ARTICLE | doi:10.20944/preprints202306.0650.v1
Subject: Medicine And Pharmacology, Gastroenterology And Hepatology Keywords: bidirectional endoscopy; children; propofol; patient time requirements
Online: 8 June 2023 (14:07:20 CEST)
The aim of this study was to compare the effectiveness of propofol-based sedation and midazo-lam sedation in same-day bidirectional endoscopy (BDE) in children. The charts of children (≤15 years old) who had undergone same-day BDE were retrospectively reviewed. Demographic data, indications, sedatives and their dosages, clinical outcomes, endoscopic findings, adverse events, and patient time requirements were compared in cases with propofol-based and midazolam se-dation. A total of 91 children [51 boys, mean age 13 years (range 9-15)] were enrolled. Propofol alone or in combination with midazolam and/or pentazocine was given in 51 (propofol-based sedation group) while midazolam alone or in combination with pentazocine was given in 40 (midazolam sedation group). The mean doses of propofol, midazolam and pentazocine were 96 mg (range 40–145 mg), 4.1 mg (range 3–5 mg) and 7.5 mg in the propofol group while the mean doses of midazolam and pentazocine were 6.2 mg (range 4–10 mg) and 15 mg in the midazolam group, respectively. The total procedure times and endoscopic findings between the two groups were similar, but the median patient time requirement in the propofol group was significantly shorter than that of the midazolam group (7.3 h vs. 8.4 h, P<0.001). No adverse events occurred in either group. Propofol-based sedation shortened patient time requirements in same-day BDE compared with midazolam sedation in children.
ARTICLE | doi:10.20944/preprints202306.0356.v1
Subject: Medicine And Pharmacology, Pharmacology And Toxicology Keywords: NSCLC; JAC4; DNA repair; radiotherapy; bidirectional effect
Online: 5 June 2023 (16:38:38 CEST)
More than 50% of patients with non-small cell lung cancer (NSCLC) are treated with radiotherapy (RT) during different phases of treatment. However, radiation pneu-monitis (RP) and resistance often lead to RT failure in NSCLC patients. JWA, a tumor suppressor gene, is known to enhance DNA damage in gastric cancer cells while protect normal cells from DNA damage induced by cisplatin. Recently, we have re-ported that JWA agonist compound 4 (JAC4) effectively protects intestinal epithelium from RT triggered damage in mice. However, the potential synergistic and attenuated effects of JAC4 in chest RT of lung cancer are not been illuminated. The aim of this study was to investigate the effects of JAC4 on the radiotoxicities of both NSCLC and normal lung tissue. CCK-8 and colony formation assays showed that JAC4 played a bidirectional role in radiation-treated SPCA-1 and BEAS-2B cells. Western blotting and immunofluorescence assays showed that JAC4 in combination with RT increased DNA damage and apoptosis in SPCA-1 cells, while the opposite effect was observed in BEAS-2B cells. Mechanistically, JAC4 inhibited homologous recombination repair (HR) and non-homologous end joining (NHEJ) in SPCA-1 cells, but not in normal cells. JAC4 increased antioxidant capacity, and reduced oxidative stress and inhibited nu-clear factor Kappa-B (NF-κB, P65) translocation to the nucleus in BEAS-2B cells. Im-portantly, the bidirectional roles of JAC4 on RT were reversed by siJWA in both SPCA-1 and BEAS-2B cells. Finally, the bidirectional effects of JAC4 in combination with RT were further validated in NSCLC xenograft model mice. In conclusion, JAC4 enhanced effect of RT on tumor growth while alleviated RP and lung injury. Our re-sults may provide new strategy for optimizing RT regimen for NSCLC.
ARTICLE | doi:10.20944/preprints201807.0113.v1
Subject: Biology And Life Sciences, Biochemistry And Molecular Biology Keywords: pan-cancer; bidirectional promoters; head-to-head genes
Online: 6 July 2018 (09:37:08 CEST)
Bidirectional gene promoters affect the transcription of two genes, leading to the hypothesis that they should exhibit protection against genetic or epigenetic changes in cancer. Therefore, they provide an excellent opportunity to learn about promoter susceptibility to somatic alteration in tumors. We tested this hypothesis using data from genome-scale DNA methylation (14 cancer types), simple somatic mutation (10 cancer types), and copy number variation profiling (14 cancer types). For DNA methylation, the difference in rank differential methylation between tumor and tumor-adjacent normal matched samples based on promoter type was tested by Wilcoxon rank sum test. Logistic regression was used to compare differences in simple somatic mutations. For copy number alteration, a mixed effects logistic regression model was used. The change in methylation between non-diseased tissues and their tumor counterparts was significantly greater in single compared to bidirectional promoters across all 14 cancer types examined. Similarly, the extent of copy number alteration was greater in single gene compared to bidirectional promoters for all 14 cancer types. Furthermore, among 10 cancer types with available simple somatic mutation data, bidirectional promoters were slightly more susceptible. These results suggest that selective pressures related with specific functional impacts during carcinogenesis drive the susceptibility of promoter regions to somatic alteration.
ARTICLE | doi:10.20944/preprints202311.0290.v1
Subject: Chemistry And Materials Science, Materials Science And Technology Keywords: thermal interface materials; graphene; hot-pressing; thermal annealing; bidirectional
Online: 6 November 2023 (09:34:26 CET)
Traditional graphene-based films normally possess high thermal conductivity (TC) only along single direction, which is not suitable for thermal interface materials (TIMs). Here, a graphene film with excellent bidirectional TC and mechanical properties was prepared by hot-pressing super-elastic graphene aerogel (SEGA). Thermal annealing at 1800℃ improves the further restacking of graphene sheets, bring the SEGA high structure stability for enduring the hot-pressing process. The junctions and nodes between the graphene layers in the hot-pressed SEGA (HPSEGA) film provide bidirectional heat transport paths. The in-plane TC and through-plane TC of HPSEGA film with thickness of 101μm reach 740 Wm-1K-1 and 42.5 Wm-1K-1, respectively. In addition, HPSEGA film with higher thickness still maintains excellent thermal transport properties due to the interconnected structure reducing the effect of the defects. The infrared thermal images visually manifest the excellent thermal-transfer capability and thermal dissipation efficiency of the HPSEGA films, indicating the great potential as advanced bidirectional TIMs.
ARTICLE | doi:10.20944/preprints202011.0649.v1
Subject: Computer Science And Mathematics, Computer Science Keywords: video super-resolution; bidirectional; recurrent method; sliding window method
Online: 25 November 2020 (15:12:38 CET)
Video super-resolution, which utilizes the relevant information of several low-resolution frames to generate high-resolution images, is a challenging task. One possible solution called sliding window method tries to divide the generation of high-resolution video sequences into independent sub-tasks, and only adjacent low-resolution images are used to estimate the high-resolution version of the central low-resolution image. Another popular method named recurrent algorithm proposes to utilize not only the low-resolution images but also the generated high-resolution images of previous frames to generate the high-resolution image. However, both methods have some unavoidable disadvantages. The former one usually leads to bad temporal consistency and requires higher computational cost while the latter method always can not make full use of information contained by optical flow or any other calculated features. Thus more investigations need to be done to explore the balance between these two methods. In this work, a bidirectional frame recurrent video super-resolution method is proposed. To be specific, a reverse training is proposed that the generated high-resolution frame is also utilized to help estimate the high-resolution version of the former frame. With the contribution of reverse training and the forward training, the idea of bidirectional recurrent method not only guarantees the temporal consistency but also make full use of the adjacent information due to the bidirectional training operation while the computational cost is acceptable. Experimental results demonstrate that the bidirectional super-resolution framework gives remarkable performance that it solves the time-related problems when the generated high-resolution image is impressive compared with recurrent-based video super-resolution method.
ARTICLE | doi:10.20944/preprints201704.0184.v1
Subject: Engineering, Electrical And Electronic Engineering Keywords: SiC bidirectional AC-DC converter; inverter; variable frequency; PLL; LCL filter
Online: 28 April 2017 (05:06:38 CEST)
The paper presents the design stages of a single-phase Silicon Carbide bidirectional DC-AC converter. This includes the LCL filter design responsible to meet grid connection requirements. A 3kW laboratory prototype of the power converter is built employing a low-cost phase locked loop and its results are presented. The design of the low-cost phase locked loop and its implementation are depicted in some detail.
ARTICLE | doi:10.20944/preprints202311.1801.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: aspect-level sentiment analysis; sentiment interplay; graph-based neural networks; bidirectional attention
Online: 28 November 2023 (10:01:37 CET)
In this paper, we present a groundbreaking methodology in the realm of aspect-level sentiment analysis, which capitalizes on the advanced capabilities of graph-based neural networks. Our approach, distinguished as the Aspect Correlation Graph Network (ACGN), represents a significant departure from conventional models. These traditional models often analyze aspects in isolation, failing to capture the intricate web of sentiment relationships that may exist within a single sentence. ACGN, however, is designed to address this gap by employing a sophisticated bidirectional attention mechanism, integrated with positional encoding. This unique combination not only enhances the model's ability to focus on relevant parts of the sentence but also aids in constructing detailed, aspect-focused representations. These representations are particularly crucial for understanding the nuanced interplay of sentiments associated with different aspects. Central to our model's architecture is the incorporation of a graph convolutional network. This network serves as a pivotal component in mapping and analyzing the complex network of sentiment correlations that can exist among various aspects within sentences. Through this integration, ACGN is able to unearth and interpret the subtle and often overlooked sentiment dynamics that traditional models might miss. Our comprehensive evaluations of the Aspect Correlation Graph Network, conducted using the SemEval 2014 datasets, have yielded promising results. These findings demonstrate a clear and significant advancement over the capabilities of existing models. Particularly, the results underscore the critical importance and utility of recognizing and understanding the connections between sentiments of different aspects in text analysis. This insight opens new avenues in the field of sentiment analysis, suggesting a broader application potential of ACGN in various contexts where understanding nuanced sentiment relationships is key. Overall, our study not only introduces a novel approach in aspect-level sentiment analysis but also sets a new standard for future research in this area. By highlighting the integral role of inter-aspect sentiment connections, ACGN paves the way for more sophisticated and accurate sentiment analysis tools, capable of handling the complexities of natural language with greater finesse and precision.
ARTICLE | doi:10.20944/preprints202311.1705.v1
Subject: Engineering, Safety, Risk, Reliability And Quality Keywords: transformer; self-supervised learning; autoencoder; remaining useful life prediction; bidirectional LSTM; turbofan engine
Online: 27 November 2023 (13:22:46 CET)
Estimating the Remaining Useful Life (RUL) of aircraft engines holds a pivotal role in enhancing safety, optimizing operations, and promoting sustainability, thus being a crucial component of modern aviation management. Precise RUL predictions offer valuable insights into an engine’s condition, enabling informed decisions regarding maintenance and crew scheduling. In this context, we propose a novel RUL prediction approach in this paper, harnessing the power of Bi-directional LSTM and Transformer architectures, known for their success in sequence modeling, such as natural languages. We adopt the encoder part of the full Transformer as the backbone of our framework, integrating it with a self-supervised denoising autoencoder that utilizes Bidirectional LSTM for improved feature extraction. Within our framework, a sequence of multivariate time series sensor measurements serves as the input, initially processed by the Bidirectional LSTM autoencoder to extract essential features. Subsequently, these feature values are fed into our Transformer encoder backbone for RUL prediction. Notably, our approach simultaneously trains the autoencoder and Transformer encoder, different from the naive sequential training method. Through a series of numerical experiments carried out on the C-MAPSS datasets, we demonstrate that the efficacy of our proposed models either surpasses or stands on par with that of other existing methods.
ARTICLE | doi:10.20944/preprints201807.0252.v1
Subject: Engineering, Electrical And Electronic Engineering Keywords: Smart home electricity management system; bidirectional DC-AC converter; high power quality; high efficiency.
Online: 14 July 2018 (20:25:57 CEST)
The management of the electrical energy still raises a huge interest for end-users at the household level. Home electricity management systems (HEMS) have recently emerged both to warrant uninterruptible power and high power quality, and to decrease the cost of electricity consumption, by either shifting it in off peak time or smoothing it. Such a HEMS requires a bidirectional DC-AC converter, specifically when an energy transfer is required between a storage system and the AC-grid, and vice versa. This article points out the relevance of an innovative topology based on sinusoidal waveforms from the generation of sine half-waves. Such a topology is based on a DC-DC stage equivalent to an adjustable output voltage source and a DC-AC stage (H-bridge) which are in series. The results of a complete experimental procedure prove the feasibility to improve the power quality of the output signals in terms of total harmonic distortion (THD-values about 5%). The complexity of the proposed converter is minimized in comparison with multilevel topologies. Finally, wide band-gap semiconductor devices (SiC MOSFETs) are helpful both to warrant the compactness and the high efficiency (about 96%) of the bidirectional converter, whatever its operation mode (inverter or rectifier mode).
ARTICLE | doi:10.20944/preprints201703.0198.v1
Subject: Engineering, Automotive Engineering Keywords: series connected battery string; layered bidirectional equalizer; power inductor; dynamic adjustment of equalization path
Online: 27 March 2017 (10:41:03 CEST)
To eliminate the influence of the inconsistency on the cycle life and the available capacity of the battery pack, and improve the balancing speed, a novel inductor-based layered bidirectional equalizer (IBLBE) is proposed. The equalizer is composed of the bottom balancing circuits and the upper balancing circuits, and the two layer circuits both consist of a plurality of balancing sub-circuits, which allow the dynamic adjustment of equalization path and equalization threshold. The battery string is modularized by layered balancing circuits to realize fast active equalization, especially for long battery strings. By controlling the bottom balancing circuits, the individual cells can be balanced in each module. At the same time, the equalization between battery modules can be realized by controlling the upper balancing circuits. Simulation and experimental results demonstrate that the proposed equalizer can achieve fast active equalization for a long battery string, and has the characteristics of multi balancing path, large balancing current and high accuracy. The advantages of the proposed equalizer are further verified by a comparison with existing active equalizer.
ARTICLE | doi:10.20944/preprints202109.0499.v1
Subject: Engineering, Civil Engineering Keywords: seismic isolation; asymmetric building; mode-adaptive bidirectional pushover analysis (MABPA); seismic retrofit; momentary energy input
Online: 29 September 2021 (14:26:15 CEST)
In this article, the main building of the former Uto City Hall, which was severely damaged in the 2016 Kumamoto earthquake, is investigated as a case study for the retrofitting of an irregular Reinforced Concrete building using the base-isolation technique. Its peak response is predicted via mode-adaptive bidirectional pushover analysis (MABPA), which was originally proposed by the authors. In the prediction step of MABPA, the peaks of the first and second modal responses are predicted considering the energy balance during a half cycle of the structural response. The numerical analysis results show that the peak relative displacement can be properly predicted by MABPA. The results also show that the performance of the retrofitted building models is satisfactory for the ground motion considered in this study, including the recorded motions in the 2016 Kumamoto earthquake.
ARTICLE | doi:10.20944/preprints202306.1815.v2
Subject: Social Sciences, Cognitive Science Keywords: neurofeedback; memory enhancement; medial temporal lobe; intracranial electrode; bidirectional control; memory encoding; intracranial electroencephalogram; intractable epilepsy
Online: 28 June 2023 (12:56:15 CEST)
Neurofeedback (NF) shows promise in enhancing memory, but its application to the medial temporal lobe (MTL) still needs to be studied. Therefore, we aimed to develop an NF system for the memory function of the MTL and examine neural activity changes, and memory task score changes through NF training. We created a memory NF system using intracranial electrodes to acquire and visualise the neural activity of the MTL during memory encoding. Twenty trials of a tug-of-war game per session were employed for NF and designed to control neural activity bidirectionally (Up/Down condition). NF training was conducted with three patients with intractable epilepsy, and we observed an increasing difference in NF signal between conditions (Up−Down) as NF training progressed. Similarities and negative correlation tendencies between the transition of neural activity and the transition of memory function were also observed. Our findings demonstrate NF's potential to modulate MTL activity and memory encoding. Future research needs further improvements to the NF system to validate its effects on memory functions. Nonetheless, this study represents a crucial step in understanding NF's application to memory and provides valuable insights for developing more efficient memory enhancement strategies.
Subject: Biology And Life Sciences, Biochemistry And Molecular Biology Keywords: sleeping Beauty transposon; bidirectional promoters; gene expression; gene therapy; synthetic biology; RPBSA; EF-1; LMP2/TAP1
Online: 28 August 2020 (11:35:53 CEST)
Promoter choice is an essential consideration for transgene expression in gene therapy. The expression of multiple genes requires ribosomal entry or skip sites, or the use of multiple promoters. Promoters systems comprised of two separate, divergent promoters may significantly increase the size of genetic cassettes intended for use in gene therapy. However, an alternative approach is to use a single, compact bidirectional promoter. We identified strong and stable bidirectional activity of the RPBSA synthetic promoter comprised of a fragment of the human Rpl13a promoter, together with additional intron / exon structures. The Rpl13a-based promoter drove long-term bidirectional activity of fluorescent proteins. Similar results were obtained for the EF1-α and LMP2/TAP1 promoters. However, in a lentiviral vector, the divergent bidirectional systems failed to produce sufficient titres to translate into an expression system for dual chimeric antigen receptors (CAR) expression. Although bidirectional promoters show excellent applicability to drive short RNA in Sleeping Beauty transposon systems, their possible use in the lentiviral applications requiring longer and more complex RNA, such as dual CAR cassettes, is limited.
ARTICLE | doi:10.20944/preprints202306.0405.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Multus Medium; Opinion Mining; Deep Learning; Product Review Analysis; Bidirectional Long Short-Term Memory; Convolutional Neural Network
Online: 6 June 2023 (08:06:40 CEST)
Advancements in technology have revolutionized communication on social media platforms, where reviews and comments greatly influence product selection. Current opinion mining methods predominantly focus on textual content, overlooking the rich information within customer-posted images, termed here as Multus-Medium. This research introduces an innovative deep learning approach, Multus Medium Opinion Mining (MMOM), capitalizing on both text and image data for comprehensive product review analysis. MMOM employs an integrated model of Bidirectional Long Short-Term Memory (BiLSTM) and embedded Convolutional Neural Network (CNN), incorporating architectures of GoogleNet and VGGNet, thus enabling efficient extraction and fusion of textual and visual features. This synergistic approach enables data collection, preprocessing, feature extraction, fusion strategy-based feature vector generation, and subsequent product recommendation. Performance evaluation on two diverse real-world datasets name as “flicker8k” and “t4sa”. These datasets show substantial improvement over existing methods. MMOM outperforms standard benchmark models, achieving an accuracy, F1 score and ROC over fliker8k are 90.38%, 88.75% and 93.08%, whereas for twitter dataset are 88.54%, 86.34%, and 92.26% respectively, the accuracy of purposed model is 7.34% and 9.54% higher than the other two mentioned techniques. These statistics highlight the robustness and applicability of MMOM across various domains. The compelling results underscore the potential of MMOM, providing a more holistic and precise approach to opinion mining in the era of social media product reviews. This research, product recommendation helps the customer to make purchasing decision. Last but not the least, the purposed scheme can further be expanded in any other sentiment task like hospital recommendation system, crop farming recommendation and medical diagnostic system etc.
ARTICLE | doi:10.20944/preprints201805.0354.v1
Subject: Engineering, Energy And Fuel Technology Keywords: Rooftop Photovoltaic (PV) System, Maximum Power Point Tracking (MPPT), Power Degradation Index, Bidirectional Hetero-Associative Memory Network (BHAM).
Online: 24 May 2018 (16:27:31 CEST)
In manual maintenance inspections of large-scaled photovoltaic (PV) or rooftop PV systems, several days are required to survey the entire PV field. To improve reliability and shorten the amount of time involved, this study proposes an electrical examination based method for locating multiple faults in the PV array. The maximum power point tracking (MPPT) algorithm is used to estimate the maximum power of each PV panel; this is then compared with metering the output power of PV array. Power degradation indexes are parameterized to quantify the degradation between maximum power and metered output power. Bidirectional hetero-associative memory (BHAM) networks are then used to locate multiple faults within the entire PV field. For a rooftop PV system with two strings, as seen in Figure 1, experimental results demonstrate that the proposed model has computational efficiency for real-time applications and that its algorithm is easily implemented in a mobile intelligent vehicle.
ARTICLE | doi:10.20944/preprints202302.0066.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Smart Tourism; Sustainable Tourism; Natural language Processing (NLP); Big Data Analytics; Deep Learning; Machine Learning; Unsupervised Learning; Bidirectional Encoder Representations from Transformers (BERT); Literature Review; Smart Societies
Online: 3 February 2023 (09:47:55 CET)
The Global natural and manmade events are exposing the fragility of the tourism industry and its impact on the global economy. Prior to the COVID-19 pandemic, tourism contributed 10.3% to the global GDP and employed 333 million people but saw a significant decline due to the pandemic. Sustainable and smart tourism requires collaboration from all stakeholders and a comprehensive understanding of global and local issues to drive responsible and innovative growth in the sector. This paper presents an approach for leveraging big data and deep learning to dis-cover holistic, multi-perspective (e.g., local, cultural, national, and international) and objective information on a subject. Specifically, we develop a machine learning pipeline to extract parameters from academic literature and public opinions on Twitter, providing a unique and comprehensive view of the industry from both academic and public perspectives. The academic-view dataset was created from the Scopus database and contains 156,759 research articles from 2000 to 2022, which were modelled to identify 33 distinct parameters in 4 categories: Tourism Types, Planning, Challenges, and Media & Technologies. A Twitter dataset of 485,813 tweets was collected over 18 months starting March 2021 to August 2022 to showcase public perception of tourism in Saudi Arabia, which was modelled to reveal 13 parameters categorized into two broader sets: Tourist Attractions and Tourism Services. Discovering system parameters are re-quired to embed autonomous capabilities in systems and for decision-making and problem-solving during system design and operations. The proposed approach improves AI-based information discovery by extending the use of scientific literature, Twitter, and other sources for autonomous, dynamic optimizations of systems, promoting novel research in the tourism sector and contributing to the development of smart and sustainable societies. The paper also presents a comprehensive knowledge structure and literature review of the tourism sector based on over 250 research articles.
ARTICLE | doi:10.20944/preprints202203.0403.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: behavioral change prediction; learned features; deep feature learning; handcrafted features; bidirectional long-short term memory; autoencoders; temporal convolutional neural network; clinical decision support system; multisensory stimulation therapy; physiological signals.
Online: 31 March 2022 (08:38:58 CEST)
Predicting change from multivariate time series has relevant applications ranging from medical to engineering fields. Multisensory stimulation therapy in patients with dementia aims to change the patient’s behavioral state. For example, patients who exhibit a baseline of agitation may be paced to change their behavioral state to relaxed. This study aims to predict changes in behavioral state from the analysis of the physiological and neurovegetative parameters to support the therapist during the stimulation session. In order to extract valuable indicators for predicting changes, both handcrafted and learned features were evaluated and compared. The handcrafted features were defined starting from the CATCH22 feature collection, while the learned ones were extracted using a Temporal Convolutional Network, and the behavioral state was predicted through Bidirectional Long Short-Term Memory Auto-Encoder, operating jointly. From the comparison with the state-of-the-art, the learned features-based approach exhibits superior performance with accuracy rates of up to 99.42% with a time window of 70 seconds and up to 98.44% with a time window of 10 seconds.
ARTICLE | doi:10.20944/preprints202208.0345.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Deep learning; solar radiation forecasting; model prediction; solar energy; multi climates data; generalizability; sustainability; Long Short-Term Memory (LSTM); Gated Recurrent Unit (GRU); Convolutional Neural Network (CNN); Hybrid CNN-Bidirectional LSTM; LSTM Autoencoder
Online: 18 August 2022 (10:59:18 CEST)
The sustainability of the planet and its inhabitants is in dire danger and is among the highest priorities on global agendas such as the Sustainable Development Goals (SDGs) of the United Nations (UN). Solar energy -- among other clean, renewable, and sustainable energies -- is seen as essential for environmental, social, and economic sustainability. Predicting solar energy accurately is critical to increasing reliability and stability, and reducing the risks and costs of the energy systems and markets. Researchers have come a long way in developing cutting-edge solar energy forecasting methods. However, these methods are far from optimal in terms of their accuracies, generalizability, benchmarking, and other requirements. Particularly, no single method performs well across all climates and weathers due to the large variations in meteorological data. This paper proposes SENERGY (an acronym for Sustainable Energy), a novel deep learning-based auto-selective approach and tool that, instead of generalising a specific model for all climates, predicts the best performing deep learning model for GHI forecasting in terms of forecasting error. The approach is based on carefully devised deep learning methods and feature sets through an extensive analysis of deep learning forecasting and classification methods using ten meteorological datasets from three continents. We analyse the tool in great detail through a range of metrics and methods for performance analysis, visualization, and comparison of solar forecasting methods. SENERGY outperforms existing methods in all performance metrics including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Forecast Skills (FS), Relative Forecasting Error, and the normalised versions of these metrics. The proposed auto-selective approach can be extended to other research problems such as wind energy forecasting and predict forecasting models based on different criteria (in addition to the minimum forecasting error used in this paper) such as the energy required or speed of model execution, different input features, different optimisations of the same models, or other user preferences.
ARTICLE | doi:10.20944/preprints202208.0233.v1
Subject: Computer Science And Mathematics, Artificial Intelligence And Machine Learning Keywords: Smart Families; Smart Homes; Sustainable Societies; Smart Cities; Deep Learning; Natural Language Processing (NLP); Social Sustainability; Environmental Sustainability; Economic Sustainability; Bidirectional Encoder Representations from Transformers (BERT); Triple Bottom Line (TBL); Internet of Things (IoT)
Online: 12 August 2022 (10:22:17 CEST)
Technological advancements and innovations have profoundly changed the lives of people giving rise to smart environments, cities, and societies. As homes are the building block of cities and societies, smart homes are critical to establishing smart living and are expected to play a key role in enabling smart cities and societies. The current academic literature and commercial advancements on smart homes have mainly focused on developing and providing smart functions for homes to provide security management and facilitate the residents in their various activities such as ambiance management. Homes are much more than physical structures, buildings, appliances, operational machines, and systems. Homes are composed of families and are inherently complex phenomena underlined by humans and their relationships with each other, subject to individual, intragroup, intergroup, and intercommunity goals. There is a clear need to understand, define, consolidate existing research, and actualize the overarching roles of smart homes, the roles of smart homes that would serve the needs of future smart cities and societies. This paper introduces our data-driven parameter discovery methodology and uses it to provide, for the first time, an extensive, rather fairly comprehensive, analysis of the families and homes landscape seen through the eyes of academics and the public using over a hundred thousand research papers and nearly a million tweets. We develop a methodology using deep learning, natural language processing (NLP), and big data analytics methods and apply it to automatically discover parameters that capture a comprehensive knowledge and design space of smart families and homes comprising social, political, economic, environmental, and other dimensions. The 66 discovered parameters and the knowledge space comprising 100s of dimensions are explained by reviewing and referencing over 300 articles from the academic literature and tweets. The knowledge and parameters discovered in this paper can be used to develop a holistic understanding of matters related to families and homes facilitating the development of better, community-specific, policies, technologies, solutions, and industries for families and homes, leading to strengthening families and homes, and in turn, empowering sustainable societies across the globe.