Machine Learning Software Research Articles

MRI-based radiomics models for the early prediction of radiation-induced temporal lobe injury in nasopharyngeal carcinoma.

This study was conducted to develop and validate a radiomics-clinics combined model-based magnetic resonance imaging (MRI) radiomics and clinical features for the early prediction of radiation-induced temporal lobe injury (RTLI) in patients with nasopharyngeal carcinoma (NPC). This retrospective study was conducted using data from 130 patients with NPC (80 patients with and 50 patients without RTLI) who received radiotherapy. Cases were assigned randomly to training (n = 91) and testing (n = 39) datasets. Data on 168 medial temporal lobe texture features were extracted from T1WI, T2WI, and T1WI-CE MRI sequences obtained at the end of radiotherapy courses. Clinics, radiomics, and radiomics-clinics combined models (based on selected radiomics signatures and clinical factors) were constructed using machine learning software. Univariate logistic regression analysis was performed to identify independent clinical factors. The area under the ROC curve (AUC) was performed to evaluate the performance of three models. A nomogram, decision curves, and calibration curves were used to assess the performance of the combined model. Six texture features and three independent clinical factors associated significantly with RTLI were used to build the combined model. The AUCs for the combined and radiomics models were 0.962 [95% confidence interval (CI), 0.9306-0.9939] and 0.904 (95% CI, 0.8431-0.9651), respectively, for the training cohort and 0.947 (95% CI, 0.8841-1.0000) and 0.891 (95% CI, 0.7903-0.9930), respectively, for the testing cohort. All of these values exceeded those for the clinics model (AUC = 0.809 and 0.713 for the training and testing cohorts, respectively). Decision curve analysis showed that the combined model had a good corrective effect. The radiomics-clinics combined model developed in this study showed good performance for predicting RTLI in patients with NPC.

Ensemble learning-based gene signature and risk model for predicting prognosis of triple-negative breast cancer.

Although medical science has been fully developed, due to the high heterogeneity of triple-negative breast cancer (TNBC), it is still difficult to use reasonable and precise treatment. In this study, based on local optimization-feature screening and genomics screening strategy, we screened 25 feature genes. In multiple machine learning algorithms, feature genes have excellent discriminative diagnostic performance among samples composed of multiple large datasets. After screening at the single-cell level, we identified genes expressed substantially in myeloid cells (MCGs) that have a potential association with TNBC. Based on MCGs, we distinguished two types of TNBC patients who showed considerable differences in survival status and immune-related characteristics. Immune-related gene risk scores (IRGRS) were established, and their validity was verified using validation cohorts. A total of 25 feature genes were obtained, among which CXCL9, CXCL10, CCL7, SPHK1, and TREM1 were identified as the result after single-cell level analysis and screening. According to these entries, the cohort was divided into MCA and MCB subtypes, and the two subtypes had significant differences in survival status and tumor-immune microenvironment. After Lasso-Cox screening, IDO1, GNLY, IRF1, CTLA4, and CXCR6 were selected for constructing IRGRS. There were significant differences in drug sensitivity and immunotherapy sensitivity among high-IRGRS and low-IRGRS groups. We revealed the dynamic relationship between TNBC and TIME, identified a potential biomarker called Granulysin (GNLY) related to immunity, and developed a multi-process machine learning package called "MPMLearning 1.0" in Python.

A data analysis method to rapidly characterize gallium concentration in plutonium matrices using LIBS

The processing of actinide samples is a complex and costly endeavor that requires compositional analysis at various stages. Laser-induced breakdown spectroscopy (LIBS) has been used to analyze actinide-containing samples in many nuclear applications including waste management, fuel processing and forensics. The LIBS spectrum obtained from actinide materials are generally extremely complex, exhibiting many thousands of strong emission lines. This makes it difficult to identify other elements within the sample of interest, given the rich and dominant actinide spectrum. In this article we describe a recent effort to identify and quantify impurities and alloying constituents in plutonium matrices using a hand-held LIBS instrument that is used to rapidly and efficiently measure an emission spectrum from a material sample. We tabulate the emission line positions and intensities of plutonium. We report the development of machine-learning software that can identify gallium and quantify its concentration in plutonium matrices. This work has the potential to provide a rapid and nearly non-destructive technique that allows more confidence in characterizing the composition of materials that are present within complex actinide associated targets. We describe how our LIBS measurements and data analysis methods have successfully quantified the gallium concentration in a variety of samples.

DeepFakes- The Digital Threat in the Real World

Objectives: Understanding and Tackling the alarming surge of Digital Imposters known as the world of DeepFakes. 
 Methods: Using Artificial Intelligence based Deep Machine Learning software; Cyber Forensics; Physical mind awareness and alertness! Deepfakes use Artificial Intelligence and Deep Machine Learning techniques to make fake images, of people and events, which are as attractive/ authentic as the original. Deepfakes is the next big Challenge 
 in Cyber Security, taking the Security mindset to the next high level. Findings: On date we have no Specialized High-Tech support at hand to handle such an extremity. We can’t even imagine that if it was a crisis. The impact might be ruinous; it can be anything. In one of the recent live impersonation cases, A Mayor of Berlin thought he was having an online meeting with former boxing champion and current mayor of Kyiv, Vital Klitschko, but later on turned out to be a conversation with a deepfake, an AI generated fake videotape, looking real and authentic. Previous DeepFake videos had some tell-tale signs that a commodity/ person/ event wasn’t real; edit or odd movements. Not presently. In recent Delhi Elections, the BJP Candidate Mr. Manoj Tiwari fabricated his old speech on “Citizenship Amendment Act” into a political campaign speech to reach different linguistic voter bases, especially Haryanvi voters. Tiwari did not have any knowledge about Haryanvi, but made his political campaign message reach Haryanvi voters through DeepFake Technology. 
 Novelty: Massive Online Videos on Internet!

A Natural Language Processing and Machine Learning Approach to Identification of Incidental Radiology Findings in Trauma Patients Discharged from the Emergency Department.

Patients undergoing diagnostic imaging studies in the emergency department (ED) commonly have incidental findings, which may represent unrecognized serious medical conditions, including cancer. Recognition of incidental findings frequently relies on manual review of textual radiology reports and can be overlooked in a busy clinical environment. Our study aimed to develop and validate a supervised machine learning model using natural language processing to automate the recognition of incidental findings in radiology reports of patients discharged from the ED. We performed a retrospective analysis of computed tomography (CT) reports from trauma patients discharged home across an integrated health system in 2019. Two independent annotators manually labeled CT reports for the presence of an incidental finding as a reference standard. We used regular expressions to derive and validate a random forest model using open-source and machine learning software. Final model performance was assessed across different ED types. The study CT reports were divided into derivation (690 reports) and validation (282 reports) sets, with a prevalence of incidental findings of 22.3%, and 22.7%, respectively. The random forest model had an area under the curve of 0.88 (95% confidence interval [CI], 0.84 to 0.92) on the derivation set and 0.92 (95% CI, 0.88 to 0.96) on the validation set. The final model was found to have a sensitivity of 92.2%, a specificity of 79.4%, and a negative predictive value of 97.2%. Similarly, strong model performance was found when stratified to a dedicated trauma center, high-volume, and low-volume community EDs. Machine learning and natural language processing can classify incidental findings in CT reports of ED patients with high sensitivity and high negative predictive value across a broad range of ED settings. These findings suggest the utility of natural language processing in automating the review of free-text reports to identify incidental findings and may facilitate interventions to improve timely follow-up.

CAS launches the CAS Innovation Incubator

CAS, a division of the American Chemical Society, is inviting applications to its innovator incubator. Launched in October, the CAS Innovation Incubator provides early-stage innovators with access to CAS content and technology, expert advice, and in some cases, financial support. “We set up this new Innovation Incubator at CAS because we want to be true to the ACS vision to improve people’s lives through the transforming power of chemistry and related sciences,” says Michael Dennis, vice president of innovation of CAS. CAS will offer successful applicants access to CAS solutions, such as CAS SciFinder, and CAS technologies, such as machine learning and artificial intelligence software that can predict synthetic routes and mine scientific patents. CAS experts will also offer support in areas such as scientific content management and AI. Applicants should be start-ups or early-stage organizations. Individual entrepreneurs from industry and academia may also be eligible. Applications should be made

Mining Project Failure Indicators From Big Data Using Machine Learning Mixed Methods

The literature revealed approximately 50% of IT-related projects around the world fail, which must frustrate a sponsor or decision maker since their ability to forecast success is statistically about the same as guessing with a random coin toss. Nonetheless, some project success/failure factors have been identified, but often the effect sizes were statistically negligible. A pragmatic mixed methods recursive approach was applied, using structured programming, machine learning (ML), and statistical software to mine a large data source for probable project success/failure indicators. Seven feature indicators were detected from ML, producing an accuracy of 79.9%, a recall rate of 81%, an F1 score of 0.798, and a ROCa of 0.849. A post-hoc regression model confirmed three indicators were significant with a 27% effect size. The contributions made to the body of knowledge included: A conceptual model comparing ML methods by artificial intelligence capability and research decision making goal, a mixed methods recursive pragmatic research design, application of the random forest ML technique with post hoc statistical methods, and a preliminary list of IT project failure indicators analyzed from big data.

RCSB Protein Data Bank: Efficient Searching and Simultaneous Access to One Million Computed Structure Models Alongside the PDB Structures Enabled by Architectural Advances

The Research Collaboratory for Structural Bioinformatics Protein Data Bank (RCSB PDB) provides open access to experimentally-determined three-dimensional (3D) structures of biomolecules. The RCSB PDB RCSB.org research-focused web portal is used annually by many millions of users around the world. They access biostructure information, run complex queries utilizing various search services (e.g., full-text, structural and chemical attribute, chemical, sequence, and structure similarity searches), and visualize macromolecules in 3D, all at no charge and with no limitations on data usage. Notwithstanding more than 24,000-fold growth of the PDB over the past five decades, experimentally-determined structures are only available for a small subset of the millions of proteins of known sequence. Recently developed machine learning software tools can predict 3D structures of proteins at accuracies comparable to lower-resolution experimental methods. The RCSB PDB now provides access to ∼1,000,000 Computed Structure Models (CSMs) of proteins coming from AlphaFold DB and the ModelArchive alongside ∼200,000 experimentally-determined PDB structures. Both CSMs and PDB structures are available on RCSB.org and via well-established RCSB PDB Data, Search, and 1D-Coordinates application programming interfaces (APIs). Simultaneous delivery of PDB data and CSMs provides users with access to complementary structural information across the human proteome and those of model organisms and selected pathogens. API enhancements are backwards-compatible and programmatic users can “opt in” to access CSMs with minimal effort. Herein, we describe modifications to RCSB PDB cyberinfrastructure required to support sixfold scaling of 3D biostructure data delivery and lay the groundwork for scaling to accommodate hundreds of millions of CSMs.

Software Fault Prediction Using an RNN-Based Deep Learning Approach and Ensemble Machine Learning Techniques

Alongside the modern software development life cycle approaches, software testing has gained more importance and has become an area researched actively within the software engineering discipline. In this study, machine learning and deep learning-related software fault predictions were made through a data set named SFP XP-TDD, which was created using three different developed software projects. A data set of five different classifiers widely used in the literature and their Rotation Forest classifier ensemble versions were trained and tested using this data set. Numerous publications in the literature discussed software fault predictions through ML algorithms addressing solutions to different problems. Some of these articles indicated the usage of feature selection algorithms to improve classification performance, while others reported operating ensemble machine learning algorithms for software fault predictions. Besides, a detailed literature review revealed that there were few studies involving software fault prediction with DL algorithms due to the small sample sizes in the data sets and the low success rates in the tests performed on these datasets. As a result, the major contribution of this research was to statistically demonstrate that DL algorithms outperformed ML algorithms in data sets with large sample values via employing three separate software fault prediction datasets. The experimental outcomes of a model that includes a layer of recurrent neural networks (RNNs) were enclosed within this study. Alongside the aforementioned and generated data sets, the study also utilized the Eclipse and Apache Active MQ data sets in to test the effectiveness of the proposed deep learning method.

Using a hermeneutic phenomenological approach to Twitter content: a social network’s analysis of green accounting as a dimension of sustainability

PurposeOwing to the worldwide outbreak of the SARS-CoV-2, social media conversations have increased. Given the increasing pressure from regulatory authorities and society, green accounting – as a dimension of sustainable development – remains the most discussed topic on most social media platforms. This study aims to incorporate a technological approach to green accounting and sustainability to enhance the innovation process inside and outside organizations.Design/methodology/approachThis study uses the hermeneutic phenomenological technique to investigate Twitter content. Tweets were subjected to a manual coding process to analyze their content, including recent advancements, challenges, cross-country initiatives and promotion strategies in green accounting. Public perception of green accounting and the COP26 climate summit was also studied.FindingsTweeters view green accounting favorably; however, they are apprehensive about its implementation. Regarding the challenges in green accounting, “corporate green washing” was the most tweeted content. The UK was the top-rated nation with respect to green accounting development. Furthermore, the most discussed breakthrough was the application of artificial intelligence in the domain of green accounting functions. However, Twitter users were observed to have directed heavy criticism at the COP26 climate summit in Glasgow.Originality/valueThis study’s primary innovation is its integration of emerging technologies such as machine learning and data mining with social media platforms such as Twitter. Incorporating manual coding of tweets is a rigorous procedure that amplifies the strength of machine learning software’s auto-coding feature.

Artifical Neural Network for Forecasting Electricity Consumption in Energy Enterprises

The concept of "Digital Transformation 2030", which defines the national goals and strategic objectives of the development of the Russian Federation for the period up to 2030, specifies specialized goals and objectives. These goals and objectives are an important message for the introduction of intelligent information management systems based on digital technologies in the electric power industry in general and energy consumption in particular. The main challenges for the transition to digital transformation are: increasing the rate of tariff growth for the end consumer; increasing deterioration of the network infrastructure; the presence of excessive network construction; increasing requirements for the quality of energy consumption. Based on the above, this article is devoted to the development of a method for the formation of an intelligent con­trol system at an energy enterprise by obtaining an early forecast of the amount of electricity required. The predicted values will help not only to increase the energy efficiency of the company through the implementation of specialized energy saving measures, but also to reduce the financial costs of electricity. The solution to this problem is presented in the form of an intelligent neural network system. The main advantages of this artificial neural network are versatility, high-speed and accurate learning, as well as a small amount of training data. The artificial neural network itself is based on the freely distributed TensorFlow machine learning software library, and a modified error backpropagation method is used as training, the main difference of which is the addition of an artificial neural network learning rate increase factor. The results of the analysis of the effectiveness of the method showed that the proposed intelligent neural network system is more accurate (including relative to similar solutions): the average error does not exceed 3.08 % over the entire time of the experiment. This will allow companies to carry out energy saving measures, which will be especially useful in the current economic realities.

Implementing machine learning methods with complex survey data: Lessons learned on the impacts of accounting sampling weights in gradient boosting.

Despite the prominent use of complex survey data and the growing popularity of machine learning methods in epidemiologic research, few machine learning software implementations offer options for handling complex samples. A major challenge impeding the broader incorporation of machine learning into epidemiologic research is incomplete guidance for analyzing complex survey data, including the importance of sampling weights for valid prediction in target populations. Using data from 15, 820 participants in the 1988-1994 National Health and Nutrition Examination Survey cohort, we determined whether ignoring weights in gradient boosting models of all-cause mortality affected prediction, as measured by the F1 score and corresponding 95% confidence intervals. In simulations, we additionally assessed the impact of sample size, weight variability, predictor strength, and model dimensionality. In the National Health and Nutrition Examination Survey data, unweighted model performance was inflated compared to the weighted model (F1 score 81.9% [95% confidence interval: 81.2%, 82.7%] vs 77.4% [95% confidence interval: 76.1%, 78.6%]). However, the error was mitigated if the F1 score was subsequently recalculated with observed outcomes from the weighted dataset (F1: 77.0%; 95% confidence interval: 75.7%, 78.4%). In simulations, this finding held in the largest sample size (N = 10,000) under all analytic conditions assessed. For sample sizes <5,000, sampling weights had little impact in simulations that more closely resembled a simple random sample (low weight variability) or in models with strong predictors, but findings were inconsistent under other analytic scenarios. Failing to account for sampling weights in gradient boosting models may limit generalizability for data from complex surveys, dependent on sample size and other analytic properties. In the absence of software for configuring weighted algorithms, post-hoc re-calculations of unweighted model performance using weighted observed outcomes may more accurately reflect model prediction in target populations than ignoring weights entirely.

CoFHE: Software and hardware Co-design for FHE-based machine learning as a service

Introduction: Privacy concerns arise whenever sensitive data is outsourced to untrusted Machine Learning as a Service (MLaaS) platforms. Fully Homomorphic Encryption (FHE) emerges one of the most promising solutions to implementing privacy-preserving MLaaS. But prior FHE-based MLaaS faces challenges from both software and hardware perspectives. First, FHE can be implemented by various schemes including BGV, BFV, and CKKS, which are good at different FHE operations, e.g., additions, multiplications, and rotations. Different neural network architectures require different numbers of FHE operations, thereby preferring different FHE schemes. However, state-of-the-art MLaaS just naïvely chooses one FHE scheme to build FHE-based neural networks without considering other FHE schemes. Second, state-of-the-art MLaaS uses power-hungry hardware accelerators to process FHE-based inferences. Typically, prior high-performance FHE accelerators consume &gt;160 Watt, due to their huge capacity (e.g., 512 MB) on-chip SRAM scratchpad memories.Methods: In this paper, we propose a software and hardware co-designed FHE-based MLaaS framework, CoFHE. From the software perspective, we propose an FHE compiler to select the best FHE scheme for a network architecture. We also build a low-power and high-density NAND-SPIN and SRAM hybrid scratchpad memory system for FHE hardware accelerators.Results: On average, under the same security and accuracy constraints, on average, CoFHE accelerates various FHE-based inferences by 18%, and reduces the energy consumption of various FHE-based inferences by 26%.Discussion: CoFHE greatly improves the latency and energy efficiency of FHE-based MLaaS.

Artificial Intelligence in Surgical Evaluation: A Study of Facial Rejuvenation Techniques.

Aesthetic facial surgeries historically rely on subjective analysis in determining success; this limits objective comparison of surgical outcomes. This case study exemplifies the use of an artificial intelligence software on objectively analyzing facial rejuvenation techniques with the aim of reducing subjective bias. Retrospectively, all patients who underwent facial rejuvenation surgery with concomitant procedures from 2015 to 2017 were included (n = 32). Patients were categorized into Groups A to C: Group A-10 superficial musculoaponeurotic system (SMAS) plication facelift (n = 10), Group B-SMASectomy facelift (n = 7), and Group C-high SMAS facelift (n = 15). Neutral repose images preoperatively and postoperatively (average >3 months) were analyzed using artificial intelligence for emotion and action unit alterations. Postoperatively, Group A experienced a decrease in happiness by 0.84% and a decrease in anger by 6.87% (P >> .1). Group B had an increase in happiness by 0.77% and an increase in anger by 1.91% (P >> .1). Both Group A and Group B did not show any discernable action unit patterns. In Group C, the lip corner puller AU increased in average intensity from 0% to 18.7%. This correlated with an average increase in detected happiness from 1.03% to 13.17% (P = .008). Conversely, the average detected anger decreased from 14.66% to 0.63% (P = .032). This study provides the first proof of concept for the use of a machine learning software application to objectively assess various aesthetic surgical outcomes in facial rejuvenation. Due to limitations in patient heterogeneity, this study does not claim one technique's superiority but serves as a conceptual foundation for future investigation.

Comparison of diagnostic accuracy of the artificial intelligence system with human readers in the diagnosis of portable chest x-rays during the COVID-19 pandemic

Background: Evaluating the performance of the available machine learning software is fundamental to ensure trustworthiness and improve automated diagnosis. This study compared the diagnostic accuracy of artificial intelligence (AI) system reporting with human readers for portable chest anteroposterior (AP) x-rays acquired patients in a semi-recumbent position. Methods: Ninety-four patients who underwent portable chest AP with clinical suspicion or confirmed COVID-19 were included in the study; among them, 65 were COVID-19 positive and 29 had symptoms. High-resolution computed tomography (HRCT) Chest was available for 39 patients. Images were read by two radiologists (R1, R2) and AI. In case of disagreement between R1 and R2, a third radiologist (R3) read the images; however, if HRCT Chest was available, we counted HRCT Chest instead of R3. Thus, the gold standard was HRCT or R1 = R2, R1 = R3, or R2 = R3. Results: The sensitivity of the AI system in detecting pleural effusion and consolidation was 100% and 91.3%, respectively. The specificity of the AI system in detecting pleural effusion and lung consolidation was 84% and 61%, respectively. Nevertheless, there is no good agreement between the gold standard and AI in the case of other chest pathologies. Conclusion: Significant moderate agreement with AI and gold standard was shown for pleural effusion and consolidation. There was no significant agreement between the gold standard and AI in the case of the widened mediastinum, collapse, and other pathologies. However, future studies with large sample sizes, multicentric with multiple clinical indications, and radiographic views are recommended.

Molecular cluster analysis using local order parameters selected by machine learning.

Accurately extracting local molecular structures is essential for understanding the mechanisms of phase and structural transitions. A promising method to characterize the local molecular structure is defining the value of the local order parameter (LOP) for each particle. This work develops the Molecular Assembly structure Learning package for Identifying Order parameters (MALIO), a machine learning package that can propose an optimal (set of) LOP(s) quickly and automatically for a huge number of LOP species and various methods of selecting neighboring particles for the calculation. We applied this package to distinguish between the nematic and smectic phases of uniaxial liquid crystal molecules, and selected candidate LOPs that could be used to precisely observe the nematic-smectic phase transition. The LOP candidates were used to observe the nucleation and subsequent percolation transition, and the effect of the choice of LOP species and neighboring particles on the statistics of local molecular structures (clusters) was examined. The procedure revealed the time evolution of the number of clusters and the dependence of the percolation curve on the number of neighboring particles for each LOP species. The LOP species with the lowest dependence on the number of neighboring particles was the best-performing LOP species in the MALIO screening strategy. These results not only show that machine learning can powerfully screen a huge number of LOP species and suggest only a few promising candidates, but also indicate that MALIO can select the best LOP species.

Machine learning versus binomial logistic regression analysis for fall risk based on SPPB scores in older adult outpatients.

To compare the performance of the diagnostic model for fall risk based on the short physical performance battery (SPPB) developed using commercial machine learning software (MLS) and binomial logistic regression analysis (BLRA). We enrolled 797 out of 850 outpatients who visited the clinic between March 2016 and November 2021. Patients were categorized into the development (n = 642) and validation (n = 155) datasets. Age, sex, number of comorbidities, number of medications, body mass index (BMI), calf circumference (left-right average), handgrip strength (left-right average), total SPPB score, and history of falls were determined. We defined fall risk by an SPPB score of ≤6 in men and ≤9 in women. The main metrics used for evaluating the machine learning model and BLRA were the area under the curve (AUC), accuracy, precision, recall (sensitivity), specificity, and F-measure. The commercial MLS automatically calculates the parameter range of the highest contribution. The participants included 797 outpatients (mean age, 76.3 years; interquartile range, 73.0-81.0; 288 men). The metrics of the current diagnostic model in the commercial MLS were as follows: AUC = 0.78, accuracy = 0.74, precision = 0.46, recall (sensitivity) = 0.81, specificity = 0.71, F-measure = 0.59. The metrics of the current diagnostic model in the BLRA were as follows: AUC = 0.77, accuracy = 0.75, precision = 0.47, recall (sensitivity) = 0.67, specificity = 0.77, F-measure = 0.55. The risk factors for falls in older adult outpatients were handgrip strength, female sex, experience of falls, BMI, and calf circumference in the commercial MLS. The diagnostic model for fall risk based on SPPB scores constructed using commercial MLS is noninferior to BLRA.

Using digital photography to monitor changes in biocrusts and ground cover in a savanna rangeland

Biocrusts form a living soil cover in Australia’s northern savannas, delivering essential ecosystem services. More accessible tools are needed to quantify and monitor ground cover, including biocrusts, as current methodologies are time-consuming, expensive, or specialised. At Victoria River Research Station (Northern Territory, Australia), long-term fire research plots were used to monitor the response of low vegetative ground and soil covers for different burning intervals and seasons. Mobile phone photographs were analysed using machine-learning software and a derived decision tree-based segmentation model (DTSM). The resulting data were compared to visual in-field assessment by trained researchers. Visual assessments and photographs were taken at two time points during the post-fire recovery period, mid-wet and dry seasons, at three burning intervals (2, 4, and 6 years) and for two different burning times, early or late dry season. DTSM-derived grass and litter cover were statistically similar to field observations in the burnt and unburnt plots. Biocrust cover derived from DTSM also matched field observations in fire treatments and unburnt control plots in the dry season, except when obscured by grass or litter. In the wet season, DTSM underestimated biocrust cover in some treatments, and DTSM did not detect biocrust obscured under dense grass cover. Nevertheless, biocrust pigment analysis confirmed a significant presence of biocrusts both on seemingly bare soil and under the grass canopy. We concluded that mobile phone photographs are suitable for monitoring dry-season ground cover. When similar colours of grass and litter cover were combined, the modelled accuracy reached 95–97%. With some refinements, DTSM analysis of photographs could accurately quantify the impact of fire disturbance on biocrusts and grass cover. However, it would be advantageous to improve the model by additional field records to determine how much biocrust occurs under the grass. This study provides land managers with an efficient method of recording ground cover over time to aid land-condition assessments.

Indoor environmental quality evaluation of smart/artificial intelligence techniques in buildings – a review

The built environment sector is responsible for around one-third of the world's final energy consumption. Smart technologies play an essential role in strengthening existing regulations and facilitating energy efficiency targets. Smart Buildings allow the response to the external conditions of buildings including grid and climatic conditions, and internal building needs such as user requirements achieved through real-time monitoring and real-time interaction which are resembled the smart buildings concept. The optimal management of occupant comfort plays a crucial role in the built environment since the occupant's productivity and health are highly influenced by Indoor Environmental Quality. This work explores the application of real-time monitoring and interaction to achieve optimal Indoor Environmental Quality, occupant comfort and energy savings in relation to smart buildings and smart technologies. To better address and indoor air quality issues, ventilation needs to become smarter. It is crucial to understand first the Key Performance Indicators of evaluating smart ventilation. In parallel, Artificial Intelligence techniques such as machine and deep learning have been increasingly and successfully applied to develop solutions for the built environment. Thus, this paper provides a review on the existing Key Performance Indicators that allows smart ventilation in smart buildings. Then, it reviews the existing literature on the machine and deep learning methods and software for assessing the smart ventilation. Finally, it shows the most recent technologies for performing experimental evaluation on the main indicators for smart ventilation. This work is expected to highlight the selection of the most optimal ventilation metrics, proper indicators, machine learning and deep learning models and measurement technologies to achieve excellent Indoor Environmental Quality and energy efficiency levels.

Analyze Soil Fertility using Deep Learning Convolutional Neural Networks

This research revolves around how plant soil potential can be further discovered and used for farming through detection of relevant nutrients and chemicals within the soil landscapes within areas and even desert climates and how we can improve land soil fertility of the purpose of farming both using Convolutional neural networks which process of imagery in layers and predictive detections of objects within image backgrounds and frontal lobes. When we view layers for farming beneath the surface to understand suitability of farming done on top. The general model applied can be summarized as follows: As shown In Appendix 1a, we can see the various layers soil has to assess the possibility of nutrient provision for farming [2]. The Objective is to examine availability of plant nutrients using convolution of Nueral networks to classify open farmlands through image analysis and layering. Convolution Nueral networks is divided into four steps starting with input of images, drafting a convolution layer, creating a pooling layer and flattening the Nueral network. It can be performed as a machine learning Algorithmic procedure with Python as well as R programming. CNN divides the images into pixels, edges, frontal lobes and shading through the support of power machine learning libraries and packages like Tensorflow and Keras.