Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs

In-flight system failure is one of the major safety concerns in the operation of unmanned aerial vehicles (UAVs) in urban environments. To address this concern, a safety framework consisting of following three main tasks can be utilized: (1) Monitoring health of the UAV and detecting failures, (2) Finding potential safe landing spots in case a critical failure is detected in step 1, and (3) Steering the UAV to a safe landing spot found in step 2. In this paper, we specifically look at the second task, where we investigate the feasibility of utilizing object detection methods to spot safe landing spots in case the UAV suffers an in-flight failure. Particularly, we investigate different versions of the YOLO objection detection method and compare their performances for the specific application of detecting a safe landing location for a UAV that has suffered an in-flight failure. We compare the performance of YOLOv3, YOLOv4, and YOLOv5l while training them by a large aerial image dataset called DOTA in a Personal Computer (PC) and also a Companion Computer (CC). We plan to use the chosen algorithm on a CC that can be attached to a UAV, and the PC is used to verify the trends that we see between the algorithms on the CC. We confirm the feasibility of utilizing these algorithms for effective emergency landing spot detection and report their accuracy and speed for that specific application. Our investigation also shows that the YOLOv5l algorithm outperforms YOLOv4 and YOLOv3 in terms of accuracy of detection while maintaining a slightly slower inference speed.

Probabilistic assessment of complex system consisting three subsystems, multi-failure threats and copula repair approach

PurposeThe purpose of this paper is to deliberate the system reliability of a system in combination of three subsystems in a series configuration in which all three subsystems function under a k-out-of-n: G operational scheme. Based on computed results, it has been demonstrated that copula repair is better than general repair for system better performance. The supplementary variable approach with implications of copula distribution has been employed for assessing the system performance.Design/methodology/approachProbabilistic assessment of complex system consisting three subsystems, multi-failure threats and copula repair approach is used in this study. Abbas Jubrin Bin, V.V. Singh, D.K. Rawal, in this research paper, have analyzed a system consisting of three subsystems in a series configuration in which all three subsystems function under a k-out-of-n: G operational scheme. The supplementary variable approach with implications of copula distribution has been employed for assessing the system performance. Based on computed results, it has been demonstrated that copula repair is better than general repair for system better performance.FindingsIn this analysis, four different cases of availability are analysed for Gumbel–Hougaard family copula and also four cases for general repair with similar failure rates are studied. The authors found that when failure rates increase, the system availability decreases, and when the system follows copula repair distribution, the system availability is better than general repair.Research limitations/implicationsThis research may be implemented in various industrial systems where the subsystems are configured under k-out-of-n: G working policy. It is also advisable that copula repair is highly recommended for best performances from the system. On the basis of mean time to system failure (MTSF) computations, the failure rate which affects system failure more needs to be controlled by monitoring, servicing and replacing stratagem.Practical implicationsThis research work has great implications in various industrial systems like power plant systems, nuclear power plant, electricity distributions system, etc. where the k-out-of-n-type of system operation scheme is validated for system operations with the multi-repair.Originality/valueThis work is a new work by authors. In the previously available technical analysis of the system, the researchers have analyzed the repairable system either supplementary variable approach, supplementary variable and system which have two subsystems in a series configuration. This research work analyzed a system with three subsystems with a multi-repair approach and supplementary variables.

OBET: On-the-Fly Byte-Level Error Tracking for Correcting and Detecting Faults in Unreliable DRAM Systems

With technology scaling, maintaining the reliability of dynamic random-access memory (DRAM) has become more challenging. Therefore, on-die error correction codes have been introduced to accommodate reliability issues in DDR5. However, the current solution still suffers from high overhead when a large DRAM capacity is used to deliver high performance. We present a DRAM chip architecture that can track faults at byte-level DRAM cell errors to address this problem. DRAM faults are classified as temporary or permanent in our proposed architecture, with no additional pins and with minor DRAM chip modifications. Hence, we achieve reliability comparable to that of other state-of-the-art solutions while incurring negligible performance and energy overhead. Furthermore, the faulty locations are efficiently exposed to the operating system (OS). Thus, we can significantly reduce the required scrubbing cycle by scrubbing only faulty DRAM pages while reducing the system failure probability up to 5000∼7000 times relative to conventional operation.

Regulatory Role of Non-Coding RNAs on Immune Responses During Sepsis

Sepsis is resulted from a systemic inflammatory response to bacterial, viral, or fungal agents. The induced inflammatory response by these microorganisms can lead to multiple organ system failure with devastating consequences. Recent studies have shown altered expressions of several non-coding RNAs such as long non-coding RNAs (lncRNAs), microRNAs (miRNAs) and circular RNAs (circRNAs) during sepsis. These transcripts have also been found to participate in the pathogenesis of multiple organ system failure through different mechanisms. NEAT1, MALAT1, THRIL, XIST, MIAT and TUG1 are among lncRNAs that participate in the pathoetiology of sepsis-related complications. miR-21, miR-155, miR-15a-5p, miR-494-3p, miR-218, miR-122, miR-208a-5p, miR-328 and miR-218 are examples of miRNAs participating in these complications. Finally, tens of circRNAs such as circC3P1, hsa_circRNA_104484, hsa_circRNA_104670 and circVMA21 and circ-PRKCI have been found to affect pathogenesis of sepsis. In the current review, we describe the role of these three classes of noncoding RNAs in the pathoetiology of sepsis-related complications.

Data Analysis for the Aero Derivative Engines Bleed System Failure Identification and Prediction

Middle size gas/diesel aero-derivative power generation engines are widely used on various industrial plants in the oil and gas industry. Bleed of Valve (BOV) system failure is one of the failure mechanisms of these engines. The BOV is part of the critical anti-surge system and this kind of failure is almost impossible to identify while the engine is in operation. If the engine operates with BOV system impaired, this leads to the high maintenance cost during overhaul, increased emission rate, fuel consumption and loss in the efficiency. This paper proposes the use of readily available sensor data in a Supervisory Control and Data Acquisition (SCADA) system in combination with a machine learning algorithm for early identification of BOV system failure. Different machine learning algorithms and dimensionality reduction techniques are evaluated on real world engine data. The experimental results show that Bleed of Valve systems failures could be effectively predicted from readily available sensor data.

Managing Prisons Through Extended Solitary Confinement: A Necessary Approach or a Signal of Prison System Failure?

In contemporary American corrections, extended solitary confinement (ESM) as a management tool has emerged as a strategy for avowedly controlling the most violent individuals and, in so doing, creating a safer prison system. We theorize that the emergence of this unique form of housing may also be viewed as a signal of prison system failure. To advance this argument, we identify how different theoretical perspectives can be used to anticipate the effects of ESM on prison system violence and order and then investigate the plausibility of this account by grounding it in analysis of qualitative data from a study of one state’s prison system. The analysis suggests theoretical and empirical warrant for both views of ESM—as an effective tool and as a symptom of system failure. Implications of the study research and policy are discussed.

Analysis of a Human-Machine Interface for Cooperative Truck Overtaking Maneuvers on Freeways: Increase Success Rate and Assess Driving Behavior during System Failures

Cooperation between road users based on V2X communication has the potential to make road traffic safer and more efficient. The exchange of information enables the cooperative orchestration of critical traffic situations, such as truck overtaking maneuvers on freeways. With the benefit of such a system, questions arise concerning system failure or the abrupt and unexpected behavior of road users. A human-machine interface (HMI) organizes and negotiates the cooperation between drivers and maintains smooth interaction, trust, and system acceptance, even in the case of a possible system failure. A study was conducted with 30 truck drivers on a dynamic truck driving simulator to analyze the negotiation of cooperation requests and the reaction of truck drivers to potential system failures. The results show that an automated cooperation request does not translate into a significantly higher cooperation success rate. System failures in cooperative truck passing maneuvers are not considered critical by truck drivers in this simulated environment. The next step in the development process is to investigate how the success rate of truck overtaking maneuvers on freeways can be further increased as well as the implementation of the system in a real vehicle to investigate the reaction behavior of truck drivers in case of system failures in a real environment.