to disclose data about the subject. Incorrect ways of management with foods not served to consumers were observed. There is a need to develop educational activities for employees and management in the context of food waste management in the foodservice sector.

Keywords: food waste, inedible products, plate waste, used deep-frying oil

Procedia PDF Downloads 116

Authors: Ankit Kamboj, Shikha Talwar, Nilesh Powar

Abstract:

To successfully deliver our products in the market, the employees need to be in a safe environment, especially in an industrial and manufacturing environment. The consequences of delinquency in wearing safety glasses while working in industrial plants could be high risk to employees, hence the need to develop a real-time automatic detection system which detects the persons (violators) not wearing safety glasses. In this study a convolutional neural network (CNN) algorithm called faster region based CNN (Faster RCNN) with rotated bounding box has been used for detecting safety glasses on persons; the algorithm has an advantage of detecting safety glasses with different orientation angles on the persons. The proposed method of rotational bounding boxes with a convolutional neural network first detects a person from the images, and then the method detects whether the person is wearing safety glasses or not. The video data is captured at the entrance of restricted zones of the industrial environment (manufacturing plant), which is further converted into images at 2 frames per second. In the first step, the CNN with pre-trained weights on COCO dataset is used for person detection where the detections are cropped as images. Then the safety goggles are labelled on the cropped images using the image labelling tool called roLabelImg, which is used to annotate the ground truth values of rotated objects more accurately, and the annotations obtained are further modified to depict four coordinates of the rectangular bounding box. Next, the faster RCNN with rotated bounding box is used to detect safety goggles, which is then compared with traditional bounding box faster RCNN in terms of detection accuracy (average precision), which shows the effectiveness of the proposed method for detection of rotatory objects. The deep learning benchmarking is done on a Dell workstation with a 16GB Nvidia GPU.

Keywords: CNN, deep learning, faster RCNN, roLabelImg rotated bounding box, safety goggle detection

Procedia PDF Downloads 121

Authors: Gholba Niranjan Dilip, Anil Kumar

Abstract:

Conduct of accurate reliable mapping of oil palm plantations and census of individual palm trees is a huge challenge. This study addresses this challenge and developed an optimized solution implemented deep learning techniques on remote sensing data. The oil palm is a very important tropical crop. To improve its productivity and land management, it is imperative to have accurate census over large areas. Since, manual census is costly and prone to approximations, a methodology for automated census using panchromatic images from Cartosat-2, SkySat and World View-3 satellites is demonstrated. It is selected two different study sites in Indonesia. The customized set of training data and ground-truth data are created for this study from Cartosat-2 images. The pre-trained model of Single Shot MultiBox Detector (SSD) Lite MobileNet V2 Convolutional Neural Network (CNN) from the TensorFlow Object Detection API is subjected to transfer learning on this customized dataset. The SSD model is able to generate the bounding boxes for each oil palm and also do the counting of palms with good accuracy on the panchromatic images. The detection yielded an F-Score of 83.16 % on seven different images. The detections are buffered and dissolved to generate polygons demarcating the boundaries of the oil palm plantations. This provided the area under the plantations and also gave maps of their location, thereby completing the automated census, with a fairly high accuracy (≈100%). The trained CNN was found competent enough to detect oil palm crowns from images obtained from multiple satellite sensors and of varying temporal vintage. It helped to estimate the increase in oil palm plantations from 2014 to 2021 in the study area. The study proved that high-resolution panchromatic satellite image can successfully be used to undertake census of oil palm plantations using CNNs.

Keywords: object detection, oil palm tree census, panchromatic images, single shot multibox detector

Procedia PDF Downloads 154

Authors: Deboraj Muchahary, Amlan Deep Borah Abir J. Mondal, Alak Majumder

Abstract:

A discrete cosine transform (DCT) is described and a technique to compute it using fast Fourier transform (FFT) is developed. In this work, DCT of a finite length sequence is obtained by incorporating CORDIC methodology in radix-2 FFT algorithm. The proposed methodology is simple to comprehend and maintains a regular structure, thereby reducing computational complexity. DCTs are used extensively in the area of digital processing for the purpose of pattern recognition. So the efficient computation of DCT maintaining a transparent design flow is highly solicited.

Keywords: DCT, DFT, CORDIC, FFT

Procedia PDF Downloads 464

Authors: Raquel Zydeck, Karina Azzolin, Luis Kosteski, Alisson Milani

Abstract:

This work presents numerical models in plane deformations (2D), using the Discrete Element Method formedbybars (LDEM) andtheFiniteElementMethod (FEM), in structuralmasonrywallswith horizontal chasesof 20%, 30%, and 50% deep, located in the central part and 1/3 oftheupperpartofthewall, withcenteredandeccentricloading. Differentcombinationsofboundaryconditionsandinteractionsbetweenthemethodswerestudied.

Keywords: chases in structural masonry walls, discrete element method formed by bars, finite element method, numerical models, boundary condition

Procedia PDF Downloads 152

Authors: K. R. Roopesh Bharatwaj, Avinash Maharana, Favour Tobi Aborisade, Roger Young

Abstract:

Presently, there are few cases of complete automation of drones and its allied intelligence capabilities. In essence, the potential of the drone has not yet been fully utilized. This paper presents feasible methods to build an intelligent drone with smart capabilities such as self-driving, and obstacle avoidance. It does this through advanced Reinforcement Learning Techniques and performs object detection using latest advanced algorithms, which are capable of processing light weight models with fast training in real time instances. For the scope of this paper, after researching on the various algorithms and comparing them, we finally implemented the Deep-Q-Networks (DQN) algorithm in the AirSim Simulator. In future works, we plan to implement further advanced self-driving and object detection algorithms, we also plan to implement voice-based speech recognition for the entire drone operation which would provide an option of speech communication between users (People) and the drone in the time of unavoidable circumstances. Thus, making drones an interactive intelligent Robotic Voice Enabled Service Assistant. This proposed drone has a wide scope of usability and is applicable in scenarios such as Disaster management, Air Transport of essentials, Agriculture, Manufacturing, Monitoring people movements in public area, and Defense. Also discussed, is the entire drone communication based on the satellite broadband Internet technology for faster computation and seamless communication service for uninterrupted network during disasters and remote location operations. This paper will explain the feasible algorithms required to go about achieving this goal and is more of a reference paper for future researchers going down this path.

Keywords: convolution neural network, natural language processing, obstacle avoidance, satellite broadband technology, self-driving

Procedia PDF Downloads 235

Authors: Husnain Yousaf, Rudy Swennen, Hannes Claes, Muhammad Amjad

Abstract:

In recent years, the Lower Triassic Main Buntsandstein sandstones in the southern Netherlands Basins have become a point of interest for their deep geothermal potential. To identify the most suitable reservoir for geothermal exploration, the diagenesis and factors affecting reservoir quality, such as porosity and permeability, are assessed. This is done by combining point-counted petrographic data with conventional core analysis. The depositional environments play a significant role in determining the distribution of lithofacies, cement, clays, and grain sizes. The position in the basin and proximity to the source areas determine the lateral variability of depositional environments. The stratigraphic distribution of depositional environments is linked to both local topography and climate, where high humidity leads to fluvial deposition and high aridity periods lead to aeolian deposition. The Middle Buntsandstein Sandstones in the southern part of the Netherlands shows high porosity and permeability in most sandstone intervals. There are various controls on reservoir quality in the examined sandstone samples. Grain sizes and total quartz content are the primary factors affecting reservoir quality. Conversely, carbonate and anhydrite cement, clay clasts, and intergranular clay represent a local control and cannot be applied on a regional scale. Similarly, enhanced secondary porosity due to feldspar dissolution is locally restricted and minor. The analysis of textural, mineralogical, and petrophysical data indicates that the aeolian and fluvial sandstones represent a heterogeneous reservoir system. The ephemeral fluvial deposits have an average porosity and permeability of <10% and <1mD, respectively, while the aeolian sandstones exhibit values of >18% and >100mD.

Keywords: reservoir quality, diagenesis, porosity, permeability, depositional environments, Buntsandstein, Netherlands

Procedia PDF Downloads 57

Authors: Mohd Imtiaz S, Saurabh Jain, Pothiraj K.

Abstract:

In today’s highly competitive passenger vehicle market, comfortable driving experience is one of the key parameters significantly weighed by the customer. Smooth ride and handling of the vehicle with exceptionally reliable wheel end solution is a paramount requirement in passenger Sports Utility Vehicle (SUV) vehicles subjected to challenging terrains and loads with rigid rear drive axle configuration. Traditional wheel-end bearing systems in passenger segment rigid rear drive axle utilizes the semi-floating layout, which imparts vertical bending loads and torsion to the axle shafts. The wheel-end bearing is usually a Single or Double Row Deep-Groove Ball Bearing (DRDGBB) or Double Row Angular Contact Ball Bearing (DRACBB). This solution is cost effective and simple in architecture. However, it lacks effectiveness against the heavy loads subjected to a SUV vehicle, especially the axial trust at high-speed cornering. This paper describes the solution of Double Row Taper Roller Bearing (DRTRB) wheel-end for a SUV vehicle in the rigid rear drive axle and improvement in terms of maximizing its load carrying capacity along with better reliability in terms of axial thrust in high-speed cornering. It describes the advantage of geometry of DRTRB over DRDGBB and DRACBB highlighting contact and load flow. The paper also highlights the vehicle level considerations affecting the B10 life of the bearing system for better selection of the DRTRB wheel-ends systems. This paper also describes real time vehicle level results along with theoretical improvements.

Keywords: axial thrust, b10 life, deep-groove ball bearing, taper roller bearing, semi-floating layout.

Procedia PDF Downloads 62

Authors: Velimir "monty" Vesselinov, Trais Kliplhuis, Hope Jasperson

Abstract:

Artificial intelligence (AI) is a powerful tool in the geothermal energy sector, aiding in both exploration and utilization. Identifying promising geothermal sites can be challenging due to limited surface indicators and the need for expensive drilling to confirm subsurface resources. Geothermal reservoirs can be located deep underground and exhibit complex geological structures, making traditional exploration methods time-consuming and imprecise. AI algorithms can analyze vast datasets of geological, geophysical, and remote sensing data, including satellite imagery, seismic surveys, geochemistry, geology, etc. Machine learning algorithms can identify subtle patterns and relationships within this data, potentially revealing hidden geothermal potential in areas previously overlooked. To address these challenges, a SIML (Science-Informed Machine Learning) technology has been developed. SIML methods are different from traditional ML techniques. In both cases, the ML models are trained to predict the spatial distribution of an output (e.g., pressure, temperature, heat flux) based on a series of inputs (e.g., permeability, porosity, etc.). The traditional ML (a) relies on deep and wide neural networks (NNs) based on simple algebraic mappings to represent complex processes. In contrast, the SIML neurons incorporate complex mappings (including constitutive relationships and physics/chemistry models). This results in ML models that have a physical meaning and satisfy physics laws and constraints. The prototype of the developed software, called GeoTGO, is accessible through the cloud. Our software prototype demonstrates how different data sources can be made available for processing, executed demonstrative SIML analyses, and presents the results in a table and graphic form.

Keywords: science-informed machine learning, artificial inteligence, exploration, utilization, hidden geothermal

Procedia PDF Downloads 31

Authors: Shaibu Baanni Azumah, William Adzawla

Abstract:

Rice is an important staple crop, with current demand higher than the domestic supply in Ghana. This has led to a high and unfavourable import bill. Therefore, recent policies and interventions in the agricultural sub-sector aim at promoting various improved agricultural technologies in order to improve domestic production and reduce the importation of rice. In this study, we examined the effect of the adoption of Urea Deep Placement (UDP) technology by rice farmers on the position of the production frontier. This involved 200 farmers selected through a multi stage sampling technique in the Northern region of Ghana. A Cobb-Douglas stochastic frontier model was fitted. The result showed that the adoption of UDP technology shifts the output frontier outward and also move the farmers closer to the frontier. Farmers were also operating under diminishing returns to scale which calls for redress. Other factors that significantly influenced rice production were farm size, labour, use of certified seeds and NPK fertilizer. Although there was an opportunity for improvement, the farmers were highly efficient (92%), compared to previous studies. Farmers’ efficiency was improved through increased education, household size, experience, access to credit, and lack of extension service provision by MoFA. The study recommends the revision of Ghana’s agricultural policy to include the UDP technology. Agricultural Extension officers of the Ministry of Food and Agriculture (MoFA) should be trained on the UDP technology to support IFDC’s drive to improve adoption by rice farmers. Rice farmers are also encouraged to expand their farm lands, improve plant population, and also increase the usage of fertilizer to improve yields. Mechanisms through which credit can be made easily accessible and effectively utilised should be identified and promoted.

Keywords: efficiency, rice farmers, stochastic frontier, UDP technology

Procedia PDF Downloads 397

Authors: Ranjot Kaur, Om P. Katare, Anupama Sharma, Sarah R. Dennison, Kamalinder K. Singh, Bhupinder Singh

Abstract:

Respiratory microbial infections being among the top leading cause of death worldwide are difficult to treat as the microbes reside deep inside the airways, where only a small fraction of drug can access after traditional oral or parenteral routes. As a result, high doses of drugs are required to maintain drug levels above minimum inhibitory concentrations (MIC) at the infection site, unfortunately leading to severe systemic side-effects. Therefore, delivering antimicrobials directly to the respiratory tract provides an attractive way out in such situations. In this context, current study embarks on the systematic development of lung lia pid-modified chitosan nanoparticles for inhalation of voriconazole. Following the principles of quality by design, the chitosan nanoparticles were prepared by ionic gelation method and further coated with major lung lipid by precipitation method. The factor screening studies were performed by fractional factorial design, followed by optimization of the nanoparticles by Box-Behnken Design. The optimized formulation has a particle size range of 170-180nm, PDI 0.3-0.4, zeta potential 14-17, entrapment efficiency 45-50% and drug loading of 3-5%. The presence of a lipid coating was confirmed by FESEM, FTIR, and X-RD. Furthermore, the nanoparticles were found to be safe upto 40µg/ml on A549 and Calu-3 cell lines. The quantitative and qualitative uptake studies also revealed the uptake of nanoparticles in lung epithelial cells. Moreover, the data from Spraytec and next-generation impactor studies confirmed the deposition of nanoparticles in lower airways. Also, the interaction of nanoparticles with DPPC monolayers signifies its biocompatibility with lungs. Overall, the study describes the methodology and potential of lipid-coated chitosan nanoparticles in futuristic inhalation nanomedicine for the management of pulmonary aspergillosis.

Keywords: dipalmitoylphosphatidylcholine, nebulization, DPPC monolayers, quality-by-design

Procedia PDF Downloads 132

Authors: Mazouz Halima, Belghachi Abdrahmane

Abstract:

Effects of electron irradiation-induced deep level defects have been studied on both n/p and p/n indium phosphide solar cells with very thin emitters. The simulation results show that n/p structure offers a somewhat better short circuit current but the p/n structure offers improved circuit voltage, not only before electron irradiation, but also after 1MeV electron irradiation with 5.1015 fluence. The simulation also shows that n/p solar cell structure is more resistant than that of p/n structure.

Keywords: InP solar cell, p/n and n/p structure, electron irradiation, output parameters

Procedia PDF Downloads 540

Authors: Kevin Wang, Jian Ge, Yinan Zhao, Kevin Willis

Abstract:

Kepler has discovered over 4000 exoplanets and candidates. However, current transit planet detection techniques based on the wavelet analysis and the Box Least Squares (BLS) algorithm have limited sensitivity in detecting minor planets with a low signal-to-noise ratio (SNR) and long periods with only 3-4 repeated signals over the mission lifetime of 4 years. This paper presents a novel precise-period transit signal detection methodology based on a new Graphics Processing Unit (GPU) Fast Folding algorithm in conjunction with a Convolutional Neural Network (CNN) to detect low SNR and/or long-period transit planet signals. A comparison with BLS is conducted on both simulated light curves and real data, demonstrating that the new method has higher speed, sensitivity, and reliability. For instance, the new system can detect transits with SNR as low as three while the performance of BLS drops off quickly around SNR of 7. Meanwhile, the GPU Fast Folding method folds light curves 25 times faster than BLS, a significant gain that allows exoplanet detection to occur at unprecedented period precision. This new method has been tested with all known transit signals with 100% confirmation. In addition, this new method has been successfully applied to the Kepler of Interest (KOI) data and identified a few new Earth-sized Ultra-short period (USP) exoplanet candidates and habitable planet candidates. The results highlight the promise for GPU Fast Folding as a replacement to the traditional BLS algorithm for finding small and/or long-period habitable and Earth-sized planet candidates in-transit data taken with Kepler and other space transit missions such as TESS(Transiting Exoplanet Survey Satellite) and PLATO(PLAnetary Transits and Oscillations of stars).

Keywords: algorithms, astronomy data analysis, deep learning, exoplanet detection methods, small planets, habitable planets, transit photometry

Procedia PDF Downloads 210

Authors: A. V. Harutyunyan

Abstract:

The investigation results of rocks at high pressures and temperatures have revealed the intervals of changes of seismic waves and density, as well as some processes taking place in rocks. In the serpentinized rocks, as a consequence of dehydration, abrupt changes in seismic waves and density have been recorded. Hydrogen-bearing components are released which combine with carbon-bearing components. As a result, hydrocarbons formed. The investigated samples are smelted. Then, geofluids and hydrocarbons migrate into the upper horizons of the Earth crust by the deep faults. Then their differentiation and accumulation in the jointed rocks of the faults and in the layers with collecting properties takes place. Under the majority of the hydrocarbon deposits, at a certain depth, magmatic centers and deep faults are recorded. The investigation results of the serpentinized rocks with numerous geological-geophysical factual data allow understanding that hydrocarbons are mainly formed in both the offshore part of the ocean and at different depths of the continental crust. Experiments have also shown that the dehydration of the serpentinized rocks is accompanied by an explosion with the instantaneous increase in pressure and temperature and smelting the studied rocks. According to numerous publications, hydrocarbons and diamonds are formed in the upper part of the mantle, at the depths of 200-400km, and as a consequence of geodynamic processes, they rise to the upper horizons of the Earth crust through narrow channels. However, the genesis of metamorphogenic diamonds and the diamonds found in the lava streams formed within the Earth crust, remains unclear. As at dehydration, super high pressures and temperatures arise. It is assumed that diamond crystals are formed from carbon containing components present in the dehydration zone. It can be assumed that besides the explosion at dehydration, secondary explosions of the released hydrogen take place. The process is naturally accompanied by seismic phenomena, causing earthquakes of different magnitudes on the surface. As for the diamondiferous kimberlites, it is well-known that the majority of them are located within the ancient shield and platforms not obligatorily connected with the deep faults. The kimberlites are formed at the shallow location of dehydrated masses in the Earth crust. Kimberlites are younger in respect of containing ancient rocks containing serpentinized bazites and ultrbazites of relicts of the paleooceanic crust. Sometimes, diamonds containing water and hydrocarbons showing their simultaneous genesis are found. So, the geofluids, hydrocarbons and diamonds, according to the new concept put forward, are formed simultaneously from serpentinized rocks as a consequence of their dehydration at different depths of the Earth crust. Based on the concept proposed by us, we suggest discussing the following: -Genesis of gigantic hydrocarbon deposits located in the offshore area of oceans (North American, Mexican Gulf, Cuanza-Kamerunian, East Brazilian etc.) as well as in the continental parts of different mainlands (Kanadian-Arctic Caspian, East Siberian etc.) - Genesis of metamorphogenic diamonds and diamonds in the lava streams (Guinea-Liberian, Kokchetav, Kanadian, Kamchatka-Tolbachinian, etc.).

Keywords: dehydration, diamonds, hydrocarbons, serpentinites

Procedia PDF Downloads 327

Authors: Vikrant Gupta, Amrit Goswami

Abstract:

The fixed income market forms the basis of the modern financial market. All other assets in financial markets derive their value from the bond market. Owing to its over-the-counter nature, corporate bonds have relatively less data publicly available and thus is researched upon far less compared to Equities. Bond price prediction is a complex financial time series forecasting problem and is considered very crucial in the domain of finance. The bond prices are highly volatile and full of noise which makes it very difficult for traditional statistical time-series models to capture the complexity in series patterns which leads to inefficient forecasts. To overcome the inefficiencies of statistical models, various machine learning techniques were initially used in the literature for more accurate forecasting of time-series. However, simple machine learning methods such as linear regression, support vectors, random forests fail to provide efficient results when tested on highly complex sequences such as stock prices and bond prices. hence to capture these intricate sequence patterns, various deep learning-based methodologies have been discussed in the literature. In this study, a recurrent neural network-based deep learning model using long short term networks for prediction of corporate bond prices has been discussed. Long Short Term networks (LSTM) have been widely used in the literature for various sequence learning tasks in various domains such as machine translation, speech recognition, etc. In recent years, various studies have discussed the effectiveness of LSTMs in forecasting complex time-series sequences and have shown promising results when compared to other methodologies. LSTMs are a special kind of recurrent neural networks which are capable of learning long term dependencies due to its memory function which traditional neural networks fail to capture. In this study, a simple LSTM, Stacked LSTM and a Masked LSTM based model has been discussed with respect to varying input sequences (three days, seven days and 14 days). In order to facilitate faster learning and to gradually decompose the complexity of bond price sequence, an Empirical Mode Decomposition (EMD) has been used, which has resulted in accuracy improvement of the standalone LSTM model. With a variety of Technical Indicators and EMD decomposed time series, Masked LSTM outperformed the other two counterparts in terms of prediction accuracy. To benchmark the proposed model, the results have been compared with traditional time series models (ARIMA), shallow neural networks and above discussed three different LSTM models. In summary, our results show that the use of LSTM models provide more accurate results and should be explored more within the asset management industry.

Keywords: bond prices, long short-term memory, time series forecasting, empirical mode decomposition

Procedia PDF Downloads 126

Authors: Braden M. Li, Inhwan Kim, Jesse S. Jur

Abstract:

One of the fundamental challenges in the electronic textile (e-textile) industry is the mismatch in compliance between the rigid electronic components integrated onto soft textile platforms. To address these problems, various printing technologies using conductive inks have been explored in an effort to improve the electromechanical performance without sacrificing the innate properties of the printed textile. However, current printing methods deposit densely layered coatings onto textile surfaces with low through-plane wetting resulting in poor electromechanical properties. This work presents an inkjet printing technique in conjunction with unique Kirigami cut designs to address these issues for printed smart textiles. By utilizing particle free reactive silver inks, our inkjet process produces conformal and micron thick silver coatings that surround individual fibers of the printed smart textile. This results in a highly conductive (0.63 Ω sq-1) printed e-textile while also maintaining the innate properties of the textile material including stretchability, flexibility, breathability and fabric hand. Kirigami is the Japanese art of paper cutting. By utilizing periodic cut designs, Kirigami imparts enhanced flexibility and delocalization of stress concentrations. Kirigami cut design parameters (i.e., cut spacing and length) were correlated to both the mechanical and electromechanical properties of the printed textiles. We demonstrate that designs using a higher cut-out ratio exponentially softens the textile substrate. Thus, our designs achieve a 30x improvement in the overall stretchability, 1000x decrease in elastic modulus, and minimal resistance change over strain regimes of 100-200% when compared to uncut designs. We also show minimal resistance change of our Kirigami inspired printed devices after being stretched to 100% for 1000 cycles. Lastly, we demonstrate a Kirigami-inspired electrocardiogram (ECG) monitoring system that improves stretchability without sacrificing signal acquisition performance. Overall this study suggests fundamental parameters affecting the performance of e-textiles and their scalability in the wearable technology industry

Keywords: kirigami, inkjet printing, flexible electronics, reactive silver ink

Procedia PDF Downloads 130

Authors: Umbreen Salim, Anila Noor

Abstract:

This paper analyses the influences and faces of colonialism in women’s participation in economic activity in postcolonial Pakistan, through postcolonial feminist economic lens. It is an attempt to probe the shifts in gender inequalities that have existed in three stages; pre-colonial, colonial, and postcolonial times in the Indo-Pak subcontinent. It delves into an inquiry of pre-colonial as it is imperative to understand the situation and context before colonisation in order to assess the deviations associated with its onset. Hence, in order to trace gender inequalities this paper analyses from Mughal Era (1526-1757) that existed before British colonisation, then, the gender inequalities that existed during British colonisation (1857- 1947) and the associated dynamics and changes in women’s vulnerabilities to participate in the economy are examined. Followed by, the postcolonial (1947 onwards) scenario of discriminations and oppressions faced by women. As part of the research methodology, primary and secondary data analysis was done. Analysis of secondary data including literary works and photographs was carried out, followed by primary data collection using ethnographic approaches and participatory tools to understand the presence of coloniality and gender inequalities embedded in the social structure through participant’s real-life stories. The data is analysed using feminist postcolonial analysis. Intersectionality has been a key tool of analysis as the paper delved into the gender inequalities through the class and caste lens briefly touching at religion. It is imperative to mention the significance of the study and very importantly the practical challenges as historical analysis of 18th and 19th century is involved. Most of the available work on history is produced by a) men and b) foreigners and mostly white authors. Since the historical analysis is mostly by men the gender analysis presented misses on many aspects of women’s issues and since the authors have been mostly white European gives it as Mohanty says, ‘under western eyes’ perspective. Whereas the edge of this paper is the authors’ deep attachment, belongingness as lived reality and work with women in Pakistan as postcolonial subjects, a better position to relate with the social reality and understand the phenomenon. The study brought some key results as gender inequalities existed before colonisation when women were hidden wheel of stable economy which was completely invisible. During the British colonisation, the vulnerabilities of women only increased and as compared to men their inferiority status further strengthened. Today, the postcolonial woman lives in deep-rooted effects of coloniality where she is divided in class and position within the class, and she has to face gender inequalities within household and in the market for economic participation. Gender inequalities have existed in pre-colonial, during colonisation and postcolonial times in Pakistan with varying dynamics, degrees and intensities for women whereby social class, caste and religion have been key factors defining the extent of discrimination and oppression. Colonialism may have physically ended but the coloniality remains and has its deep, broad and wide effects in increasing gender inequalities in women’s participation in the economy in Pakistan.

Keywords: colonialism, economic participation, gender inequalities, women

Procedia PDF Downloads 195

Authors: Chithra A. V., Somoshree Datta, Sandeep Nithyanandan

Abstract:

Sign Language Recognition (SLR) is the process of interpreting and translating sign language into spoken or written language using technological systems. It involves recognizing hand gestures, facial expressions, and body movements that makeup sign language communication. The primary goal of SLR is to facilitate communication between hearing- and speech-impaired communities and those who do not understand sign language. Due to the increased awareness and greater recognition of the rights and needs of the hearing- and speech-impaired community, sign language recognition has gained significant importance over the past 10 years. Technological advancements in the fields of Artificial Intelligence and Machine Learning have made it more practical and feasible to create accurate SLR systems. This paper presents a distinct approach to SLR by framing it as a video classification problem using Deep Learning (DL), whereby a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) has been used. This research targets the integration of sign language recognition into healthcare settings, aiming to improve communication between medical professionals and patients with hearing impairments. The spatial features from each video frame are extracted using a CNN, which captures essential elements such as hand shapes, movements, and facial expressions. These features are then fed into an RNN network that learns the temporal dependencies and patterns inherent in sign language sequences. The INCLUDE dataset has been enhanced with more videos from the healthcare domain and the model is evaluated on the same. Our model achieves 91% accuracy, representing state-of-the-art performance in this domain. The results highlight the effectiveness of treating SLR as a video classification task with the CNN-RNN architecture. This approach not only improves recognition accuracy but also offers a scalable solution for real-time SLR applications, significantly advancing the field of accessible communication technologies.

Keywords: sign language recognition, deep learning, convolution neural network, recurrent neural network

Procedia PDF Downloads 10

Authors: Ting Lu, Ya-Ru Diao, Fei Fan, Ye Xue, Lei Shi, Xian-e Tang, Meng-jun Zhan, Zhen-hua Deng

Abstract:

Accurate adult age estimation (AAE) is a significant and challenging task in forensic and archeology fields. Attempts have been made to explore optimal adult age metrics, and the rib is considered a potential age marker. The traditional way is to extract age-related features designed by experts from macroscopic or radiological images followed by classification or regression analysis. Those results still have not met the high-level requirements for practice, and the limitation of using feature design and manual extraction methods is loss of information since the features are likely not designed explicitly for extracting information relevant to age. Deep learning (DL) has recently garnered much interest in imaging learning and computer vision. It enables learning features that are important without a prior bias or hypothesis and could be supportive of AAE. This study aimed to develop DL models for AAE based on CT images and compare their performance to the manual visual scoring method. Chest CT data were reconstructed using volume rendering (VR). Retrospective data of 2500 patients aged 20.00-69.99 years were obtained between December 2019 and September 2021. Five-fold cross-validation was performed, and datasets were randomly split into training and validation sets in a 4:1 ratio for each fold. Before feeding the inputs into networks, all images were augmented with random rotation and vertical flip, normalized, and resized to 224×224 pixels. ResNeXt was chosen as the DL baseline due to its advantages of higher efficiency and accuracy in image classification. Mean absolute error (MAE) was the primary parameter. Independent data from 100 patients acquired between March and April 2022 were used as a test set. The manual method completely followed the prior study, which reported the lowest MAEs (5.31 in males and 6.72 in females) among similar studies. CT data and VR images were used. The radiation density of the first costal cartilage was recorded using CT data on the workstation. The osseous and calcified projections of the 1 to 7 costal cartilages were scored based on VR images using an eight-stage staging technique. According to the results of the prior study, the optimal models were the decision tree regression model in males and the stepwise multiple linear regression equation in females. Predicted ages of the test set were calculated separately using different models by sex. A total of 2600 patients (training and validation sets, mean age=45.19 years±14.20 [SD]; test set, mean age=46.57±9.66) were evaluated in this study. Of ResNeXt model training, MAEs were obtained with 3.95 in males and 3.65 in females. Based on the test set, DL achieved MAEs of 4.05 in males and 4.54 in females, which were far better than the MAEs of 8.90 and 6.42 respectively, for the manual method. Those results showed that the DL of the ResNeXt model outperformed the manual method in AAE based on CT reconstruction of the costal cartilage and the developed system may be a supportive tool for AAE.

Keywords: forensic anthropology, age determination by the skeleton, costal cartilage, CT, deep learning

Procedia PDF Downloads 61

Authors: R. Simões, M. Silveirinha

Abstract:

Driven by the need to understand the results of previous research that clearly shows deep unbalances of the media discourses about women and men in spite of the growing numbers of female journalists, our paper aims to progress from the 'what' to the 'why' of these unbalanced representations. Furthermore, it does so at a time when journalism is undergoing a dramatic change in terms of professional practices and in how media organizations are organized and run, affecting women in particular. While some feminist research points to the fact that female and male journalists evaluate the role of the news and production methods in similar ways feminist theorizing also suggests that thought and knowledge are highly influenced by social identity, which is also inherently affected by the experiences of gender. This is particularly important at a time of deep societal and professional changes. While there are persuasive discussions of gender identities at work in newsrooms in various countries studies on the issue will benefit from cases that focus on the particularities of local contexts. In our paper, we present one such case: the case of Portugal, a country hit hard by austerity measures that have affected all cultural industries including journalism organizations, already feeling the broader impacts of the larger societal changes of the media landscape. Can we gender these changes? How are they felt and understood by female and male journalists? And how are these discourses framed by androcentric, feminist and post-feminist sensibilities? Foregrounding questions of gender, our paper seeks to explore some of the interactions of societal and professional forces, identifying their gendered character and outlining how they shape journalism work in general and the production of unbalanced gender representations in particular. We do so grounded in feminist studies of journalism as well as feminist organizational and work studies, looking at a corpus of 20 in-depth interviews of female and male Portuguese journalists. The research findings illustrate how gender in journalism practices interacts with broader experiences of the cultural and economic contexts and show the ambivalences of these interactions in news organizations.

Keywords: gender, journalism, newsroom culture, Portuguese journalists

Procedia PDF Downloads 391

Authors: Kotaro Sasai, Daijiro Mizutani, Kiyoyuki Kaito

Abstract:

Expressways in Japan have been built in an accelerating manner since the 1960s with the aid of rapid economic growth. About 40 percent in length of expressways in Japan is now 30 years and older and has become superannuated. Time-related deterioration has therefore reached to a degree that administrators, from a standpoint of operation and maintenance, are forced to take prompt measures on a large scale aiming at repairing inner damage deep in pavements. These measures have already been performed for bridge management in Japan and are also expected to be embodied for pavement management. Thus, planning methods for the measures are increasingly demanded. Deterioration of layers around road surface such as surface course and binder course is brought about at the early stages of whole pavement deterioration process, around 10 to 30 years after construction. These layers have been repaired primarily because inner damage usually becomes significant after outer damage, and because surveys for measuring inner damage such as Falling Weight Deflectometer (FWD) survey and open-cut survey are costly and time-consuming process, which has made it difficult for administrators to focus on inner damage as much as they have been supposed to. As expressways today have serious time-related deterioration within them deriving from the long time span since they started to be used, it is obvious the idea of repairing layers deep in pavements such as base course and subgrade must be taken into consideration when planning maintenance on a large scale. This sort of maintenance requires precisely predicting degrees of deterioration as well as grasping the present situations of pavements. Methods for predicting deterioration are determined to be either mechanical or statistical. While few mechanical models have been presented, as far as the authors know of, previous studies have presented statistical methods for predicting deterioration in pavements. One describes deterioration process by estimating Markov deterioration hazard model, while another study illustrates it by estimating Proportional deterioration hazard model. Both of the studies analyze deflection data obtained from FWD surveys and present statistical methods for predicting deterioration process of layers around road surface. However, layers of base course and subgrade remain unanalyzed. In this study, data collected from FWD surveys are analyzed to predict deterioration process of layers deep in pavements in addition to surface layers by a means of estimating a deterioration hazard model using continuous indexes. This model can prevent the loss of information of data when setting rating categories in Markov deterioration hazard model when evaluating degrees of deterioration in roadbeds and subgrades. As a result of portraying continuous indexes, the model can predict deterioration in each layer of pavements and evaluate it quantitatively. Additionally, as the model can also depict probability distribution of the indexes at an arbitrary point and establish a risk control level arbitrarily, it is expected that this study will provide knowledge like life cycle cost and informative content during decision making process referring to where to do maintenance on as well as when.

Keywords: deterioration hazard model, falling weight deflectometer, inner damage, load bearing capacity, pavement

Procedia PDF Downloads 372

Authors: Thomas Monahan, Nicolas Gorius, Thanh Nguyen

Abstract:

Exoplanet atmospheric parameters retrieval is a complex, computationally intensive, inverse modeling problem in which an exoplanet’s atmospheric composition is extracted from an observed spectrum. Traditional Bayesian sampling methods require extensive time and computation, involving algorithms that compare large numbers of known atmospheric models to the input spectral data. Runtimes are directly proportional to the number of parameters under consideration. These increased power and runtime requirements are difficult to accommodate in space missions where model size, speed, and power consumption are of particular importance. The use of traditional Bayesian sampling methods, therefore, compromise model complexity or sampling accuracy. The Atmospheric Retrievals conditional Generative Adversarial Network (ARcGAN) is a deep convolutional generative adversarial network that improves on the previous model’s speed and accuracy. We demonstrate the efficacy of artificial intelligence to quickly and reliably predict atmospheric parameters and present it as a viable alternative to slow and computationally heavy Bayesian methods. In addition to its broad applicability across instruments and planetary types, ARcGAN has been designed to function on low power application-specific integrated circuits. The application of edge computing to atmospheric retrievals allows for real or near-real-time quantification of atmospheric constituents at the instrument level. Additionally, edge computing provides both high-performance and power-efficient computing for AI applications, both of which are critical for space missions. With the edge computing chip implementation, ArcGAN serves as a strong basis for the development of a similar machine-learning algorithm to reduce the downlinked data volume from the Compact Ultraviolet to Visible Imaging Spectrometer (CUVIS) onboard the DAVINCI mission to Venus.

Keywords: deep learning, generative adversarial network, edge computing, atmospheric parameters retrieval

Procedia PDF Downloads 158

Authors: Faizan Tariq, Moayid Ali Zaidi

Abstract:

Facial emotion recognition algorithms are expanding rapidly now a day. People are using different algorithms with different combinations to generate best results. There are six basic emotions which are being studied in this area. Author tried to recognize the facial expressions using object detector algorithms instead of traditional algorithms. Two object detection algorithms were chosen which are Faster R-CNN and YOLO. For pre-processing we used image rotation and batch normalization. The dataset I have chosen for the experiments is Static Facial Expression in Wild (SFEW). Our approach worked well but there is still a lot of room to improve it, which will be a future direction.

Keywords: face recognition, emotion recognition, deep learning, CNN

Procedia PDF Downloads 177

Authors: Ketevan Goletiani, Parmen Khvedelidze

Abstract:

discusses the importance of the topic, which is reflected in the advanced and developed countries in the formation of a new innovative stage of the distinctive mark of the modern world development. This phase includes the construction of the economy, which generates stockpiling and use is based. Intensifying the production and use of the results of new scientific and technical innovation has led to a sharp reduction in the cycle and accelerate the pace of product and technology updates. The world's leading countries in the development of innovative management systems for the formation of long-term and stable development of the socio-economic order conditions. The last years of the 20th century, the social and economic relations, modification, accelerating economic reforms, and profound changes in the system of the time. At the same time, the country should own place in the world geopolitical and economic space. Accelerated economic development tasks, the World Trade Organization, the European Union deep and comprehensive trade agreement, the new system of economic management, technical and technological renewal of production potential, and scientific fields in the share of the total volume of GDP growth requires new approaches. XX - XXI centuries Georgia's socio-economic changes is one of the urgent tasks in the form of a rise to the need for change, involving the use of natural resource-based economy to the latest scientific and technical achievements of an innovative and dynamic economy based on an accelerated pace. But Georgia still remains unresolved in many methodological, theoretical, and practical nature of the problem relating to the management of the economy in various fields for the development of innovative systems for optimal implementation. Therefore, the development of an innovative system for the formation of a complex and multi-problem, which is reflected in the following: countries should have higher growth rates than the geopolitical space of the neighboring countries that its competitors are. Formation of such a system is possible only in a deep theoretical research and innovative processes in the multi-level (micro, meso- and macro-levels) management on the basis of creation.

Keywords: georgia, innovative, socio-economic, innovative manage

Procedia PDF Downloads 111

Authors: Pranjal Srivastava, Piyali Sengupta

Abstract:

The performance of marine drilling risers is crucial in the offshore oil and gas industry to ensure safe drilling operation with minimum downtime. Experimental investigations on marine drilling risers are limited in the literature owing to the expensive and exhaustive test setup required to replicate the realistic riser model and ocean environment in the laboratory. Therefore, this study presents an analytical model of marine drilling riser for determining its fragility under ocean environmental loading. In this study, the marine drilling riser is idealized as a continuous beam having a concentric circular cross-section. Hydrodynamic loading acting on the marine drilling riser is determined by Morison’s equations. By considering the equilibrium of forces on the marine drilling riser for the connected and normal drilling conditions, the governing partial differential equations in terms of independent variables z (depth) and t (time) are derived. Subsequently, the Runge Kutta method and Finite Difference Method are employed for solving the partial differential equations arising from the analytical model. The proposed analytical approach is successfully validated with respect to the experimental results from the literature. From the dynamic analysis results of the proposed analytical approach, the critical design parameters peak displacements, upper and lower flex joint rotations and von Mises stresses of marine drilling risers are determined. An extensive parametric study is conducted to explore the effects of top tension, drilling depth, ocean current speed and platform drift on the critical design parameters of the marine drilling riser. Thereafter, incremental dynamic analysis is performed to derive the fragility functions of shallow water and deep-water marine drilling risers under ocean environmental loading. The proposed methodology can also be adopted for downtime estimation of marine drilling risers incorporating the ranges of uncertainties associated with the ocean environment, especially at deep and ultra-deepwater.

Keywords: drilling riser, marine, analytical model, fragility

Procedia PDF Downloads 134

Authors: Javier Muro, Anja Linstadter, Florian Manner, Lisa Schwarz, Stephan Wollauer, Paul Magdon, Gohar Ghazaryan, Olena Dubovyk

Abstract:

Monitoring the trade-off between biomass production and biodiversity in grasslands is critical to evaluate the effects of management practices across environmental gradients. New generations of remote sensing sensors and machine learning approaches can model grasslands’ characteristics with varying accuracies. However, studies often fail to cover a sufficiently broad range of environmental conditions, and evidence suggests that prediction models might be case specific. In this study, biomass production and biodiversity indices (species richness and Fishers’ α) are modeled in 150 grassland plots for three sites across Germany. These sites represent a North-South gradient and are characterized by distinct soil types, topographic properties, climatic conditions, and management intensities. Predictors used are derived from Sentinel-1 & 2 and a set of topoedaphic variables. The transferability of the models is tested by training and validating at different sites. The performance of feed-forward deep neural networks (DNN) is compared to a random forest algorithm. While biomass predictions across gradients and sites were acceptable (r2 0.5), predictions of biodiversity indices were poor (r2 0.14). DNN showed higher generalization capacity than random forest when predicting biomass across gradients and sites (relative root mean squared error of 0.5 for DNN vs. 0.85 for random forest). DNN also achieved high performance when using the Sentinel-2 surface reflectance data rather than different combinations of spectral indices, Sentinel-1 data, or topoedaphic variables, simplifying dimensionality. This study demonstrates the necessity of training biomass and biodiversity models using a broad range of environmental conditions and ensuring spatial independence to have realistic and transferable models where plot level information can be upscaled to landscape scale.

Keywords: ecosystem services, grassland management, machine learning, remote sensing

Procedia PDF Downloads 208

Authors: Sukru Merey, Caglar Sinayuc

Abstract:

Gas hydrate deposits which are found in deep ocean sediments and in permafrost regions are supposed to be a fossil fuel reserve for the future. The Black Sea is also considered rich in terms of gas hydrates. It abundantly contains gas hydrates as methane (CH₄~80 to 99.9%) source. In this study, by using the literature, seismic and other data of the Black Sea such as salinity, porosity of the sediments, common gas type, temperature distribution and pressure gradient, the optimum gas production method for the Black Sea gas hydrates was selected as mainly depressurization method. Numerical simulations were run to analyze gas production from gas hydrate deposited in turbidites in the Black Sea by depressurization.

Keywords: CH4 hydrate, Black Sea hydrates, gas hydrate experiments, HydrateResSim

Procedia PDF Downloads 610

Authors: Pau Rodriguez, Jordi Gonzalez, Josep M. Gonfaus, Xavier Roca

Abstract:

Image sharing in social networks has increased exponentially in the past years. Officially, there are 600 million Instagrammers uploading around 100 million photos and videos per day. Consequently, there is a need for developing new tools to understand the content expressed in shared images, which will greatly benefit social media communication and will enable broad and promising applications in education, advertisement, entertainment, and also psychology. Following these trends, our work aims to take advantage of the existing relationship between text and personality, already demonstrated by multiple researchers, so that we can prove that there exists a relationship between images and personality as well. To achieve this goal, we consider that images posted on social networks are typically conditioned on specific words, or hashtags, therefore any relationship between text and personality can also be observed with those posted images. Our proposal makes use of the most recent image understanding models based on neural networks to process the vast amount of data generated by social users to determine those images most correlated with personality traits. The final aim is to train a weakly-supervised image-based model for personality assessment that can be used even when textual data is not available, which is an increasing trend. The procedure is described next: we explore the images directly publicly shared by users based on those accompanying texts or hashtags most strongly related to personality traits as described by the OCEAN model. These images will be used for personality prediction since they have the potential to convey more complex ideas, concepts, and emotions. As a result, the use of images in personality questionnaires will provide a deeper understanding of respondents than through words alone. In other words, from the images posted with specific tags, we train a deep learning model based on neural networks, that learns to extract a personality representation from a picture and use it to automatically find the personality that best explains such a picture. Subsequently, a deep neural network model is learned from thousands of images associated with hashtags correlated to OCEAN traits. We then analyze the network activations to identify those pictures that maximally activate the neurons: the most characteristic visual features per personality trait will thus emerge since the filters of the convolutional layers of the neural model are learned to be optimally activated depending on each personality trait. For example, among the pictures that maximally activate the high Openness trait, we can see pictures of books, the moon, and the sky. For high Conscientiousness, most of the images are photographs of food, especially healthy food. The high Extraversion output is mostly activated by pictures of a lot of people. In high Agreeableness images, we mostly see flower pictures. Lastly, in the Neuroticism trait, we observe that the high score is maximally activated by animal pets like cats or dogs. In summary, despite the huge intra-class and inter-class variabilities of the images associated to each OCEAN traits, we found that there are consistencies between visual patterns of those images whose hashtags are most correlated to each trait.

Keywords: emotions and effects of mood, social impact theory in social psychology, social influence, social structure and social networks

Procedia PDF Downloads 183

Authors: Betty Kibirige

Abstract:

Students entering the University of Zululand (UNIZULU) Science Faculty mostly come with skills that allow them to prepare for exams and pass them in order to satisfy requirements for entry into a tertiary Institution. Some students hail from deep rural schools with limited facilities, while others come from well-resourced schools. Personal experience has shown that it may take a student the whole time at a tertiary institution following the same skills as those acquired in high school as a sure means of entering the next level in their development, namely a postgraduate program. While it is apparent that at this point in human history, it is totally impossible to teach all the possible content in any one subject, many academics approach teaching and learning from the traditional point of view. It therefore became apparent to explore ways of developing a graduate that will be able to approach life with skills that allows them to navigate knowledge by applying conceptual and critical thinking skills. Recently, the Science Faculty at the University of Zululand introduced two Engineering programs. In an endeavour to approach the development of the Engineering graduate in this institution to be able to tackle problem-solving in the present-day excessive information availability, it became necessary to study and review approaches used by various academics in order to settle for a possible best approach to the challenge at hand. This paper focuses on the development of a deep rural child in a graduate with conceptual and critical thinking skills as major attributes possessed upon graduation. For this purpose, various approaches were studied. A combination of these approaches was repackaged to form an approach that may appear novel to UNIZULU and the rural child, especially for the Engineering discipline. The approach was checked by offering quiz questions to students participating in an engineering module, observing test scores in the targeted module and make comparative studies. Test results are discussed in the article. It was concluded that students’ graduate attributes could be tailored subconsciously to indeed include conceptual and critical thinking skills, but through more than one approach depending mainly on the student's high school background.

Keywords: graduate attributes, conceptual skills, critical thinking skills, traditional approach

Procedia PDF Downloads 230

Authors: Ola Hall, Ibrahim Wahab, Thorsteinn Rognvaldsson, Mattias Ohlsson

Abstract:

The subfield of poverty and welfare estimation that applies machine learning tools and methods on satellite imagery is a nascent but rapidly growing one. This is in part driven by the sustainable development goal, whose overarching principle is that no region is left behind. Among other things, this requires that welfare levels can be accurately and rapidly estimated at different spatial scales and resolutions. Conventional tools of household surveys and interviews do not suffice in this regard. While they are useful for gaining a longitudinal understanding of the welfare levels of populations, they do not offer adequate spatial coverage for the accuracy that is needed, nor are their implementation sufficiently swift to gain an accurate insight into people and places. It is this void that satellite imagery fills. Previously, this was near-impossible to implement due to the sheer volume of data that needed processing. Recent advances in machine learning, especially the deep learning subtype, such as deep neural networks, have made this a rapidly growing area of scholarship. Despite their unprecedented levels of performance, such models lack transparency and explainability and thus have seen limited downstream applications as humans generally are apprehensive of techniques that are not inherently interpretable and trustworthy. While several studies have demonstrated the superhuman performance of AI models, none has directly compared the performance of such models and human readers in the domain of poverty studies. In the present study, we directly compare the performance of human readers and a DL model using different resolutions of satellite imagery to estimate the welfare levels of demographic and health survey clusters in Tanzania, using the wealth quintile ratings from the same survey as the ground truth data. The cluster-level imagery covers all 608 cluster locations, of which 428 were classified as rural. The imagery for the human readers was sourced from the Google Maps Platform at an ultra-high resolution of 0.6m per pixel at zoom level 18, while that of the machine learning model was sourced from the comparatively lower resolution Sentinel-2 10m per pixel data for the same cluster locations. Rank correlation coefficients of between 0.31 and 0.32 achieved by the human readers were much lower when compared to those attained by the machine learning model – 0.69-0.79. This superhuman performance by the model is even more significant given that it was trained on the relatively lower 10-meter resolution satellite data while the human readers estimated welfare levels from the higher 0.6m spatial resolution data from which key markers of poverty and slums – roofing and road quality – are discernible. It is important to note, however, that the human readers did not receive any training before ratings, and had this been done, their performance might have improved. The stellar performance of the model also comes with the inevitable shortfall relating to limited transparency and explainability. The findings have significant implications for attaining the objective of the current frontier of deep learning models in this domain of scholarship – eXplainable Artificial Intelligence through a collaborative rather than a comparative framework.

Keywords: poverty prediction, satellite imagery, human readers, machine learning, Tanzania

Procedia PDF Downloads 88