Developing well-designed presentation slides is challenging for many people, especially novices. The ability to build high quality slideshows is becoming more important in society. In this study, a neural network was used to identify novice vs. well-designed presentation slides based on visual and structural features. For such a purpose, a dataset containing 1,080 slide pairs was newly constructed. One of each pair was created by a novice, and the other was the improved one by the same person according to the experts' advice. Ten checkpoints frequently pointed out by professional consultants were extracted and set as prediction targets. The intrinsic problem was that the label distribution was imbalanced, because only a part of the samples had corresponding design problems. Therefore, re-sampling methods for addressing class imbalance were applied to improve the accuracy of the proposed model. Furthermore, we combined the target task with an assistant task for transfer and multi-task learning, which helped the proposed model achieve better performance. After the optimal settings were used for each checkpoint, the average accuracy of the proposed model rose up to 81.79%. With the advice provided by our assessment system, the novices significantly improved their slide design.

Low power consumption is important in edge artificial intelligence (AI) chips, where power supply is limited. Therefore, we propose reconfigurable neural network accelerator (ReNA), an AI chip that can process both a convolutional layer and fully connected layer with the same structure by reconfiguring the circuit. In addition, we developed tools for pre-evaluation of the performance when a deep neural network (DNN) model is implemented on ReNA. With this approach, we established the flow for the implementation of DNN models on ReNA and evaluated its power consumption. ReNA achieved 1.51TOPS/W in the convolutional layer and 1.38TOPS/W overall in a VGG16 model with a 70% pruning rate.

Deep learning applications have often been processed in the cloud or on servers. Still, for applications that require privacy protection and real-time processing, the execution environment is moved to edge devices. Edge devices that implement a neural network (NN) are physically accessible to an attacker. Therefore, physical attacks are a risk. Fault attacks on these devices are capable of misleading classification results and can lead to serious accidents. Therefore, we focus on the softmax function and evaluate a fault attack using a clock glitch against NN implemented in an 8-bit microcontroller. The clock glitch is used for fault injection, and the injection timing is controlled by monitoring the power waveform. The specific waveform is enrolled in advance, and the glitch timing pulse is generated by the sum of absolute difference (SAD) matching algorithm. Misclassification can be achieved by appropriately injecting glitches triggered by pattern detection. We propose a countermeasure against fault injection attacks that utilizes the randomization of power waveforms. The SAD matching is disabled by random number initialization on the summation register of the softmax function.

Social Skills Training (SST) has been used for years to improve individuals' social skills toward building a better daily life. In SST carried out by humans, the social skills level is usually evaluated through a verbal interview conducted by the trainer. Although this evaluation is based on psychiatric knowledge and professional experience, its quality depends on the trainer's capabilities. Therefore, to standardize such evaluations, quantifiable metrics are required. To meet this need, the second edition of the Social Responsiveness Scale (SRS-2) offers a viable solution because it has been extensively tested and standardized by empirical research works. This paper describes the development of an automated method to evaluate a person's social skills level based on SRS-2. We use multimodal features, including BERT-based features, and perform score estimation with a 0.76 Pearson correlation coefficient while using feature selection. In addition, we examine the linguistic aspects of BERT-based features through subjective evaluations. Consequently, the BERT-based features show a strong negative correlation with human subjective scores of fluency, appropriate word choice, and understandable speech structure.

The construction of a Huffman code can be understood as the problem of finding a full binary tree such that each leaf is associated with a linear function of the depth of the leaf and the sum of the function values is minimized. Fujiwara and Jacobs extended this to a general function and proved the extended problem to be NP-hard. The authors also showed the case where the functions associated with leaves are each non-decreasing and convex is solvable in polynomial time. However, the complexity of the case of non-decreasing non-convex functions remains unknown. In this paper we try to reveal the complexity by considering non-decreasing non-convex functions each of which takes the smaller value of either a linear function or a constant. As a result, we provide a polynomial-time algorithm for two subclasses of such functions.

Hansen, Kaplan, Zamir and Zwick (STOC 2019) introduced a systematic way to use “bias” for predicting an assignment to a Boolean variable in the process of PPSZ and showed that their biased PPSZ algorithm achieves a relatively large success probability improvement of PPSZ for Unique 3SAT. We propose an additional way to use “bias” and show by numerical analysis that the improvement gets increased further.

We study the gathering problem requiring a team of mobile agents to gather at a single node in arbitrary networks. The team consists of k agents with unique identifiers (IDs), and f of them are weakly Byzantine agents, which behave arbitrarily except falsifying their identifiers. The agents move in synchronous rounds and cannot leave any information on nodes. If the number of nodes n is given to agents, the existing fastest algorithm tolerates any number of weakly Byzantine agents and achieves gathering with simultaneous termination in O(n4·|Λgood|·X(n)) rounds, where |Λgood| is the length of the maximum ID of non-Byzantine agents and X(n) is the number of rounds required to explore any network composed of n nodes. In this paper, we ask the question of whether we can reduce the time complexity if we have a strong team, i.e., a team with a few Byzantine agents, because not so many agents are subject to faults in practice. We give a positive answer to this question by proposing two algorithms in the case where at least 4f2+9f+4 agents exist. Both the algorithms assume that the upper bound N of n is given to agents. The first algorithm achieves gathering with non-simultaneous termination in O((f+|&Lambdagood|)·X(N)) rounds. The second algorithm achieves gathering with simultaneous termination in O((f+|&Lambdaall|)·X(N)) rounds, where |&Lambdaall| is the length of the maximum ID of all agents. The second algorithm significantly reduces the time complexity compared to the existing one if n is given to agents and |&Lambdaall|=O(|&Lambdagood|) holds.

In the rendezvous problem, two computing entities (called agents) located at different vertices in a graph have to meet at the same vertex. In this paper, we consider the synchronous neighborhood rendezvous problem, where the agents are initially located at two adjacent vertices. While this problem can be trivially solved in O(Δ) rounds (Δ is the maximum degree of the graph), it is highly challenging to reveal whether that problem can be solved in o(Δ) rounds, even assuming the rich computational capability of agents. The only known result is that the time complexity of O($O(sqrt{n})$) rounds is achievable if the graph is complete and agents are probabilistic, asymmetric, and can use whiteboards placed at vertices. Our main contribution is to clarify the situation (with respect to computational models and graph classes) admitting such a sublinear-time rendezvous algorithm. More precisely, we present two algorithms achieving fast rendezvous additionally assuming bounded minimum degree, unique vertex identifier, accessibility to neighborhood IDs, and randomization. The first algorithm runs within $ ilde{O}(sqrt{nDelta/delta} + n/delta)$ rounds for graphs of the minimum degree larger than $sqrt{n}$, where n is the number of vertices in the graph, and δ is the minimum degree of the graph. The second algorithm assumes that the largest vertex ID is O(n), and achieves $ ilde{O}left( rac{n}{sqrt{delta}} ight)$-round time complexity without using whiteboards. These algorithms attain o(Δ)-round complexity in the case of $delta = {omega}(sqrt{n} log n)$ and δ=ω(n2/3log4/3n) respectively. We also prove that four unconventional assumptions of our algorithm, bounded minimum degree, accessibility to neighborhood IDs, initial distance one, and randomization are all inherently necessary for attaining fast rendezvous. That is, one can obtain the Ω(n)-round lower bound if either one of them is removed.

Binary sequences with high linear complexity and high 2-adic complexity have important applications in communication and cryptography. In this paper, the 2-adic complexity of a class of balanced Whiteman generalized cyclotomic sequences which have high linear complexity is considered. Through calculating the determinant of the circulant matrix constructed by one of these sequences, the result shows that the 2-adic complexity of this class of sequences is large enough to resist the attack of the rational approximation algorithm (RAA) for feedback with carry shift registers (FCSRs).

In this paper, we study Hermitian linear complementary dual (abbreviated Hermitian LCD) rank metric codes. A class of Hermitian LCD generalized Gabidulin codes are constructed by qm-self-dual bases of Fq2m over Fq2. Moreover, the exact number of qm-self-dual bases of Fq2m over Fq2 is derived. As a consequence, an upper bound and a lower bound of the number of the constructed Hermitian LCD generalized Gabidulin codes are determined.

In this paper, a macro cell switching scheme for distributed antennas is proposed. In conventional distributed antenna transmission (DAT), the macro cell to which each antenna belongs is fixed. Though a cell-free system has been investigated because of its higher system throughput, the implementation cost of front-hauls can be excessive. To increase the flexibility of resource allocation in the DAT with moderate front-haul complexity, we propose the macro cell switching of distributed antennas (DAs). In the proposed scheme, DAs switch their attribution macro cells depending on the amount of pre-assigned connections. Numerical results obtained through computer simulation show that the proposed scheme realizes a better system throughput than the conventional system, especially when the number of user equipments (UEs) is smaller and the distance between DAs are larger.

In this paper, we propose the first private decision tree evaluation (PDTE) schemes which are suitable for use in Machine Learning as a Service (MLaaS) scenarios. In our schemes, a user and a model owner send the ciphertexts of a sample and a decision tree model, respectively, and a single server classifies the sample without knowing the sample nor the decision tree. Although many PDTE schemes have been proposed so far, most of them require to reveal the decision tree to the server. This is undesirable because the classification model is the intellectual property of the model owner, and/or it may include sensitive information used to train the model, and therefore the model also should be hidden from the server. In other PDTE schemes, multiple servers jointly conduct the classification process and the decision tree is kept secret from the servers under the assumption they do not collude. Unfortunately, this assumption may not hold because MLaaS is usually provided by a single company. In contrast, our schemes do not have such problems. In principle, fully homomorphic encryption allows us to classify an encrypted sample based on an encrypted decision tree, and in fact, the existing non-interactive PDTE scheme can be modified so that the server classifies only handling ciphertexts. However, the resulting scheme is less efficient than ours. We also show the experimental results for our schemes.

In this study, Bayesian image denoising, in which the prior distribution is assumed to be a Gaussian Markov random field (GMRF), is considered. Recently, an effective algorithm for Bayesian image denoising with a standard GMRF prior has been proposed, which can help implement the overall procedure and optimize its parameters in O(n)-time, where n is the size of the image. A new GMRF-type prior, referred to as a hierarchical GMRF (HGMRF) prior, is proposed, which is obtained by applying a hierarchical Bayesian approach to the standard GMRF prior; in addition, an effective denoising algorithm based on the HGMRF prior is proposed. The proposed HGMRF method can help implement the overall procedure and optimize its parameters in O(n)-time, as well as the previous GMRF method. The restoration quality of the proposed method is found to be significantly higher than that of the previous GMRF method as well as that of a non-local means filter in several cases. Furthermore, numerical evidence implies that the proposed HGMRF prior is more suitable for the image prior than the standard GMRF prior.

It is known that quasi-cyclic (QC) codes over the finite field Fq correspond to certain Fq[x]-modules. A QC code C is specified by a generator polynomial matrix G whose rows generate C as an Fq[x]-module. The reversed code of C, denoted by R, is the code obtained by reversing all codewords of C while the dual code of C is denoted by C⊥. We call C reversible, self-orthogonal, and self-dual if R = C, C⊥ ⊇ C, and C⊥ = C, respectively. In this study, for a given C, we find an explicit formula for a generator polynomial matrix of R. A necessary and sufficient condition for C to be reversible is derived from this formula. In addition, we reveal the relations among C, R, and C⊥. Specifically, we give conditions on G corresponding to C⊥ ⊇ R, C⊥ ⊆ R, and C = R = C⊥. As an application, we employ these theoretical results to the construction of QC codes with best parameters. Computer search is used to show that there exist various binary reversible self-orthogonal QC codes that achieve the upper bounds on the minimum distance of linear codes.

The convex hull is the minimum convex surrounding a given set of points. Since the process of finding convex hulls has various practical application fields including embedded real-time systems, efficient acceleration of convex hull algorithms is an important problem in computer geometry. In this paper, we discuss an FPGA acceleration approach to address this problem. In order to compute the convex hull of an unsorted point set, it is necessary to store all the points during the computation, and thus the capacity of a on-chip memory is likely to be a major constraint for efficient FPGA implementation. On the other hand, approximate convex hulls are often sufficient for practical applications. Therefore, we propose a hardware oriented approximate convex hull algorithm, which can process the input points as a stream without storing all the points in the memory. We also propose some computation reduction techniques for efficient FPGA implementation. Then, we present FPGA implementation of the proposed algorithm, which is parallelized both in temporal and spatial domains, and evaluate its effectiveness in terms of performance and accuracy. As a result, we demonstrated 11 to 30 times faster performance compared to the widely-used convex hull software library Qhull. In addition, accuracy assessment revealed that the maximum approximation error normalized to the diameters of point sets was 0.038%, which was reasonably small for practical use cases.

We study the computational complexity of the puzzle game Critter Crunch, where the player has to rearrange Critters on a board in order to eliminate them all. Smaller Critters can be fed to larger Critters, and Critters will explode if they eat too much. Critters come in several different types, sizes, and colors. We prove the NP-hardness of levels that contain Blocker Critters, as well as levels where the player must clear the board in a given number of moves (i.e., “puzzle mode”). We also characterize the complexity of the game, as a function of the number of columns on the board, in two settings: (i) the setting where Critters may have several different colors, but only two possible sizes, and (ii) the setting where Critters come in all three sizes, but with no color variations. In both settings, the game is NP-hard for levels with exactly two columns, and solvable in linear time for levels with only one column or more than two columns.

In the upcoming Internet of Things era, reducing energy consumption of embedded processors is highly desired. Minimum Energy Point Tracking (MEPT) is one of the most efficient methods to reduce both dynamic and static energy consumption of a processor. Previous works proposed a variety of MEPT methods over the past years. However, none of them incorporate their algorithms with practical real-time operating systems, although edge computing applications often require low energy task execution with guaranteeing real-time properties. The difficulty comes from the time complexity for identifying an MEP and changing voltages, which often prevents real-time task scheduling. The conventional Dynamic Voltage and Frequency Scaling (DVFS) only scales the supply voltage. On the other hand, MEPT needs to adjust the body bias voltage in addition. This additional tuning knob makes MEPT much more complicated. This paper proposes an approximate MEPT algorithm, which reduces the complexity of identifying an MEP down to that of DVFS. The key idea is to linearly approximate the relationship between the processor frequency, supply voltage, and body bias voltage. Thanks to the approximation, optimal voltages for a specified clock frequency can be derived immediately. We also propose a task scheduling algorithm, which adjusts processor performance to the workload and then provides a soft real-time capability to the system. The operating system stochastically adjusts the average response time of the processor to be equal to a specified deadline. MEPT will be performed as a general task, and its overhead is considered in the calculation of the frequency. The experiments using a fabricated test chip and on-chip sensors show that the proposed algorithm is a maximum of 16 times more energy-efficient than DVFS. Also, the energy loss induced by the approximation is only 3% at most, and the algorithm does not sacrifice the fundamental real-time properties.

The growing threat of Hardware Trojans (HT) in the System-on-Chips (SoC) industry has given way to the embedded systems researchers to propose a series of detection methodologies to identify and detect the presence of Trojan circuits or logics inside a host design in the various stages of the chip design and manufacturing process. Many state of the art works propose different techniques for HT detection among which the popular choice remains the Side-Channel Analysis (SCA) based methods that perform differential analysis targeting the difference in consumption of power, change in electromagnetic emanation or the delay in propagation of logic in various paths of the circuit. Even though the effectiveness of these methods are well established, the evaluation is carried out on simplistic models such as AES coprocessors and the analytical approaches used for these methods are limited by some statistical metrics such as direct comparison of EM traces or the T-test coefficients. In this paper, we propose two new detection methodologies based on Machine Learning algorithms. The first method consists in applying the supervised Machine Learning (ML) algorithms on raw EM traces for the classification and detection of HT. It offers a detection rate close to 90% and false negative smaller than 5%. In the second method, we propose an outlier/novelty algorithms based approach. This method combined with the T-test based signal processing technique, when compared with state-of-the-art, offers a better performance with a detection rate close to 100% and a false positive smaller than 1%. In different experiments, the false negative is nearly the same level than the false positive and for that reason the authors only show the false positive value on the results. We have evaluated the performance of our method on a complex target design: RISC-V generic processor. Three HTs with their corresponding sizes: 0.53%, 0.27% and 0.09% of the RISC-V processors are inserted for the experimentation. In this paper we provide elaborative details of our tests and experimental process for reproducibility. The experimental results show that the inserted HTs, though minimalistic, can be successfully detected using our new methodology.

Online feeds are streamed continuously in batches with varied polarities at varying times. The system handling the online feeds must be trained to classify all the varying polarities occurring dynamically. The polarity classification system designed for the online feeds must address two significant challenges: i) stability-plasticity, ii) category-proliferation. The challenges faced in the polarity classification of online feeds can be addressed using the technique of incremental learning, which serves to learn new classes dynamically and also retains the previously learned knowledge. This paper proposes a new incremental learning methodology, ILOF (Incremental Learning of Online Feeds) to classify the feeds by adopting Deep Learning Techniques such as RNN (Recurrent Neural Networks) and LSTM (Long Short Term Memory) and also ELM (Extreme Learning Machine) for addressing the above stated problems. The proposed method creates a separate model for each batch using ELM and incrementally learns from the trained batches. The training of each batch avoids the retraining of old feeds, thus saving training time and memory space. The trained feeds can be discarded when new batch of feeds arrives. Experiments are carried out using the standard datasets comprising of long feeds (IMDB, Sentiment140) and short feeds (Twitter, WhatsApp, and Twitter airline sentiment) and the proposed method showed positive results in terms of better performance and accuracy.

Recent localization methods for wireless networks cannot be applied to dynamic networks with unknown topology. To solve this problem, we propose a localization method based on partial correlation analysis in this paper. We evaluate our proposed localization method in terms of accuracy, which shows that our proposed method can achieve high accuracy localization for dynamic networks with unknown topology.