Real-Time Detection and Instance Segmentation of Strawberry in Unstructured Environment

The real-time detection and instance segmentation of strawberries constitute fundamental components in the development of strawberry harvesting robots.Real-time identification of strawberries in an unstructured envi-ronment is a challenging task.Current instance segmentation algorithms for strawberries suffer from issues such as poor real-time performance and low accuracy.To this end,the present study proposes an Efficient YOLACT(E-YOLACT)algorithm for strawberry detection and segmentation based on the YOLACT framework.The key enhancements of the E-YOLACT encompass the development of a lightweight attention mechanism,pyramid squeeze shuffle attention(PSSA),for efficient feature extraction.Additionally,an attention-guided context-feature pyramid network(AC-FPN)is employed instead of FPN to optimize the architecture’s performance.Furthermore,a feature-enhanced model(FEM)is introduced to enhance the prediction head’s capabilities,while efficient fast non-maximum suppression(EF-NMS)is devised to improve non-maximum suppression.The experimental results demonstrate that the E-YOLACT achieves a Box-mAP and Mask-mAP of 77.9 and 76.6,respectively,on the custom dataset.Moreover,it exhibits an impressive category accuracy of 93.5%.Notably,the E-YOLACT also demonstrates a remarkable real-time detection capability with a speed of 34.8 FPS.The method proposed in this article presents an efficient approach for the vision system of a strawberry-picking robot.

Real-Time Object Detection and Face Recognition Application for the Visually Impaired

The advancement of navigation systems for the visually impaired has significantly enhanced their mobility by mitigating the risk of encountering obstacles and guiding them along safe,navigable routes.Traditional approaches primarily focus on broad applications such as wayfinding,obstacle detection,and fall prevention.However,there is a notable discrepancy in applying these technologies to more specific scenarios,like identifying distinct food crop types or recognizing faces.This study proposes a real-time application designed for visually impaired individuals,aiming to bridge this research-application gap.It introduces a system capable of detecting 20 different food crop types and recognizing faces with impressive accuracies of 83.27%and 95.64%,respectively.These results represent a significant contribution to the field of assistive technologies,providing visually impaired users with detailed and relevant information about their surroundings,thereby enhancing their mobility and ensuring their safety.Additionally,it addresses the vital aspects of social engagements,acknowledging the challenges faced by visually impaired individuals in recognizing acquaintances without auditory or tactile signals,and highlights recent developments in prototype systems aimed at assisting with face recognition tasks.This comprehensive approach not only promises enhanced navigational aids but also aims to enrich the social well-being and safety of visually impaired communities.

Analyzing the Impact of Scene Transitions on Indoor Camera Localization through Scene Change Detection in Real-Time

Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.

A YOLOv8-CE-based real-time traffic sign detection and identification method for autonomous vehicles

Traffic sign detection in real scenarios is challenging due to their complexity and small size,often preventing existing deep learning models from achieving both high accuracy and real-time performance.An improved YOLOv8 model for traffic sign detection is proposed.Firstly,by adding Coordinate Attention(CA)to the Backbone,the model gains location information,improving detection accuracy.Secondly,we also introduce EIoU to the localization function to address the ambiguity in aspect ratio descriptions by calculating the width-height difference based on CIoU.Additionally,Focal Loss is incorporated to balance sample difficulty,enhancing regression accuracy.Finally,the model,YOLOv8-CE(YOLOv8-Coordinate Attention-EIoU),is tested on the Jetson Nano,achieving real-time street scene detection and outperforming the Raspberry Pi 4B.Experimental results show that YOLOv8-CE excels in various complex scenarios,improving mAP by 2.8%over the original YOLOv8.The model size and computational effort remain similar,with the Jetson Nano achieving an inference time of 96 ms,significantly faster than the Raspberry Pi 4B.

A CNN-Based Single-Stage Occlusion Real-Time Target Detection Method

Aiming at the problem of low accuracy of traditional target detection methods for target detection in endoscopes in substation environments, a CNN-based real-time detection method for masked targets is proposed. The method adopts the overall design of backbone network, detection network and algorithmic parameter optimisation method, completes the model training on the self-constructed occlusion target dataset, and adopts the multi-scale perception method for target detection. The HNM algorithm is used to screen positive and negative samples during the training process, and the NMS algorithm is used to post-process the prediction results during the detection process to improve the detection efficiency. After experimental validation, the obtained model has the multi-class average predicted value (mAP) of the dataset. It has general advantages over traditional target detection methods. The detection time of a single target on FDDB dataset is 39 ms, which can meet the need of real-time target detection. In addition, the project team has successfully deployed the method into substations and put it into use in many places in Beijing, which is important for achieving the anomaly of occlusion target detection.

A Novel Fall Detection Framework Using Skip-DSCGAN Based on Inertial Sensor Data

With the widespread use of Internet of Things(IoT)technology in daily life and the considerable safety risks of falls for elderly individuals,research on IoT-based fall detection systems has gainedmuch attention.This paper proposes an IoT-based spatiotemporal data processing framework based on a depthwise separable convolution generative adversarial network using skip-connection(Skip-DSCGAN)for fall detection.The method uses spatiotemporal data from accelerometers and gyroscopes in inertial sensors as input data.A semisupervised learning approach is adopted to train the model using only activities of daily living(ADL)data,which can avoid data imbalance problems.Furthermore,a quantile-based approach is employed to determine the fall threshold,which makes the fall detection frameworkmore robust.This proposed fall detection framework is evaluated against four other generative adversarial network(GAN)models with superior anomaly detection performance using two fall public datasets(SisFall&MobiAct).The test results show that the proposed method achieves better results,reaching 96.93% and 92.75% accuracy on the above two test datasets,respectively.At the same time,the proposed method also achieves satisfactory results in terms ofmodel size and inference delay time,making it suitable for deployment on wearable devices with limited resources.In addition,this paper also compares GAN-based semisupervised learning methods with supervised learning methods commonly used in fall detection.It clarifies the advantages of GAN-based semisupervised learning methods in fall detection.

A Double-Interactively Recurrent Fuzzy Cerebellar Model Articulation Controller Model Combined with an Improved Particle Swarm Optimization Method for Fall Detection

In many Eastern and Western countries,falling birth rates have led to the gradual aging of society.Older adults are often left alone at home or live in a long-term care center,which results in them being susceptible to unsafe events(such as falls)that can have disastrous consequences.However,automatically detecting falls fromvideo data is challenging,and automatic fall detection methods usually require large volumes of training data,which can be difficult to acquire.To address this problem,video kinematic data can be used as training data,thereby avoiding the requirement of creating a large fall data set.This study integrated an improved particle swarm optimization method into a double interactively recurrent fuzzy cerebellar model articulation controller model to develop a costeffective and accurate fall detection system.First,it obtained an optical flow(OF)trajectory diagram from image sequences by using the OF method,and it solved problems related to focal length and object offset by employing the discrete Fourier transform(DFT)algorithm.Second,this study developed the D-IRFCMAC model,which combines spatial and temporal(recurrent)information.Third,it designed an IPSO(Improved Particle Swarm Optimization)algorithm that effectively strengthens the exploratory capabilities of the proposed D-IRFCMAC(Double-Interactively Recurrent Fuzzy Cerebellar Model Articulation Controller)model in the global search space.The proposed approach outperforms existing state-of-the-art methods in terms of action recognition accuracy on the UR-Fall,UP-Fall,and PRECIS HAR data sets.The UCF11 dataset had an average accuracy of 93.13%,whereas the UCF101 dataset had an average accuracy of 92.19%.The UR-Fall dataset had an accuracy of 100%,the UP-Fall dataset had an accuracy of 99.25%,and the PRECIS HAR dataset had an accuracy of 99.07%.

LDA-ID:An LDA-Based Framework for Real-Time Network Intrusion Detection

Network intrusion poses a severe threat to the Internet.However,existing intrusion detection models cannot effectively distinguish different intrusions with high-degree feature overlap.In addition,efficient real-time detection is an urgent problem.To address the two above problems,we propose a Latent Dirichlet Allocation topic model-based framework for real-time network Intrusion Detection(LDA-ID),consisting of static and online LDA-ID.The problem of feature overlap is transformed into static LDA-ID topic number optimization and topic selection.Thus,the detection is based on the latent topic features.To achieve efficient real-time detection,we design an online computing mode for static LDA-ID,in which a parameter iteration method based on momentum is proposed to balance the contribution of prior knowledge and new information.Furthermore,we design two matching mechanisms to accommodate the static and online LDA-ID,respectively.Experimental results on the public NSL-KDD and UNSW-NB15 datasets show that our framework gets higher accuracy than the others.

Portable FBAR based E-nose for cold chain real-time bananas shelf time detection

Being cheap,nondestructive,and easy to use,gas sensors play important roles in the food industry.However,most gas sensors are suitable more for laboratory-quality fast testing rather than for cold-chain continuous and cumulative testing.Also,an ideal electronic nose(E-nose)in a cold chain should be stable to its surroundings and remain highly accurate and portable.In this work,a portable film bulk acoustic resonator(FBAR)-based E-nose was built for real-time measurement of banana shelf time.The sensor chamber to contain the portable circuit of the E-nose is as small as a smartphone,and by introducing an air-tight FBAR as a reference,the E-nose can avoid most of the drift caused by surroundings.With the help of porous layer by layer(LBL)coating of the FBAR,the sensitivity of the E-nose is 5 ppm to ethylene and 0.5 ppm to isoamyl acetate and isoamyl butyrate,while the detection range is large enough to cover a relative humidity of 0.8.In this regard,the E-nose can easily discriminate between yellow bananas with green necks and entirely yellow bananas while allowing the bananas to maintain their biological activities in their normal storage state,thereby showing the possibility of real-time shelf time detection.This portable FBAR-based E-nose has a large testing scale,high sensitivity,good humidity tolerance,and low frequency drift to its surroundings,thereby meeting the needs of cold-chain usage.

Force Sensitive Resistors-Based Real-Time Posture Detection System Using Machine Learning Algorithms

To detect the improper sitting posture of a person sitting on a chair,a posture detection system using machine learning classification has been proposed in this work.The addressed problem correlates to the third Sustainable Development Goal(SDG),ensuring healthy lives and promoting well-being for all ages,as specified by the World Health Organization(WHO).An improper sitting position can be fatal if one sits for a long time in the wrong position,and it can be dangerous for ulcers and lower spine discomfort.This novel study includes a practical implementation of a cushion consisting of a grid of 3×3 force-sensitive resistors(FSR)embedded to read the pressure of the person sitting on it.Additionally,the Body Mass Index(BMI)has been included to increase the resilience of the system across individual physical variances and to identify the incorrect postures(backward,front,left,and right-leaning)based on the five machine learning algorithms:ensemble boosted trees,ensemble bagged trees,ensemble subspace K-Nearest Neighbors(KNN),ensemble subspace discriminant,and ensemble RUSBoosted trees.The proposed arrangement is novel as existing works have only provided simulations without practical implementation,whereas we have implemented the proposed design in Simulink.The results validate the proposed sensor placements,and the machine learning(ML)model reaches a maximum accuracy of 99.99%,which considerably outperforms the existing works.The proposed concept is valuable as it makes it easier for people in workplaces or even at individual household levels to work for long periods without suffering from severe harmful effects from poor posture.

Towards Cache-Assisted Hierarchical Detection for Real-Time Health Data Monitoring in IoHT

Real-time health data monitoring is pivotal for bolstering road services’safety,intelligence,and efficiency within the Internet of Health Things(IoHT)framework.Yet,delays in data retrieval can markedly hinder the efficacy of big data awareness detection systems.We advocate for a collaborative caching approach involving edge devices and cloud networks to combat this.This strategy is devised to streamline the data retrieval path,subsequently diminishing network strain.Crafting an adept cache processing scheme poses its own set of challenges,especially given the transient nature of monitoring data and the imperative for swift data transmission,intertwined with resource allocation tactics.This paper unveils a novel mobile healthcare solution that harnesses the power of our collaborative caching approach,facilitating nuanced health monitoring via edge devices.The system capitalizes on cloud computing for intricate health data analytics,especially in pinpointing health anomalies.Given the dynamic locational shifts and possible connection disruptions,we have architected a hierarchical detection system,particularly during crises.This system caches data efficiently and incorporates a detection utility to assess data freshness and potential lag in response times.Furthermore,we introduce the Cache-Assisted Real-Time Detection(CARD)model,crafted to optimize utility.Addressing the inherent complexity of the NP-hard CARD model,we have championed a greedy algorithm as a solution.Simulations reveal that our collaborative caching technique markedly elevates the Cache Hit Ratio(CHR)and data freshness,outshining its contemporaneous benchmark algorithms.The empirical results underscore the strength and efficiency of our innovative IoHT-based health monitoring solution.To encapsulate,this paper tackles the nuances of real-time health data monitoring in the IoHT landscape,presenting a joint edge-cloud caching strategy paired with a hierarchical detection system.Our methodology yields enhanced cache efficiency and data freshness.The corroborative numerical data accentuates the feasibility and relevance of our model,casting a beacon for the future trajectory of real-time health data monitoring systems.

Enhancing Fire Detection Performance Based on Fine-Tuned YOLOv10

In recent years,early detection and warning of fires have posed a significant challenge to environmental protection and human safety.Deep learning models such as Faster R-CNN(Faster Region based Convolutional Neural Network),YOLO(You Only Look Once),and their variants have demonstrated superiority in quickly detecting objects from images and videos,creating new opportunities to enhance automatic and efficient fire detection.The YOLO model,especially newer versions like YOLOv10,stands out for its fast processing capability,making it suitable for low-latency applications.However,when applied to real-world datasets,the accuracy of fire prediction is still not high.This study improves the accuracy of YOLOv10 for real-time applications through model fine-tuning techniques and data augmentation.The core work of the research involves creating a diverse fire image dataset specifically suited for fire detection applications in buildings and factories,freezing the initial layers of the model to retain general features learned from the dataset by applying the Squeeze and Excitation attention mechanism and employing the Stochastic Gradient Descent(SGD)with a momentum optimization algorithm to enhance accuracy while ensuring real-time fire detection.Experimental results demonstrate the effectiveness of the proposed fire prediction approach,where the YOLOv10 small model exhibits the best balance compared to other YOLO family models such as nano,medium,and balanced.Additionally,the study provides an experimental evaluation to highlight the effectiveness of model fine-tuning compared to the YOLOv10 baseline,YOLOv8 and Faster R-CNN based on two criteria:accuracy and prediction time.

Real-Time Tunable Gas Sensing Platform Based on SnO_(2) Nanoparticles Activated by Blue Micro-Light-Emitting Diodes

Micro-light-emitting diodes(μLEDs)have gained significant interest as an activation source for gas sensors owing to their advantages,including room temperature operation and low power consumption.However,despite these benefits,challenges still exist such as a limited range of detectable gases and slow response.In this study,we present a blueμLED-integrated light-activated gas sensor array based on SnO_(2)nanoparticles(NPs)that exhibit excellent sensitivity,tunable selectivity,and rapid detection with micro-watt level power consumption.The optimal power forμLED is observed at the highest gas response,supported by finite-difference time-domain simulation.Additionally,we first report the visible light-activated selective detection of reducing gases using noble metal-decorated SnO_(2)NPs.The noble metals induce catalytic interaction with reducing gases,clearly distinguishing NH3,H2,and C2H5OH.Real-time gas monitoring based on a fully hardwareimplemented light-activated sensing array was demonstrated,opening up new avenues for advancements in light-activated electronic nose technologies.

LSTM Based Neural Network Model for Anomaly Event Detection in Care-Independent Smart Homes

This study introduces a long-short-term memory(LSTM)-based neural network model developed for detecting anomaly events in care-independent smart homes,focusing on the critical application of elderly fall detection.It balances the dataset using the Synthetic Minority Over-sampling Technique(SMOTE),effectively neutralizing bias to address the challenge of unbalanced datasets prevalent in time-series classification tasks.The proposed LSTM model is trained on the enriched dataset,capturing the temporal dependencies essential for anomaly recognition.The model demonstrated a significant improvement in anomaly detection,with an accuracy of 84%.The results,detailed in the comprehensive classification and confusion matrices,showed the model’s proficiency in distinguishing between normal activities and falls.This study contributes to the advancement of smart home safety,presenting a robust framework for real-time anomaly monitoring.

NFA:A neural factorization autoencoder based online telephony fraud detection

The proliferation of internet communication channels has increased telecom fraud,causing billions of euros in losses for customers and the industry each year.Fraudsters constantly find new ways to engage in illegal activity on the network.To reduce these losses,a new fraud detection approach is required.Telecom fraud detection involves identifying a small number of fraudulent calls from a vast amount of call traffic.Developing an effective strategy to combat fraud has become challenging.Although much effort has been made to detect fraud,most existing methods are designed for batch processing,not real-time detection.To solve this problem,we propose an online fraud detection model using a Neural Factorization Autoencoder(NFA),which analyzes customer calling patterns to detect fraudulent calls.The model employs Neural Factorization Machines(NFM)and an Autoencoder(AE)to model calling patterns and a memory module to adapt to changing customer behaviour.We evaluate our approach on a large dataset of real-world call detail records and compare it with several state-of-the-art methods.Our results show that our approach outperforms the baselines,with an AUC of 91.06%,a TPR of 91.89%,an FPR of 14.76%,and an F1-score of 95.45%.These results demonstrate the effectiveness of our approach in detecting fraud in real-time and suggest that it can be a valuable tool for preventing fraud in telecommunications networks.

Virtual Assembly Collision Detection Algorithm Using Backpropagation Neural Network

As computer graphics technology continues to advance,Collision Detection(CD)has emerged as a critical element in fields such as virtual reality,computer graphics,and interactive simulations.CD is indispensable for ensuring the fidelity of physical interactions and the realism of virtual environments,particularly within complex scenarios like virtual assembly,where both high precision and real-time responsiveness are imperative.Despite ongoing developments,current CD techniques often fall short in meeting these stringent requirements,resulting in inefficiencies and inaccuracies that impede the overall performance of virtual assembly systems.To address these limitations,this study introduces a novel algorithm that leverages the capabilities of a Backpropagation Neural Network(BPNN)to optimize the structural composition of the Hybrid Bounding Volume Tree(HBVT).Through this optimization,the research proposes a refined Hybrid Hierarchical Bounding Box(HHBB)framework,which is specifically designed to enhance the computational efficiency and precision of CD processes.The HHBB framework strategically reduces the complexity of collision detection computations,thereby enabling more rapid and accurate responses to collision events.Extensive experimental validation within virtual assembly environments reveals that the proposed algorithm markedly improves the performance of CD,particularly in handling complex models.The optimized HBVT architecture not only accelerates the speed of collision detection but also significantly diminishes error rates,presenting a robust and scalable solution for real-time applications in intricate virtual systems.These findings suggest that the proposed approach offers a substantial advancement in CD technology,with broad implications for its application in virtual reality,computer graphics,and related fields.

Deep Transfer Learning-Enabled Activity Identification and Fall Detection for Disabled People

The human motion data collected using wearables like smartwatches can be used for activity recognition and emergency event detection.This is especially applicable in the case of elderly or disabled people who live self-reliantly in their homes.These sensors produce a huge volume of physical activity data that necessitates real-time recognition,especially during emergencies.Falling is one of the most important problems confronted by older people and people with movement disabilities.Numerous previous techniques were introduced and a few used webcam to monitor the activity of elderly or disabled people.But,the costs incurred upon installation and operation are high,whereas the technology is relevant only for indoor environments.Currently,commercial wearables use a wireless emergency transmitter that produces a number of false alarms and restricts a user’s movements.Against this background,the current study develops an Improved WhaleOptimizationwithDeep Learning-Enabled Fall Detection for Disabled People(IWODL-FDDP)model.The presented IWODL-FDDP model aims to identify the fall events to assist disabled people.The presented IWODLFDDP model applies an image filtering approach to pre-process the image.Besides,the EfficientNet-B0 model is utilized to generate valuable feature vector sets.Next,the Bidirectional Long Short Term Memory(BiLSTM)model is used for the recognition and classification of fall events.Finally,the IWO method is leveraged to fine-tune the hyperparameters related to the BiLSTM method,which shows the novelty of the work.The experimental analysis outcomes established the superior performance of the proposed IWODL-FDDP method with a maximum accuracy of 97.02%.

Deep Forest-Based Fall Detection in Internet of Medical Things Environment

This article introduces a new medical internet of things(IoT)framework for intelligent fall detection system of senior people based on our proposed deep forest model.The cascade multi-layer structure of deep forest classifier allows to generate new features at each level with minimal hyperparameters compared to deep neural networks.Moreover,the optimal number of the deep forest layers is automatically estimated based on the early stopping criteria of validation accuracy value at each generated layer.The suggested forest classifier was successfully tested and evaluated using a public SmartFall dataset,which is acquired from three-axis accelerometer in a smartwatch.It includes 92781 training samples and 91025 testing samples with two labeled classes,namely non-fall and fall.Classification results of our deep forest classifier demonstrated a superior performance with the best accuracy score of 98.0%compared to three machine learning models,i.e.,K-nearest neighbors,decision trees and traditional random forest,and two deep learning models,which are dense neural networks and convolutional neural networks.By considering security and privacy aspects in the future work,our proposed medical IoT framework for fall detection of old people is valid for real-time healthcare application deployment.

Deep Transfer Learning Driven Automated Fall Detection for Quality of Living of Disabled Persons

Mobile communication and the Internet of Things(IoT)technologies have recently been established to collect data from human beings and the environment.The data collected can be leveraged to provide intelligent services through different applications.It is an extreme challenge to monitor disabled people from remote locations.It is because day-to-day events like falls heavily result in accidents.For a person with disabilities,a fall event is an important cause of mortality and post-traumatic complications.Therefore,detecting the fall events of disabled persons in smart homes at early stages is essential to provide the necessary support and increase their survival rate.The current study introduces a Whale Optimization Algorithm Deep Transfer Learning-DrivenAutomated Fall Detection(WOADTL-AFD)technique to improve the Quality of Life for persons with disabilities.The primary aim of the presented WOADTL-AFD technique is to identify and classify the fall events to help disabled individuals.To attain this,the proposed WOADTL-AFDmodel initially uses amodified SqueezeNet feature extractor which proficiently extracts the feature vectors.In addition,the WOADTLAFD technique classifies the fall events using an extreme Gradient Boosting(XGBoost)classifier.In the presented WOADTL-AFD technique,the WOA approach is used to fine-tune the hyperparameters involved in the modified SqueezeNet model.The proposedWOADTL-AFD technique was experimentally validated using the benchmark datasets,and the results confirmed the superior performance of the proposedWOADTL-AFD method compared to other recent approaches.

Teamwork Optimization with Deep Learning Based Fall Detection for IoT-Enabled Smart Healthcare System

The current advancement in cloud computing,Artificial Intelligence(AI),and the Internet of Things(IoT)transformed the traditional healthcare system into smart healthcare.Healthcare services could be enhanced by incorporating key techniques like AI and IoT.The convergence of AI and IoT provides distinct opportunities in the medical field.Fall is regarded as a primary cause of death or post-traumatic complication for the ageing population.Therefore,earlier detection of older person falls in smart homes is required to improve the survival rate of an individual or provide the necessary support.Lately,the emergence of IoT,AI,smartphones,wearables,and so on making it possible to design fall detection(FD)systems for smart home care.This article introduces a new Teamwork Optimization with Deep Learning based Fall Detection for IoT Enabled Smart Healthcare Systems(TWODLFDSHS).The TWODL-FDSHS technique’s goal is to detect fall events for a smart healthcare system.Initially,the presented TWODL-FDSHS technique exploits IoT devices for the data collection process.Next,the TWODLFDSHS technique applies the TWO with Capsule Network(CapsNet)model for feature extraction.At last,a deep random vector functional link network(DRVFLN)with an Adam optimizer is exploited for fall event detection.A wide range of simulations took place to exhibit the enhanced performance of the presentedTWODL-FDSHS technique.The experimental outcomes stated the enhancements of the TWODL-FDSHS method over other models with increased accuracy of 98.30%on the URFD dataset.