Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge.

Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" - there are a few common findings followed by many more relatively rare conditions. In chest radiography, diagnosis is both a long-tailed and multi-label problem, as patients often present with multiple findings simultaneously. While researchers have begun to study the problem of long-tailed learning in medical image recognition, few have studied the interaction of label imbalance and label co-occurrence posed by long-tailed, multi-label disease classification. To engage with the research community on this emerging topic, we conducted an open challenge, CXR-LT, on long-tailed, multi-label thorax disease classification from chest X-rays (CXRs). We publicly release a large-scale benchmark dataset of over 350,000 CXRs, each labeled with at least one of 26 clinical findings following a long-tailed distribution. We synthesize common themes of top-performing solutions, providing practical recommendations for long-tailed, multi-label medical image classification. Finally, we use these insights to propose a path forward involving vision-language foundation models for few- and zero-shot disease classification.

Incorporation of water quality index models with machine learning-based techniques for real-time assessment of aquatic ecosystems.

Water quality index (WQI) is a well-established tool for assessing the overall quality of fresh inland-waters. However, the effectiveness of real-time assessment of aquatic ecosystems using the WQI is usually impacted by the absence of some water quality parameters in which their accurately in-situ measurements are impossible and face difficulties. Using a rich water quality dataset spanned from 1980 to 2023, we employed four machine learning-based models to estimate the British Colombia WQI (BCWQI) in the Lake Päijänne, Finland, without parameters like chemical oxygen demand (COD) and total phosphorus (TP). Measurement of both COD and TP is time-consuming, needs laboratory equipment and labor costs, and faces sampling-related difficulties. Our results suggest the machine learning-based models successfully estimate the BCWQI in Lake Päijänne when TP and COD are omitted from the dataset. The long-short term memory model is the least sensitive model to exclusion of COD and TP from inputs. This model with the coefficient of determination and root-mean squared error of 0.91 and 0.11, respectively, outperforms the support vector regression, random forest, and neural network models in real-time estimation of the BCWQI in Lake Päijänne. Incorporation of BCWQI with the machine learning-based models could enhance assessment of overall quality of inland-waters with a limited database in a more economical and time-saving way. Our proposed method is an effort to replace the traditional offline water quality assessment tools with a real-time model and improve understanding of decision-makers on the effectiveness of management practices on the changes in lake water quality.

Comparative study for coastal aquifer vulnerability assessment using deep learning and metaheuristic algorithms.

Coastal aquifer vulnerability assessment (CAVA) studies are essential for mitigating the effects of seawater intrusion (SWI) worldwide. In this research, the vulnerability of the coastal aquifer in the Lahijan region of northwest Iran was investigated. A vulnerability map (VM) was created applying hydrogeological parameters derived from the original GALDIT model (OGM). The significance of OGM parameters was assessed using the mean decrease accuracy (MDA) method, with the current state of SWI emerging as the most crucial factor for evaluating vulnerability. To optimize GALDIT weights, we introduced the biogeography-based optimization (BBO) and gray wolf optimization (GWO) techniques to obtain to hybrid OGM-BBO and OGM-GWO models, respectively. Despite considerable research focused on enhancing CAVA models, efforts to modify the weights and rates of OGM parameters by incorporating deep learning algorithms remain scarce. Hence, a convolutional neural network (CNN) algorithm was applied to produce the VM. The area under the receiver-operating characteristic curves for OGM-BBO, OGM-GWO, and VMCNN were 0.794, 0.835, and 0.982, respectively. According to the CNN-based VM, 41% of the aquifer displayed very high and high vulnerability to SWI, concentrated primarily along the coastline. Additionally, 32% of the aquifer exhibited very low and low vulnerability to SWI, predominantly in the southern and southwestern regions. The proposed model can be extended to evaluate the vulnerability of various coastal aquifers to SWI, thereby assisting land use planers and policymakers in identifying at-risk areas. Moreover, deep-learning-based approaches can help clarify the associations between aquifer vulnerability and contamination resulting from SWI.

Improving the prediction of wildfire susceptibility on Hawai'i Island, Hawai'i, using explainable hybrid machine learning models.

This study presents a comparative analysis of four Machine Learning (ML) models used to map wildfire susceptibility on Hawai'i Island, Hawai'i. Extreme Gradient Boosting (XGBoost) combined with three meta-heuristic algorithms - Whale Optimization (WOA), Black Widow Optimization (BWO), and Butterfly Optimization (BOA) - were employed to map areas susceptible to wildfire. To generate a wildfire inventory, 1408 wildfire points were identified within the study area from 2004 to 2022. The four ML models (XGBoost, WOA-XGBoost, BWO-XGBoost, and BOA-XGBoost) were run using 14 wildfire-conditioning factors categorized into four main groups: topographical, meteorological, vegetation, and anthropogenic. Six performance metrics - sensitivity, specificity, positive predictive values, negative predictive values, the Area Under the receiver operating characteristic Curve (AUC), and the average precision (AP) of Precision-Recall Curves (PRCs) - were used to compare the predictive performance of the ML models. The SHapley Additive exPlanations (SHAP) framework was also used to interpret the importance values of the 14 influential variables for the modeling of wildfire on Hawai'i Island using the four models. The results of the wildfire modeling indicated that all four models performed well, with the BWO-XGBoost model exhibiting a slightly higher prediction performance (AUC = 0.9269), followed by WOA-XGBoost (AUC = 0.9253), BOA-XGBoost (AUC = 0.9232), and XGBoost (AUC = 0.9164). SHAP analysis revealed that the distance from a road, annual temperature, and elevation were the most influential factors. The wildfire susceptibility maps generated in this study can be used by local authorities for wildfire management and fire suppression activity.

Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge.

Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" - there are a few common findings followed by many more relatively rare conditions. In chest radiography, diagnosis is both a long-tailed and multi-label problem, as patients often present with multiple findings simultaneously. While researchers have begun to study the problem of long-tailed learning in medical image recognition, few have studied the interaction of label imbalance and label co-occurrence posed by long-tailed, multi-label disease classification. To engage with the research community on this emerging topic, we conducted an open challenge, CXR-LT, on long-tailed, multi-label thorax disease classification from chest X-rays (CXRs). We publicly release a large-scale benchmark dataset of over 350,000 CXRs, each labeled with at least one of 26 clinical findings following a long-tailed distribution. We synthesize common themes of top-performing solutions, providing practical recommendations for long-tailed, multi-label medical image classification. Finally, we use these insights to propose a path forward involving vision-language foundation models for few- and zero-shot disease classification.

Development of global monthly dataset of CMIP6 climate variables for estimating evapotranspiration.

Reliable projection of evapotranspiration (ET) is important for planning sustainable water management for the agriculture field in the context of climate change. A global dataset of monthly climate variables was generated to estimate potential ET (PET) using 14 General Circulation Models (GCMs) for four main shared socioeconomic pathways (SSPs). The generated dataset has a spatial resolution of 0.5° × 0.5° and a period ranging from 1950 to 2100 and can estimate historical and future PET using the Penman-Monteith method. Furthermore, this dataset can be applied to various PET estimation methods based on climate variables. This paper presents that the dataset generated to estimate future PET could reflect the greenhouse gas concentration level of the SSP scenarios in latitude bands. Therefore, this dataset can provide vital information for users to select appropriate GCMs for estimating reasonable PETs and help determine bias correction methods to reduce between observation and model based on the scale of climate variables in each GCM.

Cell type specific IL-27p28 (IL-30) deletion in mice uncovers an unexpected regulatory function of IL-30 in autoimmune inflammation.

IL-27 is an IL-12 family cytokine with immune regulatory properties, capable of modulating inflammatory responses, including autoimmunity. While extensive studies investigated the major target cells of IL-27 mediating its functions, the source of IL-27 especially during tissue specific autoimmune inflammation has not formally been examined. IL-27p28 subunit, also known as IL-30, was initially discovered as an IL-27-specific subunit, and it has thus been deemed as a surrogate marker to denote IL-27 expression. However, IL-30 can be secreted independently of Ebi3, a subunit that forms bioactive IL-27 with IL-30. Moreover, IL-30 itself may act as a negative regulator antagonizing IL-27. In this study, we exploited various cell type specific IL-30-deficient mouse models and examined the source of IL-30 in a T cell mediated autoimmune neuroinflammation. We found that IL-30 expressed by infiltrating and CNS resident APC subsets, infiltrating myeloid cells and microglia, is central in limiting the inflammation. However, dendritic cell-derived IL-30 was dispensable for the disease development. Unexpectedly, in cell type specific IL-30 deficient mice that develop severe EAE, IL-30 expression in the remaining wild-type APC subsets is disproportionately increased, suggesting that increased endogenous IL-30 production may be involved in the severe pathogenesis. In support, systemic recombinant IL-30 administration exacerbates EAE severity. Our results demonstrate that dysregulated endogenous IL-30 expression may interfere with immune regulatory functions of IL-27, promoting encephalitogenic inflammation in vivo.

Lymphocyte activation gene 3 (Lag3) supports Foxp3 + Treg cell function by restraining c-Myc-dependent aerobic glycolysis.

Lymphocyte activation gene 3 (Lag3) has emerged as the next-generation immune checkpoint molecule due to its ability to inhibit effector T cell activity. Foxp3 + regulatory T (Treg) cells, a master regulator of immunity and tolerance, also highly express Lag3. While Lag3 is thought to be necessary for Treg cell-mediated regulation of immunity, the precise roles and underlying mechanisms remain largely elusive. In this study, we report that Lag3 is indispensable for Treg cells to control autoimmune inflammation. Utilizing a newly generated Treg cell specific Lag3 mutant mouse model, we found that these animals are highly susceptible to autoimmune diseases, suggesting defective Treg cell function. Genome wide transcriptome analysis further uncovered that Lag3 mutant Treg cells upregulated genes involved in metabolic processes. Mechanistically, we found that Lag3 limits Treg cell expression of Myc, a key regulator of aerobic glycolysis. We further found that Lag3-dependent Myc expression determines Treg cells’ metabolic programming as well as the in vivo function to suppress autoimmune inflammation. Taken together, our results uncovered a novel function of Lag3 in supporting Treg cell suppressive function by regulating Myc-dependent metabolic programming.

IFN-Induced Protein with Tetratricopeptide Repeats 2 Limits Autoimmune Inflammation by Regulating Myeloid Cell Activation and Metabolic Activity.

Besides antiviral functions, type I IFN expresses potent anti-inflammatory properties and is being widely used to treat certain autoimmune conditions, such as multiple sclerosis. In a murine model of multiple sclerosis, experimental autoimmune encephalomyelitis, administration of IFN-ß effectively attenuates the disease development. However, the precise mechanisms underlying IFN-ß-mediated treatment remain elusive. In this study, we report that IFN-induced protein with tetratricopeptide repeats 2 (Ifit2), a type I and type III IFN-stimulated gene, plays a previously unrecognized immune-regulatory role during autoimmune neuroinflammation. Mice deficient in Ifit2 displayed greater susceptibility to experimental autoimmune encephalomyelitis and escalated immune cell infiltration in the CNS. Ifit2 deficiency was also associated with microglial activation and increased myeloid cell infiltration. We also observed that myelin debris clearance and the subsequent remyelination were substantially impaired in Ifit2-/- CNS tissues. Clearing myelin debris is an important function of the reparative-type myeloid cell subset to promote remyelination. Indeed, we observed that bone marrow-derived macrophages, CNS-infiltrating myeloid cells, and microglia from Ifit2-/- mice express cytokine and metabolic genes associated with proinflammatory-type myeloid cell subsets. Taken together, our findings uncover a novel regulatory function of Ifit2 in autoimmune inflammation in part by modulating myeloid cell function and metabolic activity.

Highly Sensitive and Reliable Piezoresistive Strain Sensor Based on Cobalt Nanoporous Carbon-Incorporated Laser-Induced Graphene for Smart Healthcare Wearables.

The development of highly sensitive, reliable, and cost-effective strain sensors is a big challenge for wearable smart electronics and healthcare applications, such as soft robotics, point-of-care systems, and electronic skins. In this study, we newly fabricated a highly sensitive and reliable piezoresistive strain sensor based on polyhedral cobalt nanoporous carbon (Co-NPC)-incorporated laser-induced graphene (LIG) for wearable smart healthcare applications. The synergistic integration of Co-NPC and LIG enables the performance improvement of the strain sensor by providing an additional conductive pathway and robust mechanical properties with a high surface area of Co-NPC nanoparticles. The proposed porous graphene nanosheets exploited with Co-NPC nanoparticles demonstrated an outstanding sensitivity of 1,177 up to a strain of 18%, which increased to 39,548 beyond 18%. Additionally, the fabricated sensor exhibited an ultralow limit of detection (0.02%) and excellent stability over 20,000 cycles even under high strain conditions (10%). Finally, we successfully demonstrated and evaluated the sensor performance for practical use in healthcare wearables by monitoring wrist pulse, neck pulse, and joint flexion movement. Owing to the outstanding performance of the sensor, the fabricated sensor has great potential in electronic skins, human-machine interactions, and soft robotics applications.

Hysteresis-Free Double-Network Hydrogel-Based Strain Sensor for Wearable Smart Bioelectronics.

Hydrogel-based electronics have attracted substantial attention in the field of biological engineering, energy storage devices, and soft actuators due to their resemblance to living tissues, biocompatibility, tunable softness, and consolidated structures. However, combining the properties of quick resilience, hysteresis-free, and robust mechanical properties in physically cross-linked hydrogels is still a great challenge. Herein, we present a vinyl hybrid silica nanoparticle (VSNPs)/polyacrylamide (PAAm)/alginate double-network hydrogel-based strain sensor with the characteristics of quick resilience, hysteresis-free, and a low limit of detection (LOD). The physical cross-linking among PAAm chains and covalent cross-linking between PAAm, alginate, and N,N-methylenebisacrylamide chains promotes excellent mechanical properties. Moreover, the incorporation of VSNPs reinforces the mechanical strength by the dynamic cross-linking of the PAAm network to maintain the integrity of the hydrogel and works as a stress buffer to dissipate energy. The as-prepared hydrogel-based sensor exhibits a strain sensitivity (i.e., gauge factor) of 1.73 (up to 100% strain), a response time of 0.16 s, an ultra-low electrical hysteresis of 2.43%, and a low LOD of 0.4%. The outstanding properties of the hydrogel are further used to illustrate the utility of the sensor in e-skin, ranging from low-strain applications, such as carotid pulse and artificial sound detection, to large bending applications, such as sign language translations. In addition, an efficient and cost-effective synthesis of double-network hydrogel that can overcome the bottleneck of the electromechanical properties of single network hydrogel has potential prospects in soft actuators, tissue engineering, and various biomedical applications.

Tissue Resident Foxp3+ Regulatory T Cells: Sentinels and Saboteurs in Health and Disease.

Foxp3+ regulatory T (Treg) cells are a CD4 T cell subset with unique immune regulatory function that are indispensable in immunity and tolerance. Their indisputable importance has been investigated in numerous disease settings and experimental models. Despite the extensive efforts in determining the cellular and molecular mechanisms operating their functions, our understanding their biology especially in vivo remains limited. There is emerging evidence that Treg cells resident in the non-lymphoid tissues play a central role in regulating tissue homeostasis, inflammation, and repair. Furthermore, tissue-specific properties of those Treg cells that allow them to express tissue specific functions have been explored. In this review, we will discuss the potential mechanisms and key cellular/molecular factors responsible for the homeostasis and functions of tissue resident Treg cells under steady-state and inflammatory conditions.

Machine learning-based diagnosis and risk factor analysis of cardiocerebrovascular disease based on KNHANES.

The prevalence of cardiocerebrovascular disease (CVD) is continuously increasing, and it is the leading cause of human death. Since it is difficult for physicians to screen thousands of people, high-accuracy and interpretable methods need to be presented. We developed four machine learning-based CVD classifiers (i.e., multi-layer perceptron, support vector machine, random forest, and light gradient boosting) based on the Korea National Health and Nutrition Examination Survey. We resampled and rebalanced KNHANES data using complex sampling weights such that the rebalanced dataset mimics a uniformly sampled dataset from overall population. For clear risk factor analysis, we removed multicollinearity and CVD-irrelevant variables using VIF-based filtering and the Boruta algorithm. We applied synthetic minority oversampling technique and random undersampling before ML training. We demonstrated that the proposed classifiers achieved excellent performance with AUCs over 0.853. Using Shapley value-based risk factor analysis, we identified that the most significant risk factors of CVD were age, sex, and the prevalence of hypertension. Additionally, we identified that age, hypertension, and BMI were positively correlated with CVD prevalence, while sex (female), alcohol consumption and, monthly income were negative. The results showed that the feature selection and the class balancing technique effectively improve the interpretability of models.

Multifunctional hybrid skin patch for wearable smart healthcare applications.

Recent advances in wearable patches have included various sensors to monitor either physiological signs, such as the heart rate and respiration rate, or metabolites. Nevertheless, most of these have focused only on a single physiological measurement at a time, which significantly inhibits the calibration of various biological signals and diagnostic facilities. In this study, a novel multifunctional hybrid skin patch was developed for the electrochemical analysis of sweat glucose levels and simultaneous monitoring of electrocardiograms (ECGs). Furthermore, pH and temperature sensors were co-integrated onto the same patch for the calibration of the glucose biosensor to prevent inevitable inhibition and weakening of enzyme activity due to changes in the sweat pH and temperature levels. The fabricated electrochemical glucose biosensor exhibited excellent linearity (R2 = 0.9986) and sensitivity (29.10 µA mM-1 cm-2), covering the normal range of human sweat. The potentiometric pH sensor displayed a good response with an excellent sensitivity of -77.81 mV/pH and high linearity (R2 = 0.991), indicating that it can distinguish variations in the typical pH range for human sweat. Furthermore, the P, QRS complex, and T peaks in the measured ECG waveforms could be clearly distinguished, indicating the reliability of the fabricated flexible dry electrodes for continuous monitoring. The fabricated skin patch overcomes the inconvenience of the mandatory attachment of multiple patches on the human body by fully integrating all the electrochemical and electrophysiological sensors on a single patch, thus facilitating advanced glycemic control and continuous ECG monitoring for smart management of chronic diseases and healthcare applications.

Artificial intelligence model comparison for risk factor analysis of patent ductus arteriosus in nationwide very low birth weight infants cohort.

Despite the many comorbidities and high mortality rate in preterm infants with patent ductus arteriosus (PDA), therapeutic strategies vary depending on the clinical setting, and most studies of the related risk factors are based on small sample populations. We aimed to compare the performance of artificial intelligence (AI) analysis with that of conventional analysis to identify risk factors associated with symptomatic PDA (sPDA) in very low birth weight infants. This nationwide cohort study included 8369 very low birth weight (VLBW) infants. The participants were divided into an sPDA group and an asymptomatic PDA or spontaneously close PDA (nPDA) group. The sPDA group was further divided into treated and untreated subgroups. A total of 47 perinatal risk factors were collected and analyzed. Multiple logistic regression was used as a standard analytic tool, and five AI algorithms were used to identify the factors associated with sPDA. Combining a large database of risk factors from nationwide registries and AI techniques achieved higher accuracy and better performance of the PDA prediction tasks, and the ensemble methods showed the best performances.

Cutting Edge: Steroid Responsiveness in Foxp3+ Regulatory T Cells Determines Steroid Sensitivity during Allergic Airway Inflammation in Mice.

Glucocorticoids are a highly effective first-line treatment option for many inflammatory diseases, including asthma. Some patients develop a steroid-resistant condition, yet, the cellular and molecular mechanisms underlying steroid resistance remain largely unknown. In this study, we used a murine model of steroid-resistant airway inflammation and report that combining systemic dexamethasone and intranasal IL-27 is able to reverse the inflammation. Foxp3+ regulatory T cells (Tregs) were required during dexamethasone/IL-27 treatment of steroid-resistant allergic inflammation, and importantly, direct stimulation of Tregs via glucocorticoid or IL-27 receptors was essential. Mechanistically, IL-27 stimulation in Tregs enhanced expression of the agonistic glucocorticoid receptor-α isoform. Overexpression of inhibitory glucocorticoid receptor-ß isoform in Tregs alone was sufficient to elicit steroid resistance in a steroid-sensitive allergic inflammation model. Taken together, our results demonstrate for the first time, to our knowledge, that Tregs are instrumental during steroid resistance and that manipulating steroid responsiveness in Tregs may represent a novel strategy to treat steroid refractory asthma.

Automatic Classification of the Korean Triage Acuity Scale in Simulated Emergency Rooms Using Speech Recognition and Natural Language Processing: a Proof of Concept Study.

BACKGROUND: Rapid triage reduces the patients' stay time at an emergency department (ED). The Korean Triage Acuity Scale (KTAS) is mandatorily applied at EDs in South Korea. For rapid triage, we studied machine learning-based triage systems composed of a speech recognition model and natural language processing-based classification. METHODS: We simulated 762 triage cases that consisted of 18 classes with six types of the main symptom (chest pain, dyspnea, fever, stroke, abdominal pain, and headache) and three levels of KTAS. In addition, we recorded conversations between emergency patients and clinicians during the simulation. We used speech recognition models to transcribe the conversation. Bidirectional Encoder Representation from Transformers (BERT), support vector machine (SVM), random forest (RF), and k-nearest neighbors (KNN) were used for KTAS and symptom classification. Additionally, we evaluated the Shapley Additive exPlanations (SHAP) values of features to interpret the classifiers. RESULTS: The character error rate of the speech recognition model was reduced to 25.21% through transfer learning. With auto-transcribed scripts, support vector machine (area under the receiver operating characteristic curve [AUROC], 0.86; 95% confidence interval [CI], 0.81-0.9), KNN (AUROC, 0.89; 95% CI, 0.85-0.93), RF (AUROC, 0.86; 95% CI, 0.82-0.9) and BERT (AUROC, 0.82; 95% CI, 0.75-0.87) achieved excellent classification performance. Based on SHAP, we found "stress", "pain score point", "fever", "breath", "head" and "chest" were the important vocabularies for determining KTAS and symptoms. CONCLUSION: We demonstrated the potential of an automatic KTAS classification system using speech recognition models, machine learning and BERT-based classifiers.

IL-30† (IL-27A): a familiar stranger in immunity, inflammation, and cancer.

Over the years, interleukin (IL)-27 has received much attention because of its highly divergent, sometimes even opposing, functions in immunity. IL-30, the p28 subunit that forms IL-27 together with Ebi3 and is also known as IL-27p28 or IL-27A, has been considered a surrogate to represent IL-27. However, it was later discovered that IL-30 can form complexes with other protein subunits, potentially leading to overlapping or discrete functions. Furthermore, there is emerging evidence that IL-30 itself may perform immunomodulatory functions independent of Ebi3 or other binding partners and that IL-30 production is strongly associated with certain cancers in humans. In this review, we will discuss the biology of IL-30 and other IL-30-associated cytokines and their functions in inflammation and cancer.

SPICE-IT: Smart COVID-19 pandemic controlled eradication over NDN-IoT.

Internet of things (IoT) application in e-health can play a vital role in countering rapidly spreading diseases that can effectively manage health emergency scenarios like pandemics. Efficient disease control also requires monitoring of Standard operating procedure (SOP) follow-up of the population in the disease-prone area with a cost-effective reporting and responding mechanism to register any violation. However, the IoT devices have limited resources and the application requires delay-sensitive data transmission. Named Data Networking (NDN) can significantly reduce content retrieval delays but inherits cache overflow and network congestion challenges. Therefore, we are motivated to present a novel smart COVID-19 pandemic-controlled eradication over NDN-IoT (SPICE-IT) mechanism. SPICE-IT introduces autonomous monitoring in indoor environments with efficient pull-based reporting mechanism that records violations at local servers and cloud server. Intelligent face mask detection and temperature monitoring mechanism examines every person. Cloud server controls the response action from the centre with an adaptive decision-making mechanism. Long short-term memory (LSTM) based caching mechanism reduces the cache overflow and overall network congestion problem.

Towards Energy Efficient Home Automation: A Deep Learning Approach.

Home Automation Systems (HAS) attracted much attention during the last decade due to the developments in new wireless technologies, such as Bluetooth 4.0, 5G, WiFi 6, etc. In order to enable automation as a service in smart homes, a number of challenges must be addressed, such as fulfilling the electrical energy demands, scheduling the operational time of appliances, applying machine learning models in real-time, optimal human appliances interaction, etc. In order to address the aforementioned challenges and control the wastage of energy due to the lifestyle of the home users, we propose a system for automatically controlling the energy consumption by employing machine and deep learning techniques to smart home networks. The proposed system works in three phases, (1) feature extraction and classification based on 1-dimensional Deep Convolutional Neural Network (1D-DCNN) which extract important energy patterns from the historic energy data, (2) a load forecasting system based on Long-short Term Memory (LSTM) is proposed to forecast the load based on the extracted features in phase 1 and (3) a scheduling algorithm based on the forecasted data obtained from phase 2 is designed to schedule the operational time of smart home appliances. The proposed scheme efficiently automates the smart home appliances to consume less energy while adapting to the lifestyle of smart home users. The validation of the proposed scheme is tested with a number of simulation scenarios incorporating datasets from authentic data sources. The simulation results show that the proposed smart home automation system can be a game-changer in fulfilling the energy demands of the home users without installing renewable and other energy sources in the future.