The International Solid-State Circuits Conference (ISSCC) is the flagship conference of the IEEE Solid-State Circuits Society. The theme for ISSCC 2025 is "The Silicon Engine Driving the Artificial Intelligence (...
详细信息
In video surveillance,anomaly detection requires training machine learning models on spatio-temporal video ***,sometimes the video-only data is not sufficient to accurately detect all the abnormal ***,we propose a nov...
详细信息
In video surveillance,anomaly detection requires training machine learning models on spatio-temporal video ***,sometimes the video-only data is not sufficient to accurately detect all the abnormal ***,we propose a novel audio-visual spatiotemporal autoencoder specifically designed to detect anomalies for video surveillance by utilizing audio data along with video *** paper presents a competitive approach to a multi-modal recurrent neural network for anomaly detection that combines separate spatial and temporal autoencoders to leverage both spatial and temporal features in audio-visual *** proposed model is trained to produce low reconstruction error for normal data and high error for abnormal data,effectively distinguishing between the two and assigning an anomaly *** is conducted on normal datasets,while testing is performed on both normal and anomalous *** anomaly scores from the models are combined using a late fusion technique,and a deep dense layer model is trained to produce decisive scores indicating whether a sequence is normal or *** model’s performance is evaluated on the University of California,San Diego Pedestrian 2(UCSD PED 2),University of Minnesota(UMN),and Tampere University of Technology(TUT)Rare Sound Events datasets using six evaluation *** is compared with state-of-the-art methods depicting a high Area Under Curve(AUC)and a low Equal Error Rate(EER),achieving an(AUC)of 93.1 and an(EER)of 8.1 for the(UCSD)dataset,and an(AUC)of 94.9 and an(EER)of 5.9 for the UMN *** evaluations demonstrate that the joint results from the combined audio-visual model outperform those from separate models,highlighting the competitive advantage of the proposed multi-modal approach.
作者：
Arian AziziMona GhassemiZero Emission
Realization of Optimized Energy Systems(ZEROES)LaboratoryDepartment of Electrical and Computer EngineeringThe University of Texas at DallasRichardsonTexasUSA
The next generation of aircraft,including more electric aircraft and all-electric aircraft(AEA),requires electric power systems with high power density and low system mass *** the voltage of the system to the range of...
详细信息
The next generation of aircraft,including more electric aircraft and all-electric aircraft(AEA),requires electric power systems with high power density and low system mass *** the voltage of the system to the range of a few kV,medium voltage(MV),is a reasonable approach to achieving high-power-density and low-system-mass EPSs for aircraft *** voltages,however,pose many challenges for aviation MV power cables such as arcs and arc tracking,partial discharges(PDs),and thermal *** this regard,thermal management is more challenging since heat transfer by convection is greatly reduced at wide-body aircraft's cruising altitudes due to the reduced air *** this paper,a finite element method(FEM)model is devel-oped in COMSOL Multiphysics for an aircraft bipolar MVDC(5 kV)power *** the model,the maximum permissible cable current at a low pressure of 18.8 kPa(at an altitude of 12.2 km from sea level,the usual cruising altitude for wide-body aircraft)is ***,an analytical model is developed based on analytical and proven empirical correlations governing conductive,radiative,and convective heat transfers at the steady state to estimate the ampacity of the bipolar cable system at reduced *** was shown that the proposed analytical model can be used for atmospheric pressure and systems with a larger number of poles,expanding its range of *** results of the FEM and analytical models correlate at wide ranges of parameters such as ambient temperature,duct size,distance between the positive and negative pole cables,and the overall diameter of the *** influence of horizontal and vertical arrangement of poles is included in the analytical *** results of this study can be used to design bipolar MVDC power cable systems for the envisaged wide-body AEA.
This research proposes a quad-mode H-beam metasurface (MTS)-embedded dual-band circularly-polarized (CP) multi-tiered antenna scheme with 5G (n79) and Wi-Fi 6E capabilities. The proposed antenna scheme consists of thr...
详细信息
This study presents a comprehensive optimization and comparative analysis of thermoelectric(TE)infrared(IR)detec-tors using Bi_(2)Te_(3) and Si *** theoretical modeling and numerical simulations,we explored the impact...
详细信息
This study presents a comprehensive optimization and comparative analysis of thermoelectric(TE)infrared(IR)detec-tors using Bi_(2)Te_(3) and Si *** theoretical modeling and numerical simulations,we explored the impact of TE mate-rial properties,device structure,and operating conditions on responsivity,detectivity,noise equivalent temperature difference(NETD),and noise equivalent power(NEP).Our study offers an optimally designed IR detector with responsivity and detectivity approaching 2×10^(5) V/W and 6×10^(9) cm∙Hz^(1/2)/W,*** enhancement is attributed to unique design features,includ-ing raised thermal collectors and long suspended thin thermoelectric wire sensing elements embedded in low thermal conductivity organic materials like ***,we demonstrate the compatibility of Bi_(2)Te_(3)-based detector fabrication pro-cesses with existing MEMS foundry processes,facilitating scalability and ***,for TE IR detectors,zT/κemerges as a critical parameter contrary to conventional TE material selection based solely on zT(where zT is the thermoelec-tric figure of merit andκis the thermal conductivity).
Resource slicing in low Earth orbit satellite networks (LSN) is essential to support diversified services. In this paper, we investigate a resource slicing problem in LSN to reserve resources in satellites to achieve ...
详细信息
This paper discusses a method for classification of breast cancer imaging data through the application of an adaptive neuro-fuzzy inference system (ANFIS) and particle swarm optimization (PSO) for hyperparameter optim...
详细信息
Solar radiation plays a critical role in the carbon sequestration processes of terrestrial ecosystems, making it a key factor in environmental sustainability among various renewable energy sources. This study integrat...
详细信息
Climate change poses significant challenges to agricultural management,particularly in adapting to extreme weather conditions that impact agricultural *** works with traditional Reinforcement Learning(RL)methods often...
详细信息
Climate change poses significant challenges to agricultural management,particularly in adapting to extreme weather conditions that impact agricultural *** works with traditional Reinforcement Learning(RL)methods often falter under such extreme *** address this challenge,our study introduces a novel approach by integrating Continual Learning(CL)with RL to form Continual Reinforcement Learning(CRL),enhancing the adaptability of agricultural management *** the Gym-DSSAT simulation environment,our research enables RL agents to learn optimal fertilization strategies based on variable weather *** incorporating CL algorithms,such as Elastic Weight Consolidation(EWC),with established RL techniques like Deep Q-Networks(DQN),we developed a framework in which agents can learn and retain knowledge across diverse weather *** CRL approach was tested under climate variability to assess the robustness and adaptability of the induced policies,particularly under extreme weather events like severe *** results showed that continually learned policies exhibited superior adaptability and performance compared to optimal policies learned through the conventional RL methods,especially in challenging conditions of reduced rainfall and increased *** pioneering work,which combines CL with RL to generate adaptive policies for agricultural management,is expected to make significant advancements in precision agriculture in the era of climate change.
Breast cancer remains a significant global health issue, primarily affecting females and requiring advanced detection methods to improve patient outcomes. While computer-aided diagnostic methods have progressed, limit...
详细信息
暂无评论