Search

Intelligent Transportation System (ITS) provides services for proper traffic assistance. ITS helps in creating a transportation system that is smart, safe and efficient. Vehicular Ad-hoc Network supplies internet connectivity to vehicles and helps in traffic guidance. This paper uses a modified transformer architecture for time-series vehicular data to predict traffic flow. Time-series sequences are generated from the dataset for capturing temporal dependencies. Our proposed transformer-based model has been engineered to capture inter-feature correlations along with inter-sample correlations. The 2D-Transformers model has a significant decrease in error compared with Transformers and LSTM-based models. The prediction generated from the model can be transmitted throughout a network of vehicles. So, a holistic networking model is proposed where the vehicles will be connected to Road-side Units (RSUs) and the backbone network will be Software Defined Network (SDN). The traditional design principles, that incorporate data, control and management planes together in a network device, are incapable to adapt with this much data growth, bandwidth, speed, security, and scalability compared to SDN as it provides with centralized programmable mechanism reliably. The trained parameters learned using the transformer model can be passed throughout the network for traffic guidance.

Gastrointestinal (GI) cancer is the most common cancer in men and women. GI cancers are increasing every year worldwide. In the biomedical industry, Radiation treatment is a frequent choice for treating cancers of the GI tract in which the oncologist focuses the high range of X-ray beams on the tumor while avoiding the healthy organs. Manual segmentation of healthy organs to focus X-ray beams only on the tumor portion is very tedious and time-consuming, which can lead the treatment from a few minutes to hours. Deep learning techniques can concur with this problem by segmentation of healthy organs. This research article proposes a deep learning-based model Pyramid Scene Parsing Network (PSPNet) for segmenting organs such as the stomach, small bowel, and large bowel in the GI tract. The model has been simulated with five feature encoding networks: ResNext 50, Timm_Gernet_S, ResNet 34, EfficientNet B1, and MobileNet V2. These encoders were used for downsampling the feature map in the PSPNet architecture. The implementations have been performed using the UW Madison GI tract dataset, which contains 38,496 MRI scans of cancer patients. The model was evaluated using validation dice, Jaccard, and validation loss. The results reveal that the PSPNet model combined with ResNet 34 as encoder outperforms the other feature encoding networks with validation dice as 0.8842, validation Jaccard as 0.8531, and validation loss as 0.1365. Radiation oncologists can use the proposed model to speed up radiation therapy for cancer treatment.

For a lower limb exoskeleton, accurate and continuous estimation of the gait phase in real time is a fundamental requirement to provide a well-tailored assistive action at the proper time in the gait cycle (GC). This article presents a new gait phase estimator for a portable hip exoskeleton based on discrete wavelet transform (DWT) and adaptive oscillators. The algorithm is capable of continuously tracking the gait phase and identifying the relevant biomechanical gait events online, i.e., heel strike (HS) and toe-off (TO). The proposed method exploits only the hip joint angle signals measured by hip encoders, avoiding the need to use additional sensors to those already built in the exoskeleton. The novel phase estimator has been benchmarked against a state-of-the-art method, based on the maximum flexion angle (MFA), with pressure-sensitive insoles used as the reference ground truth for the event detection. To validate the method, two experimental activities were carried out. Experiments conducted with eight healthy subjects walking on a treadmill at different speeds, with and without hip assistance, demonstrated that the DWT-based method outperformed the MFA method in all operative conditions, reducing the rms of the phase reset error by 64.0% in assistive mode, and identifying the HS and TO events with low delay (0.4% and 1.1% GC, respectively, for HS and TO). Experiments carried out with three transfemoral amputees showed similar performance, paving the way for clinical applications of the method. [ABSTRACT FROM AUTHOR]

Automatic systems to monitor people and subsequently improve people’s lives have been emerging in the last few years, and currently, they are capable of identifying many activities of daily living (ADLs). An important field of research in this context is the monitoring of health risks and the identification of falls. It is estimated that every year, one in three persons older than 65 years will fall, and fall events are associated with high mortality rates among the elderly. We propose an anomaly identification framework to detect falls, which incorporates a spatial-temporal convolutional graph network (ST-GCN) as a feature extractor and uses an encoder process to reconstruct ADLs and identify falls as anomalies. As the publicly available fall datasets are few and generally unbalanced, training a reliable model using approaches that need explicit labeling is challenging. Thus, a focus on learning without external supervision is desirable. Treating a fall as an exception of ADLs allows us to recognize falls as anomalies without explicit labels. Given its modular architecture, our framework can robustly represent visual information and use the encoder’s reconstruction error to identify falls as anomalies. We assess our framework’s ability to recognize falls by training it with only ADLs. We perform three types of experiments: single dataset training and evaluation that consists of separate 90% of the data to train the model 5% to adjust the model, and the rest to the test. A joint dataset experiment, where we combine two datasets to increase the number of samples our model is trained on, and a cross-dataset evaluation, where we train on one dataset and evaluate using another one. Besides presenting state-of-the-art results on our experiments, particularly on the cross-dataset one, the model also presents a low number of false events, which makes it an ideal candidate for real-world application.

Financial and economic news is continuously monitored by financial market participants. According to the efficient market hypothesis, all past information is reflected in stock prices and new information is instantaneously absorbed in determining future stock prices. Hence, prompt extraction of positive or negative sentiments from news is very important for investment decision-making by traders, portfolio managers and investors. Sentiment analysis models can provide an efficient method for extracting actionable signals from the news. However, financial sentiment analysis is challenging due to domain-specific language and unavailability of large labeled datasets. General sentiment analysis models are ineffective when applied to specific domains such as finance. To overcome these challenges, we design an evaluation platform which we use to assess the effectiveness and performance of various sentiment analysis approaches, based on combinations of text representation methods and machine-learning classifiers. We perform more than one hundred experiments using publicly available datasets, labeled by financial experts. We start the evaluation with specific lexicons for sentiment analysis in finance and gradually build the study to include word and sentence encoders, up to the latest available NLP transformers. The results show improved efficiency of contextual embeddings in sentiment analysis compared to lexicons and fixed word and sentence encoders, even when large datasets are not available. Furthermore, distilled versions of NLP transformers produce comparable results to their larger teacher models, which makes them suitable for use in production environments.

Traditional visual simultaneous localization and mapping (SLAM) systems mostly based on small-area static environments. In recent years, some studies focused on combining semantic information with visual SLAM. However, most of them are hard to obtain better performance in the large-scale dynamic environment. And the accuracy, rapidity of the system still needs to strengthen. In this paper, we develop a more efficient semantic SLAM system in the two-wheeled mobile robot by using semantic segmentation to recognize people, chairs, and other objects in every keyframe. With a preliminary understanding of the environment, fusing the RGB-D camera and encoders information, to localization and creating a dense colored octree map without dynamic objects. Besides, for the incomplete identification of movable objects, we used image processing algorithms to enhance the semantic segmentation effect. In the proposed method, enhanced semantic segmentation in keyframes dramatically increases the efficiency of the system. Moreover, fusing the different sensors can highly raise localization accuracy. We conducted experiments on various datasets and in some real environments and compared them with DRE-SLAM, DS-SLAM, to evaluate the performance of the proposed approach. The results suggest we significantly improve the processing efficiency, robustness, and quality of the map.

The complications of identifying radiation effects in electromechanical sensors in the presence of mechanical variation are discussed. A corresponding analysis method is developed to separate radiation degradation effects from expected sensing variation due to mechanical tolerances of test fixtures. This is achieved by statistically characterizing the fixture variation for each sensor before irradiation, and evaluating the statistical significance of any sensitivity changes after irradiation. The method is demonstrated using a contactless Hall-effect rotary encoder IC commonly used in robotic systems. Sensitivity changes in measurements relevant to robotic controller design are isolated and quantified as a maximum positioning error of 0.5° and an angular velocity error of 1.5%. These measurements can be used to improve a commercial off-the-shelf robotic system’s tolerance to radiation by designing motion controllers robust to sensitivity changes prior to total device failure. [ABSTRACT FROM AUTHOR]

We report on the first experimental demonstration of superposition coded modulation (SCM) for polarization-multiplexed coherent-detection optical fiber links. The proposed coded modulation scheme is combined with phase-shifted bit-to-symbol mapping (PSM) in order to achieve geometric and passive shaping of the signal's waveform. The output constellations in SCM-PSM exhibit nonbijective quasi-Gaussian statistical distributions that asymptotically reach the Shannon capacity limit, showing up to 0.7 dB sensitivity improvement for 256-ary SCM-PSM with respect to 256-ary quadrature amplitude modulation (QAM). The characteristic wave formation based on superposition of antipodal symbols and the lack of need for additional encoders for signal shaping, greatly reduces the transmitter and receiver processing complexity in comparison to conventional alternatives. Single-level coding strategy (SL-SCM) is employed in the framework of bit-interleaved coded modulation with iterative decoding (BICM-ID) for forward error correction. The fiber transmission system is characterized in terms of signal-to-noise ratio for back-to-back case and correlated with simulated results for ideal transmission over additive white Gaussian noise channel. Thereafter, successful demodulation and decoding after dispersion-unmanaged transmission over 240-km standard single mode fiber of dual-polarization 6-Gbaud 16-, 32- and 64-ary SCM-PSM is experimentally demonstrated. [ABSTRACT FROM PUBLISHER]

Speed and differential speed measurements are necessary for almost all of manufacturing steel processes. Use of incremental rotary encoder is the cheapest method for this purpose. Classical theoretical algorithms are analyzed in terms of error and sampling time. These methods are used for a temper mill real case, showing the practical limitations in both speed and differential speed. A new differential speed measurement algorithm is introduced, showing how to solve eccentricity problems and that a bad processing but not slippage is the source of observed false elongation peaks. Thus, incremental rotary encoder with a proper processing algorithm can offer higher accuracy than other more expensive noncontact speed sensors. [ABSTRACT FROM AUTHOR]

It is known that tail-biting codes T' constructed from trellis coded modulation (TCM) with a delay processor can achieve large minimum Euclidean distances. In this paper, concatenated space-time block coding (STBC) with T' for multiple-input multiple-output (MIMO) and MIMO-OFDM (orthogonal frequency-division multiplexing) systems is investigated. We propose an improved system which is implemented by inserting a specific block interleaver between the encoders of coded modulation and STBC. We also propose sliding-window-type iterative decoding using partial hard-decision feedback (SW-IDPHF) with low complexity to decode T', which provides better error performance as compared to sliding-window-type iterative decoding using full hard-decision feedback (SW-IDFHF). In addition, we apply sliding-window-type iterative decoding using soft-decision feedback (SW-IDSF) to T' for improved error performance. The decoder of concatenated system based on T' can converge faster and provide better ultimate error performance as compared to the case of BICM under various channel conditions for either MIMO or MIMO-OFDM systems. [ABSTRACT FROM PUBLISHER]

Speed and position sensing in servo drives is an issue that is still not completely understood. Expressions like "accuracy" and "resolution" still get mixed up when engineers talk about encoders. These words, however, do describe different characteristics and should not be confused. The introduction of digital control has made this issue much more important for servo drive applications than before. This paper presents some general explanations of speed and motion sensing as well as different encoder technologies available today and their characteristics, particularly with respect to digitally controlled servo drives. [ABSTRACT FROM AUTHOR]

We propose a simplified configuration of all-optical analog-to-digital (A/D) conversion using nonlinear optical loop mirrors (NOLMs). While the conventional scheme of such all-optical A/D conversion requires encoders and threshold, for -bit resolution, the proposed configuration realizes an -bit resolution only using a single encoder and threshold, based on a split-and-delay technique, in which the encoder and the threshold operate more than times as fast as the sampling speed. After discussing detailed design issues of the NOLM-based encoder with particular emphasis on the so-called counterpropagating effects, all-optical 3-bit A/D conversion at 10 GS/s is experimentally demonstrated using the proposed configuration. [ABSTRACT FROM PUBLISHER]

This paper demonstrates a high-performance optical-code-division-multiple-access (O-CDMA) network testbed using the spectral phase encoded time spreading (SPECTS) method. Through additional time and polarization multiplexing, a total of 32 10-Gb/s users are supported while sharing eight O-CDMA spreading codes. User detection is achieved with time gating and nonlinear thresholding to suppress the multiaccess interference of other users. Incorporation of forward error correction successfully reduces the performance loss imposed by coherent beat interference, resulting in error-free performance (BER<10-11), significant per-user power penalty reduction, and the elimination of a bit-error-rate noise floor. The testbed also applies bandwidth suppression within the encoders and decoders, yielding a 52% increase in spectral efficiency [ABSTRACT FROM PUBLISHER]

This paper describes a study of the performance of various configurations for placing multiple optical amplifiers in a typical coherent ultrashort light pulse code-division multiple access (CULP-CDMA) communication system using the additive noise model. For this study, a comprehensive performance analysis was developed that takes into account multiple-access noise, noise due to optical amplifiers, and thermal noise using the saddle-point approximation technique. Prior to obtaining the overall system performance, the input/output statistical models for different elements of the system such as encoders/decoders, star coupler, and optical amplifiers were obtained. Performance comparisons between an ideal and lossless quantum-limited case and a typical CULP-CDMA with various losses exhibit more than 30 dB more power requirement to obtain the same bit-error rate (BER). Considering the saturation effect of optical amplifiers, this paper discusses an algorithm for amplifiers' gain setting in various stages of the network in order to overcome the nonlinear effects on signal modulation in optical amplifiers. Finally, using this algorithm, various configurations of multiple optical amplifiers in CULP-CDMA are discussed and the rules for the required optimum number of amplifiers are shown with their corresponding optimum locations to be implemented along the CULP-CDMA system. [ABSTRACT FROM PUBLISHER]

Low-density parity-check (LDPC) codes are excellent candidates for optical network applications due to their inherent low complexity of both encoders and decoders. A cyclic or quasi-cyclic form of finite geometry LDPC codes simplifies the encoding procedure. In addition, the complexity of an iterative decoder for such codes, namely the min-sum algorithm, is lower than the complexity of a turbo or Reed-Solomon decoder. In fact, simple hard-decoding algorithms such as the bit-flipping algorithm perform very well on codes from projective planes. In this paper, the authors consider LDPC codes from affine planes, projective planes, oval designs, and unitals. The bit-error-rate (BER) performance of these codes is significantly better than that of any other known foward-error correction techniques for optical communications. A coding gain of 9-10 dB at a BER of 10-9, depending on the code rate, demonstrated here is the best result reported so far. In order to assess the performance of the proposed coding schemes, a very realistic simulation model is used that takes into account in a natural way all major impairments in long-haul optical transmission such as amplified spontaneous emission noise, pulse distortion due to fiber nonlinearities, chromatic dispersion, crosstalk effects, and intersymbol interference. This approach gives a much better estimate of the code's performance than the commonly used additive white Gaussian noise channel model. [ABSTRACT FROM PUBLISHER]

This paper extends a pulse propagation previously developed by Marcuse for the characterization of pulse transmission in single mode fibers to the case of pulsed optical code-division multiple-access (CDMA) systems that employ encoders and decoders based on ladder networks. The model accounts for important degradation factors such as fiber dispersion, source linewidth (coherence), chip time duration and phase and delay mismatch between the source encoder and the destination decoder. Although results are only presented for the autocorrelation signal, the model can be employed to analyze the impact of the above mentioned [ABSTRACT FROM PUBLISHER]

In this letter, we show, for the first time, that an integrated spectral optical code-division multiple-access (OCDMA) technique has a comparable performance with respect to coherent OCDMA techniques based on a crosstalk analysis. The code set is further studied on its resilience against imbalances in the 3-dB couplers of the en/decoders (E/Ds). The orthogonality remains acceptable for imbalance penalties up to 1 dB. The analysis done in the letter considers a cascade and a tree E/D which shows negligible differences in performance. [ABSTRACT FROM PUBLISHER]

This letter presents a high-capacity optical code-division multiple-access (O-CDMA) network testbed based on the spectral phase-encoded time-spreading technique. Two 10-Gb/s/user O-CDMA network architectures (time-slotted and time-slotted polarization multiplexed) are investigated. The first O-CDMA network testbed architecture utilizes eight encoders and a decoder to produce 16 users equally distributed in two time slots while the second architecture evenly distributes 32 users in two time slots and two polarizations. The 16-user testbed achieved error-free performance. The 32-user testbed obtained bit-error rates below 10-8 without using forward-error-correction techniques [ABSTRACT FROM PUBLISHER]

We propose bidirectional fiber-optic code division multiple access networks based on the multiwavelength optical code, and the feasibility of the network is demonstrated experimentally. Encoders/decoders are implemented with AWG routers and fiber delay lines, and incoherent light sources are used. Due to the loop-back configuration of the AWG router-based encoder/decoder, bidirectional transmission is possible in the proposed access network. Decoding of broad-spectrum encoded signals (Δf=1.6 THz, Δλ=12.8 nm at 1550 nm) after transmission over a 40-km fiber link was performed with dispersion compensation [ABSTRACT FROM PUBLISHER]