Misdetection Probability Research Articles

Real-Time Traffic Flow Statistics Based on Dual-Granularity Classification

Article Real-Time Traffic Flow Statistics Based on Dual-Granularity Classification Yanchao Bi, Yuyan Yin, Xinfeng Liu *, Xiushan Nie, Chenxi Zou, and Junbiao Du 1 School of Computer Science and Technology, Shandong Jianzhu University, Jinan 250101, China * Correspondence: liuxinfeng18@sdjzu.edu.cn Received: 17 June 2023 Accepted: 13 September 2023 Published: 26 September 2023 Abstract: Traffic detection devices can cause accuracy degradation over time. Considering problems such as time-consuming and laborious manual statistics, high misdetection probabilities, and model tracking failures, there is an urgent need to develop a deep learning model (which can stably achieve detection accuracy over 90%) to evaluate whether the device accuracy still satisfies the requirements or not. In this study, based on dual-granularity classification, a real-time traffic flow statistics method is proposed to address the above problems. The method is divided into two stages. The first stage uses YOLOv5 to acquire all the motorized and non-motorized vehicles appearing in the scene. The second stage uses EfficientNet to acquire the motorized vehicles obtained in the previous stage and classify such vehicles into six categories. Through this dual-granularity classification, the considered problem is simplified and the probability of false detection is reduced significantly. To correlate the front and back frames of the video, vehicle tracking is implemented using DeepSORT, and vehicle re-identification is implemented in conjunction with the ResNet50 model to improve the tracking accuracy. The experimental results show that the method used in this study solves the problems of misdetection and tracking effectively. Moreover, the proposed method achieves 98.7% real-time statistical accuracy by combining the two-lane counting method.

Generalized Penalized Constrained Regression: Sharp Guarantees in High Dimensions with Noisy Features

The generalized penalized constrained regression (G-PCR) is a penalized model for high-dimensional linear inverse problems with structured features. This paper presents a sharp error performance analysis of the G-PCR in the over-parameterized high-dimensional setting. The analysis is carried out under the assumption of a noisy or erroneous Gaussian features matrix. To assess the performance of the G-PCR problem, the study employs multiple metrics such as prediction risk, cosine similarity, and the probabilities of misdetection and false alarm. These metrics offer valuable insights into the accuracy and reliability of the G-PCR model under different circumstances. Furthermore, the derived results are specialized and applied to well-known instances of G-PCR, including l1-norm penalized regression for sparse signal recovery and l2-norm (ridge) penalization. These specific instances are widely utilized in regression analysis for purposes such as feature selection and model regularization. To validate the obtained results, the paper provides numerical simulations conducted on both real-world and synthetic datasets. Using extensive simulations, we show the universality and robustness of the results of this work to the assumed Gaussian distribution of the features matrix. We empirically investigate the so-called double descent phenomenon and show how optimal selection of the hyper-parameters of the G-PCR can help mitigate this phenomenon. The derived expressions and insights from this study can be utilized to optimally select the hyper-parameters of the G-PCR. By leveraging these findings, one can make well-informed decisions regarding the configuration and fine-tuning of the G-PCR model, taking into consideration the specific problem at hand as well as the presence of noisy features in the high-dimensional setting.

A Comparative Analysis of Supervised and Unsupervised Models for Detecting Attacks on the Intrusion Detection Systems

Intrusion Detection Systems are expected to detect and prevent malicious activities in a network, such as a smart grid. However, they are the main systems targeted by cyber-attacks. A number of approaches have been proposed to classify and detect these attacks, including supervised machine learning. However, these models require large labeled datasets for training and testing. Therefore, this paper compares the performance of supervised and unsupervised learning models in detecting cyber-attacks. The benchmark of CICDDOS 2019 was used to train, test, and validate the models. The supervised models are Gaussian Naïve Bayes, Classification and Regression Decision Tree, Logistic Regression, C-Support Vector Machine, Light Gradient Boosting, and Alex Neural Network. The unsupervised models are Principal Component Analysis, K-means, and Variational Autoencoder. The performance comparison is made in terms of accuracy, probability of detection, probability of misdetection, probability of false alarm, processing time, prediction time, training time per sample, and memory size. The results show that the Alex Neural Network model outperforms the other supervised models, while the Variational Autoencoder model has the best results compared to unsupervised models.

Two-Stage Preamble Detector for LEO Satellite-Based NTN IoT Random Access

In this paper, we propose an enhanced random access preamble (PA) detector for the low earth orbit (LEO) satellite-based non-terrestrial network (NTN) Internet-of-Things (IoT) that efficiently detects non-orthogonal PAs while suppressing interference. The proposed detector operates in two stages to efficiently suppress the interference caused by non-orthogonal PAs. In the first stage, reconstruction and cancellation of non-orthogonal PAs are performed. In the second stage, final PA detection is performed iteratively using the reconstructed PAs and received signal. In addition, we theoretically derive the probability of PA misdetection, PA collision, and successful PA detection under typical NTN line-of-sight (LoS) channel conditions. Simulation results verify that the proposed two-stage PA detector (TSPD) achieves performance close to the theoretical upper bound in terms of successful PA detection probability. The TSPD also shows a significantly greater successful PA detection probability than the conventional PA detector using orthogonal PAs while satisfying the random access requirement for the 3rd generation partnership project (3GPP) standard. Moreover, compared to the conventional PA detector for non-orthogonal PA, which adopts an interference cancellation scheme, the TSPD achieves up to 25.6 times lower detection complexity.

Impact of Dataset and Model Parameters on Machine Learning Performance for the Detection of GPS Spoofing Attacks on Unmanned Aerial Vehicles

GPS spoofing attacks are a severe threat to unmanned aerial vehicles. These attacks manipulate the true state of the unmanned aerial vehicles, potentially misleading the system without raising alarms. Several techniques, including machine learning, have been proposed to detect these attacks. Most of the studies applied machine learning models without identifying the best hyperparameters, using feature selection and importance techniques, and ensuring that the used dataset is unbiased and balanced. However, no current studies have discussed the impact of model parameters and dataset characteristics on the performance of machine learning models; therefore, this paper fills this gap by evaluating the impact of hyperparameters, regularization parameters, dataset size, correlated features, and imbalanced datasets on the performance of six most commonly known machine learning techniques. These models are Classification and Regression Decision Tree, Artificial Neural Network, Random Forest, Logistic Regression, Gaussian Naïve Bayes, and Support Vector Machine. Thirteen features extracted from legitimate and simulated GPS attack signals are used to perform this investigation. The evaluation was performed in terms of four metrics: accuracy, probability of misdetection, probability of false alarm, and probability of detection. The results indicate that hyperparameters, regularization parameters, correlated features, dataset size, and imbalanced datasets adversely affect a machine learning model’s performance. The results also show that the Classification and Regression Decision Tree classifier has an accuracy of 99.99%, a probability of detection of 99.98%, a probability of misdetection of 0.2%, and a probability of false alarm of 1.005%, after removing correlated features and using tuned parameters in a balanced dataset. Random Forest can achieve an accuracy of 99.94%, a probability of detection of 99.6%, a probability of misdetection of 0.4%, and a probability of false alarm of 1.01% in similar conditions.

An Ensemble-Based Machine Learning Approach for Cyber-Attacks Detection in Wireless Sensor Networks

Wireless Sensor Networks (WSNs) are the key underlying technology of the Internet of Things (IoT); however, these networks are energy constrained. Security has become a major challenge with the significant increase in deployed sensors, necessitating effective detection and mitigation approaches. Machine learning (ML) is one of the most effective methods for building cyber-attack detection systems. This paper presents a lightweight ensemble-based ML approach, Weighted Score Selector (WSS), for detecting cyber-attacks in WSNs. The proposed approach is implemented using a blend of supervised ML classifiers, in which the most effective classifier is promoted dynamically for the detection process to gain higher detection performance quickly. We compared the performance of the proposed approach to three classical ensemble techniques: Boosting-based, Bagging-based, and Stacking-based. The performance comparison was conducted in terms of accuracy, probability of false alarm, probability of detection, probability of misdetection, model size, processing time, and average prediction time per sample. We applied two independent feature selection techniques. We utilized the simulation-based labeled dataset, WSN-DS, that comprises samples of four internal network-layer Denial of Service attack types: Grayhole, Blackhole, Flooding, and TDMA scheduling, in addition to normal traffic. The simulation revealed promising results for our proposed approach.

A Fitting Recognition Approach Combining Depth-Attention YOLOv5 and Prior Synthetic Dataset

To address power transmission lines (PTLs) traveling through complex environments leading to misdetections and omissions in fitting recognition using cameras, we propose a fitting recognition approach combining depth-attention YOLOv5 and prior synthetic dataset to improve the validity of fitting recognition. First, datasets with inspection features are automatically synthesized based on prior series data, achieving better results with a smaller data volume for the deep learning model and reducing the cost of obtaining fitting datasets. Next, a unique data collection mode is proposed using a developed flying-walking power transmission line inspection robot (FPTLIR) as the acquisition platform. The obtained image data in this collection mode has obvious time-space, stability, and depth difference, fusing the two data types in the deep learning model to improve the accuracy. Finally, a depth-attention mechanism is proposed to change the attention on the images with depth information, reducing the probability of model misdetection and omission. Test field experiments results show that compared with YOLOv5, the mAP5095 (mean average precision on step size 0.05 for thresholds from 0.5 to 0.95) of our depth-attention YOLOv5 model for fitting is 68.1%, the recall is 98.3%, and the precision is 98.3%. Among them, AP, recall, and precision increased by 5.2%, 4.8%, and 4.1%, respectively. Test field experiments verify the feasibility of the depth-attention YOLOv5. Line field experiments results show that the mAP5095 of our depth-attention YOLOv5 model for fittings is 64.6%, and the mAPs of each class are improved compared with other attention mechanisms. The inference speed of depth-attention YOLOv5 is 3 ms slower than the standard YOLOv5 model and 10 ms to 15 ms faster than other attention mechanisms, verifying the validity of the depth-attention YOLOv5. The proposed approach improves the accuracy of the fitting recognition on PTLs, providing a recognition and localization basis for the automation and intelligence of inspection robots.

Dynamic Selection Techniques for Detecting GPS Spoofing Attacks on UAVs.

Unmanned aerial vehicles are prone to several cyber-attacks, including Global Positioning System spoofing. Several techniques have been proposed for detecting such attacks. However, the recurrence and frequent Global Positioning System spoofing incidents show a need for effective security solutions to protect unmanned aerial vehicles. In this paper, we propose two dynamic selection techniques, Metric Optimized Dynamic selector and Weighted Metric Optimized Dynamic selector, which identify the most effective classifier for the detection of such attacks. We develop a one-stage ensemble feature selection method to identify and discard the correlated and low importance features from the dataset. We implement the proposed techniques using ten machine-learning models and compare their performance in terms of four evaluation metrics: accuracy, probability of detection, probability of false alarm, probability of misdetection, and processing time. The proposed techniques dynamically choose the classifier with the best results for detecting attacks. The results indicate that the proposed dynamic techniques outperform the existing ensemble models with an accuracy of 99.6%, a probability of detection of 98.9%, a probability of false alarm of 1.56%, a probability of misdetection of 1.09%, and a processing time of 1.24 s.

FMCW Radar Network: Multiple Access and Interference Mitigation

With the increasing proliferation of radars on vehicles, interference among vehicular radars is becoming a serious issue. In this work, we consider a frequency modulated continuous wave (FMCW) radar network with coherent radar interference where all radars adopt the same chirp slopes. Four asynchronous non-cooperative media access control (MAC) protocols are used for mutual radar interference mitigation. We propose two cross-layer performance metrics - multiple access capacity and probability of target misdetection to quantify the network performance under each MAC protocol. Based on our analysis and extensive simulations, we find the pure random access achieves a very poor trade-off between multiple access capacity and probability of target misdetection. However, such a trade-off can be significantly improved by frequency hopping and phase coding. This shows that proper MAC protocols can achieve very good performance even without synchronization and coordination. We describe new insights behind such gains that can be valuable for FMCW radar MAC design.

Aggregate Preamble Sequence Design and Detection for Massive IoT With Deep Learning

Massive Internet of Things (mIoT) is a major use case of the fifth generation (5G) wireless systems. mIoT aims to support a large number of connection requests from IoT devices. However, the conventional Long Term Evolution (LTE) random access procedure hinders the support of mIoT due to the limited number of available preambles. In this paper, we propose to aggregate two Zadoff-Chu preamble sequences from two different roots to obtain a larger set of preambles by considering all possible combinations of preamble sequence pairs. Decoding the aggregate preambles is challenging because the receiver needs to decode two preamble sequences where each one is allocated half of the transmit power. We propose two receiver architectures for preamble decoding. The first one is a threshold-based receiver which only requires minor changes to the LTE preamble receiver architecture. The second proposed preamble decoder architecture exploits a deep neural network. Simulations show that the proposed aggregate preamble design results in a lower service time for backlogged IoT devices compared to existing collision avoidance techniques. Moreover, the proposed receiver architectures can decode the aggregate preambles with low probabilities of misdetection and false alarm (less than 11%), especially in the high signal-to-noise ratio (SNR) regime.

Modifying Hamming code and using the replication method to protect memory against triple soft errors

As technology scaling increases computer memory’s bit-cell density and reduces the voltage of semiconductors, the number of soft errors due to radiation induced single event upsets (SEU) and multi-bit upsets (MBU) also increases. To address this, error-correcting codes (ECC) can be used to detect and correct soft errors, while x-modular-redundancy improves fault tolerance. This paper presents a technique that provides high error-correction performance, high speed, and low complexity. The proposed technique ensures that only correct values get passed to the system output or are processed in spite of the presence of up to three-bit errors. The Hamming code is modified in order to provide a high probability of MBU detection. In addition, the paper describes the new technique and associated analysis scheme for its implementation. The new technique has been simulated, evaluated, and compared to error correction codes with similar decoding complexity to better understand the overheads required, the gained capabilities to protect data against three-bit errors, and to reduce the misdetection probability and false-detection probability of four-bit errors.

MIMO-Based Reliable Grant-Free Massive Access With QoS Differentiation for 5G and Beyond

Grant-free (GF) access has been one of the enablers for the various use cases in 5th generation (5G) mobile system, especially for time-critical massive machine-type communication (mMTC). However, these use cases have diverse quality of service (QoS) requirements, which can be measured in terms of an access success rate from a GF random access perspective. Consequently, a GF scheme that enables supporting of diverse QoS is highly sought. This article proposes a GF access scheme in which high-QoS users superpose multiple preambles to improve their access success rate as a result of the diversity in access collision and multiple access interference seen by multiple preambles. We further show that in the presence of multiple antennas in the base station (BS), a low-complexity receiver can correctly detect active preambles with a significantly high probability, even under severe multiple access interference caused by non-orthogonal preamble transmission. A theoritical performance analysis is conducted by modeling the preamble reception as a multiple measurement vector-based compressive sensing problem. The preamble misdetection probability is shown to decrease exponentially as the number antennas at BS increases. Numerical results demonstrate multiple-order improvement in terms of the access success rate for critical-QoS users, even under severe noise and multiple access contamination.

A hybrid spectrum sensing approach to select suitable spectrum band for cognitive users

In recent years, the usage of wireless devices and wireless service has been increased exponentially and it results in spectrum scarcity. The policies of regulatory authority employ static spectrum allocation methods and assign new spectrum band for offering new kind of services to the users. These approaches lead to poor utilization of available spectrum bands. The cognitive radio (CR) provides better solution to these problems and it mainly focuses on efficient utilization of available spectrum bands. CR network (CRN) has to adopt spectrum management techniques to assign the unused spectrum band to the CR users by following a sequence of actions such as spectrum sensing, decision and management. Spectrum sensing is a vital process in spectrum allocation. In the traditional approaches, sensing accuracy is brought down by the probabilities of misdetection and false alarm rate and hence, sensing accuracy becomes low. As a result, the Cognitive Users (CUs) face the challenge of prolonged time to complete perfect cognitive radio communication. To overcome this issue, a cooperative spectrum sensing technique with a characteristic based cluster classifier has been proposed. This classifier learns the states and their transitions in the radio frequency environment, as well as the primary user activities at regular time intervals to support the spectrum decision technique. The novelty of the work is to propose a hybrid approach which combines clustering with expected maximization (EM) algorithm and reinforcement learning (RL) techniques. This hybrid approach enhances the system performance with accurate sensing results and by identifying the optimum spectrum band through hierarchical access model using interweaving approach, energy consumption is minimized. The simulation results show that by decreasing the probabilities of error ratio, false alarm rate and missed detection, the accuracy of sensing results is improved. Further, this hybrid approach outperforms the traditional approaches in terms of probability of detection even in low SNR values.

Context-Aware Sensing via Dynamic Programming for Edge-Assisted Wearable Systems

Healthcare applications supported by the Internet of Things enable personalized monitoring of a patient in everyday settings. Such applications often consist of battery-powered sensors coupled to smart gateways at the edge layer. Smart gateways offer several local computing and storage services (e.g., data aggregation, compression, local decision making), and also provide an opportunity for implementing local closed-loop optimization of different parameters of the sensor layer, particularly energy consumption. To implement efficient optimization methods, information regarding the context and state of patients need to be considered to find opportunities to adjust energy to demanded accuracy. Edge-assisted optimization can manage energy consumption of the sensor layer but may also adversely affect the quality of sensed data, which could compromise the reliable detection of health deterioration risk factors. In this article, we propose two approaches: myopic and Markov decision processes (MDPs)—to consider both energy constraints and risk factor requirements for achieving a twofold goal: energy savings while satisfying accuracy requirements of abnormality detection in a patient’s vital signs. Vital signs, including heart rate, respiration rate, and oxygen saturation, are extracted from a photoplethysmogram signal and errors of extracted features are compared to a ground truth that is modeled as a Gaussian distribution. We control the sensor’s sensing energy to minimize the power consumption while meeting a desired level of satisfactory detection performance. We present experimental results on realistic case studies using a reconfigurable photoplethysmogram sensor in an IoT system, and show that compared to nonadaptive methods, myopic reduces an average of 16.9% in sensing energy consumption with the maximum probability of abnormality misdetection on the order of 0.17 in a 24-hour health monitoring system. In addition, over 4 weeks of monitoring, we demonstrate that our MDP policy can extend the battery life on average of more than 2x while fulfilling the same average probability of misdetection compared to the myopic method. We illustrate results comparing myopic , MDP, and nonadaptive methods to monitor 14 subjects over 1 month.

Cooperative Spectrum Sensing Using Maximum a Posteriori as a Detection Technique for Dynamic Spectrum Access Networks

Over the past few years, dynamic spectrum access has been gaining an increasing attention as a solution to the spectrum scarcity problem. In this paper, a primary user detection technique based on Maximum A Posteriori estimation is proposed for dynamic spectrum access networks. In the proposed technique, a set of secondary users acting as sensing nodes send their individual decisions about the existence of the primary user to a central fusion center. The fusion center uses the received data to form a codeword then, applies the maximum a posteriori estimation rule to make a final decision regarding the presence of the primary user. The proposed technique takes into consideration the accuracy of the local decisions provided by the secondary users when making a final decision. In this paper, we analyze the performance of the proposed scheme and derive closed-form expressions for the upper bounds of the false alarm and misdetection probabilities. The results show that the proposed technique outperforms other combining techniques in terms of its ability to detect the primary user and, accordingly, minimizes the harmful interference to the licensed network. Moreover, the proposed technique achieves better performance at a lower number of reporting secondary users which compensates for the complexity of the maximum a posteriori estimation.

Element-Wise Adaptive Thresholds for Learned Iterative Shrinkage Thresholding Algorithms

In this paper, we propose element-wise adaptive threshold methods for learned iterative shrinkage thresholding algorithms. The threshold for each element is adapted in such a way that it is set to be smaller when the previously recovered estimate or the current one-step gradient descent at that element has a larger value. This adaptive threshold gives a lower misdetection probability of the true support, which speedups the convergence to the optimal solution. We show that the proposed element-wise threshold adaption method has better convergence rate than the existing non-adaptive threshold methods. Numerical results show that the proposed neural network has the best recovery performance among the tested algorithms. In addition, it is robust to the sparsity mismatch, which is very desirable in the case of unknown signal sparsity.

Distributed coalition formation game for enhancing cooperative spectrum sensing in cognitive radioad hocnetworks

Cooperative spectrum sensing (CSS) among secondary users (SUs) in cognitive radio ad hoc networks exhibits an essential trade-off minimising the misdetection probability of the primary user and maintaining a reasonable false alarm probability to obtain efficient spectrum utilisation. In this study, distributed coalition formation game with a genetic algorithm is proposed to select the optimal coalitional head. It provides an incentive to SUs that improve their detection performance and cooperation among SUs. Since spectrum sensing will incur a cost for SUs, an incentive mechanism is necessary to motivate active participation. Consider the CSS problem as a non-transferable coalition game and it is used to allow the SUs to self-organise into disjoint coalitions while accounting for the CSS. The authors calculate payoff for each SU to form minimum winning coalition and to analyse their strategy profile for joining in coalition based on its utility maximisation. Simulation results reveal that the proposed algorithm has significantly improved sensing accuracy, minimised energy consumption and thereby enhanced CSS.

Multi-beam Transmissions for Blockage Resilience and Reliability in Millimeter-Wave Systems

Directionality in millimeter-wave (mmW) systems make link establishment and maintenance challenging, due to the search-time overhead of beam scanning and the vulnerability of directional links to blockages. In this paper, we propose a communication protocol called SmartLink, which exploits the clustering phenomenon at mmW frequencies to establish a multi-beam link between a base station and a user. By utilizing multiple clusters, SmartLink enables efficient link maintenance and sustained throughput. We develop a logarithmic-time search algorithm called multi-lobe beam search (MLBS), which is used in SmartLink to discover the clusters. MLBS probes several directions simultaneously, using multi-lobe beam patterns. The number of simultaneous lobes is selected to minimize the search time of the clusters. We provide detailed analysis of the false alarm and misdetection probabilities for the designed beam patterns. Following cluster discovery, SmartLink divides antennas into sub-arrays to generate the optimal multi-lobe beam pattern that maximizes the average data rate under blockage. Extensive simulations using actual channel traces obtained by utilizing phased-array antennas at 29 GHz are used to verify the efficiency of SmartLink. MLBS decreases the discovery time by up to 88% compared to common existing search schemes, and exploiting multiple clusters improves the average data rate by 10%.

TBM: A trust-based monitoring security scheme to improve the service authentication in the Internet of Things communications

Securing communications and information sharing within the Internet of Things (IoT) paradigm is challenging because of the increase in the size and mobility of the user population. Moreover, managing a central security architecture requires adaptability and integration with a cloud network. In this manuscript, a trust-based monitoring (TBM) scheme was designed for improving the security features in cloud-assisted IoT environments. This security scheme employs middleware and intelligent agents for managing user- and communication-level security. TBM operates in three security administering phases namely spoof detection, trust construction, and message authentication. The intelligent agents are responsible for ensuring secure communication by exchanging trust and signal strength observations with the middleware. These agents also assist with monitoring, processing, and task switching to reduce communication costs. TBM was evaluated through extensive simulations. The results demonstrate its consistency in achieving lower response and detection times, misdetection probabilities, and false positive rates. In addition, it was found to improve network lifetime through reduced energy consumption.

Performance improvement of multiuser cognitive relay networks with full-duplex cooperative sensing and energy harvesting

Energy harvesting cognitive radio has been considered as a promising technology in the fifth generation (5G) of wireless networks to solve the lack of spectrum and energy. In this paper, a novel wireless energy harvesting relay network is proposed for a multiuser cognitive radio to obtain the maximum throughput and decrease the false alarm and misdetection probabilities. The secondary user (SU) can harvest energy from solar sources while utilizing the licensed spectrum of the primary user (PU). Cooperative spectrum sensing is applied to improve the performance of the secondary network and decrease collision and sensing time. In this paper, the SU can carry out the transmitting, harvesting, and sensing using a full-duplex technique at the same time. Furthermore, we analyze the spectrum sensing of the proposed multiuser network under a data fusion scheme to discover the frequency hole. We demonstrate that the optimization problem can convert into a convex problem and achieve the optimal regulated rate of energy harvesting based on the Lagrangian function. This new network provides improved throughput, precise spectrum sensing, and high energy harvesting compared to the existing works studied so far. Finally, we verify the efficiency of the proposed method via simulation results and show that the optimal regulated rate is determined based on the priority of given constraints.