Abstract Many security cameras have been put up in places like airports, roads, and banks for the safety of these public places. These cameras make a lot of video data, and most security camera recordings are only ever seen when something strange happens. This means that monitoring has to be done by people, which is time-consuming and often wrong, so automatic ways of monitoring have to be used. In this paper, we propose a system that automatically detects irregular events in videos based on the integration of Inflated 3D Convolution Network (I3D-ResNet50) and deep Multiple Instance Learning (MIL). This system considers both regular and unusual videos as negative and positive packets, respectively. Each video snippet is a case of that packet. An anomaly score is generated for each video snippet using a fully connected Neural Network (NN). After processing videos, we used an I3D-ResNet50 to extract features after applying 10-crop augmentations to the UCF-101 dataset that contains 130 GB of videos with 13 abnormal events such as fighting, stealing, abuse, etc., as well as normal events. Our experimental results show that the AUC is 82.85% with only 10,000 iterations compared with other approaches. This means that our model is better at spotting anomalies in real-time videos.

Abstract This paper explores the use of chest CT scans for early detection of COVID-19 and improved patient outcomes. The proposed method employs advanced techniques, including binary cross-entropy, transfer learning, and deep convolutional neural networks, to achieve accurate results. The COVIDx dataset, which contains 104,009 chest CT images from 1,489 patients, is used for a comprehensive analysis of the virus. A sample of 13,413 images from this dataset is categorised into two groups: 7,395 CT scans of individuals with confirmed COVID-19 and 6,018 images of normal cases. The study presents pre-trained transfer learning models such as ResNet (50), VGG (19), VGG (16), and Inception V3 to enhance the DCNN for classifying the input CT images. The binary cross-entropy metric is used to compare COVID-19 cases with normal cases based on predicted probabilities for each class. Stochastic Gradient Descent and Adam optimizers are employed to address overfitting issues. The study shows that the proposed pre-trained transfer learning models achieve accuracies of 99.07%, 98.70%, 98.55%, and 96.23%, respectively, in the validation set using the Adam optimizer. Therefore, the proposed work demonstrates the effectiveness of pre-trained transfer learning models in enhancing the accuracy of DCNNs for image classification. Furthermore, this paper provides valuable insights for the development of more accurate and efficient diagnostic tools for COVID-19.

Optimization algorithms are used to improve model accuracy. The optimization process undergoes multiple cycles until convergence. A variety of optimization strategies have been developed to overcome the obstacles involved in the learning process. Some of these strategies have been considered in this study to learn more about their complexities. It is crucial to analyse and summarise optimization techniques methodically from a machine learning standpoint since this can provide direction for future work in both machine learning and optimization. The approaches under consideration include the Stochastic Gradient Descent (SGD), Stochastic Optimization Descent with Momentum, Rung Kutta, Adaptive Learning Rate, Root Mean Square Propagation, Adaptive Moment Estimation, Deep Ensembles, Feedback Alignment, Direct Feedback Alignment, Adfactor, AMSGrad, and Gravity. prove the ability of each optimizer applied to machine learning models. Firstly, tests on a skin cancer using the ISIC standard dataset for skin cancer detection were applied using three common optimizers (Adaptive Moment, SGD, and Root Mean Square Propagation) to explore the effect of the algorithms on the skin images. The optimal training results from the analysis indicate that the performance values are enhanced using the Adam optimizer, which achieved 97.30% accuracy. The second dataset is COVIDx CT images, and the results achieved are 99.07% accuracy based on the Adam optimizer. The result indicated that the utilisation of optimizers such as SGD and Adam improved the accuracy in training, testing, and validation stages.

Early detection and diagnosis of thyroid nodules are very important to rescue patients before the cancer spreads all over the patient’s body. A computer-aided diagnosis (CAD) system is proposed to detect the malignancy of thyroid nodules using magnetic resonance imaging (MRI) scans. This system extracts three descriptive features from T2-weighted (T2) MRI. These features are 1st-order reflectivity, 2nd-order reflectivity, and spherical harmonic. The 1st-order reflectivity is represented by sufficient statistics, (i.e. CDF percentiles), extracted from the cumulative distribution function (CDF) generated from it. After-ward, these features are fed to a neural network (NN) individually for diagnosis. Then, the classification outputs for these networks are fused using another NN for final diagnosis. The developed system is trained and tested using leave-one-subject-out (LOSO) cross-validation technique on MRI scans from 63 patients. The proposed fusion system shows incredible improvements in diagnostic accuracy, compared with other machine learning approach and a well-know pretrained deep learning network as well as individual feature classification. The overall sensitivity, specificity, F1-score, and accuracy of the proposed system are 91.3%, 95%, 91.3%, and 93.65%, respectively. The reported results, based on the fusion of reflectivity features as well as morphological feature, show the promise of the developed system in differentiating between benign and malignant thyroid nodules.

A new efficient design of second-order spectralnull (2-OSN) codes is presented. The new codes are obtained by applying the technique used to design parallel decoding balanced (i.e., 1-OSN) codes to the random walk method introduced by some of the authors for designing 2-OSN codes. This gives new non-recursive efficient code designs, which are less redundant than the code designs found in the literature. In particular, if k ∈ IIN is the length of a 1-OSN code then the new 2-OSN coding scheme has length n = k + r ∈ IIN with an extra redundancy of r ≃ 2 log2k + (1/2) log2log2k - 0.174 check bits, with k and r even and n multiple of 4. The whole coding process requires O(k log k) bit operations and O(k) bit memory elements.

An m-ary block code, m = 2, 3, 4,..., of length n ϵ IN is called balanced if, and only if, every codeword is balanced; that is, the real sum of the codeword components, or weight, is equal to ⌊(m - 1)n/2⌋. This paper presents efficient encoding schemes to m-ary balanced codes with parallel (hence, fast) decoding. In fact, the decoding time complexity is O(1) digit operations. These schemes are a generalization to the m-ary alphabet of Knuth's complementation method with parallel decoding. Let (nw)mindicate the number of m-ary words w of length n and weight w ϵ(0,1, ... , (m - 1)n}. For any m ϵ IN, m ≥ 2, a simple implementation of the method is given which uses r ϵ IN check digits to balance k ≤ {(⌊(m-1)r/2⌋)m- (m mod 2 + [(m - 1)k] mod 2}}/(m - 1) information digits with an encoding time complexity of O(mk logmk) digit operations. A refined implementation of the parallel decoding method is also given with r check digits and k ≤ (mr-1)/(m -1) information digits, where the encoding time complexity is O(k√logmk). Thus, the proposed codes are less redundant than the m-ary balanced codes with parallel decoding found in the literature and yet maintain the same complexity.

A new efficient coding scheme is given for second-order spectral-null (2-OSN) codes. The new method applies the Knuth's optimal parallel decoding scheme for balanced (i.e., 1-OSN) codes to the random walk method introduced by Tallini and Bose to design 2-OSN codes. If k ∈ IN is the length of a 1-OSN code then the new 2-OSN coding scheme has length n = k+r ∈ IN with an extra redundancy of r ≳ 2 log2k + (1/2) log2log2k - 0.674 check bits. The whole coding process requires O(n log n) bit operations and 0(n) bit memory elements.

The error detecting problem for limited magnitude errors over high radix channels is studied. In this error model, the error magnitude does not exceed a certain limited value and it is known beforehand. For asymmetric, unidirectional, and symmetric channels, both all and t error detecting codes are studied. In all these cases, close-to-optimal codes are proposed.

Vehicular networks are expected to enable vehicles on the road to exchange safety information; enhancing traffic flow and minimizing accidents. With vehicle positions being the most frequently exchanged information in vehicular networks, it becomes imperative to establish a strong level of trust in the announced positions before a vehicle initiates a response. This paper proposes a position verification scheme as part of a misbehavior detection framework that encompasses analysis techniques needed for the verification of exchanged vehicular messages. The scheme involves the estimation of a vehicle's trajectory via the integration of road and map information, as opposed to only depending on the vehicle's kinematics for future trajectory prediction. The trajectory estimation procedure uses the vehicle's previously received position updates to find a bestfit area within the road topology in which the vehicle is expected to be. The vehicle's current position announcement is compared against this plausible area to decide whether the position is consistent with the expected location. Our proposed scheme is verified via extensive simulations, developed on ns2, demonstrating the importance of integrating road and map information into position verification.

Vehicular networks will enable vehicles on the road to utilize wireless communication to exchange safety information; enhancing traffic flow and minimizing accidents. With vehicle positions being the most frequently exchanged information in vehicular networks; it becomes imperative to establish a strong level of trust in the announced positions before a vehicle may take action in response. This paper proposes a position verification scheme that involves the collaborative exchange of one-hop neighbor information in order to help a vehicle make better judgments of position announcements. Vehicles can assess neighborhood connectivity and use the logical traffic flow to form a verdict on trusting a position announcement, thus enabling the detection of possible position falsifications. The scheme analyzes accumulated 2-hop neighbors' information in order to define a plausibility area within which a vehicle should exist in order for its position to be considered "correct". In very sparse traffic scenarios, a vehicle will depend on measuring the consistency of a vehicle's Received Signal Strength (RSS) with its announced position. Performance evaluation was carried out via simulation, and results show that defining this plausibility area yields accurate detection of position falsifications with low false positives.

Some new classes of systematic t-unidirectional error-detecting codes over Zmare designed. It is shown that the constructed codes can detect two errors using two check digits. Furthermore, the constructed codes can detect up to mr-2+ r-2 errors using r ges 3 check bits. A bound on the maximum number of detectable errors using r check digits is also given.

In the ARQ (Automatic Retransmission Request) protocol, the sender keeps retransmitting a codeword until it receives a positive acknowledgment from the receiver sent through the feedback channel. This paper proposes Plain and Diversity Combining ARQ Hybrid protocol communication schemes suitable for the m(≥ 2)-ary asymmetric channel using t-Asymmetric Error Correcting/All Asymmetric Error Detecting (t-AEC/AAED) codes. The analysis shows that error correction definitely improves the throughput of the system compared to the ARQ protocol which uses only error detecting codes. The paper provides simple analytic expressions and bounds for the average number of retransmissions in both Plain and Diversity Combining t-AEC/AAED ARQ (t ≥ 0) protocol systems over the m-ary asymmetric channel, m ≥ 2. These can be applied into the design and analysis of error controlling schemes in practical systems such as VLSI and optical communications.

In the automatic repeat request (ARQ) protocol, the sender keeps retransmitting a code word until it receives a positive acknowledgment from the receiver sent through the feedback channel. This correspondence proposes plain and diversity combining hybrid ARQ protocol communication schemes suitable for the m(ges2)-ary asymmetric channel using t-asymmetric error correcting/all asymmetric error detecting (t-AEC/AAED) codes. The analysis shows that error correction definitely improves the throughput of the system compared to the ARQ protocol which uses only error detecting codes. The correspondence provides simple analytic expressions for the average number of transmissions of a code word in both plain and diversity combining t-AEC/AAED ARQ (tges0) protocol systems over the m-ary asymmetric channel, mges2. An example is shown on how to get very close to the Z-channel capacity